Fixed path issue with obsolete branch

Normalize timestamps before comparison.

.github/ISSUE_TEMPLATE.md

@@ -1,4 +1,4 @@
-Dear Zipline Maintainers,
+Dear Catalyst Maintainers,
 
 Before I tell you about my issue, let me describe my environment:
 
@@ -7,7 +7,7 @@ Before I tell you about my issue, let me describe my environment:
 * Operating System: (Windows Version or `$ uname --all`)
 * Python Version: `$ python --version`
 * Python Bitness: `$ python -c 'import math, sys;print(int(math.log(sys.maxsize + 1, 2) + 1))'`
-* How did you install Zipline: (`pip`, `conda`, or `other (please explain)`)
+* How did you install Catalyst: (`pip`, `conda`, or `other (please explain)`)
 * Python packages: `$ pip freeze` or `$ conda list`
 
 Now that you know a little about me, let me tell you about the issue I am

.gitignore

@@ -78,3 +78,7 @@ zipline.iml
 ./data
 
 TAGS
+
+python2
+python3
+scratch

README.rst

@@ -1,196 +1 @@
-========
-Catalyst
-========
-
-|version status|
-
-Catalyst is an algorithmic trading library for crypto-assets written in Python.
-It allows trading strategies to be easily expressed and backtested against historical data, providing analytics and insights regarding a particular strategy's performance.
-Catalyst will be expanded to support live-trading of crypto-assets in the coming months.
-Please visit `<enigma.co>`_ to learn about Catalyst, or refer to the 
-`whitepaper <https://www.enigma.co/enigma_catalyst.pdf>`_ for further technical details.
-
-Catalyst builds on top of the well-established `Zipline <https://github.com/quantopian/zipline>`_ project.
-We did our best to minimize structural changes to the general API to maximize compatibility with existing trading algorithms, developer knowledge, and tutorials.
-For now, please refer to the `Zipline API Docs <http://zipline.io>`_ as a general reference and bring any other questions you have to our #dev channel on `Slack <https://join.slack.com/enigmacatalyst/shared_invite/MTkzMjQ0MTg1NTczLTE0OTY3MjE3MDEtZGZmMTI5YzI3ZA>`_.
-
-Our primary contributions include the:
-
-- Intruction of an open trading calendar, that permits simulation to allow trades on weekends, holidays, and outside of normal business hours.
-- Curation of OHLCV data bundle from `Poloniex's API <https://poloniex.com/support/api/>`_, which contains data in five-minute intervals as early as 2/19/2015.
-- Support for backtesting for daily trading strategies, support for five-minute backtesting is in development.
-- Addition Bitcoin price (USDT_BTC) as a benchmark asset for comparing performance.
-
-Interested in getting involved?
-`Join us on Slack! <https://join.slack.com/enigmacatalyst/shared_invite/MTkzMjQ0MTg1NTczLTE0OTY3MjE3MDEtZGZmMTI5YzI3ZA>`_
-
-
-Installation
-============
-
-At the moment, Catalyst has some fairly specific and strict depedency requirements.
-We recommend the use of Python virtual environments if you wish to simplify the installation process, or otherwise isolate Catalyst's dependencies from your other projects.
-If you don't have ``virtualenv`` installed, see our later section on Virtual Environments.
-
-.. code-block:: bash
-
-    $ virtualenv catalyst-venv
-    $ source ./catalyst-venv/bin/activate
-    $ pip install enigma-catalyst
-
-**Note:** A successful installation will require several minutes in order to compile dependencies that expose C APIs.
-
-Dependencies
-------------
-
-Catalyst's depedencies can be found in the ``etc/requirements.txt`` file.
-If you need to install them outside of a typical ``pip install``, this is done using:
-
-.. code-block:: bash
-
-    $ pip install -r etc/requirements.txt
-
-Though not required by Catalyst directly, our example algorithms use matplotlib to visually display backtest results.
-If you wish to run any examples or use matplotlib during development, it can be installed using:
-
-.. code-block:: bash
-
-    $ pip install matplotlib
-
-**Note:** If you plan to use matplotlib and virtualenv on Mac OS X, see our later section for additional setup instructions.
-
-Getting Started
-===============
-
-The following code implements a simple buy and hodl algorithm.  The full source can be found in ``catalyst/examples/buy_and_hodl.py``.
-
-.. code:: python
-
-    import numpy as np
-    
-    from catalyst.api import (
-        order_target_value,
-        symbol,
-        record,
-        cancel_order,
-        get_open_orders,
-    )
-    
-    ASSET = 'USDT_BTC'
-    
-    TARGET_HODL_RATIO = 0.8
-    RESERVE_RATIO = 1.0 - TARGET_HODL_RATIO
-
-    def initialize(context):
-        context.is_buying = True
-        context.asset = symbol(ASSET)
-
-    def handle_data(context, data):
-        cash = context.portfolio.cash
-        target_hodl_value = TARGET_HODL_RATIO * context.portfolio.starting_cash
-        reserve_value = RESERVE_RATIO * context.portfolio.starting_cash
-        
-        # Cancel any outstanding orders from the previous day
-        orders = get_open_orders(context.asset) or []
-        for order in orders:
-            cancel_order(order)
-        
-        # Stop buying after passing reserve threshold
-        if cash <= reserve_value:
-            context.is_buying = False
-        
-        # Retrieve current price from pricing data
-        price = data[context.asset].price
-        
-        # Check if still buying and could (approximately) afford another purchase                    
-        if context.is_buying and cash > price:
-            # Place order to make position in asset equal to target_hodl_value
-            order_target_value(
-                context.asset,
-                target_hodl_value,
-                limit_price=1.1 * price,
-                stop_price=0.9 * price,
-            )
-        
-        # Record any state for later analysis
-        record(
-            price=price,
-            cash=context.portfolio.cash,
-            leverage=context.account.leverage,
-        )
-
-
-You can then run this algorithm using the Catalyst CLI. From the command
-line, run:
-
-.. code:: bash
-
-    $ catalyst ingest
-    $ catalyst run -f buy_and_hodl.py --start 2015-3-1 --end 2017-6-28 --capital-base 100000 -o bah.pickle
-
-This will download the crypto-asset price data from a poloniex bundle
-curated by Enigma in the specified time range and stream it through
-the algorithm and plot the resulting performance using matplotlib.
-
-You can find other examples in the ``catalyst/examples`` directory.
-
-Limitations
------------
-
-This project is currently in a pre-alpha state and has some limitations we'd like to address:
-
-- *Minimum Denomination:* The smallest tradable unit in Catalyst is equal to 1/1000th of a full coin. We plan to enable more granular increments, but have capped it at 1/1000th for the time being.
-- *Supported Assets:* Currently the poloniex bundle comes prepopulated with data for all 90 registered trading pairs. However, due to limitations in how portfolios are currently modeled, we recommend sticking to ``USDT_*`` trading pairs. USDT is an independent currency listed on Poloniex whose price is pegged to the US dollar. Currently, this list includes: ``USDT_BTC``, ``USDT_DASH``, ``USDT_ETC``, ``USDT_ETH``, ``USDT_LTC``, ``USDT_NXT``, ``USDT_REP``, ``USDT_STR``, ``USDT_XMR``, ``USDT_XRP``, and ``USDT_ZEC``. We plan to add support for basing your portfolio in arbitrary currencies and provide native support for modeling ForEx trades in the near future!
-
-Virtual Environments
-====================
-
-Here we will provide a brief tutorial for installing ``virtualenv`` and its basic usage.
-For more information regarding ``virtualenv``, please refer to this `virtualenv guide <http://python-guide-pt-br.readthedocs.io/en/latest/dev/virtualenvs/>`_.
-
-The ``virtualenv`` command can be installed using:
-
-.. code-block:: bash
-
-    $ pip install virtualenv
-
-To create a new virtual environment, choose a directory, e.g. ``/path/to/venv-dir``, where project-specific packages and files will be stored.  The environment is created by running:
-
-.. code-block:: bash
-
-    $ virtualenv /path/to/venv-dir
-
-To enter an environment, run the ``bin/activate`` script located in ``/path/to/venv-dir`` using:
-
-.. code-block:: bash
-
-    $ source /path/to/venv-dir/bin/activate
-
-Exiting an environment is accomplished using ``deactivate``, and removing it entirely is done by deleting ``/path/to/venv-dir``.
-
-OS X + virtualenv + matplotlib
--------------------------------------
-
-A note about using matplotlib in virtual enviroments on OS X: it may be necessary to run
-
-.. code-block:: python
-
-    echo "backend: TkAgg" > ~/.matplotlib/matplotlibrc
-
-in order to override the default ``macosx`` backend for your system, which may not be accessible from inside the virtual environment.
-This will allow Catalyst to open matplotlib charts from within a virtual environment, which is useful for displaying the performance of your backtests.  To learn more about matplotlib backends, please refer to the
-`matplotlib backend documentation <https://matplotlib.org/faq/usage_faq.html#what-is-a-backend>`_.
-
-Disclaimer
-==========
-
-Keep in mind that this project is still under active development, and is not recommended for production use in its current state.
-We are deeply committed to improving the overall user experience, reliability, and feature-set offered by Catalyst.
-If you have any suggestions, feedback, or general improvements regarding any of these topics, please let us know!
-
-Hello World,
-
-The Enigma Team
-
-.. |version status| image:: https://img.shields.io/pypi/pyversions/enigma-catalyst.svg
-   :target: https://pypi.python.org/pypi/enigma-catalyst
+All the documentation for `Catalyst <https://github.com/enigmampc/catalyst>`_ can be found in the `catalyst-docs wiki <https://github.com/enigmampc/catalyst-docs/wiki>`_.

catalyst/__main__.py

@@ -28,9 +28,9 @@ except NameError:
     '--strict-extensions/--non-strict-extensions',
     is_flag=True,
     help='If --strict-extensions is passed then catalyst will not run if it'
-    ' cannot load all of the specified extensions. If this is not passed or'
-    ' --non-strict-extensions is passed then the failure will be logged but'
-    ' execution will continue.',
+         ' cannot load all of the specified extensions. If this is not passed or'
+         ' --non-strict-extensions is passed then the failure will be logged but'
+         ' execution will continue.',
 )
 @click.option(
     '--default-extension/--no-default-extension',
@@ -64,6 +64,7 @@ def extract_option_object(option):
     option_object : click.Option
         The option object that this decorator will create.
     """
+
     @option
     def opt():
         pass
@@ -95,7 +96,9 @@ def ipython_only(option):
         def _(*args, **kwargs):
             kwargs[argname] = None
             return f(*args, **kwargs)
+
         return _
+
     return d
 
 
@@ -117,13 +120,13 @@ def ipython_only(option):
     '--define',
     multiple=True,
     help="Define a name to be bound in the namespace before executing"
-    " the algotext. For example '-Dname=value'. The value may be any python"
-    " expression. These are evaluated in order so they may refer to previously"
-    " defined names.",
+         " the algotext. For example '-Dname=value'. The value may be any python"
+         " expression. These are evaluated in order so they may refer to previously"
+         " defined names.",
 )
 @click.option(
     '--data-frequency',
-    type=click.Choice({'daily', 'minute'}),
+    type=click.Choice({'daily', '5-minute', 'minute'}),
     default='daily',
     show_default=True,
     help='The data frequency of the simulation.',
@@ -149,7 +152,7 @@ def ipython_only(option):
     default=pd.Timestamp.utcnow(),
     show_default=False,
     help='The date to lookup data on or before.\n'
-    '[default: <current-time>]'
+         '[default: <current-time>]'
 )
 @click.option(
     '-s',
@@ -170,7 +173,7 @@ def ipython_only(option):
     metavar='FILENAME',
     show_default=True,
     help="The location to write the perf data. If this is '-' the perf will"
-    " be written to stdout.",
+         " be written to stdout.",
 )
 @click.option(
     '--print-algo/--no-print-algo',
@@ -184,6 +187,29 @@ def ipython_only(option):
     default=None,
     help='Should the algorithm methods be resolved in the local namespace.'
 ))
+@click.option(
+    '--live/--no-live',
+    is_flag=True,
+    default=False,
+    help='Enable live trading.',
+)
+@click.option(
+    '-x',
+    '--exchange-name',
+    type=click.Choice({'bitfinex', 'bittrex'}),
+    help='The name of the targeted exchange (supported: bitfinex, bittrex).',
+)
+@click.option(
+    '-n',
+    '--algo-namespace',
+    help='A label assigned to the algorithm for data storage purposes.'
+)
+@click.option(
+    '-c',
+    '--base-currency',
+    help='The base currency used to calculate statistics '
+         '(e.g. usd, btc, eth).',
+)
 @click.pass_context
 def run(ctx,
         algofile,
@@ -197,21 +223,37 @@ def run(ctx,
         end,
         output,
         print_algo,
-        local_namespace):
+        local_namespace,
+        live,
+        exchange_name,
+        algo_namespace,
+        base_currency):
     """Run a backtest for the given algorithm.
     """
-    # check that the start and end dates are passed correctly
-    if start is None and end is None:
-        # check both at the same time to avoid the case where a user
-        # does not pass either of these and then passes the first only
-        # to be told they need to pass the second argument also
-        ctx.fail(
-            "must specify dates with '-s' / '--start' and '-e' / '--end'",
-        )
-    if start is None:
-        ctx.fail("must specify a start date with '-s' / '--start'")
-    if end is None:
-        ctx.fail("must specify an end date with '-e' / '--end'")
+
+    if live:
+        if exchange_name is None:
+            ctx.fail("must specify an exchange name '-x' in live execution "
+                     "mode '--live'")
+        if algo_namespace is None:
+            ctx.fail("must specify an algorithm name '-n' in live execution "
+                     "mode '--live'")
+        if base_currency is None:
+            ctx.fail("must specify a base currency '-c' in live "
+                     "execution mode '--live'")
+    else:
+        # check that the start and end dates are passed correctly
+        if start is None and end is None:
+            # check both at the same time to avoid the case where a user
+            # does not pass either of these and then passes the first only
+            # to be told they need to pass the second argument also
+            ctx.fail(
+                "must specify dates with '-s' / '--start' and '-e' / '--end'",
+            )
+        if start is None:
+            ctx.fail("must specify a start date with '-s' / '--start'")
+        if end is None:
+            ctx.fail("must specify an end date with '-e' / '--end'")
 
     if (algotext is not None) == (algofile is not None):
         ctx.fail(
@@ -238,6 +280,10 @@ def run(ctx,
         print_algo=print_algo,
         local_namespace=local_namespace,
         environ=os.environ,
+        live=live,
+        exchange=exchange_name,
+        algo_namespace=algo_namespace,
+        base_currency=base_currency
     )
 
     if output == '-':
@@ -265,11 +311,11 @@ def catalyst_magic(line, cell=None):
                 '--algotext', cell,
                 '--output', os.devnull,  # don't write the results by default
             ] + ([
-                # these options are set when running in line magic mode
-                # set a non None algo text to use the ipython user_ns
-                '--algotext', '',
-                '--local-namespace',
-            ] if cell is None else []) + line.split(),
+                     # these options are set when running in line magic mode
+                     # set a non None algo text to use the ipython user_ns
+                     '--algotext', '',
+                     '--local-namespace',
+                 ] if cell is None else []) + line.split(),
             '%s%%catalyst' % ((cell or '') and '%'),
             # don't use system exit and propogate errors to the caller
             standalone_mode=False,
@@ -290,6 +336,13 @@ def catalyst_magic(line, cell=None):
     show_default=True,
     help='The data bundle to ingest.',
 )
+@click.option(
+    '-c',
+    '--compile-locally',
+    is_flag=True,
+    default=False,
+    help='Download dataset from source and compile bundle locally.',
+)
 @click.option(
     '--assets-version',
     type=int,
@@ -301,7 +354,7 @@ def catalyst_magic(line, cell=None):
     default=True,
     help='Print progress information to the terminal.'
 )
-def ingest(bundle, assets_version, show_progress):
+def ingest(bundle, compile_locally, assets_version, show_progress):
     """Ingest the data for the given bundle.
     """
     bundles_module.ingest(
@@ -310,6 +363,7 @@ def ingest(bundle, assets_version, show_progress):
         pd.Timestamp.utcnow(),
         assets_version,
         show_progress,
+        compile_locally,
     )
 
 
@@ -327,14 +381,14 @@ def ingest(bundle, assets_version, show_progress):
     '--before',
     type=Timestamp(),
     help='Clear all data before TIMESTAMP.'
-    ' This may not be passed with -k / --keep-last',
+         ' This may not be passed with -k / --keep-last',
 )
 @click.option(
     '-a',
     '--after',
     type=Timestamp(),
     help='Clear all data after TIMESTAMP'
-    ' This may not be passed with -k / --keep-last',
+         ' This may not be passed with -k / --keep-last',
 )
 @click.option(
     '-k',
@@ -342,7 +396,7 @@ def ingest(bundle, assets_version, show_progress):
     type=int,
     metavar='N',
     help='Clear all but the last N downloads.'
-    ' This may not be passed with -e / --before or -a / --after',
+         ' This may not be passed with -e / --before or -a / --after',
 )
 def clean(bundle, before, after, keep_last):
     """Clean up data downloaded with the ingest command.

catalyst/algorithm.py

@@ -133,7 +133,10 @@ from catalyst.utils.security_list import SecurityList
 import catalyst.protocol
 from catalyst.sources.requests_csv import PandasRequestsCSV
 
-from catalyst.gens.sim_engine import MinuteSimulationClock
+from catalyst.gens.sim_engine import (
+    MinuteSimulationClock,
+    FiveMinuteSimulationClock,
+)
 from catalyst.sources.benchmark_source import BenchmarkSource
 from catalyst.catalyst_warnings import ZiplineDeprecationWarning
 
@@ -170,7 +173,7 @@ class TradingAlgorithm(object):
     algo_filename : str, optional
         The filename for the algoscript. This will be used in exception
         tracebacks. default: '<string>'.
-    data_frequency : {'daily', 'minute'}, optional
+    data_frequency : {'daily', '5-minute', 'minute'}, optional
         The duration of the bars.
     instant_fill : bool, optional
         Whether to fill orders immediately or on next bar. default: False
@@ -223,7 +226,7 @@ class TradingAlgorithm(object):
             script : str
                 Algoscript that contains initialize and
                 handle_data function definition.
-            data_frequency : {'daily', 'minute'}
+            data_frequency : {'daily', '5-minute', 'minute'}
                The duration of the bars.
             capital_base : float <default: 1.0e5>
                How much capital to start with.
@@ -305,7 +308,10 @@ class TradingAlgorithm(object):
         self.asset_finder = self.trading_environment.asset_finder
 
         # Initialize Pipeline API data.
-        self.init_engine(kwargs.pop('get_pipeline_loader', None))
+        self.init_engine(
+            kwargs.pop('get_pipeline_loader', None),
+            self.sim_params.data_frequency,
+        )
         self._pipelines = {}
         # Create an always-expired cache so that we compute the first time data
         # is requested.
@@ -419,16 +425,28 @@ class TradingAlgorithm(object):
 
         self.restrictions = NoRestrictions()
 
-    def init_engine(self, get_loader):
+    def init_engine(self, get_loader, data_frequency):
         """
         Construct and store a PipelineEngine from loader.
 
         If get_loader is None, constructs an ExplodingPipelineEngine
         """
         if get_loader is not None:
+            if data_frequency == 'daily':
+                all_dates = self.trading_calendar.all_sessions
+            elif data_frequency == '5-minute':
+                all_dates = self.trading_calendar.all_five_minutes
+            elif data_frequency == 'minute':
+                all_dates = self.trading_calendar.all_minutes
+            else:
+                raise ValueError(
+                    'Cannot initialize engine with '
+                    'data frequency: {}'.format(data_frequency)
+                )
+
             self.engine = SimplePipelineEngine(
                 get_loader,
-                self.trading_calendar.all_sessions,
+                all_dates,
                 self.asset_finder,
             )
         else:
@@ -449,7 +467,7 @@ class TradingAlgorithm(object):
         self._in_before_trading_start = True
 
         with handle_non_market_minutes(data) if \
-                self.data_frequency == "minute" else ExitStack():
+                self.data_frequency in ('minute', '5-minute') else ExitStack():
             self._before_trading_start(self, data)
 
         self._in_before_trading_start = False
@@ -505,10 +523,11 @@ class TradingAlgorithm(object):
         market_closes = trading_o_and_c['market_close']
         minutely_emission = False
 
-        if self.sim_params.data_frequency == 'minute':
+        if self.sim_params.data_frequency in set(('minute', '5-minute')):
             market_opens = trading_o_and_c['market_open']
 
-            minutely_emission = self.sim_params.emission_rate == "minute"
+            minutely_emission = self.sim_params.emission_rate in \
+                set(('minute', '5-minute'))
         else:
             # in daily mode, we want to have one bar per session, timestamped
             # as the last minute of the session.
@@ -528,10 +547,19 @@ class TradingAlgorithm(object):
         # FIXME generalize these values
         before_trading_start_minutes = days_at_time(
             self.sim_params.sessions,
-            time(8, 45),
-            "US/Eastern"
+            time(0, 0),
+            'UTC',
         )
 
+        if self.sim_params.data_frequency == '5-minute':
+            return FiveMinuteSimulationClock(
+                self.sim_params.sessions,
+                execution_opens,
+                execution_closes,
+                before_trading_start_minutes,
+                minute_emission=minutely_emission,
+            )
+
         return MinuteSimulationClock(
             self.sim_params.sessions,
             execution_opens,
@@ -660,8 +688,11 @@ class TradingAlgorithm(object):
                     # Assume data is daily if timestamp times are
                     # standardized, otherwise assume minute bars.
                     times = data.major_axis.time
-                    if np.all(times == times[0]):
+                    time_count = times.nunique()
+                    if time_count == 1:
                         self.sim_params.data_frequency = 'daily'
+                    elif time_count == 288:
+                        self.sim_params.data_frequency = '5-minute'
                     else:
                         self.sim_params.data_frequency = 'minute'
 
@@ -683,6 +714,8 @@ class TradingAlgorithm(object):
 
                 if self.sim_params.data_frequency == 'daily':
                     equity_reader_arg = 'equity_daily_reader'
+                elif self.sim_params.data_frequency == '5-minute':
+                    equity_daily_reader = 'equity_5_minute_reader'
                 elif self.sim_params.data_frequency == 'minute':
                     equity_reader_arg = 'equity_minute_reader'
                 equity_reader = PanelBarReader(
@@ -926,9 +959,9 @@ class TradingAlgorithm(object):
                   The arena from the simulation parameters. This will normally
                   be ``'backtest'`` but some systems may use this distinguish
                   live trading from backtesting.
-              data_frequency : {'daily', 'minute'}
+              data_frequency : {'daily', '5-minute', 'minute'}
                   data_frequency tells the algorithm if it is running with
-                  daily data or minute data.
+                  daily, minute, or five-minute mode.
               start : datetime
                   The start date for the simulation.
               end : datetime
@@ -1103,11 +1136,18 @@ class TradingAlgorithm(object):
                           'time_rule= when calling schedule_function without '
                           'specifying a date_rule', stacklevel=3)
         
+        freq = self.sim_params.data_frequency
+
         date_rule = date_rule or date_rules.every_day()
-        time_rule = ((time_rule or time_rules.every_minute())
-                     if self.sim_params.data_frequency == 'minute' else
-                     # If we are in daily mode the time_rule is ignored.
-                     time_rules.every_minute())
+        if freq is 'daily':
+            # ignore time rule in daily mode
+            time_rule = time_rules.every_minute()
+        else:
+            # use provided time rule or default to every minute or 5 minutes
+            # based on desired data frequency.
+            time_rule = time_rule or (time_rules.every_5_minutes()
+                                      if freq is '5-minute' else
+                                      time_rules.every_minute())
 
         # Check the type of the algorithm's schedule before pulling calendar
         # Note that the ExchangeTradingSchedule is currently the only
@@ -1782,7 +1822,7 @@ class TradingAlgorithm(object):
 
     @data_frequency.setter
     def data_frequency(self, value):
-        assert value in ('daily', 'minute')
+        assert value in ('daily', '5-minute', 'minute')
         self.sim_params.data_frequency = value
 
     @api_method

catalyst/assets/_assets.pyx

@@ -20,31 +20,31 @@ Cythonized Asset object.
 cimport cython
 from cpython.number cimport PyNumber_Index
 from cpython.object cimport (
-    Py_EQ,
-    Py_NE,
-    Py_GE,
-    Py_LE,
-    Py_GT,
-    Py_LT,
+Py_EQ,
+Py_NE,
+Py_GE,
+Py_LE,
+Py_GT,
+Py_LT,
 )
 from cpython cimport bool
 
+import pandas as pd
+from datetime import timedelta
 import numpy as np
 from numpy cimport int64_t
 import warnings
 cimport numpy as np
 
 from catalyst.utils.calendars import get_calendar
-
+from catalyst.exchange.exchange_errors import InvalidSymbolError, SidHashError
 
 # IMPORTANT NOTE: You must change this template if you change
 # Asset.__reduce__, or else we'll attempt to unpickle an old version of this
 # class
 CACHE_FILE_TEMPLATE = '/tmp/.%s-%s.v7.cache'
 
-
 cdef class Asset:
-
     cdef readonly int sid
     # Cached hash of self.sid
     cdef int sid_hash
@@ -73,8 +73,8 @@ cdef class Asset:
     })
 
     def __init__(self,
-                 int sid, # sid is required
-                 object exchange, # exchange is required
+                 int sid,  # sid is required
+                 object exchange,  # exchange is required
                  object symbol="",
                  object asset_name="",
                  object start_date=None,
@@ -230,9 +230,7 @@ cdef class Asset:
         calendar = get_calendar(self.exchange)
         return calendar.is_open_on_minute(dt_minute)
 
-
 cdef class Equity(Asset):
-
     def __repr__(self):
         attrs = ('symbol', 'asset_name', 'exchange',
                  'start_date', 'end_date', 'first_traded', 'auto_close_date',
@@ -250,8 +248,8 @@ cdef class Equity(Asset):
         """
         def __get__(self):
             warnings.warn("The security_start_date property will soon be "
-            "retired. Please use the start_date property instead.",
-            DeprecationWarning)
+                          "retired. Please use the start_date property instead.",
+                          DeprecationWarning)
             return self.start_date
 
     property security_end_date:
@@ -261,8 +259,8 @@ cdef class Equity(Asset):
         """
         def __get__(self):
             warnings.warn("The security_end_date property will soon be "
-            "retired. Please use the end_date property instead.",
-            DeprecationWarning)
+                          "retired. Please use the end_date property instead.",
+                          DeprecationWarning)
             return self.end_date
 
     property security_name:
@@ -272,13 +270,11 @@ cdef class Equity(Asset):
         """
         def __get__(self):
             warnings.warn("The security_name property will soon be "
-            "retired. Please use the asset_name property instead.",
-            DeprecationWarning)
+                          "retired. Please use the asset_name property instead.",
+                          DeprecationWarning)
             return self.asset_name
 
-
 cdef class Future(Asset):
-
     cdef readonly object root_symbol
     cdef readonly object notice_date
     cdef readonly object expiration_date
@@ -303,8 +299,8 @@ cdef class Future(Asset):
     })
 
     def __init__(self,
-                 int sid, # sid is required
-                 object exchange, # exchange is required
+                 int sid,  # sid is required
+                 object exchange,  # exchange is required
                  object symbol="",
                  object root_symbol="",
                  object asset_name="",
@@ -388,6 +384,160 @@ cdef class Future(Asset):
         super_dict['multiplier'] = self.multiplier
         return super_dict
 
+cdef class TradingPair(Asset):
+    cdef readonly float leverage
+    cdef readonly object market_currency
+    cdef readonly object base_currency
+
+    _kwargnames = frozenset({
+        'sid',
+        'symbol',
+        'asset_name',
+        'start_date',
+        'end_date',
+        'first_traded',
+        'auto_close_date',
+        'exchange',
+        'exchange_full',
+        'leverage',
+        'market_currency',
+        'base_currency'
+    })
+    def __init__(self,
+                 object symbol,
+                 object exchange,
+                 object start_date=None,
+                 object asset_name=None,
+                 int sid=0,
+                 float leverage=1.0,
+                 object end_date=None,
+                 object first_traded=None,
+                 object auto_close_date=None,
+                 object exchange_full=None):
+        """
+        Replicates the Asset constructor with some built-in conventions
+        and a new 'leverage' attribute.
+
+        Symbol
+        ------
+        Catalyst defines its own set of "universal" symbols to reference
+        trading pairs across exchanges. This is required because exchanges
+        are not adhering to a universal symbolism. For example, Bitfinex
+        uses the BTC symbol for Bitcon while Kraken uses XBT. In addition,
+        pairs are sometimes presented differently. For example, Bitfinex
+        puts the market currency before the base currency without a
+        separator, Bittrex puts the base currency first and uses a dash
+        seperator.
+
+        Here is the Catalyst convention: [Market Currency]_[Base Currency]
+        For example: btc_usd, eth_btc, neo_eth, ltc_eur.
+
+        The symbol for each currency (e.g. btc, eth, ltc) is generally
+        aligned with the Bittrex exchange.
+
+        Sid
+        ---
+        The sid of each asset is calculated based on a numeric hash of the
+        universal symbol. This simple approach avoids maintaining a mapping
+        of sids.
+
+        Leverage
+        --------
+        In contrast with equities, crypto exchanges generally assign
+        leverage values to specific trading pairs. Pairs with the
+        highest volume and market cap generally benefit from high leverage.
+        New currencies from ICO generally cannot be leveraged.
+
+        The leverage value is either None or and integer.
+
+        Leverage allows you to open a larger position with a smaller amount
+        of funds. For example, if you open a $5,000 position in BTC/USD
+        with 5:1 leverage, only one-fifth of this amount, or $1000, will be
+        tied to the position from your balance. Your remaining balance will
+        be available for opening more positions. If you open this same
+        position with 2:1 leverage, $2,500 of your balance will be tied to
+        the position. If you open with 1:1 leverage, $5,000 of your balance
+        will be tied to the position.
+
+        :param symbol:
+        :param exchange:
+        :param start_date:
+        :param asset_name:
+        :param sid:
+        :param leverage:
+        :param end_date:
+        :param first_traded:
+        :param auto_close_date:
+        :param exchange_full:
+        """
+
+        symbol = symbol.lower()
+        try:
+            self.market_currency, self.base_currency = symbol.split('_')
+        except Exception as e:
+            raise InvalidSymbolError(symbol=symbol, error=e)
+
+        if sid == 0 or sid is None:
+            try:
+                sid = abs(hash(symbol)) % (10 ** 4)
+            except Exception as e:
+                raise SidHashError(symbol=symbol)
+
+        if asset_name is None:
+            asset_name = ' / '.join(symbol.split('_')).upper()
+
+        if start_date is None:
+            start_date = pd.Timestamp.utcnow()
+
+        if end_date is None:
+            end_date = pd.Timestamp.utcnow() + timedelta(days=365)
+
+        super().__init__(
+            sid,
+            exchange,
+            symbol=symbol,
+            asset_name=asset_name,
+            start_date=start_date,
+            end_date=end_date,
+            first_traded=first_traded,
+            auto_close_date=auto_close_date,
+            exchange_full=exchange_full,
+        )
+
+        self.leverage = leverage
+
+    def __repr__(self):
+        return 'Trading Pair {symbol}({sid}) Exchange: {exchange}, ' \
+               'Introduced On: {start_date}, ' \
+               'Market Currency: {market_currency}, ' \
+               'Base Currency: {base_currency}, ' \
+               'Exchange Leverage: {leverage}'.format(
+            symbol=self.symbol,
+            sid=self.sid,
+            exchange=self.exchange,
+            start_date=self.start_date,
+            market_currency=self.market_currency,
+            base_currency=self.base_currency,
+            leverage=self.leverage
+        )
+
+    cpdef __reduce__(self):
+        """
+        Function used by pickle to determine how to serialize/deserialize this
+        class.  Should return a tuple whose first element is self.__class__,
+        and whose second element is a tuple of all the attributes that should
+        be serialized/deserialized during pickling.
+        """
+        return (self.__class__, (self.symbol,
+                                 self.exchange,
+                                 self.start_date,
+                                 self.asset_name,
+                                 self.sid,
+                                 self.leverage,
+                                 self.end_date,
+                                 self.first_traded,
+                                 self.auto_close_date,
+                                 self.exchange_full))
 
 def make_asset_array(int size, Asset asset):
     cdef np.ndarray out = np.empty([size], dtype=object)

catalyst/data/_minute_bar_internal.pyx

@@ -35,6 +35,17 @@ def minute_value(ndarray[long_t, ndim=1] market_opens,
 
     return market_opens[q] + r
 
+@cython.cdivision(True)
+def five_minute_value(ndarray[long_t, ndim=1] market_opens,
+                      Py_ssize_t pos,
+                      short five_minutes_per_day):
+
+    cdef short q, r
+    q = cython.cdiv(pos, five_minutes_per_day)
+    r = cython.cmod(pos, five_minutes_per_day)
+
+    return market_opens[q] + r
+
 def find_position_of_minute(ndarray[long_t, ndim=1] market_opens,
                             ndarray[long_t, ndim=1] market_closes,
                             long_t minute_val,
@@ -88,6 +99,26 @@ def find_position_of_minute(ndarray[long_t, ndim=1] market_opens,
 
     return (market_open_loc * minutes_per_day) + delta
 
+def find_position_of_five_minute(ndarray[long_t, ndim=1] market_opens,
+                                 ndarray[long_t, ndim=1] market_closes,
+                                 long_t five_minute_val,
+                                 short five_minutes_per_day,
+                                 bool forward_fill):
+
+    cdef Py_ssize_t market_open_loc, market_open, delta
+
+    market_open_loc = \
+        searchsorted(market_opens, five_minute_val, side='right') - 1
+    market_open = market_opens[market_open_loc]
+    market_close = market_closes[market_open_loc]
+
+    if not forward_fill and ((five_minute_val - market_open) >= five_minutes_per_day):
+        raise ValueError("Given five minutes is not between an open and a close")
+
+    delta = int_min(five_minute_val - market_open, market_close - market_open)
+
+    return (market_open_loc * five_minutes_per_day) + delta
+
 def find_last_traded_position_internal(
         ndarray[long_t, ndim=1] market_opens,
         ndarray[long_t, ndim=1] market_closes,
@@ -157,3 +188,51 @@ def find_last_traded_position_internal(
     # we've gone to the beginning of this asset's range, and still haven't
     # found a trade event
     return -1
+
+def find_last_traded_five_minute_position_internal(
+        ndarray[long_t, ndim=1] market_opens,
+        ndarray[long_t, ndim=1] market_closes,
+        long_t end_five_minute,
+        long_t start_five_minute,
+        volumes,
+        short five_minutes_per_day):
+    cdef Py_ssize_t minute_pos, current_minute, q
+
+    five_minute_pos = int_min(
+        find_position_of_five_minute(
+            market_opens,
+            market_closes,
+            end_five_minute,
+            five_minutes_per_day,
+            True,
+        ),
+        len(volumes) - 1,
+    )
+
+    while five_minute_pos >= 0:
+        current_five_minute = five_minute_value(
+            market_opens, five_minute_pos, five_minutes_per_day
+        )
+
+        q = cython.cdiv(five_minute_pos, five_minutes_per_day)
+        if current_five_minute > market_closes[q]:
+            five_minute_pos = find_position_of_five_minute(
+                market_opens,
+                market_closes,
+                market_closes[q],
+                five_minutes_per_day,
+                False,
+            )
+            continue
+
+        if current_five_minute < start_five_minute:
+            return -1
+
+        if volumes[five_minute_pos] != 0:
+            return five_minute_pos
+
+        five_minute_pos -= 1
+
+    # we've gone to the beginning of this asset's range, and still haven't
+    # found a trade event
+    return -1

catalyst/data/bundles/base.py

@@ -0,0 +1,524 @@
+#
+# Copyright 2017 Enigma MPC, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+from itertools import count
+import tarfile
+from time import time, sleep
+
+from abc import abstractmethod, abstractproperty
+import logbook
+import pandas as pd
+
+from . import core as bundles
+
+from catalyst.utils.cli import (
+    item_show_count,
+    maybe_show_progress
+)
+from catalyst.utils.memoize import lazyval
+
+logbook.StderrHandler().push_application()
+log = logbook.Logger(__name__)
+
+DEFAULT_RETRIES = 5
+
+class BaseBundle(object):
+    def __init__(self, asset_filter=[]):
+        self._asset_filter = asset_filter
+        self._reset()
+
+    def _reset(self):
+        self._splits = []
+        self._dividends = []
+
+    @lazyval
+    def name(self):
+        raise NotImplementedError()
+
+    @lazyval
+    def exchange(self):
+        raise NotImplementedError()
+
+    @lazyval
+    def calendar_name(self):
+        raise NotImplementedError()
+
+    @lazyval
+    def minutes_per_day(self):
+        raise NotImplementedError()
+
+    @lazyval
+    def five_minutes_per_day(self):
+        raise NotImplementedError()
+
+    @lazyval
+    def frequencies(self):
+        raise NotImplementedError()
+
+    @lazyval
+    def md_column_names(self):
+        return _dtypes_to_cols(self.md_dtypes)
+
+    @lazyval
+    def md_dtypes(self):
+        raise NotImplementedError()
+
+    @lazyval
+    def column_names(self):
+        return _dtypes_to_cols(self.dtypes)
+
+    @lazyval
+    def dtypes(self):
+        raise NotImplementedError()
+
+    @lazyval
+    def tar_url(self):
+        raise NotImplementedError()
+
+    @lazyval
+    def wait_time(self):
+        raise NotImplementedError()
+
+    @abstractproperty
+    def splits(self):
+        raise NotImplementedError()
+
+    @abstractproperty
+    def dividends(self):
+        raise NotImplementedError()
+
+    @abstractmethod
+    def fetch_raw_metadata_frame(self, api_key, page_number):
+        raise NotImplementedError()
+
+    def post_process_symbol_metadata(self, metadata, data):
+        return metadata
+    
+    @abstractmethod
+    def fetch_raw_symbol_frame(self, api_key, symbol, start_date, end_date):
+        raise NotImplementedError()
+    
+    def ingest(self,
+               environ,
+               asset_db_writer,
+               minute_bar_writer,
+               five_minute_bar_writer,
+               daily_bar_writer,
+               adjustment_writer,
+               calendar,
+               start_session,
+               end_session,
+               cache,
+               show_progress,
+               is_compile,
+               output_dir):
+
+        try:
+            api_key = environ.get('CATALYST_API_KEY')
+            retries = environ.get('CATALYST_DOWNLOAD_ATTEMPTS', 5)
+
+            if is_compile:
+                # User has instructed local compilation and ingestion of bundle.
+                # Fetch raw metadata for all symbols.
+                raw_metadata = self._fetch_metadata_frame(
+                    api_key,
+                    cache=cache,
+                    retries=retries,
+                    environ=environ,
+                    show_progress=show_progress,
+                )
+
+                # Compile daily symbol data if bundle supports daily mode and
+                # persist the dataset to disk.
+                symbol_map = raw_metadata.symbol
+                if 'daily' in self.frequencies:
+                    daily_bar_writer.write(
+                        self._fetch_symbol_iter(
+                            api_key,
+                            cache,
+                            symbol_map,
+                            calendar,
+                            start_session,
+                            end_session,
+                            'daily',
+                            retries,
+                        ),
+                        assets=raw_metadata.index,
+                        show_progress=show_progress,
+                    )
+
+                # Post-process metadata using cached symbol frames, and write to
+                # disk.  This metadata must be written before any attempt to write
+                # either minute or 5-minute data.
+                metadata = self._post_process_metadata(
+                    raw_metadata,
+                    cache,
+                    show_progress=show_progress,
+                )
+                asset_db_writer.write(metadata)
+
+                # Compile 5-minute symbol data if bundle supports 5-minute mode and
+                # persist the dataset to disk.
+                '''
+                if '5-minute' in self.frequencies:
+                    five_minute_bar_writer.write(
+                        self._fetch_symbol_iter(
+                            api_key,
+                            cache,
+                            symbol_map,
+                            calendar,
+                            start_session,
+                            end_session,
+                            '5-minute',
+                            retries,
+                        ),
+                        length=len(symbol_map),
+                        show_progress=show_progress,
+                    )
+                '''
+
+                # Compile minute symbol data if bundle supports minute mode and
+                # persist the dataset to disk.
+                if 'minute' in self.frequencies:
+                    minute_bar_writer.write(
+                        self._fetch_symbol_iter(
+                            api_key,
+                            cache,
+                            symbol_map,
+                            calendar,
+                            start_session,
+                            end_session,
+                            'minute',
+                            retries,
+                        ),
+                        show_progress=show_progress,
+                    )
+
+                # For legacy purposes, this call is required to ensure the database
+                # contains an appropriately initialized file structure.  We don't
+                # forsee a usecase for adjustments at this time, but may later
+                # choose to expose this functionality in the future.
+                adjustment_writer.write(
+                    splits=(
+                        pd.concat(self.splits, ignore_index=True)
+                        if len(self.splits) > 0 else
+                        None
+                    ),
+                    dividends=(
+                        pd.concat(self.dividends, ignore_index=True)
+                        if len(self.dividends) > 0 else
+                        None
+                    ),
+                )
+            else:
+                # Otherwise, user has instructed to download and untar bundle
+                # directly from the bundles `tar_url`.
+                self._download_and_untar(show_progress, output_dir)
+        except Exception as e:
+            log.exception(
+                ' Failed to ingest {name}:\n{msg}'.format(
+                    name=self.name,
+                    msg=str(e),
+                )
+            )
+        else:
+            self._reset()
+
+    def _download_and_untar(self, show_progress, output_dir):
+        # Download bundle conditioned on whether the user would like progress
+        # information to be displayed in the CLI.
+        if show_progress:
+            data = bundles.download_with_progress(
+                self.tar_url,
+                chunk_size=bundles.ONE_MEGABYTE,
+                label='Downloading {name} bundle'.format(name=self.name),
+            )
+        else:
+            data = bundles.download_without_progress(self.tar_url)
+
+        # File transfer has completed, untar the bundle to the appropriate
+        # data directory.
+        with tarfile.open('r', fileobj=data) as tar:
+            tar.extractall(output_dir)
+
+    def _fetch_metadata_frame(self,
+                             api_key,
+                             cache,
+                             retries=DEFAULT_RETRIES,
+                             environ=None,
+                             show_progress=False):
+        
+        # Setup raw metadata iterator to fetch pages if necessary.
+        raw_iter = self._fetch_metadata_iter(api_key, cache, retries, environ)
+
+        # Concatenate all frame in iterator to compute a single metadata frame.
+        with maybe_show_progress(
+            raw_iter,
+            show_progress,
+            label='Fetching symbol metadata',
+            item_show_func=item_show_count(),
+            length=3,
+            show_percent=False,
+        ) as blocks:
+            metadata = pd.concat(blocks, ignore_index=True)
+        
+        return metadata
+
+    def _fetch_metadata_iter(self, api_key, cache, retries, environ):
+        for page_number in count(1):
+            # Attempt to load metadata page from cache.  If it does not exist,
+            # poll the API upto `retries` times in order to get raw DataFrame.
+            key = 'metadata-page-{pn}.frame'.format(pn=page_number)
+            try:
+                raw = cache[key]
+            except KeyError:
+                for _ in range(retries):
+                    try:
+                        raw = self.fetch_raw_metadata_frame(
+                            api_key,
+                            page_number,
+                        )
+                        break
+                    except ValueError as e:
+                        raw = pd.DataFrame([])
+                        break
+                    except Exception as e:
+                        log.exception(
+                            'Failed to load metadata from {}. '
+                            'Retrying.'.format(self.name)
+                        ) 
+                else:
+                    raise ValueError(
+                        'Failed to download metadata page {} after {} '
+                        'attempts.'.format(page_number, retries)
+                    )
+
+
+            if raw.empty:
+                # Empty DataFrame signals completion.
+                break
+
+            # Apply selective asset filtering, useful for benchmark
+            # ingestion.
+            if self._asset_filter:
+                raw = raw[raw.symbol.isin(self._asset_filter)]
+
+            # Update cached value for key.
+            cache[key] = raw
+
+            # Return metadata frame to application.
+            yield raw
+
+    def _post_process_metadata(self, metadata, cache, show_progress=False):
+        # Create empty data frame using target metadata column names and dtypes
+        final_metadata = pd.DataFrame(
+            columns=self.md_column_names,
+            index=metadata.index,
+        )
+        
+        # Iterate over the available symbols, loading the asset's raw symbol
+        # data from the cache.  The final metadata is computed and recorded in
+        # the appropriate row depending on the asset's id.
+        with maybe_show_progress(
+            metadata.symbol.iteritems(),
+            show_progress,
+            label='Post-processing symbol metadata',
+            item_show_func=item_show_count(len(metadata)),
+            length=len(metadata),
+            show_percent=False,
+        ) as symbols_map:
+            for asset_id, symbol in symbols_map:
+                # Attempt to load data from disk, the cache should have an entry
+                # for each symbol at this point of the execution. If one does
+                # not exist, we should fail.
+                key = '{sym}.daily.frame'.format(sym=symbol)
+                try:
+                    raw_data = cache[key]
+                except KeyError:
+                    raise ValueError(
+                      'Unable to find cached data for symbol: {0}'.format(symbol)
+                    )
+
+                # Perform and require post-processing of metadata.
+                final_symbol_metadata = self.post_process_symbol_metadata(
+                    asset_id,
+                    metadata.iloc[asset_id],
+                    raw_data,        
+                )
+
+                # Record symbol's final metadata.
+                final_metadata.iloc[asset_id] = final_symbol_metadata
+
+            # Register all assets with the bundle's default exchange.
+            final_metadata['exchange'] = self.exchange
+
+        return final_metadata
+
+    def _fetch_symbol_iter(self,
+                           api_key,
+                           cache,
+                           symbol_map,
+                           calendar,
+                           start_session,
+                           end_session,
+                           data_frequency,
+                           retries):
+
+        for asset_id, symbol in symbol_map.iteritems():
+            # Record start time of iteration, compare at end of iteration to
+            # adhere to the datas source's rate limit policy.
+            start_time = pd.Timestamp.utcnow()
+
+            # Fetch new data if cached data is absent or stale, otherwise
+            # returns the cached data unaltered.  The `should_sleep` flag
+            # indicates that an API call was attempted, and that we should be
+            # ensure aren't exceeding our rate limit before proceeding to the
+            # next symbol. If the raw_data is updated, it is cached before being
+            # returned.
+            raw_data, should_sleep = self._maybe_update_symbol_frame(
+                start_time,
+                api_key,
+                cache,
+                symbol,
+                calendar,
+                start_session,
+                end_session,
+                data_frequency,
+                retries,
+            )
+
+            # TODO(cfromknecht) further data validation?
+
+            # Pass asset_id and symbol data to writer.
+            yield asset_id, raw_data
+
+            # If an API call was made during this iteration and the time to
+            # reach this point was less than the inter-request `wait_time`,
+            # sleep until after enough time has elapsed to prevent getting rate
+            # limited.
+            if should_sleep:
+                remaining = pd.Timestamp.utcnow() - start_time + self.wait_time
+                if remaining.value > 0:
+                    sleep(remaining.value / 10**9)
+
+    def _maybe_update_symbol_frame(self,
+                                   start_time,
+                                   api_key,
+                                   cache,
+                                   symbol,
+                                   calendar,
+                                   start_session,
+                                   end_session,
+                                   data_frequency,
+                                   retries):
+
+        # Attempt to load pre-existing symbol data from cache.
+        key = '{sym}.{freq}.frame'.format(sym=symbol, freq=data_frequency)
+        try:
+            raw_data = cache[key]
+        except KeyError:
+            raw_data = None
+
+        # Select the most recent date in cached dataset if it exists,
+        # otherwise use the provided `start_session`.
+        last = start_session
+        if raw_data is not None and len(raw_data) > 0:
+            last = raw_data.index[-1].tz_localize('UTC')
+        
+        should_sleep = False
+
+        # Determine time at which cached data will be considered stale.
+        cache_expiration = last + pd.Timedelta(days=2)
+        if start_time <= cache_expiration and raw_data is not None:
+            # Data is fresh enough to reuse, no need to update. Iterator can
+            # proceed to next symbol directly since no API call was required.
+            return raw_data, should_sleep
+
+        # If we arrive here, we must have attempted an API call.
+        # Setting this flag tells the iterator to pause before starting
+        # the next asset, that we don't exceed the data source's rate
+        # limit.
+        should_sleep = True
+
+        raw_data = self._fetch_symbol_frame(
+            api_key,
+            symbol,
+            calendar,
+            start_session,
+            end_session,
+            data_frequency,
+            retries=retries,
+        )
+
+        # Cache latest symbol data.
+        cache[key] = raw_data
+
+        return raw_data, should_sleep
+
+    def _fetch_symbol_frame(self,
+                            api_key,
+                            symbol,
+                            calendar,
+                            start_session,
+                            end_session,
+                            data_frequency,
+                            retries=DEFAULT_RETRIES):
+
+        # Data for symbol is old enough to attempt an update or is not
+        # present in the cache.  Fetch raw data for a single symbol 
+        # with requested intervals and frequency. Retry as necessary.
+        for _ in range(retries):
+            try:
+                raw_data = self.fetch_raw_symbol_frame(
+                    api_key,
+                    symbol,
+                    calendar,
+                    start_session,
+                    end_session,
+                    data_frequency,
+                )
+                raw_data.index = pd.to_datetime(raw_data.index, utc=True)
+                raw_data.index = raw_data.index.tz_localize('UTC')
+
+                # Filter incoming data to fit start and end sessions.
+                raw_data = raw_data[
+                    (raw_data.index >= start_session) &
+                    (raw_data.index <= end_session)
+                ]
+
+                # Filter out any duplicates entries, keep last one, since
+                # previous frame is probably an incomplete.
+                raw_data = raw_data[~raw_data.index.duplicated(keep='last')]
+
+                return raw_data
+
+            except Exception as e:
+                log.exception(
+                    'Exception raised fetching {name} data. Retrying.'
+                    .format(name=self.name)
+                )
+        else:
+            raise ValueError(
+                'Failed to download data for symbol {sym} '
+                'after {n} attempts.'.format(
+                    sym=symbol,
+                    n=retries,
+                )
+            )
+
+
+def _dtypes_to_cols(dtypes):
+    return [name for name, _ in dtypes]

catalyst/data/bundles/base_pricing.py

@@ -0,0 +1,80 @@
+#
+# Copyright 2017 Enigma MPC, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from catalyst.data.bundles.base import BaseBundle
+from catalyst.utils.memoize import lazyval
+
+class BasePricingBundle(BaseBundle):
+    @lazyval
+    def md_dtypes(self):
+        return [
+            ('symbol', 'object'),
+            ('start_date', 'datetime64[ns]'),
+            ('end_date', 'datetime64[ns]'),
+            ('ac_date', 'datetime64[ns]'),
+        ]
+
+    @lazyval
+    def dtypes(self):
+        return [
+            ('date', 'datetime64[ns]'),
+            ('open', 'float64'),
+            ('high', 'float64'),
+            ('low', 'float64'),
+            ('close', 'float64'),
+            ('volume', 'float64'),
+        ]
+
+class BaseCryptoPricingBundle(BasePricingBundle):
+    @lazyval
+    def calendar_name(self):
+        return 'OPEN'
+
+    @lazyval
+    def minutes_per_day(self):
+        return 1440
+
+    @lazyval
+    def five_minutes_per_day(self):
+        return 288
+
+    @property
+    def splits(self):
+        return []
+
+    @property
+    def dividends(self):
+        return []
+
+class BaseEquityPricingBundle(BasePricingBundle):
+    @lazyval
+    def calendar_name(self):
+        return 'NYSE'
+
+    @lazyval
+    def minutes_per_day(self):
+        return 390
+
+    @lazyval
+    def five_minutes_per_day(self):
+        return 78
+
+    @property
+    def splits(self):
+        return self._splits
+
+    @property
+    def dividends(self):
+        return self._dividends

catalyst/data/bundles/core.py

@@ -17,6 +17,10 @@ from ..us_equity_pricing import (
     SQLiteAdjustmentReader,
     SQLiteAdjustmentWriter,
 )
+from ..five_minute_bars import (
+    BcolzFiveMinuteBarReader,
+    BcolzFiveMinuteBarWriter,
+)
 from ..minute_bars import (
     BcolzMinuteBarReader,
     BcolzMinuteBarWriter,
@@ -33,6 +37,7 @@ from catalyst.utils.input_validation import ensure_timestamp, optionally
 import catalyst.utils.paths as pth
 from catalyst.utils.preprocess import preprocess
 from catalyst.utils.calendars import get_calendar
+from catalyst.utils.cli import maybe_show_progress
 
 ONE_MEGABYTE = 1024 * 1024
 
@@ -43,16 +48,21 @@ def asset_db_path(bundle_name, timestr, environ=None, db_version=None):
     )
 
 
-def minute_equity_path(bundle_name, timestr, environ=None):
+def minute_path(bundle_name, timestr, environ=None):
     return pth.data_path(
-        minute_equity_relative(bundle_name, timestr, environ),
+        minute_relative(bundle_name, timestr, environ),
         environ=environ,
     )
 
-
-def daily_equity_path(bundle_name, timestr, environ=None):
+def five_minute_path(bundle_name, timestr, environ=None):
     return pth.data_path(
-        daily_equity_relative(bundle_name, timestr, environ),
+        five_minute_relative(bundle_name, timestr, environ),
+        environ=environ,
+    )
+
+def daily_path(bundle_name, timestr, environ=None):
+    return pth.data_path(
+        daily_relative(bundle_name, timestr, environ),
         environ=environ,
     )
 
@@ -79,11 +89,13 @@ def cache_relative(bundle_name, timestr, environ=None):
     return bundle_name, '.cache'
 
 
-def daily_equity_relative(bundle_name, timestr, environ=None):
+def daily_relative(bundle_name, timestr, environ=None):
     return bundle_name, timestr, 'daily_equities.bcolz'
 
+def five_minute_relative(bundle_name, timestr, environ=None):
+    return bundle_name, timestr, 'five_minute.bcolz'
 
-def minute_equity_relative(bundle_name, timestr, environ=None):
+def minute_relative(bundle_name, timestr, environ=None):
     return bundle_name, timestr, 'minute_equities.bcolz'
 
 
@@ -158,7 +170,9 @@ def download_with_progress(url, chunk_size, **progress_kwargs):
 
     total_size = int(resp.headers['content-length'])
     data = BytesIO()
-    with click.progressbar(length=total_size, **progress_kwargs) as pbar:
+
+    progress_kwargs['length'] = total_size
+    with maybe_show_progress(None, True, **progress_kwargs) as pbar:
         for chunk in resp.iter_content(chunk_size=chunk_size):
             data.write(chunk)
             pbar.update(len(chunk))
@@ -192,19 +206,20 @@ RegisteredBundle = namedtuple(
      'start_session',
      'end_session',
      'minutes_per_day',
+     'five_minutes_per_day',
      'ingest',
      'create_writers']
 )
 
 BundleData = namedtuple(
     'BundleData',
-    'asset_finder equity_minute_bar_reader equity_daily_bar_reader '
+    'asset_finder minute_bar_reader five_minute_bar_reader daily_bar_reader '
     'adjustment_reader',
 )
 
 BundleCore = namedtuple(
     'BundleCore',
-    'bundles register unregister ingest load clean',
+    'bundles register_bundle register unregister ingest load clean',
 )
 
 
@@ -258,6 +273,8 @@ def _make_bundle_core():
     -------
     bundles : mappingproxy
         The mapping of bundles to bundle payloads.
+    register_bundle : Bundle
+        A bundle instance to add to the ``bundles`` mapping.
     register : callable
         The function which registers new bundles in the ``bundles`` mapping.
     unregister : callable
@@ -275,13 +292,31 @@ def _make_bundle_core():
     # warn when trampling another bundle.
     bundles = mappingproxy(_bundles)
 
+    def register_bundle(bundle_cls,
+                        asset_filter=None,
+                        start_session=None,
+                        end_session=None,
+                        create_writers=True):
+        bundle = bundle_cls(asset_filter=asset_filter)
+        return register(
+            bundle.name,
+            bundle.ingest,
+            calendar_name=bundle.calendar_name,
+            minutes_per_day=bundle.minutes_per_day,
+            five_minutes_per_day=bundle.five_minutes_per_day,
+            start_session=start_session,
+            end_session=end_session,
+            create_writers=create_writers,
+        )
+
     @curry
     def register(name,
                  f,
-                 calendar_name='NYSE',
+                 calendar_name='OPEN',
                  start_session=None,
                  end_session=None,
-                 minutes_per_day=390,
+                 minutes_per_day=1440,
+                 five_minutes_per_day=288,
                  create_writers=True):
         """Register a data bundle ingest function.
 
@@ -362,6 +397,7 @@ def _make_bundle_core():
             start_session=start_session,
             end_session=end_session,
             minutes_per_day=minutes_per_day,
+            five_minutes_per_day=five_minutes_per_day,
             ingest=f,
             create_writers=create_writers,
         )
@@ -393,7 +429,8 @@ def _make_bundle_core():
                environ=os.environ,
                timestamp=None,
                assets_versions=(),
-               show_progress=False):
+               show_progress=False,
+               is_compile=False):
         """Ingest data for a given bundle.
 
         Parameters
@@ -443,7 +480,7 @@ def _make_bundle_core():
                     pth.data_path([], environ=environ))
                 )
                 daily_bars_path = wd.ensure_dir(
-                    *daily_equity_relative(
+                    *daily_relative(
                         name, timestr, environ=environ,
                     )
                 )
@@ -457,10 +494,20 @@ def _make_bundle_core():
                 # when we create the SQLiteAdjustmentWriter below. The
                 # SQLiteAdjustmentWriter needs to open the daily ctables so
                 # that it can compute the adjustment ratios for the dividends.
-
                 daily_bar_writer.write(())
+
+                five_minute_bar_writer = BcolzFiveMinuteBarWriter(
+                    wd.ensure_dir(*five_minute_relative(
+                        name, timestr, environ=environ)
+                    ),
+                    calendar,
+                    start_session,
+                    end_session,
+                    five_minutes_per_day=bundle.five_minutes_per_day,
+                )
+
                 minute_bar_writer = BcolzMinuteBarWriter(
-                    wd.ensure_dir(*minute_equity_relative(
+                    wd.ensure_dir(*minute_relative(
                         name, timestr, environ=environ)
                     ),
                     calendar,
@@ -468,6 +515,7 @@ def _make_bundle_core():
                     end_session,
                     minutes_per_day=bundle.minutes_per_day,
                 )
+
                 assets_db_path = wd.getpath(*asset_db_relative(
                     name, timestr, environ=environ,
                 ))
@@ -484,6 +532,7 @@ def _make_bundle_core():
                 )
             else:
                 daily_bar_writer = None
+                five_minute_bar_writer = None
                 minute_bar_writer = None
                 asset_db_writer = None
                 adjustment_db_writer = None
@@ -495,6 +544,7 @@ def _make_bundle_core():
                 environ,
                 asset_db_writer,
                 minute_bar_writer,
+                five_minute_bar_writer,
                 daily_bar_writer,
                 adjustment_db_writer,
                 calendar,
@@ -502,6 +552,7 @@ def _make_bundle_core():
                 end_session,
                 cache,
                 show_progress,
+                is_compile,
                 pth.data_path([name, timestr], environ=environ),
             )
 
@@ -577,11 +628,14 @@ def _make_bundle_core():
             asset_finder=AssetFinder(
                 asset_db_path(name, timestr, environ=environ),
             ),
-            equity_minute_bar_reader=BcolzMinuteBarReader(
-                minute_equity_path(name, timestr, environ=environ),
+            minute_bar_reader=BcolzMinuteBarReader(
+                minute_path(name, timestr, environ=environ),
             ),
-            equity_daily_bar_reader=BcolzDailyBarReader(
-                daily_equity_path(name, timestr, environ=environ),
+            five_minute_bar_reader=BcolzFiveMinuteBarReader(
+                five_minute_path(name, timestr, environ=environ),
+            ),
+            daily_bar_reader=BcolzDailyBarReader(
+                daily_path(name, timestr, environ=environ),
             ),
             adjustment_reader=SQLiteAdjustmentReader(
                 adjustment_db_path(name, timestr, environ=environ),
@@ -670,7 +724,15 @@ def _make_bundle_core():
 
         return cleaned
 
-    return BundleCore(bundles, register, unregister, ingest, load, clean)
+    return BundleCore(
+        bundles,
+        register_bundle,
+        register,
+        unregister,
+        ingest,
+        load,
+        clean,
+    )
 
 
-bundles, register, unregister, ingest, load, clean = _make_bundle_core()
+bundles, register_bundle, register, unregister, ingest, load, clean = _make_bundle_core()

catalyst/data/bundles/poloniex.py

@@ -1,38 +1,169 @@
-from io import BytesIO
-import tarfile
+#
+# Copyright 2017 Enigma MPC, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
 
-from . import core as bundles
+from datetime import datetime
 
-POLONIEX_BUNDLE_URL = (
-    'https://www.dropbox.com/s/9naqffawnq8o4r2/poloniex-bundle.tar?dl=1'
-)
+import pandas as pd
 
-@bundles.register(
-    'poloniex',
-    create_writers=False,
-    calendar_name='OPEN',
-    minutes_per_day=1440)
-def quantopian_quandl_bundle(environ,
-                             asset_db_writer,
-                             minute_bar_writer,
-                             daily_bar_writer,
-                             adjustment_writer,
-                             calendar,
-                             start_session,
-                             end_session,
-                             cache,
-                             show_progress,
-                             output_dir):
-    if show_progress:
-        data = bundles.download_with_progress(
-            POLONIEX_BUNDLE_URL,
-            chunk_size=bundles.ONE_MEGABYTE,
-            label="Downloading Bundle: poloniex",
+from six.moves.urllib.parse import urlencode
+
+from catalyst.data.bundles.core import register_bundle
+from catalyst.data.bundles.base_pricing import BaseCryptoPricingBundle
+from catalyst.utils.memoize import lazyval
+
+class PoloniexBundle(BaseCryptoPricingBundle):
+    @lazyval
+    def name(self):
+        return 'poloniex'
+
+    @lazyval
+    def exchange(self):
+        return 'POLO'
+
+    @lazyval
+    def frequencies(self):
+        return set((
+            'daily',
+            #'5-minute',
+        ))
+
+    @lazyval
+    def tar_url(self):
+        return (
+            'https://s3.amazonaws.com/enigmaco/catalyst-bundles/poloniex/poloniex-bundle.tar.gz'
         )
-    else:
-        data = bundles.download_without_progress(POLONIEX_BUNDLE_URL)
 
-    with tarfile.open('r', fileobj=data) as tar:
-        if show_progress:
-            print("Writing data to %s." % output_dir)
-        tar.extractall(output_dir)
+    @lazyval
+    def wait_time(self):
+        return pd.Timedelta(milliseconds=170)
+
+    def fetch_raw_metadata_frame(self, api_key, page_number):
+        if page_number > 1:
+            return pd.DataFrame([])
+
+        raw = pd.read_json(
+            self._format_metadata_url(
+              api_key,
+              page_number,
+            ),
+            orient='index',
+        )
+
+        raw = raw.sort_index().reset_index()
+        raw.rename(
+            columns={'index':'symbol'},
+            inplace=True,
+        )
+
+        raw = raw[raw['isFrozen'] == 0]
+
+        return raw
+
+    def post_process_symbol_metadata(self, asset_id, sym_md, sym_data):
+        start_date = sym_data.index[0]
+        end_date = sym_data.index[-1]
+        ac_date = end_date + pd.Timedelta(days=1)
+
+        return (
+            sym_md.symbol,
+            start_date,
+            end_date,
+            ac_date,
+        )
+
+    def fetch_raw_symbol_frame(self,
+                               api_key,
+                               symbol,
+                               calendar,
+                               start_date,
+                               end_date,
+                               frequency):
+        raw = pd.read_json(
+            self._format_data_url(
+                api_key,
+                symbol,
+                start_date,
+                end_date,
+                frequency,
+            ),
+            orient='records',
+        )
+        raw.set_index('date', inplace=True)
+
+        # BcolzDailyBarReader introduces a 1/1000 factor in the way pricing is stored
+        # on disk, which we compensate here to get the right pricing amounts
+        # ref: data/us_equity_pricing.py
+        scale = 1000
+        raw.loc[:, 'open'] /= scale
+        raw.loc[:, 'high'] /= scale
+        raw.loc[:, 'low'] /= scale
+        raw.loc[:, 'close'] /= scale
+        raw.loc[:, 'volume'] *= scale
+
+        return raw
+
+    '''
+    HELPER METHODS
+    '''
+
+    def _format_metadata_url(self, api_key, page_number):
+        query_params = [
+            ('command', 'returnTicker'),
+        ]
+
+        return self._format_polo_query(query_params)
+
+
+    def _format_data_url(self,
+                         api_key,
+                         symbol,
+                         start_date,
+                         end_date,
+                         data_frequency):
+        period_map = {
+            'daily': 86400,
+#            '5-minute': 300,
+        }
+
+        try:
+            period = period_map[data_frequency]
+        except KeyError:
+            return None
+
+        query_params = [
+            ('command', 'returnChartData'),
+            ('currencyPair', symbol),
+            ('start', start_date.value / 10**9),
+            ('end', end_date.value / 10**9),
+            ('period', period),
+        ]
+            
+        return self._format_polo_query(query_params)
+    
+    def _format_polo_query(self, query_params):
+        return 'https://poloniex.com/public?{query}'.format(
+            query=urlencode(query_params),
+        )
+
+''' 
+As a second parameter, you can pass an array of currency pairs 
+that will be processed as an asset_filter to only process that 
+subset of assets in the bundle, such as:
+register_bundle(PoloniexBundle, ['USDT_BTC',])
+
+For a production environment make sure to use (to bundle all pairs):
+register_bundle(PoloniexBundle)
+'''
+register_bundle(PoloniexBundle, create_writers=False)

catalyst/data/bundles/quandl.py

@@ -1,3 +1,28 @@
+#
+# Copyright 2017 Enigma MPC, Inc.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from datetime import datetime
+
+import pandas as pd
+
+from six.moves.urllib.parse import urlencode
+
+from catalyst.data.bundles.core import register_bundle
+from catalyst.data.bundles.base_pricing import BaseEquityPricingBundle
+from catalyst.utils.memoize import lazyval
+
 """
 Module for building a complete daily dataset from Quandl's WIKI dataset.
 """
@@ -17,350 +42,190 @@ from . import core as bundles
 
 log = Logger(__name__)
 seconds_per_call = (pd.Timedelta('10 minutes') / 2000).total_seconds()
-# Invalid symbols that quandl has had in its metadata:
-excluded_symbols = frozenset({'TEST123456789'})
 
+class QuandlBundle(BaseEquityPricingBundle):
+    @lazyval
+    def name(self):
+        return 'quandl'
 
-def _fetch_raw_metadata(api_key, cache, retries, environ):
-    """Generator that yields each page of data from the metadata endpoint
-    as a dataframe.
-    """
-    for page_number in count(1):
-        key = 'metadata-page-%d' % page_number
-        try:
-            raw = cache[key]
-        except KeyError:
-            for _ in range(retries):
-                try:
-                    raw = pd.read_csv(
-                        format_metadata_url(api_key, page_number),
-                        date_parser=pd.tseries.tools.to_datetime,
-                        parse_dates=[
-                            'oldest_available_date',
-                            'newest_available_date',
-                        ],
-                        dtypes={
-                            'dataset_code': 'int',
-                            'name': 'str',
-                            'oldest_available_date': 'str',
-                            'newest_available_date': 'str',
-                        },
-                        usecols=[
-                            'dataset_code',
-                            'name',
-                            'oldest_available_date',
-                            'newest_available_date',
-                        ],
-                    )
-                    break
-                except ValueError:
-                    # when we are past the last page we will get a value
-                    # error because there will be no columns
-                    raw = pd.DataFrame([])
-                    break
-                except Exception:
-                    pass
-            else:
-                raise ValueError(
-                    'Failed to download metadata page %d after %d'
-                    ' attempts.' % (page_number, retries),
-                )
+    @lazyval
+    def exchange(self):
+        return 'QUANDL'
 
-            cache[key] = raw
+    @lazyval
+    def frequencies(self):
+        return set(('daily',))
 
-        if raw.empty:
-            # use the empty dataframe to signal completion
-            break
-        yield raw
+    @lazyval
+    def tar_url(self):
+        return 'https://s3.amazonaws.com/quantopian-public-zipline-data/quandl'
 
+    @lazyval
+    def wait_time(self):
+        return pd.Timedelta(milliseconds=300)
 
-def fetch_symbol_metadata_frame(api_key,
-                                cache,
-                                retries=5,
-                                environ=None,
-                                show_progress=False):
-    """
-    Download Quandl symbol metadata.
+    @lazyval
+    def _excluded_symbols(self):
+        """
+        Invalid symbols that quandl has had in its metadata:
+        """
+        return frozenset({'TEST123456789'})
 
-    Parameters
-    ----------
-    api_key : str
-        The quandl api key to use. If this is None then no api key will be
-        sent.
-    cache : DataFrameCache
-        The cache to use for persisting the intermediate data.
-    retries : int, optional
-        The number of times to retry each request before failing.
-    environ : mapping[str -> str], optional
-        The environment to use to find the catalyst home. By default this
-        is ``os.environ``.
-    show_progress : bool, optional
-        Show a progress bar for the download of this data.
-
-    Returns
-    -------
-    metadata_frame : pd.DataFrame
-        A dataframe with the following columns:
-          symbol: the asset's symbol
-          name: the full name of the asset
-          start_date: the first date of data for this asset
-          end_date: the last date of data for this asset
-          auto_close_date: end_date + one day
-          exchange: the exchange for the asset; this is always 'quandl'
-        The index of the dataframe will be used for symbol->sid mappings but
-        otherwise does not have specific meaning.
-    """
-    raw_iter = _fetch_raw_metadata(api_key, cache, retries, environ)
-
-    def item_show_func(_, _it=iter(count())):
-        'Downloading page: %d' % next(_it)
-
-    with maybe_show_progress(raw_iter,
-                             show_progress,
-                             item_show_func=item_show_func,
-                             label='Downloading WIKI metadata: ') as blocks:
-        data = pd.concat(blocks, ignore_index=True).rename(columns={
-            'dataset_code': 'symbol',
-            'name': 'asset_name',
-            'oldest_available_date': 'start_date',
-            'newest_available_date': 'end_date',
-        }).sort_values('symbol')
-
-    data = data[~data.symbol.isin(excluded_symbols)]
-    # cut out all the other stuff in the name column
-    # we need to escape the paren because it is actually splitting on a regex
-    data.asset_name = data.asset_name.str.split(r' \(', 1).str.get(0)
-    data['exchange'] = 'QUANDL'
-
-    data['start_date'] = data['start_date'].astype(datetime)
-    data['end_date'] = data['end_date'].astype(datetime)
-
-    data['auto_close_date'] = data['end_date'] + pd.Timedelta(days=1)
-    return data
-
-
-def format_metadata_url(api_key, page_number):
-    """Build the query RL for the quandl WIKI metadata.
-    """
-    query_params = [
-        ('per_page', '100'),
-        ('sort_by', 'id'),
-        ('page', str(page_number)),
-        ('database_code', 'WIKI'),
-    ]
-    if api_key is not None:
-        query_params = [('api_key', api_key)] + query_params
-    return (
-        'https://www.quandl.com/api/v3/datasets.csv?' + urlencode(query_params)
-    )
-
-
-def format_wiki_url(api_key, symbol, start_date, end_date):
-    """
-    Build a query URL for a quandl WIKI dataset.
-    """
-    query_params = [
-        ('start_date', start_date.strftime('%Y-%m-%d')),
-        ('end_date', end_date.strftime('%Y-%m-%d')),
-        ('order', 'asc'),
-    ]
-    if api_key is not None:
-        query_params = [('api_key', api_key)] + query_params
-
-    return (
-        "https://www.quandl.com/api/v3/datasets/WIKI/"
-        "{symbol}.csv?{query}".format(
-            symbol=symbol,
-            query=urlencode(query_params),
-        )
-    )
-
-
-def fetch_single_equity(api_key,
-                        symbol,
-                        start_date,
-                        end_date,
-                        retries=5):
-    """
-    Download data for a single equity.
-    """
-    for _ in range(retries):
-        try:
-            return pd.read_csv(
-                format_wiki_url(api_key, symbol, start_date, end_date),
-                parse_dates=['Date'],
-                index_col='Date',
-                usecols=[
-                    'Open',
-                    'High',
-                    'Low',
-                    'Close',
-                    'Volume',
-                    'Date',
-                    'Ex-Dividend',
-                    'Split Ratio',
-                ],
-                na_values=['NA'],
-            ).rename(columns={
-                'Open': 'open',
-                'High': 'high',
-                'Low': 'low',
-                'Close': 'close',
-                'Volume': 'volume',
-                'Date': 'date',
-                'Ex-Dividend': 'ex_dividend',
-                'Split Ratio': 'split_ratio',
-            })
-        except Exception:
-            log.exception("Exception raised reading Quandl data. Retrying.")
-    else:
-        raise ValueError(
-            "Failed to download data for %r after %d attempts." % (
-                symbol, retries
-            )
+    def fetch_raw_metadata_frame(self, api_key, page_number):
+        raw = pd.read_csv(
+            self._format_metadata_url(api_key, page_number),
+            date_parser=pd.tseries.tools.to_datetime,
+            parse_dates=[
+                'oldest_available_date',
+                'newest_available_date',
+            ],
+            dtype={
+                'dataset_code': 'str',
+                'name': 'str',
+                'oldest_available_date': 'str',
+                'newest_available_date': 'str',
+            },
+            usecols=[
+                'dataset_code',
+                'name',
+                'oldest_available_date',
+                'newest_available_date',
+            ],
+        ).rename(
+            columns={
+                'dataset_code': 'symbol',
+                'name': 'asset_name',
+                'oldest_available_date': 'start_date',
+                'newest_available_date': 'end_date',
+            },
         )
 
+        raw['start_date'] = raw['start_date'].astype(datetime)
+        raw['end_date'] = raw['end_date'].astype(datetime)
+        raw['ac_date'] = raw['end_date'] + pd.Timedelta(days=1)
 
-def _update_splits(splits, asset_id, raw_data):
-    split_ratios = raw_data.split_ratio
-    df = pd.DataFrame({'ratio': 1 / split_ratios[split_ratios != 1]})
-    df.index.name = 'effective_date'
-    df.reset_index(inplace=True)
-    df['sid'] = asset_id
-    splits.append(df)
+        # Filter out invalid symbols
+        raw = raw[~raw.symbol.isin(self._excluded_symbols)]
 
+        # cut out all the other stuff in the name column
+        # we need to escape the paren because it is actually splitting on a regex
+        raw.asset_name = raw.asset_name.str.split(r' \(', 1).str.get(0)
 
-def _update_dividends(dividends, asset_id, raw_data):
-    divs = raw_data.ex_dividend
-    df = pd.DataFrame({'amount': divs[divs != 0]})
-    df.index.name = 'ex_date'
-    df.reset_index(inplace=True)
-    df['sid'] = asset_id
-    # we do not have this data in the WIKI dataset
-    df['record_date'] = df['declared_date'] = df['pay_date'] = pd.NaT
-    dividends.append(df)
+        return raw
 
-
-def gen_symbol_data(api_key,
-                    cache,
-                    symbol_map,
-                    calendar,
-                    start_session,
-                    end_session,
-                    splits,
-                    dividends,
-                    retries):
-    for asset_id, symbol in symbol_map.iteritems():
-        start_time = time()
-        try:
-            # see if we have this data cached.
-            raw_data = cache[symbol]
-            should_sleep = False
-        except KeyError:
-            # we need to fetch the data and then write it to our cache
-            raw_data = cache[symbol] = fetch_single_equity(
+    def fetch_raw_symbol_frame(self,
+                               api_key,
+                               symbol,
+                               calendar,
+                               start_session,
+                               end_session,
+                               data_frequency):
+        raw_data = pd.read_csv(
+            self._format_wiki_url(
                 api_key,
                 symbol,
-                start_date=start_session,
-                end_date=end_session,
-            )
-            should_sleep = True
-
-        _update_splits(splits, asset_id, raw_data)
-        _update_dividends(dividends, asset_id, raw_data)
+                start_session,
+                end_session,
+                data_frequency,
+            ),
+            parse_dates=['Date'],
+            index_col='Date',
+            usecols=[
+                'Open',
+                'High',
+                'Low',
+                'Close',
+                'Volume',
+                'Date',
+                'Ex-Dividend',
+                'Split Ratio',
+            ],
+            na_values=['NA'],
+        ).rename(columns={
+            'Open': 'open',
+            'High': 'high',
+            'Low': 'low',
+            'Close': 'close',
+            'Volume': 'volume',
+            'Date': 'date',
+            'Ex-Dividend': 'ex_dividend',
+            'Split Ratio': 'split_ratio',
+        })
 
         sessions = calendar.sessions_in_range(start_session, end_session)
 
-        raw_data = raw_data.reindex(
+        return raw_data.reindex(
             sessions.tz_localize(None),
             copy=False,
         ).fillna(0.0)
-        yield asset_id, raw_data
 
-        if should_sleep:
-            remaining = seconds_per_call - time() - start_time
-            if remaining > 0:
-                sleep(remaining)
+    def post_process_symbol_metadata(self, asset_id, sym_md, sym_data):
+        self._update_splits(asset_id, sym_data)
+        self._update_dividends(asset_id, sym_data)
+
+        return sym_md
+
+    def _update_splits(self, asset_id, raw_data):
+        split_ratios = raw_data.split_ratio
+        df = pd.DataFrame({'ratio': 1 / split_ratios[split_ratios != 1]})
+        df.index.name = 'effective_date'
+        df.reset_index(inplace=True)
+        df['sid'] = asset_id
+        self.splits.append(df)
 
 
-@bundles.register('quandl')
-def quandl_bundle(environ,
-                  asset_db_writer,
-                  minute_bar_writer,
-                  daily_bar_writer,
-                  adjustment_writer,
-                  calendar,
-                  start_session,
-                  end_session,
-                  cache,
-                  show_progress,
-                  output_dir):
-    """Build a catalyst data bundle from the Quandl WIKI dataset.
-    """
-    api_key = environ.get('QUANDL_API_KEY')
-    metadata = fetch_symbol_metadata_frame(
-        api_key,
-        cache=cache,
-        show_progress=show_progress,
-    )
-    symbol_map = metadata.symbol
-
-    # data we will collect in `gen_symbol_data`
-    splits = []
-    dividends = []
-
-    asset_db_writer.write(metadata)
-    daily_bar_writer.write(
-        gen_symbol_data(
-            api_key,
-            cache,
-            symbol_map,
-            calendar,
-            start_session,
-            end_session,
-            splits,
-            dividends,
-            environ.get('QUANDL_DOWNLOAD_ATTEMPTS', 5),
-        ),
-        assets=metadata.index,
-        show_progress=show_progress,
-    )
-    adjustment_writer.write(
-        splits=pd.concat(splits, ignore_index=True),
-        dividends=pd.concat(dividends, ignore_index=True),
-    )
+    def _update_dividends(self, asset_id, raw_data):
+        divs = raw_data.ex_dividend
+        df = pd.DataFrame({'amount': divs[divs != 0]})
+        df.index.name = 'ex_date'
+        df.reset_index(inplace=True)
+        df['sid'] = asset_id
+        # we do not have this data in the WIKI dataset
+        df['record_date'] = df['declared_date'] = df['pay_date'] = pd.NaT
+        self.dividends.append(df)
 
 
-QUANTOPIAN_QUANDL_URL = (
-    'https://s3.amazonaws.com/quantopian-public-zipline-data/quandl'
-)
+    def _format_metadata_url(self, api_key, page_number):
+        """Build the query RL for the quandl WIKI metadata.
+        """
+        query_params = [
+            ('per_page', '100'),
+            ('sort_by', 'id'),
+            ('page', str(page_number)),
+            ('database_code', 'WIKI'),
+        ]
+        if api_key is not None:
+            query_params = [('api_key', api_key)] + query_params
 
-
-@bundles.register('quantopian-quandl', create_writers=False)
-def quantopian_quandl_bundle(environ,
-                             asset_db_writer,
-                             minute_bar_writer,
-                             daily_bar_writer,
-                             adjustment_writer,
-                             calendar,
-                             start_session,
-                             end_session,
-                             cache,
-                             show_progress,
-                             output_dir):
-    if show_progress:
-        data = bundles.download_with_progress(
-            QUANTOPIAN_QUANDL_URL,
-            chunk_size=bundles.ONE_MEGABYTE,
-            label="Downloading Bundle: quantopian-quandl",
+        return (
+            'https://www.quandl.com/api/v3/datasets.csv?' + urlencode(query_params)
         )
-    else:
-        data = bundles.download_without_progress(QUANTOPIAN_QUANDL_URL)
-
-    with tarfile.open('r', fileobj=data) as tar:
-        if show_progress:
-            print("Writing data to %s." % output_dir)
-        tar.extractall(output_dir)
 
 
-register_calendar_alias("QUANDL", "NYSE")
+    def _format_wiki_url(self,
+                         api_key,
+                         symbol,
+                         start_date,
+                         end_date,
+                         data_frequency):
+        """
+        Build a query URL for a quandl WIKI dataset.
+        """
+        query_params = [
+            ('start_date', start_date.strftime('%Y-%m-%d')),
+            ('end_date', end_date.strftime('%Y-%m-%d')),
+            ('order', 'asc'),
+        ]
+        if api_key is not None:
+            query_params = [('api_key', api_key)] + query_params
+
+        return (
+            "https://www.quandl.com/api/v3/datasets/WIKI/"
+            "{symbol}.csv?{query}".format(
+                symbol=symbol,
+                query=urlencode(query_params),
+            )
+        )
+
+register_calendar_alias('QUANDL', 'NYSE')
+register_bundle(QuandlBundle)

catalyst/data/data_portal.py

@@ -42,6 +42,7 @@ from catalyst.assets.roll_finder import (
 )
 from catalyst.data.dispatch_bar_reader import (
     AssetDispatchMinuteBarReader,
+    AssetDispatchFiveMinuteBarReader,
     AssetDispatchSessionBarReader
 )
 from catalyst.data.resample import (
@@ -114,12 +115,16 @@ class DataPortal(object):
         The calendar instance used to provide minute->session information.
     first_trading_day : pd.Timestamp
         The first trading day for the simulation.
-    equity_daily_reader : BcolzDailyBarReader, optional
+    daily_reader : BcolzDailyBarReader, optional
         The daily bar reader for equities. This will be used to service
         daily data backtests or daily history calls in a minute backetest.
         If a daily bar reader is not provided but a minute bar reader is,
         the minutes will be rolled up to serve the daily requests.
-    equity_minute_reader : BcolzMinuteBarReader, optional
+    five_minute_reader : BcolzFiveMinuteBarReader, optional
+        The five minute bar reader for equities. This will be used to service
+        5-minute data backtests or five-minute history calls.  This can be used
+        to serve daily calls if no daily bar reader is provided.
+    minute_reader : BcolzMinuteBarReader, optional
         The minute bar reader for equities. This will be used to service
         minute data backtests or minute history calls. This can be used
         to serve daily calls if no daily bar reader is provided.
@@ -144,8 +149,9 @@ class DataPortal(object):
                  asset_finder,
                  trading_calendar,
                  first_trading_day,
-                 equity_daily_reader=None,
-                 equity_minute_reader=None,
+                 daily_reader=None,
+                 five_minute_reader=None,
+                 minute_reader=None,
                  future_daily_reader=None,
                  future_minute_reader=None,
                  adjustment_reader=None,
@@ -180,7 +186,7 @@ class DataPortal(object):
             # Infer the last session from the provided readers.
             last_sessions = [
                 reader.last_available_dt
-                for reader in [equity_daily_reader, future_daily_reader]
+                for reader in [daily_reader, future_daily_reader]
                 if reader is not None
             ]
             if last_sessions:
@@ -194,7 +200,11 @@ class DataPortal(object):
             # Infer the last minute from the provided readers.
             last_minutes = [
                 reader.last_available_dt
-                for reader in [equity_minute_reader, future_minute_reader]
+                for reader in [
+                    minute_reader,
+                    five_minute_reader,
+                    future_minute_reader,
+                ]
                 if reader is not None
             ]
             if last_minutes:
@@ -202,10 +212,12 @@ class DataPortal(object):
             else:
                 self._last_available_minute = None
 
-        aligned_equity_minute_reader = self._ensure_reader_aligned(
-            equity_minute_reader)
-        aligned_equity_session_reader = self._ensure_reader_aligned(
-            equity_daily_reader)
+        aligned_minute_reader = self._ensure_reader_aligned(
+            minute_reader)
+        aligned_five_minute_reader = self._ensure_reader_aligned(
+            five_minute_reader)
+        aligned_session_reader = self._ensure_reader_aligned(
+            daily_reader)
         aligned_future_minute_reader = self._ensure_reader_aligned(
             future_minute_reader)
         aligned_future_session_reader = self._ensure_reader_aligned(
@@ -217,12 +229,15 @@ class DataPortal(object):
         }
 
         aligned_minute_readers = {}
+        aligned_five_minute_readers = {}
         aligned_session_readers = {}
 
-        if aligned_equity_minute_reader is not None:
-            aligned_minute_readers[Equity] = aligned_equity_minute_reader
-        if aligned_equity_session_reader is not None:
-            aligned_session_readers[Equity] = aligned_equity_session_reader
+        if aligned_minute_reader is not None:
+            aligned_minute_readers[Equity] = aligned_minute_reader
+        if aligned_five_minute_reader is not None:
+            aligned_five_minute_readers[Equity] = aligned_five_minute_reader
+        if aligned_session_reader is not None:
+            aligned_session_readers[Equity] = aligned_session_reader
 
         if aligned_future_minute_reader is not None:
             aligned_minute_readers[Future] = aligned_future_minute_reader
@@ -252,6 +267,13 @@ class DataPortal(object):
             self._last_available_minute,
         )
 
+        _dispatch_five_minute_reader = AssetDispatchFiveMinuteBarReader(
+            self.trading_calendar,
+            self.asset_finder,
+            aligned_five_minute_readers,
+            self._last_available_minute,
+        )
+
         _dispatch_session_reader = AssetDispatchSessionBarReader(
             self.trading_calendar,
             self.asset_finder,
@@ -261,6 +283,7 @@ class DataPortal(object):
 
         self._pricing_readers = {
             'minute': _dispatch_minute_reader,
+            '5-minute': _dispatch_five_minute_reader,
             'daily': _dispatch_session_reader,
         }
 
@@ -514,15 +537,17 @@ class DataPortal(object):
                     )
             else:
                 if field == "last_traded":
-                    return self.get_last_traded_dt(asset, dt, 'minute')
+                    return self.get_last_traded_dt(asset, dt, data_frequency)
                 elif field == "price":
-                    return self._get_minute_spot_value(
-                        asset, "close", dt, ffill=True,
+                    return self._get_minutely_spot_value(
+                        asset, "close", dt, data_frequency, ffill=True,
                     )
                 elif field == "contract":
                     return self._get_current_contract(asset, dt)
                 else:
-                    return self._get_minute_spot_value(asset, field, dt)
+                    return self._get_minutely_spot_value(
+                        asset, field, dt, data_frequency,
+                     )
 
         if assets_is_scalar:
             return get_single_asset_value(assets)
@@ -648,8 +673,14 @@ class DataPortal(object):
 
         return spot_value
 
-    def _get_minute_spot_value(self, asset, column, dt, ffill=False):
-        reader = self._get_pricing_reader('minute')
+    def _get_minutely_spot_value(self,
+                                asset,
+                                column,
+                                dt,
+                                data_frequency,
+                                ffill=False):
+
+        reader = self._get_pricing_reader(data_frequency)
 
         if ffill:
             # If forward filling, we want the last minute with values (up to
@@ -680,8 +711,32 @@ class DataPortal(object):
         # the value we found came from a different day, so we have to adjust
         # the data if there are any adjustments on that day barrier
         return self.get_adjusted_value(
-            asset, column, query_dt,
-            dt, "minute", spot_value=result
+            asset,
+            column,
+            query_dt,
+            dt,
+            data_frequency,
+            spot_value=result
+        )
+
+
+    def _get_five_minute_spot_value(self, asset, column, dt, ffill=False):
+        return self._get_minutely_spot_value(
+            asset,
+            column,
+            dt,
+            ffill, 
+            '5-minute',
+        )
+        
+
+    def _get_minute_spot_value(self, asset, column, dt, ffill=False):
+        return self._get_minutely_spot_value(
+            asset,
+            column,
+            dt,
+            ffill, 
+            'minute',
         )
 
     def _get_daily_spot_value(self, asset, column, dt):

catalyst/data/dispatch_bar_reader.py

@@ -130,13 +130,17 @@ class AssetDispatchBarReader(with_metaclass(ABCMeta)):
 
         return results
 
-
 class AssetDispatchMinuteBarReader(AssetDispatchBarReader):
 
     def _dt_window_size(self, start_dt, end_dt):
         return len(self.trading_calendar.minutes_in_range(start_dt, end_dt))
 
 
+class AssetDispatchFiveMinuteBarReader(AssetDispatchBarReader):
+
+    def _dt_window_size(self, start_dt, end_dt):
+        return len(self.trading_calendar.five_minutes_in_range(start_dt, end_dt))
+
 class AssetDispatchSessionBarReader(AssetDispatchBarReader):
 
     def _dt_window_size(self, start_dt, end_dt):

catalyst/data/five_minute_bars.py

@@ -24,6 +24,10 @@ from bcolz import ctable
 from intervaltree import IntervalTree
 import logbook
 import numpy as np
+from numpy import (
+    iinfo,
+    uint64,
+)
 import pandas as pd
 from pandas import HDFStore
 import tables
@@ -31,31 +35,39 @@ from six import with_metaclass
 from toolz import keymap, valmap
 
 from catalyst.data._minute_bar_internal import (
-    minute_value,
-    find_position_of_minute,
-    find_last_traded_position_internal
+    five_minute_value,
+    find_position_of_five_minute,
+    find_last_traded_five_minute_position_internal,
 )
 
 from catalyst.gens.sim_engine import NANOS_IN_MINUTE
 
 from catalyst.data.bar_reader import BarReader, NoDataOnDate
-from catalyst.data.us_equity_pricing import check_uint32_safe
+from catalyst.data.us_equity_pricing import (
+    winsorise_uint64,
+    check_uint64_safe,
+)
 from catalyst.utils.calendars import get_calendar
-from catalyst.utils.cli import maybe_show_progress
+from catalyst.utils.cli import (
+    item_show_count,
+    maybe_show_progress,
+)
 from catalyst.utils.memoize import lazyval
 
-
 logger = logbook.Logger('FiveMinuteBars')
 
-CRYPTO_ASSETS_FIVE_MINUTES_PER_DAY = 288
-US_EQUITIES_MINUTES_PER_DAY = 390
-FUTURES_MINUTES_PER_DAY = 1440
+OPEN_FIVE_MINUTES_PER_DAY = 288
 
-DEFAULT_EXPECTEDLEN = US_EQUITIES_MINUTES_PER_DAY * 252 * 15
-DEFAULT_EXPECTED_CRYPTO_LEN = CRYPTO_ASSETS_FIVE_MINUTES_PER_DAY * 366 * 15
+DEFAULT_EXPECTEDLEN_CRYPTO = OPEN_FIVE_MINUTES_PER_DAY * 366 * 15
 
-OHLC_RATIO = 1000
+OHLC_RATIO = 1000000
 
+OHLC = frozenset(['open', 'high', 'low', 'close'])
+OHLCV = frozenset(['open', 'high', 'low', 'close', 'volume'])
+
+UINT64_MAX = iinfo(uint64).max
+
+NANOS_IN_FIVE_MINUTES = 5 * NANOS_IN_MINUTE
 
 class BcolzFiveMinuteOverlappingData(Exception):
     pass
@@ -68,13 +80,13 @@ class BcolzFiveMinuteWriterColumnMismatch(Exception):
 class FiveMinuteBarReader(BarReader):
     @property
     def data_frequency(self):
-        return "five-minute"
+        return "5-minute"
 
 
 def _calc_five_minute_index(market_opens, five_minutes_per_day):
     five_minutes = np.zeros(len(market_opens) * five_minutes_per_day,
                        dtype='datetime64[ns]')
-    deltas = np.arange(0, five_minutes_per_day, dtype='timedelta64[m]')
+    deltas = 5 * np.arange(0, five_minutes_per_day, dtype='timedelta64[m]')
     for i, market_open in enumerate(market_opens):
         start = market_open.asm8
         five_minute_values = start + deltas
@@ -116,19 +128,19 @@ def _sid_subdir_path(sid):
 
 
 def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
-    """Adapt OHLCV columns into uint32 columns.
+    """Adapt OHLCV columns into uint64 columns.
 
     Parameters
     ----------
     cols : dict
         A dict mapping each column name (open, high, low, close, volume)
-        to a float column to convert to uint32.
+        to a float column to convert to uint64.
     scale_factor : int
-        Factor to use to scale float values before converting to uint32.
+        Factor to use to scale float values before converting to uint64.
     sid : int
         Sid of the relevant asset, for logging.
     invalid_data_behavior : str
-        Specifies behavior when data cannot be converted to uint32.
+        Specifies behavior when data cannot be converted to uint64.
         If 'raise', raises an exception.
         If 'warn', logs a warning and filters out incompatible values.
         If 'ignore', silently filters out incompatible values.
@@ -137,6 +149,7 @@ def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
     scaled_highs = np.nan_to_num(cols['high']) * scale_factor
     scaled_lows = np.nan_to_num(cols['low']) * scale_factor
     scaled_closes = np.nan_to_num(cols['close']) * scale_factor
+    volumes = np.nan_to_num(cols['volume'])
 
     exclude_mask = np.zeros_like(scaled_opens, dtype=bool)
 
@@ -145,11 +158,12 @@ def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
         ('high', scaled_highs),
         ('low', scaled_lows),
         ('close', scaled_closes),
+        ('volume', volumes),
     ]:
         max_val = scaled_col.max()
 
         try:
-            check_uint32_safe(max_val, col_name)
+            check_uint64_safe(max_val, col_name)
         except ValueError:
             if invalid_data_behavior == 'raise':
                 raise
@@ -157,20 +171,20 @@ def convert_cols(cols, scale_factor, sid, invalid_data_behavior):
             if invalid_data_behavior == 'warn':
                 logger.warn(
                     'Values for sid={}, col={} contain some too large for '
-                    'uint32 (max={}), filtering them out',
+                    'uint64 (max={}), filtering them out',
                     sid, col_name, max_val,
                 )
 
             # We want to exclude all rows that have an unsafe value in
             # this column.
-            exclude_mask &= (scaled_col >= np.iinfo(np.uint32).max)
+            exclude_mask &= (scaled_col >= iinfo(uint64).max)
 
-    # Convert all cols to uint32.
-    opens = scaled_opens.astype(np.uint32)
-    highs = scaled_highs.astype(np.uint32)
-    lows = scaled_lows.astype(np.uint32)
-    closes = scaled_closes.astype(np.uint32)
-    volumes = cols['volume'].astype(np.uint32)
+    # Convert all cols to uint64.
+    opens = scaled_opens.astype(uint64)
+    highs = scaled_highs.astype(uint64)
+    lows = scaled_lows.astype(uint64)
+    closes = scaled_closes.astype(uint64)
+    volumes = volumes.astype(uint64)
 
     # Exclude rows with unsafe values by setting to zero.
     opens[exclude_mask] = 0
@@ -200,7 +214,7 @@ class BcolzFiveMinuteBarMetadata(object):
     """
     FORMAT_VERSION = 3
 
-    METADATA_FILENAME = 'metadata.json'
+    METADATA_FILENAME = 'five-minute-metadata.json'
 
     @classmethod
     def metadata_path(cls, rootdir):
@@ -257,7 +271,7 @@ class BcolzFiveMinuteBarMetadata(object):
                 calendar,
                 start_session,
                 end_session,
-                minutes_per_day,
+                five_minutes_per_day,
                 version=version,
             )
 
@@ -290,7 +304,7 @@ class BcolzFiveMinuteBarMetadata(object):
         ohlc_ratio : int
             The default ratio by which to multiply the pricing data to
             convert the floats from floats to an integer to fit within
-            the np.uint32. If ohlc_ratios_per_sid is None or does not
+            the np.uint64. If ohlc_ratios_per_sid is None or does not
             contain a mapping for a given sid, this ratio is used.
         ohlc_ratios_per_sid : dict
              A dict mapping each sid in the output to the factor by
@@ -334,7 +348,7 @@ class BcolzFiveMinuteBarMetadata(object):
             'version': self.version,
             'ohlc_ratio': self.default_ohlc_ratio,
             'ohlc_ratios_per_sid': self.ohlc_ratios_per_sid,
-            'minutes_per_day': self.five_minutes_per_day,
+            'five_minutes_per_day': self.five_minutes_per_day,
             'calendar_name': self.calendar.name,
             'start_session': str(self.start_session.date()),
             'end_session': str(self.end_session.date()),
@@ -374,13 +388,13 @@ class BcolzFiveMinuteBarWriter(object):
         The last trading session in the data set.
     default_ohlc_ratio : int, optional
         The default ratio by which to multiply the pricing data to
-        convert from floats to integers that fit within np.uint32. If
+        convert from floats to integers that fit within np.uint64. If
         ohlc_ratios_per_sid is None or does not contain a mapping for a
         given sid, this ratio is used. Default is OHLC_RATIO (1000).
     ohlc_ratios_per_sid : dict, optional
         A dict mapping each sid in the output to the ratio by which to
         multiply the pricing data to convert the floats from floats to
-        an integer to fit within the np.uint32.
+        an integer to fit within the np.uint64.
     expectedlen : int, optional
         The expected length of the dataset, used when creating the initial
         bcolz ctable.
@@ -405,9 +419,9 @@ class BcolzFiveMinuteBarWriter(object):
 
     The open, high, low, and close columns are integers which are 1000 times
     the quoted price, so that the data can represented and stored as an
-    np.uint32, supporting market prices quoted up to the thousands place.
+    np.uint64, supporting market prices quoted up to the thousands place.
 
-    volume is a np.uint32 with no mutation of the tens place.
+    volume is a np.uint64 with no mutation of the tens place.
 
     The 'index' for each individual asset are a repeating period of minutes of
     length `minutes_per_day` starting from each market open.
@@ -450,7 +464,7 @@ class BcolzFiveMinuteBarWriter(object):
                  five_minutes_per_day,
                  default_ohlc_ratio=OHLC_RATIO,
                  ohlc_ratios_per_sid=None,
-                 expectedlen=DEFAULT_EXPECTED_CRYPTO_LEN,
+                 expectedlen=DEFAULT_EXPECTEDLEN_CRYPTO,
                  write_metadata=True):
 
         self._rootdir = rootdir
@@ -466,11 +480,11 @@ class BcolzFiveMinuteBarWriter(object):
         self._default_ohlc_ratio = default_ohlc_ratio
         self._ohlc_ratios_per_sid = ohlc_ratios_per_sid
 
-        self._minute_index = _calc_minute_index(
-            self._schedule.market_open, self._minutes_per_day)
+        self._five_minute_index = _calc_five_minute_index(
+            self._schedule.market_open, self._five_minutes_per_day)
 
         if write_metadata:
-            metadata = BcolzMinuteBarMetadata(
+            metadata = BcolzFiveMinuteBarMetadata(
                 self._default_ohlc_ratio,
                 self._ohlc_ratios_per_sid,
                 self._calendar,
@@ -575,7 +589,7 @@ class BcolzFiveMinuteBarWriter(object):
         if not os.path.exists(sid_containing_dirname):
             # Other sids may have already created the containing directory.
             os.makedirs(sid_containing_dirname)
-        initial_array = np.empty(0, np.uint32)
+        initial_array = np.empty(0, np.uint64)
         table = ctable(
             rootdir=path,
             columns=[
@@ -612,7 +626,7 @@ class BcolzFiveMinuteBarWriter(object):
         five_minute_offset = len(table) % self._five_minutes_per_day
         num_to_prepend = numdays * self._five_minutes_per_day - five_minute_offset
 
-        prepend_array = np.zeros(num_to_prepend, np.uint32)
+        prepend_array = np.zeros(num_to_prepend, np.uint64)
         # Fill all OHLCV with zeros.
         table.append([prepend_array] * 5)
         table.flush()
@@ -667,7 +681,11 @@ class BcolzFiveMinuteBarWriter(object):
         for k, v in kwargs.items():
             table.attrs[k] = v
 
-    def write(self, data, show_progress=False, invalid_data_behavior='warn'):
+    def write(self,
+              data,
+              length=None,
+              show_progress=False,
+              invalid_data_behavior='warn'):
         """Write a stream of minute data.
 
         Parameters
@@ -687,14 +705,15 @@ class BcolzFiveMinuteBarWriter(object):
         show_progress : bool, optional
             Whether or not to show a progress bar while writing.
         """
-        ctx = maybe_show_progress(
+        with maybe_show_progress(
             data,
+            length=length,
+            show_percent=False,
             show_progress=show_progress,
-            item_show_func=lambda e: e if e is None else str(e[0]),
-            label="Merging minute equity files:",
-        )
-        write_sid = self.write_sid
-        with ctx as it:
+            item_show_func=item_show_count(length),
+            label='Compiling five-minute data',
+        ) as it:
+            write_sid = self.write_sid
             for e in it:
                 write_sid(*e, invalid_data_behavior=invalid_data_behavior)
 
@@ -796,10 +815,13 @@ class BcolzFiveMinuteBarWriter(object):
         # Get the number of minutes already recorded in this sid's ctable
         num_rec_mins = table.size
 
-        all_minutes = self._minute_index
+        all_minutes = self._five_minute_index
         # Get the latest minute we wish to write to the ctable
         last_minute_to_write = pd.Timestamp(dts[-1], tz='UTC')
 
+        #print 'all_minutes[-1]:', all_minutes[num_rec_mins-1]
+        #print 'last_minute_to_write:', last_minute_to_write
+
         # In the event that we've already written some minutely data to the
         # ctable, guard against overwriting that data.
         if num_rec_mins > 0:
@@ -817,11 +839,11 @@ class BcolzFiveMinuteBarWriter(object):
 
         minutes_count = all_minutes_in_window.size
 
-        open_col = np.zeros(minutes_count, dtype=np.uint32)
-        high_col = np.zeros(minutes_count, dtype=np.uint32)
-        low_col = np.zeros(minutes_count, dtype=np.uint32)
-        close_col = np.zeros(minutes_count, dtype=np.uint32)
-        vol_col = np.zeros(minutes_count, dtype=np.uint32)
+        open_col = np.zeros(minutes_count, dtype=uint64)
+        high_col = np.zeros(minutes_count, dtype=uint64)
+        low_col = np.zeros(minutes_count, dtype=uint64)
+        close_col = np.zeros(minutes_count, dtype=uint64)
+        vol_col = np.zeros(minutes_count, dtype=uint64)
 
         dt_ixs = np.searchsorted(all_minutes_in_window.values,
                                  dts.astype('datetime64[ns]'))
@@ -853,7 +875,7 @@ class BcolzFiveMinuteBarWriter(object):
         day_ix = self._session_labels.get_loc(day)
         # Add one to the 0-indexed day_ix to get the number of days.
         num_days = day_ix + 1
-        return num_days * self._minutes_per_day
+        return num_days * self._five_minutes_per_day
 
     def truncate(self, date):
         """Truncate data beyond this date in all ctables."""
@@ -991,7 +1013,7 @@ class BcolzFiveMinuteBarReader(FiveMinuteBarReader):
         market_closes = self._market_closes.values.astype('datetime64[m]')
         minutes_per_day = (market_closes - market_opens).astype(np.int64) / 5
         early_indices = np.where(
-            minutes_per_day != self._minutes_per_day - 1)[0]
+            minutes_per_day != self._five_minutes_per_day - 1)[0]
         early_opens = self._market_opens[early_indices]
         early_closes = self._market_closes[early_indices]
         minutes = [(market_open, early_close)
@@ -1019,9 +1041,9 @@ class BcolzFiveMinuteBarReader(FiveMinuteBarReader):
         """
         itree = IntervalTree()
         for market_open, early_close in self._minutes_to_exclude():
-            start_pos = self._find_position_of_minute(early_close) + 1
+            start_pos = self._find_position_of_five_minute(early_close) + 1
             end_pos = (
-                self._find_position_of_minute(market_open)
+                self._find_position_of_five_minute(market_open)
                 +
                 self._five_minutes_per_day
                 -
@@ -1110,7 +1132,7 @@ class BcolzFiveMinuteBarReader(FiveMinuteBarReader):
             minute_pos = self._last_get_value_dt_position
         else:
             try:
-                minute_pos = self._find_position_of_minute(dt)
+                minute_pos = self._find_position_of_five_minute(dt)
             except ValueError:
                 raise NoDataOnDate()
 
@@ -1132,15 +1154,15 @@ class BcolzFiveMinuteBarReader(FiveMinuteBarReader):
         return value
 
     def get_last_traded_dt(self, asset, dt):
-        minute_pos = self._find_last_traded_position(asset, dt)
+        minute_pos = self._find_last_traded_five_minute_position(asset, dt)
         if minute_pos == -1:
             return pd.NaT
         return self._pos_to_minute(minute_pos)
 
-    def _find_last_traded_position(self, asset, dt):
+    def _find_last_traded_five_minute_position(self, asset, dt):
         volumes = self._open_minute_file('volume', asset)
-        start_date_minute = asset.start_date.value / NANOS_IN_MINUTE
-        dt_minute = dt.value / NANOS_IN_MINUTE
+        start_date_minute = asset.start_date.value / NANOS_IN_FIVE_MINUTE
+        dt_minute = dt.value / NANOS_IN_FIVE_MINUTE
 
         try:
             # if we know of a dt before which this asset has no volume,
@@ -1152,13 +1174,13 @@ class BcolzFiveMinuteBarReader(FiveMinuteBarReader):
         if dt_minute < earliest_dt_to_search:
             return -1
 
-        pos = find_last_traded_position_internal(
+        pos = find_last_traded_five_minute_position_internal(
             self._market_open_values,
             self._market_close_values,
             dt_minute,
             earliest_dt_to_search,
             volumes,
-            self._minutes_per_day,
+            self._five_minutes_per_day,
         )
 
         if pos == -1:
@@ -1175,15 +1197,15 @@ class BcolzFiveMinuteBarReader(FiveMinuteBarReader):
         return pos
 
     def _pos_to_minute(self, pos):
-        minute_epoch = minute_value(
+        minute_epoch = five_minute_value(
             self._market_open_values,
             pos,
-            self._minutes_per_day
+            self._five_minutes_per_day
         )
 
         return pd.Timestamp(minute_epoch, tz='UTC', unit="m")
 
-    def _find_position_of_minute(self, minute_dt):
+    def _find_position_of_five_minute(self, minute_dt):
         """
         Internal method that returns the position of the given minute in the
         list of every trading minute since market open of the first trading
@@ -1202,11 +1224,11 @@ class BcolzFiveMinuteBarReader(FiveMinuteBarReader):
         int: The position of the given minute in the list of all trading
         minutes since market open on the first trading day.
         """
-        return find_position_of_minute(
+        return find_position_of_five_minute(
             self._market_open_values,
             self._market_close_values,
-            minute_dt.value / NANOS_IN_MINUTE,
-            self._minutes_per_day,
+            minute_dt.value / NANOS_IN_FIVE_MINUTE,
+            self._five_minutes_per_day,
             False,
         )
 
@@ -1230,8 +1252,8 @@ class BcolzFiveMinuteBarReader(FiveMinuteBarReader):
             (minutes in range, sids) with a dtype of float64, containing the
             values for the respective field over start and end dt range.
         """
-        start_idx = self._find_position_of_minute(start_dt)
-        end_idx = self._find_position_of_minute(end_dt)
+        start_idx = self._find_position_of_five_minute(start_dt)
+        end_idx = self._find_position_of_five_minute(end_dt)
 
         num_minutes = (end_idx - start_idx + 1)
 
@@ -1250,7 +1272,7 @@ class BcolzFiveMinuteBarReader(FiveMinuteBarReader):
             if field != 'volume':
                 out = np.full(shape, np.nan)
             else:
-                out = np.zeros(shape, dtype=np.uint32)
+                out = np.zeros(shape, dtype=uint64)
 
             for i, sid in enumerate(sids):
                 carray = self._open_minute_file(field, sid)

catalyst/data/loader.py

@@ -33,7 +33,7 @@ from ..utils.paths import (
 )
 from ..utils.deprecate import deprecated
 
-from catalyst.curate.poloniex import PoloniexCurator
+from catalyst.data.bundles.poloniex import PoloniexBundle
 from catalyst.utils.calendars import get_calendar
 
 
@@ -93,19 +93,18 @@ def has_data_for_dates(series_or_df, first_date, last_date):
     dts = series_or_df.index
     if not isinstance(dts, pd.DatetimeIndex):
         raise TypeError("Expected a DatetimeIndex, but got %s." % type(dts))
-    first, last = dts[[0, -1]]
-    return (first <= first_date) and (last >= last_date)
+    first, last = dts[[0, -1]].tz_localize(None)
+    return (first <= first_date.tz_localize(None)) and (last >= last_date.tz_localize(None))
+
+def load_crypto_market_data(trading_day=None, trading_days=None, bm_symbol='USDT_BTC',
+                            bundle=None, bundle_data=None, environ=None):
 
-def load_crypto_market_data(trading_day=None,
-                            trading_days=None,
-                            bm_symbol='USDT_BTC',
-                            environ=None):
     if trading_day is None:
         trading_day = get_calendar('OPEN').trading_day
     if trading_days is None:
         trading_days = get_calendar('OPEN').all_sessions
 
-    first_date = trading_days[0]
+    first_date = trading_days[1]
     now = pd.Timestamp.utcnow()
 
     # We expect to have benchmark and treasury data that's current up until
@@ -122,7 +121,14 @@ def load_crypto_market_data(trading_day=None,
 
     # We'll attempt to download new data if the latest entry in our cache is
     # before this date.
-    last_date = trading_days[trading_days.get_loc(now, method='ffill') - 2]
+    if(bundle_data):
+        # If we are using the bundle to retrieve the cryptobenchmark, find the last
+        # date for which there is trading data in the bundle
+        asset = bundle_data.asset_finder.lookup_symbol(symbol=bm_symbol,as_of_date=None)
+        ix = bundle_data.daily_bar_reader._last_rows[asset.sid]
+        last_date = pd.to_datetime(bundle_data.daily_bar_reader._spot_col('day')[ix],unit='s')
+    else:
+        last_date = trading_days[trading_days.get_loc(now, method='ffill') - 2]
     
     br = ensure_crypto_benchmark_data(
         bm_symbol,
@@ -132,21 +138,25 @@ def load_crypto_market_data(trading_day=None,
         # We need the trading_day to figure out the close prior to the first
         # date so that we can compute returns for the first date.
         trading_day,
+        bundle,
+        bundle_data,
         environ,
     )
+    # Override first_date for treasury data since we have it for many more years
+    # and is independent of crypto data
+    first_date_treasury = pd.Timestamp('1990-01-02', tz='UTC') 
     tc = ensure_treasury_data(
         bm_symbol,
-        first_date,
+        first_date_treasury,
         last_date,
         now,
         environ,
     )
     benchmark_returns = br[br.index.slice_indexer(first_date, last_date)]
-    treasury_curves = tc[tc.index.slice_indexer(first_date, last_date)]
+    treasury_curves = tc[tc.index.slice_indexer(first_date_treasury, last_date)]
     return benchmark_returns, treasury_curves
 
 
-
 def load_market_data(trading_day=None, trading_days=None, bm_symbol='SPY',
                      environ=None):
     """
@@ -232,17 +242,23 @@ def load_market_data(trading_day=None, trading_days=None, bm_symbol='SPY',
     treasury_curves = tc[tc.index.slice_indexer(first_date, last_date)]
     return benchmark_returns, treasury_curves
 
-def ensure_crypto_benchmark_data(symbol, first_date, last_date, now,
-                                trading_day, environ=None):
+
+def ensure_crypto_benchmark_data(symbol,
+                                 first_date,
+                                 last_date,
+                                 now,
+                                 trading_day,
+                                 bundle,
+                                 bundle_data,
+                                 environ=None):
+
     filename = get_benchmark_filename(symbol)
-    source_filename = '/var/tmp/catalyst/data/poloniex/crypto_prices-{0}.csv'.\
-        format(symbol)
 
     logger.info(
         ('Loading benchmark data for {symbol!r} '
             'from {first_date} to {last_date}'),
         symbol=symbol,
-        first_date=first_date - trading_day,
+        first_date=first_date,
         last_date=last_date
     )
 
@@ -255,106 +271,60 @@ def ensure_crypto_benchmark_data(symbol, first_date, last_date, now,
         environ,
     )
 
-
     if data is not None:
         return data
 
     # If no cached data was found or it was missing any dates then download the
     # necessary data.
-    logger.info(
-        ('Downloading benchmark data for {symbol!r} '
-            'from {first_date} to {last_date}'),
-        symbol=symbol,
-        first_date=first_date - trading_day,
-        last_date=last_date
-    )
 
-    def dateparse(time_in_secs):
-        return datetime.datetime.fromtimestamp(float(time_in_secs), pytz.utc)
+    if(bundle == 'poloniex'):
+        '''
+        If we're using the Poloniex bundle, we'll get the benchmark from the bundle
+        instead of downloading it from Poloniex every time we need it.
+        Poloniex has a captcha for API queries originating from outside the US that 
+        prevents users abroad from getting Catalyst to work
+        '''
+        logger.info(
+            ('Retrieving benchmark data from bundle for {symbol!r} from {first_date} to {last_date}'),
+            symbol=symbol, first_date=first_date, last_date=last_date)
 
-    def compute_daily_bars(five_min_bars, schedule):
-        # filter and copy the entry at the beginning of each session
-        daily_bars = five_min_bars[
-            five_min_bars.index.isin(schedule)
-        ].copy()
+        asset = bundle_data.asset_finder.lookup_symbol(symbol=symbol,as_of_date=None)
+        fields = ['day', 'close']
+        raw = bundle_data.daily_bar_reader.load_raw_arrays(
+            columns=fields,
+            start_date=first_date - trading_day,
+            end_date=last_date,
+            assets=[asset,])
+        bench_raw = pd.concat([pd.DataFrame(raw[0], columns=['date']),pd.DataFrame(raw[1], columns=['close'])], axis=1)
+        bench_raw['date'] = pd.to_datetime(bench_raw['date'],unit='s')
+        bench_raw.set_index('date', inplace=True)
+        bench_raw.sort_index(inplace=True)
+        bench_raw = bench_raw[pd.to_datetime(first_date - trading_day):pd.to_datetime(last_date)]
 
-        day_offset = pd.Timedelta(days=1)
+    else:
+        # This is how it used to be: downloading the benchmark everytime. 
+        # Leaving this code here to be repurposed in the future for other bundles.
+        logger.info(
+            ('Downloading benchmark data for {symbol!r} from {first_date} to {last_date}'),
+            symbol=symbol, first_date=first_date, last_date=last_date)
 
-        # iterate through session starts doing:
-        # 1. filter five_min_bars to get all entries in one day
-        # 2. compute daily bar entry
-        # 3. record in rid-th row of daily_bars
-        for rid, start_date in enumerate(daily_bars.index):
-            # compute beginning of next session
-            end_date = start_date + day_offset
-
-            # filter for entries session entries
-            day_data = five_min_bars[
-                (five_min_bars.index >= start_date) &
-                (five_min_bars.index < end_date)
-            ]
-
-            # compute and record daily bar
-            daily_bars.iloc[rid] = (
-                day_data.open.iloc[0],   # first open price
-                day_data.high.max(),     # max of high prices
-                day_data.low.min(),      # min of low prices
-                day_data.close.iloc[-1], # last close prices
-                day_data.volume.sum(),   # sum of all volumes
-            )
-
-        # scale to allow trading 10-ths of a coin
-        scale = 10.0
-        daily_bars.loc[:, 'open'] /= scale
-        daily_bars.loc[:, 'high'] /= scale
-        daily_bars.loc[:, 'low'] /= scale
-        daily_bars.loc[:, 'close'] /= scale
-        daily_bars.loc[:, 'volume'] *= scale
-        
-        return daily_bars
-
-    
-    five_min_bars = None
-    try:
-        # load five minute bars from csv cache
-        five_min_bars = pd.read_csv(
-            source_filename,
-            names=['date', 'open', 'high', 'low', 'close', 'volume'],
-            index_col=[0],
-            parse_dates=True,
-            date_parser=dateparse,
-        )
-        five_min_bars.index = pd.to_datetime(five_min_bars.index, utc=True, unit='s')
-    except (OSError, IOError):
-        # Otherwise load from Poloniex API
+        # Load benchmark symbol from Poloniex API
         try:
-            pc = PoloniexCurator()
-            pc.append_data_single_pair(symbol)
-
-            five_min_bars = pc.to_dataframe(
-                time.mktime(first_date.timetuple()),
-                time.mktime(last_date.timetuple()),
-                currencyPair=symbol,
+            bundle = PoloniexBundle()
+            bench_raw = bundle._fetch_symbol_frame(
+                None,
+                symbol,
+                get_calendar(bundle.calendar_name),
+                first_date - trading_day,
+                last_date,
+                'daily',
             )
         except (OSError, IOError, HTTPError):
-            logger.exception('Failed to new crypto benchmark returns')
+            logger.exception('Failed to fetch new crypto benchmark returns')
             raise
 
-    # compute daily bars for open calendar
-    open_calendar = get_calendar('OPEN')
-    daily_bars = compute_daily_bars(
-        five_min_bars,
-        open_calendar.all_sessions,
-    )
-
-    # filter daily bars to include first_date and last_date
-    daily_bars = daily_bars[
-        (daily_bars.index >= (first_date - trading_day)) &
-        (daily_bars.index <= last_date)
-    ]
-
     # select close column and compute percent change between days
-    daily_close = daily_bars[['close']]
+    daily_close = bench_raw[['close']]
     daily_close = daily_close.pct_change(1).iloc[1:]
 
     try:
@@ -430,6 +400,7 @@ def ensure_benchmark_data(symbol, first_date, last_date, now, trading_day,
         logger.warn("Still don't have expected data after redownload!")
     return data
 
+
 def ensure_benchmark_data(symbol, first_date, last_date, now, trading_day,
                           environ=None):
     """
@@ -544,11 +515,6 @@ def ensure_treasury_data(symbol, first_date, last_date, now, environ=None):
 
 def _load_cached_data(filename, first_date, last_date, now, resource_name,
                       environ=None):
-    if resource_name == 'benchmark':
-        from_csv = pd.Series.from_csv
-    else:
-        from_csv = pd.DataFrame.from_csv
-
     # Path for the cache.
     path = get_data_filepath(filename, environ)
 
@@ -556,8 +522,10 @@ def _load_cached_data(filename, first_date, last_date, now, resource_name,
     # yet, so don't try to read from 'path'.
     if os.path.exists(path):
         try:
-            data = from_csv(path)
-            data.index = pd.to_datetime(data.index).tz_localize('UTC')
+            data = pd.DataFrame.from_csv(path)
+            if data.empty:
+                raise ValueError("File is empty.")
+            data.index = pd.to_datetime(data.index, infer_datetime_format=True, errors='coerce' ).tz_localize('UTC')
             if has_data_for_dates(data, first_date, last_date):
                 return data
 
@@ -583,7 +551,7 @@ def _load_cached_data(filename, first_date, last_date, now, resource_name,
             )
 
     logger.info(
-        "Cache at {path} does not have data from {start} to {end}.\n",
+        "Cache at {path} does not have data from {start} to {end}.",
         start=first_date,
         end=last_date,
         path=path,

catalyst/data/us_equity_pricing.py

@@ -73,7 +73,10 @@ from catalyst.utils.sqlite_utils import (
     coerce_string_to_conn,
 )
 from catalyst.utils.memoize import lazyval
-from catalyst.utils.cli import maybe_show_progress
+from catalyst.utils.cli import (
+    item_show_count,
+    maybe_show_progress,
+)
 from ._equities import _compute_row_slices, _read_bcolz_data
 from ._adjustments import load_adjustments_from_sqlite
 
@@ -117,7 +120,15 @@ UINT64_MAX = iinfo(uint64).max
 def check_uint32_safe(value, colname):
     if value >= UINT32_MAX:
         raise ValueError(
-            "Value %s from column '%s' is too large" % (value, colname)
+            "Value %s from column '%s' is too large "
+            "for uint32" % (value, colname)
+        )
+
+def check_uint64_safe(value, colname):
+    if value >= UINT64_MAX:
+        raise ValueError(
+            "Value %s from column '%s' is too large "
+            "for uint64" % (value, colname)
         )
 
 
@@ -218,10 +229,7 @@ class BcolzDailyBarWriter(object):
 
     @property
     def progress_bar_message(self):
-        return "Merging daily equity files:"
-
-    def progress_bar_item_show_func(self, value):
-        return value if value is None else str(value[0])
+        return 'Compiling daily data'
 
     def write(self,
               data,
@@ -249,15 +257,17 @@ class BcolzDailyBarWriter(object):
         table : bcolz.ctable
             The newly-written table.
         """
+        total = None if assets is None else len(assets)
         ctx = maybe_show_progress(
             (
                 (sid, self.to_ctable(df, invalid_data_behavior))
                 for sid, df in data
             ),
             show_progress=show_progress,
-            item_show_func=self.progress_bar_item_show_func,
             label=self.progress_bar_message,
-            length=len(assets) if assets is not None else None,
+            item_show_func=item_show_count(total),
+            length=total,
+            show_percent=False,
         )
         with ctx as it:
             return self._write_internal(it, assets)

catalyst/examples/buy_and_hodl.py

@@ -23,9 +23,8 @@ from catalyst.api import (
     get_open_orders,
 )
 
-
 def initialize(context):
-    context.ASSET_NAME = 'USDT_ETH'
+    context.ASSET_NAME = 'USDT_BTC'
     context.TARGET_HODL_RATIO = 0.8
     context.RESERVE_RATIO = 1.0 - context.TARGET_HODL_RATIO
 
@@ -37,7 +36,11 @@ def initialize(context):
     context.is_buying = True
     context.asset = symbol(context.ASSET_NAME)
 
+    context.i = 0
+
 def handle_data(context, data):
+    context.i += 1
+
     starting_cash = context.portfolio.starting_cash
     target_hodl_value = context.TARGET_HODL_RATIO * starting_cash
     reserve_value = context.RESERVE_RATIO * starting_cash
@@ -67,6 +70,7 @@ def handle_data(context, data):
 
     record(
         price=price,
+        volume=data[context.asset].volume,
         cash=cash,
         starting_cash=context.portfolio.starting_cash,
         leverage=context.account.leverage,
@@ -74,12 +78,13 @@ def handle_data(context, data):
 
 def analyze(context=None, results=None):
     import matplotlib.pyplot as plt
+
     # Plot the portfolio and asset data.
-    ax1 = plt.subplot(511)
+    ax1 = plt.subplot(611)
     results[['portfolio_value']].plot(ax=ax1)
     ax1.set_ylabel('Portfolio Value (USD)')
 
-    ax2 = plt.subplot(512, sharex=ax1)
+    ax2 = plt.subplot(612, sharex=ax1)
     ax2.set_ylabel('{asset} (USD)'.format(asset=context.ASSET_NAME))
     (context.TICK_SIZE * results[['price']]).plot(ax=ax2)
 
@@ -95,11 +100,11 @@ def analyze(context=None, results=None):
         color='g',
     )
 
-    ax3 = plt.subplot(513, sharex=ax1)
+    ax3 = plt.subplot(613, sharex=ax1)
     results[['leverage', 'alpha', 'beta']].plot(ax=ax3)
     ax3.set_ylabel('Leverage ')
 
-    ax4 = plt.subplot(514, sharex=ax1)
+    ax4 = plt.subplot(614, sharex=ax1)
     results[['starting_cash', 'cash']].plot(ax=ax4)
     ax4.set_ylabel('Cash (USD)')
 
@@ -113,7 +118,7 @@ def analyze(context=None, results=None):
         'benchmark_period_return',
     ]]
 
-    ax5 = plt.subplot(515, sharex=ax1)
+    ax5 = plt.subplot(615, sharex=ax1)
     results[[
         'treasury',
         'algorithm',
@@ -121,6 +126,10 @@ def analyze(context=None, results=None):
     ]].plot(ax=ax5)
     ax5.set_ylabel('Percent Change')
 
+    ax6 = plt.subplot(616, sharex=ax1)
+    results[['volume']].plot(ax=ax6)
+    ax6.set_ylabel('Volume (mCoins/5min)')
+
     plt.legend(loc=3)
 
     # Show the plot.

catalyst/examples/buy_low_sell_high.py

@@ -0,0 +1,155 @@
+'''
+This algorithm requires an additional library (ta-lib) beyond those required by catalyst.
+Install it first by running: 
+$ pip install TA-Lib
+
+If you get build errors like "fatal error: ta-lib/ta_libc.h: No such file or directory"
+it typically means that it can't find the underlying TA-Lib library and needs to be installed.
+See https://mrjbq7.github.io/ta-lib/install.html for instructions on how to install 
+the required dependencies.
+'''
+
+import talib
+from logbook import Logger
+
+from catalyst.api import (
+    order,
+    order_target_percent,
+    symbol,
+    record,
+    get_open_orders,
+)
+from catalyst.exchange.stats_utils import get_pretty_stats
+
+algo_namespace = 'buy_low_sell_high_xrp'
+log = Logger(algo_namespace)
+
+
+def initialize(context):
+    log.info('initializing algo')
+    context.ASSET_NAME = 'XRP_USD'
+    context.asset = symbol(context.ASSET_NAME)
+
+    context.TARGET_POSITIONS = 5000
+    context.PROFIT_TARGET = 0.1
+    context.SLIPPAGE_ALLOWED = 0.05
+
+    context.retry_check_open_orders = 10
+    context.retry_update_portfolio = 10
+    context.retry_order = 5
+
+    context.errors = []
+    pass
+
+
+def _handle_data(context, data):
+    prices = data.history(
+        context.asset,
+        fields='price',
+        bar_count=20,
+        frequency='15m'
+    )
+    rsi = talib.RSI(prices.values, timeperiod=14)[-1]
+    log.info('got rsi: {}'.format(rsi))
+
+    # Buying more when RSI is low, this should lower our cost basis
+    if rsi <= 30:
+        buy_increment = 50
+    elif rsi <= 40:
+        buy_increment = 20
+    elif rsi <= 70:
+        buy_increment = 5
+    else:
+        buy_increment = None
+
+    cash = context.portfolio.cash
+    log.info('base currency available: {cash}'.format(cash=cash))
+
+    price = data.current(context.asset, 'price')
+    log.info('got price {price}'.format(price=price))
+
+    record(
+        price=price,
+        rsi=rsi,
+    )
+
+    orders = get_open_orders(context.asset)
+    if orders:
+        log.info('skipping bar until all open orders execute')
+        return
+
+    is_buy = False
+    cost_basis = None
+    if context.asset in context.portfolio.positions:
+        position = context.portfolio.positions[context.asset]
+
+        cost_basis = position.cost_basis
+        log.info(
+            'found {amount} positions with cost basis {cost_basis}'.format(
+                amount=position.amount,
+                cost_basis=cost_basis
+            )
+        )
+
+        if position.amount >= context.TARGET_POSITIONS:
+            log.info('reached positions target: {}'.format(position.amount))
+            return
+
+        if price < cost_basis:
+            is_buy = True
+        elif position.amount > 0 and \
+                        price > cost_basis * (1 + context.PROFIT_TARGET):
+            profit = (price * position.amount) - (cost_basis * position.amount)
+            log.info('closing position, taking profit: {}'.format(profit))
+            order_target_percent(
+                asset=context.asset,
+                target=0,
+                limit_price=price * (1 - context.SLIPPAGE_ALLOWED),
+            )
+        else:
+            log.info('no buy or sell opportunity found')
+    else:
+        is_buy = True
+
+    if is_buy:
+        if buy_increment is None:
+            log.info('the rsi is too high to consider buying {}'.format(rsi))
+            return
+
+        if price * buy_increment > cash:
+            log.info('not enough base currency to consider buying')
+            return
+
+        log.info(
+            'buying position cheaper than cost basis {} < {}'.format(
+                price,
+                cost_basis
+            )
+        )
+        order(
+            asset=context.asset,
+            amount=buy_increment,
+            limit_price=price * (1 + context.SLIPPAGE_ALLOWED)
+        )
+
+
+def handle_data(context, data):
+    log.info('handling bar {}'.format(data.current_dt))
+    # try:
+    _handle_data(context, data)
+    # except Exception as e:
+    #     log.warn('aborting the bar on error {}'.format(e))
+    #     context.errors.append(e)
+
+    log.info('completed bar {}, total execution errors {}'.format(
+        data.current_dt,
+        len(context.errors)
+    ))
+
+    if len(context.errors) > 0:
+        log.info('the errors:\n{}'.format(context.errors))
+
+
+def analyze(context, stats):
+    log.info('the daily stats:\n{}'.format(get_pretty_stats(stats)))
+    pass

catalyst/examples/dual_vwap.py

@@ -52,7 +52,7 @@ def initialize(context):
 
     schedule_function(
         rebalance,
-        date_rules.every_day(),
+        time_rules=times_rules.every_minute(),
     )
 
 

catalyst/exchange/algorithm_exchange.py

@@ -0,0 +1,452 @@
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+import os
+import signal
+import sys
+import pickle
+from datetime import timedelta
+from time import sleep
+from os import listdir
+from os.path import isfile, join
+from collections import deque
+
+import logbook
+import pandas as pd
+
+import catalyst.protocol as zp
+from catalyst.algorithm import TradingAlgorithm
+from catalyst.data.minute_bars import BcolzMinuteBarWriter, \
+    BcolzMinuteBarReader
+from catalyst.errors import OrderInBeforeTradingStart
+from catalyst.exchange.exchange_clock import ExchangeClock
+from catalyst.exchange.exchange_errors import (
+    ExchangeRequestError,
+    ExchangePortfolioDataError,
+    ExchangeTransactionError
+)
+from catalyst.exchange.exchange_utils import get_exchange_minute_writer_root, \
+    save_algo_object, get_algo_object, get_algo_folder
+from catalyst.exchange.stats_utils import get_pretty_stats
+from catalyst.finance.performance.period import calc_period_stats
+from catalyst.gens.tradesimulation import AlgorithmSimulator
+from catalyst.utils.api_support import (
+    api_method,
+    disallowed_in_before_trading_start)
+from catalyst.utils.input_validation import error_keywords
+
+log = logbook.Logger("ExchangeTradingAlgorithm")
+
+
+class ExchangeAlgorithmExecutor(AlgorithmSimulator):
+    def __init__(self, *args, **kwargs):
+        super(self.__class__, self).__init__(*args, **kwargs)
+
+
+class ExchangeTradingAlgorithm(TradingAlgorithm):
+    def __init__(self, *args, **kwargs):
+        self.exchange = kwargs.pop('exchange', None)
+        self.algo_namespace = kwargs.pop('algo_namespace', None)
+        self.orders = {}
+        self.minute_stats = deque(maxlen=60)
+        self.is_running = True
+
+        self.retry_check_open_orders = 5
+        self.retry_synchronize_portfolio = 5
+        self.retry_get_open_orders = 5
+        self.retry_order = 2
+        self.retry_delay = 5
+
+        self.stats_minutes = 5
+
+        super(self.__class__, self).__init__(*args, **kwargs)
+        # self._create_minute_writer()
+
+        signal.signal(signal.SIGINT, self.signal_handler)
+
+        log.info('exchange trading algorithm successfully initialized')
+
+    def _create_minute_writer(self):
+        root = get_exchange_minute_writer_root(self.exchange.name)
+        filename = os.path.join(root, 'metadata.json')
+
+        if os.path.isfile(filename):
+            writer = BcolzMinuteBarWriter.open(
+                root, self.sim_params.end_session)
+        else:
+            writer = BcolzMinuteBarWriter(
+                rootdir=root,
+                calendar=self.trading_calendar,
+                minutes_per_day=1440,
+                start_session=self.sim_params.start_session,
+                end_session=self.sim_params.end_session,
+                write_metadata=True
+            )
+
+        self.exchange.minute_writer = writer
+        self.exchange.minute_reader = BcolzMinuteBarReader(root)
+
+    def signal_handler(self, signal, frame):
+        self.is_running = False
+
+        if self._analyze is None:
+            log.info('Interruption signal detected {}, exiting the '
+                     'algorithm'.format(signal))
+
+        else:
+            log.info('Interruption signal detected {}, calling `analyze()` '
+                     'before exiting the algorithm'.format(signal))
+
+            algo_folder = get_algo_folder(self.algo_namespace)
+            folder = join(algo_folder, 'daily_perf')
+            files = [f for f in listdir(folder) if isfile(join(folder, f))]
+
+            daily_perf_list = []
+            for item in files:
+                filename = join(folder, item)
+                with open(filename, 'rb') as handle:
+                    daily_perf_list.append(pickle.load(handle))
+
+            stats = pd.DataFrame(daily_perf_list)
+
+            self.analyze(stats)
+
+        sys.exit(0)
+
+    def _create_clock(self):
+
+        # The calendar's execution times are the minutes over which we actually
+        # want to run the clock. Typically the execution times simply adhere to
+        # the market open and close times. In the case of the futures calendar,
+        # for example, we only want to simulate over a subset of the full 24
+        # hour calendar, so the execution times dictate a market open time of
+        # 6:31am US/Eastern and a close of 5:00pm US/Eastern.
+
+        # In our case, we are trading around the clock, so the market close
+        # corresponds to the last minute of the day.
+
+        # This method is taken from TradingAlgorithm.
+        # The clock has been replaced to use RealtimeClock
+        # TODO: should we apply a time skew? not sure to understand the utility.
+        return ExchangeClock(
+            self.sim_params.sessions,
+            time_skew=self.exchange.time_skew
+        )
+
+    def _create_generator(self, sim_params):
+        if self.perf_tracker is None:
+            self.perf_tracker = get_algo_object(
+                algo_name=self.algo_namespace,
+                key='perf_tracker'
+            )
+
+        # Call the simulation trading algorithm for side-effects:
+        # it creates the perf tracker
+        TradingAlgorithm._create_generator(self, sim_params)
+        self.trading_client = ExchangeAlgorithmExecutor(
+            self,
+            sim_params,
+            self.data_portal,
+            self._create_clock(),
+            self._create_benchmark_source(),
+            self.restrictions,
+            universe_func=self._calculate_universe
+        )
+
+        return self.trading_client.transform()
+
+    def updated_portfolio(self):
+        """
+        We skip the entire performance tracker business and update the
+        portfolio directly.
+        :return:
+        """
+        return self.exchange.portfolio
+
+    def updated_account(self):
+        return self.exchange.account
+
+    def _synchronize_portfolio(self, attempt_index=0):
+        try:
+            self.exchange.synchronize_portfolio()
+
+            # Applying the updated last_sales_price to the positions
+            # in the performance tracker. This seems a bit redundant
+            # but it will make sense when we have multiple exchange portfolios
+            # feeding into the same performance tracker.
+            tracker = self.perf_tracker.todays_performance.position_tracker
+            for asset in self.exchange.portfolio.positions:
+                position = self.exchange.portfolio.positions[asset]
+                tracker.update_position(
+                    asset=asset,
+                    last_sale_date=position.last_sale_date,
+                    last_sale_price=position.last_sale_price
+                )
+        except ExchangeRequestError as e:
+            log.warn(
+                'update portfolio attempt {}: {}'.format(attempt_index, e)
+            )
+            if attempt_index < self.retry_synchronize_portfolio:
+                sleep(self.retry_delay)
+                self._synchronize_portfolio(attempt_index + 1)
+            else:
+                raise ExchangePortfolioDataError(
+                    data_type='update-portfolio',
+                    attempts=attempt_index,
+                    error=e
+                )
+
+    def _check_open_orders(self, attempt_index=0):
+        try:
+            return self.exchange.check_open_orders()
+        except ExchangeRequestError as e:
+            log.warn(
+                'check open orders attempt {}: {}'.format(attempt_index, e)
+            )
+            if attempt_index < self.retry_check_open_orders:
+                sleep(self.retry_delay)
+                return self._check_open_orders(attempt_index + 1)
+            else:
+                raise ExchangePortfolioDataError(
+                    data_type='order-status',
+                    attempts=attempt_index,
+                    error=e
+                )
+
+    def prepare_period_stats(self, start_dt, end_dt):
+        """
+        Creates a dictionary representing the state of the tracker.
+
+
+        I rewrote this in an attempt to better control the stats.
+        I don't want things to happen magically through complex logic
+        pertaining to backtesting.
+
+        """
+        tracker = self.perf_tracker
+        period = tracker.todays_performance
+
+        pos_stats = period.position_tracker.stats()
+        period_stats = calc_period_stats(pos_stats, period.ending_cash)
+
+        stats = dict(
+            period_start=tracker.period_start,
+            period_end=tracker.period_end,
+            capital_base=tracker.capital_base,
+            progress=tracker.progress,
+            ending_value=period.ending_value,
+            ending_exposure=period.ending_exposure,
+            capital_used=period.cash_flow,
+            starting_value=period.starting_value,
+            starting_exposure=period.starting_exposure,
+            starting_cash=period.starting_cash,
+            ending_cash=period.ending_cash,
+            portfolio_value=period.ending_cash + period.ending_value,
+            pnl=period.pnl,
+            returns=period.returns,
+            period_open=period.period_open,
+            period_close=period.period_close,
+            gross_leverage=period_stats.gross_leverage,
+            net_leverage=period_stats.net_leverage,
+            short_exposure=pos_stats.short_exposure,
+            long_exposure=pos_stats.long_exposure,
+            short_value=pos_stats.short_value,
+            long_value=pos_stats.long_value,
+            longs_count=pos_stats.longs_count,
+            shorts_count=pos_stats.shorts_count,
+        )
+
+        # Merging cumulative risk
+        stats.update(tracker.cumulative_risk_metrics.to_dict())
+
+        # Merging latest recorded variables
+        stats.update(self.recorded_vars)
+
+        stats['positions'] = period.position_tracker.get_positions_list()
+
+        # we want the key to be absent, not just empty
+        # Only include transactions for given dt
+        stats['transactions'] = dict()
+        for date in period.processed_transactions:
+            if start_dt <= date < end_dt:
+                stats['transactions'][date] = \
+                    period.processed_transactions[date]
+
+        stats['orders'] = dict()
+        for date in period.orders_by_modified:
+            if start_dt <= date < end_dt:
+                stats['orders'][date] = \
+                    period.orders_by_modified[date]
+
+        return stats
+
+    def handle_data(self, data):
+        if not self.is_running:
+            return
+
+        self._synchronize_portfolio()
+
+        transactions = self._check_open_orders()
+        for transaction in transactions:
+            self.perf_tracker.process_transaction(transaction)
+
+        if self._handle_data:
+            self._handle_data(self, data)
+
+        # Unlike trading controls which remain constant unless placing an
+        # order, account controls can change each bar. Thus, must check
+        # every bar no matter if the algorithm places an order or not.
+        self.validate_account_controls()
+
+        try:
+            # Since the clock runs 24/7, I trying to disable the daily
+            # Performance tracker and keep only minute and cumulative
+            self.perf_tracker.update_performance()
+
+            minute_stats = self.prepare_period_stats(
+                data.current_dt, data.current_dt + timedelta(minutes=1))
+            # Saving the last hour in memory
+            self.minute_stats.append(minute_stats)
+
+            print_df = pd.DataFrame(list(self.minute_stats))
+            log.debug(
+                'statistics for the last {stats_minutes} minutes:\n{stats}'.format(
+                    stats_minutes=self.stats_minutes,
+                    stats=get_pretty_stats(print_df, self.stats_minutes)
+                ))
+
+            today = pd.to_datetime('today', utc=True)
+            daily_stats = self.prepare_period_stats(
+                start_dt=today,
+                end_dt=pd.Timestamp.utcnow()
+            )
+            save_algo_object(
+                algo_name=self.algo_namespace,
+                key=today.strftime('%Y-%m-%d'),
+                obj=daily_stats,
+                rel_path='daily_perf'
+            )
+
+        except Exception as e:
+            log.warn('unable to calculate performance: {}'.format(e))
+
+        try:
+            save_algo_object(
+                algo_name=self.algo_namespace,
+                key='perf_tracker',
+                obj=self.perf_tracker
+            )
+        except Exception as e:
+            log.warn('unable to save minute perfs to disk: {}'.format(e))
+
+        try:
+            save_algo_object(
+                algo_name=self.algo_namespace,
+                key='portfolio_{}'.format(self.exchange.name),
+                obj=self.exchange.portfolio
+            )
+        except Exception as e:
+            log.warn('unable to save portfolio to disk: {}'.format(e))
+
+    def _order(self,
+               asset,
+               amount,
+               limit_price=None,
+               stop_price=None,
+               style=None,
+               attempt_index=0):
+        try:
+            return self.exchange.order(asset, amount, limit_price,
+                                       stop_price,
+                                       style)
+        except ExchangeRequestError as e:
+            log.warn(
+                'order attempt {}: {}'.format(attempt_index, e)
+            )
+            if attempt_index < self.retry_order:
+                sleep(self.retry_delay)
+                return self._order(
+                    asset, amount, limit_price, stop_price, style,
+                    attempt_index + 1)
+            else:
+                raise ExchangeTransactionError(
+                    transaction_type='order',
+                    attempts=attempt_index,
+                    error=e
+                )
+
+    @api_method
+    @disallowed_in_before_trading_start(OrderInBeforeTradingStart())
+    def order(self,
+              asset,
+              amount,
+              limit_price=None,
+              stop_price=None,
+              style=None):
+        amount, style = self._calculate_order(asset, amount,
+                                              limit_price, stop_price,
+                                              style)
+
+        order_id = self._order(asset, amount, limit_price, stop_price, style)
+
+        if order_id is not None:
+            order = self.portfolio.open_orders[order_id]
+            self.perf_tracker.process_order(order)
+
+        return order
+
+    def round_order(self, amount):
+        """
+        We need fractions with cryptocurrencies
+
+        :param amount:
+        :return:
+        """
+        return amount
+
+    @api_method
+    def batch_market_order(self, share_counts):
+        raise NotImplementedError()
+
+    def _get_open_orders(self, asset=None, attempt_index=0):
+        try:
+            return self.exchange.get_open_orders(asset)
+        except ExchangeRequestError as e:
+            log.warn(
+                'open orders attempt {}: {}'.format(attempt_index, e)
+            )
+            if attempt_index < self.retry_get_open_orders:
+                sleep(self.retry_delay)
+                return self._get_open_orders(asset, attempt_index + 1)
+            else:
+                raise ExchangePortfolioDataError(
+                    data_type='open-orders',
+                    attempts=attempt_index,
+                    error=e
+                )
+
+    @error_keywords(sid='Keyword argument `sid` is no longer supported for '
+                        'get_open_orders. Use `asset` instead.')
+    @api_method
+    def get_open_orders(self, asset=None):
+        return self._get_open_orders(asset)
+
+    @api_method
+    def get_order(self, order_id):
+        return self.exchange.get_order(order_id)
+
+    @api_method
+    def cancel_order(self, order_param):
+        order_id = order_param
+        if isinstance(order_param, zp.Order):
+            order_id = order_param.id
+        self.exchange.cancel_order(order_id)

catalyst/exchange/asset_finder_exchange.py

@@ -0,0 +1,91 @@
+from logbook import Logger
+
+log = Logger('AssetFinderExchange')
+
+
+class AssetFinderExchange(object):
+    def __init__(self, exchange):
+        self.exchange = exchange
+        self._asset_cache = {}
+
+    @property
+    def sids(self):
+        """
+        This seems to be used to pre-fetch assets.
+        I don't think that we need this for live-trading.
+        Leaving the list empty.
+        """
+        return list()
+
+    def retrieve_all(self, sids, default_none=False):
+        """
+        Retrieve all assets in `sids`.
+
+        Parameters
+        ----------
+        sids : iterable of int
+            Assets to retrieve.
+        default_none : bool
+            If True, return None for failed lookups.
+            If False, raise `SidsNotFound`.
+
+        Returns
+        -------
+        assets : list[Asset or None]
+            A list of the same length as `sids` containing Assets (or Nones)
+            corresponding to the requested sids.
+
+        Raises
+        ------
+        SidsNotFound
+            When a requested sid is not found and default_none=False.
+        """
+        for sid in sids:
+            if sid in self._asset_cache:
+                log.info('got asset from cache: {}'.format(sid))
+            else:
+                log.info('fetching asset: {}'.format(sid))
+        return list()
+
+    def lookup_symbol(self, symbol, as_of_date, fuzzy=False):
+        """Lookup an asset by symbol.
+
+        Parameters
+        ----------
+        symbol : str
+            The ticker symbol to resolve.
+        as_of_date : datetime or None
+            Look up the last owner of this symbol as of this datetime.
+            If ``as_of_date`` is None, then this can only resolve the equity
+            if exactly one equity has ever owned the ticker.
+        fuzzy : bool, optional
+            Should fuzzy symbol matching be used? Fuzzy symbol matching
+            attempts to resolve differences in representations for
+            shareclasses. For example, some people may represent the ``A``
+            shareclass of ``BRK`` as ``BRK.A``, where others could write
+            ``BRK_A``.
+
+        Returns
+        -------
+        equity : Asset
+            The equity that held ``symbol`` on the given ``as_of_date``, or the
+            only equity to hold ``symbol`` if ``as_of_date`` is None.
+
+        Raises
+        ------
+        SymbolNotFound
+            Raised when no equity has ever held the given symbol.
+        MultipleSymbolsFound
+            Raised when no ``as_of_date`` is given and more than one equity
+            has held ``symbol``. This is also raised when ``fuzzy=True`` and
+            there are multiple candidates for the given ``symbol`` on the
+            ``as_of_date``.
+        """
+        log.debug('looking up symbol: {}'.format(symbol))
+
+        if symbol in self._asset_cache:
+            return self._asset_cache[symbol]
+        else:
+            asset = self.exchange.get_asset(symbol)
+            self._asset_cache[symbol] = asset
+            return asset

catalyst/exchange/bitfinex/bitfinex.py

@@ -0,0 +1,529 @@
+import base64
+import hashlib
+import hmac
+import json
+import re
+import time
+
+import numpy as np
+import pandas as pd
+import pytz
+import requests
+import six
+from catalyst.assets._assets import TradingPair
+from logbook import Logger
+
+# from websocket import create_connection
+from catalyst.exchange.exchange import Exchange
+from catalyst.exchange.exchange_errors import (
+    ExchangeRequestError,
+    InvalidHistoryFrequencyError,
+    InvalidOrderStyle, OrderCancelError)
+from catalyst.exchange.exchange_execution import ExchangeLimitOrder, \
+    ExchangeStopLimitOrder, ExchangeStopOrder
+from catalyst.finance.order import Order, ORDER_STATUS
+from catalyst.protocol import Account
+
+# Trying to account for REST api instability
+# https://stackoverflow.com/questions/15431044/can-i-set-max-retries-for-requests-request
+requests.adapters.DEFAULT_RETRIES = 20
+
+BITFINEX_URL = 'https://api.bitfinex.com'
+
+log = Logger('Bitfinex')
+warning_logger = Logger('AlgoWarning')
+
+
+class Bitfinex(Exchange):
+    def __init__(self, key, secret, base_currency, portfolio=None):
+        self.url = BITFINEX_URL
+        self.key = key
+        self.secret = secret.encode('UTF-8')
+        self.name = 'bitfinex'
+        self.assets = {}
+        self.load_assets()
+        self.base_currency = base_currency
+        self._portfolio = portfolio
+        self.minute_writer = None
+        self.minute_reader = None
+
+    def _request(self, operation, data, version='v1'):
+        payload_object = {
+            'request': '/{}/{}'.format(version, operation),
+            'nonce': '{0:f}'.format(time.time() * 1000000),
+            # convert to string
+            'options': {}
+        }
+
+        if data is None:
+            payload_dict = payload_object
+        else:
+            payload_dict = payload_object.copy()
+            payload_dict.update(data)
+
+        payload_json = json.dumps(payload_dict)
+        if six.PY3:
+            payload = base64.b64encode(bytes(payload_json, 'utf-8'))
+        else:
+            payload = base64.b64encode(payload_json)
+
+        m = hmac.new(self.secret, payload, hashlib.sha384)
+        m = m.hexdigest()
+
+        # headers
+        headers = {
+            'X-BFX-APIKEY': self.key,
+            'X-BFX-PAYLOAD': payload,
+            'X-BFX-SIGNATURE': m
+        }
+
+        if data is None:
+            request = requests.get(
+                '{url}/{version}/{operation}'.format(
+                    url=self.url,
+                    version=version,
+                    operation=operation
+                ), data={},
+                headers=headers)
+        else:
+            request = requests.post(
+                '{url}/{version}/{operation}'.format(
+                    url=self.url,
+                    version=version,
+                    operation=operation
+                ),
+                headers=headers)
+
+        return request
+
+    def _get_v2_symbol(self, asset):
+        pair = asset.symbol.split('_')
+        symbol = 't' + pair[0].upper() + pair[1].upper()
+        return symbol
+
+    def _get_v2_symbols(self, assets):
+        """
+        Workaround to support Bitfinex v2
+        TODO: Might require a separate asset dictionary
+
+        :param assets:
+        :return:
+        """
+
+        v2_symbols = []
+        for asset in assets:
+            v2_symbols.append(self._get_v2_symbol(asset))
+
+        return v2_symbols
+
+    def _create_order(self, order_status):
+        """
+        Create a Catalyst order object from a Bitfinex order dictionary
+        :param order_status:
+        :return: Order
+        """
+        if order_status['is_cancelled']:
+            status = ORDER_STATUS.CANCELLED
+        elif not order_status['is_live']:
+            log.info('found executed order {}'.format(order_status))
+            status = ORDER_STATUS.FILLED
+        else:
+            status = ORDER_STATUS.OPEN
+
+        amount = float(order_status['original_amount'])
+        filled = float(order_status['executed_amount'])
+
+        if order_status['side'] == 'sell':
+            amount = -amount
+            filled = -filled
+
+        price = float(order_status['price'])
+        order_type = order_status['type']
+
+        stop_price = None
+        limit_price = None
+
+        # TODO: is this comprehensive enough?
+        if order_type.endswith('limit'):
+            limit_price = price
+        elif order_type.endswith('stop'):
+            stop_price = price
+
+        executed_price = float(order_status['avg_execution_price'])
+
+        # TODO: bitfinex does not specify comission. I could calculate it but not sure if it's worth it.
+        commission = None
+
+        date = pd.Timestamp.utcfromtimestamp(float(order_status['timestamp']))
+        date = pytz.utc.localize(date)
+        order = Order(
+            dt=date,
+            asset=self.assets[order_status['symbol']],
+            amount=amount,
+            stop=stop_price,
+            limit=limit_price,
+            filled=filled,
+            id=str(order_status['id']),
+            commission=commission
+        )
+        order.status = status
+
+        return order, executed_price
+
+    def get_balances(self):
+        log.debug('retrieving wallets balances')
+        try:
+            response = self._request('balances', None)
+            balances = response.json()
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        if 'message' in balances:
+            raise ExchangeRequestError(
+                error='unable to fetch balance {}'.format(balances['message'])
+            )
+
+        std_balances = dict()
+        for balance in balances:
+            currency = balance['currency'].lower()
+            std_balances[currency] = float(balance['available'])
+
+        return std_balances
+
+    @property
+    def account(self):
+        account = Account()
+
+        account.settled_cash = None
+        account.accrued_interest = None
+        account.buying_power = None
+        account.equity_with_loan = None
+        account.total_positions_value = None
+        account.total_positions_exposure = None
+        account.regt_equity = None
+        account.regt_margin = None
+        account.initial_margin_requirement = None
+        account.maintenance_margin_requirement = None
+        account.available_funds = None
+        account.excess_liquidity = None
+        account.cushion = None
+        account.day_trades_remaining = None
+        account.leverage = None
+        account.net_leverage = None
+        account.net_liquidation = None
+
+        return account
+
+    @property
+    def time_skew(self):
+        # TODO: research the time skew conditions
+        return pd.Timedelta('0s')
+
+    def get_account(self):
+        # TODO: fetch account data and keep in cache
+        return None
+
+    def get_candles(self, data_frequency, assets, bar_count=None):
+        """
+        Retrieve OHLVC candles from Bitfinex
+
+        :param data_frequency:
+        :param assets:
+        :param bar_count:
+        :return:
+
+        Available Frequencies
+        ---------------------
+        '1m', '5m', '15m', '30m', '1h', '3h', '6h', '12h', '1D', '7D', '14D',
+         '1M'
+        """
+
+        # TODO: use BcolzMinuteBarReader to read from cache
+        freq_match = re.match(r'([0-9].*)(m|h|d)', data_frequency, re.M | re.I)
+        if freq_match:
+            number = int(freq_match.group(1))
+            unit = freq_match.group(2)
+
+            if unit == 'd':
+                converted_unit = 'D'
+            else:
+                converted_unit = unit
+
+            frequency = '{}{}'.format(number, converted_unit)
+            allowed_frequencies = ['1m', '5m', '15m', '30m', '1h', '3h', '6h',
+                                   '12h', '1D', '7D', '14D', '1M']
+
+            if frequency not in allowed_frequencies:
+                raise InvalidHistoryFrequencyError(
+                    frequency=data_frequency
+                )
+        elif data_frequency == 'minute':
+            frequency = '1m'
+        elif data_frequency == 'daily':
+            frequency = '1D'
+        else:
+            raise InvalidHistoryFrequencyError(
+                frequency=data_frequency
+            )
+
+        # Making sure that assets are iterable
+        asset_list = [assets] if isinstance(assets, TradingPair) else assets
+        ohlc_map = dict()
+        for asset in asset_list:
+            symbol = self._get_v2_symbol(asset)
+            url = '{url}/v2/candles/trade:{frequency}:{symbol}'.format(
+                url=self.url,
+                frequency=frequency,
+                symbol=symbol
+            )
+
+            if bar_count:
+                is_list = True
+                url += '/hist?limit={}'.format(int(bar_count))
+            else:
+                is_list = False
+                url += '/last'
+
+            try:
+                response = requests.get(url)
+            except Exception as e:
+                raise ExchangeRequestError(error=e)
+
+            if 'error' in response.content:
+                raise ExchangeRequestError(
+                    error='Unable to retrieve candles: {}'.format(
+                        response.content)
+                )
+
+            candles = response.json()
+
+            def ohlc_from_candle(candle):
+                ohlc = dict(
+                    open=np.float64(candle[1]),
+                    high=np.float64(candle[3]),
+                    low=np.float64(candle[4]),
+                    close=np.float64(candle[2]),
+                    volume=np.float64(candle[5]),
+                    price=np.float64(candle[2]),
+                    last_traded=pd.Timestamp.utcfromtimestamp(
+                        candle[0] / 1000.0)
+                )
+                return ohlc
+
+            if is_list:
+                ohlc_bars = []
+                # We can to list candles from old to new
+                for candle in reversed(candles):
+                    ohlc = ohlc_from_candle(candle)
+                    ohlc_bars.append(ohlc)
+
+                ohlc_map[asset] = ohlc_bars
+
+            else:
+                ohlc = ohlc_from_candle(candles)
+                ohlc_map[asset] = ohlc
+
+        return ohlc_map[assets] \
+            if isinstance(assets, TradingPair) else ohlc_map
+
+    def create_order(self, asset, amount, is_buy, style):
+        """
+        Creating order on the exchange.
+
+        :param asset:
+        :param amount:
+        :param is_buy:
+        :param style:
+        :return:
+        """
+        exchange_symbol = self.get_symbol(asset)
+        if isinstance(style, ExchangeLimitOrder) \
+                or isinstance(style, ExchangeStopLimitOrder):
+            price = style.get_limit_price(is_buy)
+            order_type = 'limit'
+
+        elif isinstance(style, ExchangeStopOrder):
+            price = style.get_stop_price(is_buy)
+            order_type = 'stop'
+
+        else:
+            raise InvalidOrderStyle(exchange=self.name,
+                                    style=style.__class__.__name__)
+
+        req = dict(
+            symbol=exchange_symbol,
+            amount=str(float(abs(amount))),
+            price="{:.20f}".format(float(price)),
+            side='buy' if is_buy else 'sell',
+            type='exchange ' + order_type,  # TODO: support margin trades
+            exchange=self.name,
+            is_hidden=False,
+            is_postonly=False,
+            use_all_available=0,
+            ocoorder=False,
+            buy_price_oco=0,
+            sell_price_oco=0
+        )
+
+        date = pd.Timestamp.utcnow()
+        try:
+            response = self._request('order/new', req)
+            order_status = response.json()
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        if 'message' in order_status:
+            raise ExchangeRequestError(
+                error='unable to create Bitfinex order {}'.format(
+                    order_status['message'])
+            )
+
+        order_id = str(order_status['id'])
+        order = Order(
+            dt=date,
+            asset=asset,
+            amount=amount,
+            stop=style.get_stop_price(is_buy),
+            limit=style.get_limit_price(is_buy),
+            id=order_id
+        )
+
+        return order
+
+    def get_open_orders(self, asset=None):
+        """Retrieve all of the current open orders.
+
+        Parameters
+        ----------
+        asset : Asset
+            If passed and not None, return only the open orders for the given
+            asset instead of all open orders.
+
+        Returns
+        -------
+        open_orders : dict[list[Order]] or list[Order]
+            If no asset is passed this will return a dict mapping Assets
+            to a list containing all the open orders for the asset.
+            If an asset is passed then this will return a list of the open
+            orders for this asset.
+        """
+        try:
+            response = self._request('orders', None)
+            order_statuses = response.json()
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        if 'message' in order_statuses:
+            raise ExchangeRequestError(
+                error='Unable to retrieve open orders: {}'.format(
+                    order_statuses['message'])
+            )
+
+        orders = list()
+        for order_status in order_statuses:
+            order, executed_price = self._create_order(order_status)
+            if asset is None or asset == order.sid:
+                orders.append(order)
+
+        return orders
+
+    def get_order(self, order_id):
+        """Lookup an order based on the order id returned from one of the
+        order functions.
+
+        Parameters
+        ----------
+        order_id : str
+            The unique identifier for the order.
+
+        Returns
+        -------
+        order : Order
+            The order object.
+        """
+        try:
+            response = self._request(
+                'order/status', {'order_id': int(order_id)})
+            order_status = response.json()
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        if 'message' in order_status:
+            raise ExchangeRequestError(
+                error='Unable to retrieve order status: {}'.format(
+                    order_status['message'])
+            )
+        return self._create_order(order_status)
+
+    def cancel_order(self, order_param):
+        """Cancel an open order.
+
+        Parameters
+        ----------
+        order_param : str or Order
+            The order_id or order object to cancel.
+        """
+        order_id = order_param.id \
+            if isinstance(order_param, Order) else order_param
+
+        try:
+            response = self._request('order/cancel', {'order_id': order_id})
+            status = response.json()
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        if 'message' in status:
+            raise OrderCancelError(
+                order_id=order_id,
+                exchange=self.name,
+                error=status['message']
+            )
+
+    def tickers(self, assets):
+        """
+        Fetch ticket data for assets
+        https://docs.bitfinex.com/v2/reference#rest-public-tickers
+
+        :param assets:
+        :return:
+        """
+        symbols = self._get_v2_symbols(assets)
+        log.debug('fetching tickers {}'.format(symbols))
+
+        try:
+            response = requests.get(
+                '{url}/v2/tickers?symbols={symbols}'.format(
+                    url=self.url,
+                    symbols=','.join(symbols),
+                )
+            )
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        if 'error' in response.content:
+            raise ExchangeRequestError(
+                error='Unable to retrieve tickers: {}'.format(
+                    response.content)
+            )
+
+        tickers = response.json()
+
+        ticks = dict()
+        for index, ticker in enumerate(tickers):
+            if not len(ticker) == 11:
+                raise ExchangeRequestError(
+                    error='Invalid ticker in response: {}'.format(ticker)
+                )
+
+            ticks[assets[index]] = dict(
+                timestamp=pd.Timestamp.utcnow(),
+                bid=ticker[1],
+                ask=ticker[3],
+                last_price=ticker[7],
+                low=ticker[10],
+                high=ticker[9],
+                volume=ticker[8],
+            )
+
+        log.debug('got tickers {}'.format(ticks))
+        return ticks

catalyst/exchange/bitfinex/symbols.json

@@ -0,0 +1,114 @@
+{
+  "btcusd": {
+    "symbol": "btc_usd",
+    "start_date": "2010-01-01"
+  },
+  "bchusd": {
+    "symbol": "bch_usd",
+    "start_date": "2010-01-01"
+  },
+  "ltcusd": {
+    "symbol": "ltc_usd",
+    "start_date": "2010-01-01"
+  },
+  "ltcbtc": {
+    "symbol": "ltc_btc",
+    "start_date": "2010-01-01"
+  },
+  "ethusd": {
+    "symbol": "eth_usd",
+    "start_date": "2010-01-01"
+  },
+  "ethbtc": {
+    "symbol": "eth_btc",
+    "start_date": "2010-01-01"
+  },
+  "etcbtc": {
+    "symbol": "etc_btc",
+    "start_date": "2010-01-01"
+  },
+  "etcusd": {
+    "symbol": "etc_usd",
+    "start_date": "2010-01-01"
+  },
+  "rrtusd": {
+    "symbol": "rrt_usd",
+    "start_date": "2010-01-01"
+  },
+  "rrtbtc": {
+    "symbol": "rrt_btc",
+    "start_date": "2010-01-01"
+  },
+  "zecusd": {
+    "symbol": "zec_usd",
+    "start_date": "2010-01-01"
+  },
+  "zecbtc": {
+    "symbol": "zec_btc",
+    "start_date": "2010-01-01"
+  },
+  "xmrusd": {
+    "symbol": "xmr_usd",
+    "start_date": "2010-01-01"
+  },
+  "xmrbtc": {
+    "symbol": "xmr_btc",
+    "start_date": "2010-01-01"
+  },
+  "dshusd": {
+    "symbol": "dsh_usd",
+    "start_date": "2010-01-01"
+  },
+  "dshbtc": {
+    "symbol": "dsh_btc",
+    "start_date": "2010-01-01"
+  },
+  "bccbtc": {
+    "symbol": "bcc_btc",
+    "start_date": "2010-01-01"
+  },
+  "bcubtc": {
+    "symbol": "bcu_btc",
+    "start_date": "2010-01-01"
+  },
+  "bccusd": {
+    "symbol": "bcc_usd",
+    "start_date": "2010-01-01"
+  },
+  "bcuusd": {
+    "symbol": "bcu_usd",
+    "start_date": "2010-01-01"
+  },
+  "xrpusd": {
+    "symbol": "xrp_usd",
+    "start_date": "2010-01-01"
+  },
+  "xrpbtc": {
+    "symbol": "xrp_btc",
+    "start_date": "2010-01-01"
+  },
+  "iotusd": {
+    "symbol": "iot_usd",
+    "start_date": "2010-01-01"
+  },
+  "iotbtc": {
+    "symbol": "iot_btc",
+    "start_date": "2010-01-01"
+  },
+  "ioteth": {
+    "symbol": "iot_eth",
+    "start_date": "2010-01-01"
+  },
+  "eosusd": {
+    "symbol": "eos_usd",
+    "start_date": "2010-01-01"
+  },
+  "eosbtc": {
+    "symbol": "eos_btc",
+    "start_date": "2010-01-01"
+  },
+  "eoseth": {
+    "symbol": "eos_eth",
+    "start_date": "2010-01-01"
+  }
+}

catalyst/exchange/bittrex/bittrex.py

@@ -0,0 +1,307 @@
+import json
+
+import pandas as pd
+from catalyst.assets._assets import TradingPair
+from logbook import Logger
+from six.moves import urllib
+
+from catalyst.exchange.bittrex.bittrex_api import Bittrex_api
+from catalyst.exchange.exchange import Exchange
+from catalyst.exchange.exchange_errors import InvalidHistoryFrequencyError, \
+    ExchangeRequestError, InvalidOrderStyle, OrderNotFound, OrderCancelError, \
+    CreateOrderError
+from catalyst.finance.execution import LimitOrder, StopLimitOrder
+from catalyst.finance.order import Order, ORDER_STATUS
+
+log = Logger('Bittrex')
+
+URL2 = 'https://bittrex.com/Api/v2.0'
+
+
+class Bittrex(Exchange):
+    def __init__(self, key, secret, base_currency, portfolio=None):
+        self.api = Bittrex_api(key=key, secret=secret.encode('UTF-8'))
+        self.name = 'bittrex'
+        self.base_currency = base_currency
+        self._portfolio = portfolio
+
+        self.minute_writer = None
+        self.minute_reader = None
+
+        self.assets = dict()
+        self.load_assets()
+
+    @property
+    def account(self):
+        pass
+
+    @property
+    def time_skew(self):
+        # TODO: research the time skew conditions
+        return pd.Timedelta('0s')
+
+    def sanitize_curency_symbol(self, exchange_symbol):
+        """
+        Helper method used to build the universal pair.
+        Include any symbol mapping here if appropriate.
+
+        :param exchange_symbol:
+        :return universal_symbol:
+        """
+        return exchange_symbol.lower()
+
+    def fetch_symbol_map(self):
+        """
+        Since Bittrex gives us a complete dictionary of symbols,
+        we can build the symbol map ad-hoc as opposed to maintaining
+        a static file. We must be careful with mapping any unconventional
+        symbol name as appropriate.
+
+        :return symbol_map:
+        """
+        symbol_map = dict()
+
+        markets = self.api.getmarkets()
+        for market in markets:
+            exchange_symbol = market['MarketName']
+            symbol = '{market}_{base}'.format(
+                market=self.sanitize_curency_symbol(market['MarketCurrency']),
+                base=self.sanitize_curency_symbol(market['BaseCurrency'])
+            )
+            symbol_map[exchange_symbol] = dict(
+                symbol=symbol,
+                start_date=pd.to_datetime(market['Created'], utc=True)
+            )
+
+        return symbol_map
+
+    def get_balances(self):
+        try:
+            log.debug('retrieving wallet balances')
+            balances = self.api.getbalances()
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        std_balances = dict()
+        for balance in balances:
+            currency = balance['Currency'].lower()
+            std_balances[currency] = balance['Available']
+        return std_balances
+
+    def create_order(self, asset, amount, is_buy, style):
+        log.info('creating {} order'.format('buy' if is_buy else 'sell'))
+        exchange_symbol = self.get_symbol(asset)
+
+        if isinstance(style, LimitOrder) or isinstance(style, StopLimitOrder):
+            if isinstance(style, StopLimitOrder):
+                log.warn('{} will ignore the stop price'.format(self.name))
+
+            price = style.get_limit_price(is_buy)
+            try:
+                if is_buy:
+                    order_status = self.api.buylimit(exchange_symbol, amount,
+                                                     price)
+                else:
+                    order_status = self.api.selllimit(exchange_symbol,
+                                                      abs(amount), price)
+            except Exception as e:
+                raise ExchangeRequestError(error=e)
+
+            if 'uuid' in order_status:
+                order_id = order_status['uuid']
+                order = Order(
+                    dt=pd.Timestamp.utcnow(),
+                    asset=asset,
+                    amount=amount,
+                    stop=style.get_stop_price(is_buy),
+                    limit=style.get_limit_price(is_buy),
+                    id=order_id
+                )
+                return order
+            else:
+                raise CreateOrderError(exchange=self.name, error=order_status)
+        else:
+            raise InvalidOrderStyle(exchange=self.name,
+                                    style=style.__class__.__name__)
+
+    def get_open_orders(self, asset):
+        symbol = self.get_symbol(asset)
+        try:
+            open_orders = self.api.getopenorders(symbol)
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        orders = list()
+        for order_status in open_orders:
+            order = self._create_order(order_status)
+            orders.append(order)
+
+        return orders
+
+    def _create_order(self, order_status):
+        log.info(
+            'creating catalyst order from Bittrex {}'.format(order_status))
+        if order_status['CancelInitiated']:
+            status = ORDER_STATUS.CANCELLED
+        elif order_status['Closed'] is not None:
+            status = ORDER_STATUS.FILLED
+        else:
+            status = ORDER_STATUS.OPEN
+
+        date = pd.to_datetime(order_status['Opened'], utc=True)
+        amount = order_status['Quantity']
+        filled = amount - order_status['QuantityRemaining']
+        order = Order(
+            dt=date,
+            asset=self.assets[order_status['Exchange']],
+            amount=amount,
+            stop=None,  # Not yet supported by Bittrex
+            limit=order_status['Limit'],
+            filled=filled,
+            id=order_status['OrderUuid'],
+            commission=order_status['CommissionPaid']
+        )
+        order.status = status
+
+        executed_price = order_status['PricePerUnit']
+
+        return order, executed_price
+
+    def get_order(self, order_id):
+        log.info('retrieving order {}'.format(order_id))
+        try:
+            order_status = self.api.getorder(order_id)
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        if order_status is None:
+            raise OrderNotFound(order_id=order_id, exchange=self.name)
+
+        return self._create_order(order_status)
+
+    def cancel_order(self, order_param):
+        order_id = order_param.id \
+            if isinstance(order_param, Order) else order_param
+        log.info('cancelling order {}'.format(order_id))
+
+        try:
+            status = self.api.cancel(order_id)
+        except Exception as e:
+            raise ExchangeRequestError(error=e)
+
+        if 'message' in status:
+            raise OrderCancelError(
+                order_id=order_id,
+                exchange=self.name,
+                error=status['message']
+            )
+
+    def get_candles(self, data_frequency, assets, bar_count=None):
+        """
+        Supported Intervals
+        -------------------
+        day, oneMin, fiveMin, thirtyMin, hour
+
+        :param data_frequency:
+        :param assets:
+        :param bar_count:
+        :return:
+        """
+        log.info('retrieving candles')
+
+        if data_frequency == 'minute' or data_frequency == '1m':
+            frequency = 'oneMin'
+        elif data_frequency == '5m':
+            frequency = 'fiveMin'
+        elif data_frequency == '30m':
+            frequency = 'thirtyMin'
+        elif data_frequency == '1h':
+            frequency = 'hour'
+        elif data_frequency == 'daily' or data_frequency == '1D':
+            frequency = 'day'
+        else:
+            raise InvalidHistoryFrequencyError(
+                frequency=data_frequency
+            )
+
+        # Making sure that assets are iterable
+        asset_list = [assets] if isinstance(assets, TradingPair) else assets
+        ohlc_map = dict()
+        for asset in asset_list:
+            url = '{url}/pub/market/GetTicks?marketName={symbol}' \
+                  '&tickInterval={frequency}&_=1499127220008'.format(
+                url=URL2,
+                symbol=self.get_symbol(asset),
+                frequency=frequency
+            )
+
+            try:
+                data = json.loads(urllib.request.urlopen(url).read().decode())
+            except Exception as e:
+                raise ExchangeRequestError(error=e)
+
+            if data['message']:
+                raise ExchangeRequestError(
+                    error='Unable to fetch candles {}'.format(data['message'])
+                )
+
+            candles = data['result']
+
+            def ohlc_from_candle(candle):
+                ohlc = dict(
+                    open=candle['O'],
+                    high=candle['H'],
+                    low=candle['L'],
+                    close=candle['C'],
+                    volume=candle['V'],
+                    price=candle['C'],
+                    last_traded=pd.to_datetime(candle['T'], utc=True)
+                )
+                return ohlc
+
+            ordered_candles = list(reversed(candles))
+            if bar_count is None:
+                ohlc_map[asset] = ohlc_from_candle(ordered_candles[0])
+            else:
+                ohlc_bars = []
+                for candle in ordered_candles[:bar_count]:
+                    ohlc = ohlc_from_candle(candle)
+                    ohlc_bars.append(ohlc)
+
+                ohlc_map[asset] = ohlc_bars
+
+        return ohlc_map[assets] \
+            if isinstance(assets, TradingPair) else ohlc_map
+
+    def tickers(self, assets):
+        """
+        As of v1.1, Bittrex only allows one ticker at the time.
+        So we have to make multiple calls to fetch multiple assets.
+
+        :param assets:
+        :return:
+        """
+        log.info('retrieving tickers')
+
+        ticks = dict()
+        for asset in assets:
+            symbol = self.get_symbol(asset)
+            try:
+                ticker = self.api.getticker(symbol)
+            except Exception as e:
+                raise ExchangeRequestError(error=e)
+
+            # TODO: catch invalid ticker
+            ticks[asset] = dict(
+                timestamp=pd.Timestamp.utcnow(),
+                bid=ticker['Bid'],
+                ask=ticker['Ask'],
+                last_price=ticker['Last']
+            )
+
+        log.debug('got tickers {}'.format(ticks))
+        return ticks
+
+    def get_account(self):
+        log.info('retrieving account data')
+        pass

catalyst/exchange/bittrex/bittrex_api.py

@@ -0,0 +1,127 @@
+#!/usr/bin/env python
+import json
+import time
+import hmac
+import hashlib
+
+from six.moves import urllib
+
+# Workaround for backwards compatibility
+# https://stackoverflow.com/questions/3745771/urllib-request-in-python-2-7
+urlopen = urllib.request.urlopen
+
+
+class Bittrex_api(object):
+    def __init__(self, key, secret):
+        self.key = key
+        self.secret = secret
+        self.public = ['getmarkets', 'getcurrencies', 'getticker',
+                       'getmarketsummaries', 'getmarketsummary',
+                       'getorderbook', 'getmarkethistory']
+        self.market = ['buylimit', 'buymarket', 'selllimit', 'sellmarket',
+                       'cancel', 'getopenorders']
+        self.account = ['getbalances', 'getbalance', 'getdepositaddress',
+                        'withdraw', 'getorder', 'getorderhistory',
+                        'getwithdrawalhistory', 'getdeposithistory']
+
+    def query(self, method, values={}):
+        if method in self.public:
+            url = 'https://bittrex.com/api/v1.1/public/'
+        elif method in self.market:
+            url = 'https://bittrex.com/api/v1.1/market/'
+        elif method in self.account:
+            url = 'https://bittrex.com/api/v1.1/account/'
+        else:
+            return 'Something went wrong, sorry.'
+
+        url += method + '?' + urllib.parse.urlencode(values)
+
+        if method not in self.public:
+            url += '&apikey=' + self.key
+            url += '&nonce=' + str(int(time.time()))
+            signature = hmac.new(self.secret, url, hashlib.sha512).hexdigest()
+            headers = {'apisign': signature}
+        else:
+            headers = {}
+
+        req = urllib.request.Request(url, headers=headers)
+        response = json.loads(urlopen(req).read())
+
+        if response["result"]:
+            return response["result"]
+        else:
+            return response["message"]
+
+    def getmarkets(self):
+        return self.query('getmarkets')
+
+    def getcurrencies(self):
+        return self.query('getcurrencies')
+
+    def getticker(self, market):
+        return self.query('getticker', {'market': market})
+
+    def getmarketsummaries(self):
+        return self.query('getmarketsummaries')
+
+    def getmarketsummary(self, market):
+        return self.query('getmarketsummary', {'market': market})
+
+    def getorderbook(self, market, type, depth=20):
+        return self.query('getorderbook',
+                          {'market': market, 'type': type, 'depth': depth})
+
+    def getmarkethistory(self, market, count=20):
+        return self.query('getmarkethistory',
+                          {'market': market, 'count': count})
+
+    def buylimit(self, market, quantity, rate):
+        return self.query('buylimit', {'market': market, 'quantity': quantity,
+                                       'rate': rate})
+
+    def buymarket(self, market, quantity):
+        return self.query('buymarket',
+                          {'market': market, 'quantity': quantity})
+
+    def selllimit(self, market, quantity, rate):
+        return self.query('selllimit', {'market': market, 'quantity': quantity,
+                                        'rate': rate})
+
+    def sellmarket(self, market, quantity):
+        return self.query('sellmarket',
+                          {'market': market, 'quantity': quantity})
+
+    def cancel(self, uuid):
+        return self.query('cancel', {'uuid': uuid})
+
+    def getopenorders(self, market):
+        return self.query('getopenorders', {'market': market})
+
+    def getbalances(self):
+        return self.query('getbalances')
+
+    def getbalance(self, currency):
+        return self.query('getbalance', {'currency': currency})
+
+    def getdepositaddress(self, currency):
+        return self.query('getdepositaddress', {'currency': currency})
+
+    def withdraw(self, currency, quantity, address):
+        return self.query('withdraw',
+                          {'currency': currency, 'quantity': quantity,
+                           'address': address})
+
+    def getorder(self, uuid):
+        return self.query('getorder', {'uuid': uuid})
+
+    def getorderhistory(self, market, count):
+        return self.query('getorderhistory',
+                          {'market': market, 'count': count})
+
+    def getwithdrawalhistory(self, currency, count):
+        return self.query('getwithdrawalhistory',
+                          {'currency': currency, 'count': count})
+
+    def getdeposithistory(self, currency, count):
+        return self.query('getdeposithistory',
+                          {'currency': currency, 'count': count})

catalyst/exchange/data_portal_exchange.py

@@ -0,0 +1,121 @@
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from time import sleep
+
+from logbook import Logger
+
+from catalyst.data.data_portal import DataPortal
+from catalyst.exchange.exchange_errors import (
+    ExchangeRequestError,
+    ExchangeBarDataError
+)
+
+log = Logger('DataPortalExchange')
+
+
+class DataPortalExchange(DataPortal):
+    def __init__(self, exchange, *args, **kwargs):
+        self.exchange = exchange
+
+        # TODO: put somewhere accessible by each algo
+        self.retry_get_history_window = 5
+        self.retry_get_spot_value = 5
+        self.retry_delay = 5
+
+        super(DataPortalExchange, self).__init__(*args, **kwargs)
+
+    def _get_history_window(self,
+                            assets,
+                            end_dt,
+                            bar_count,
+                            frequency,
+                            field,
+                            data_frequency,
+                            ffill=True,
+                            attempt_index=0):
+        try:
+            return self.exchange.get_history_window(
+                assets,
+                end_dt,
+                bar_count,
+                frequency,
+                field,
+                data_frequency,
+                ffill)
+        except ExchangeRequestError as e:
+            log.warn(
+                'get history attempt {}: {}'.format(attempt_index, e)
+            )
+            if attempt_index < self.retry_get_history_window:
+                sleep(self.retry_delay)
+                return self._get_history_window(assets,
+                                                end_dt,
+                                                bar_count,
+                                                frequency,
+                                                field,
+                                                data_frequency,
+                                                ffill,
+                                                attempt_index + 1)
+            else:
+                raise ExchangeBarDataError(
+                    data_type='history',
+                    attempts=attempt_index,
+                    error=e
+                )
+
+    def get_history_window(self,
+                           assets,
+                           end_dt,
+                           bar_count,
+                           frequency,
+                           field,
+                           data_frequency,
+                           ffill=True):
+        return self._get_history_window(assets,
+                                        end_dt,
+                                        bar_count,
+                                        frequency,
+                                        field,
+                                        data_frequency,
+                                        ffill)
+
+    def _get_spot_value(self, assets, field, dt, data_frequency,
+                        attempt_index=0):
+        try:
+            return self.exchange.get_spot_value(assets, field, dt,
+                                                data_frequency)
+        except ExchangeRequestError as e:
+            log.warn(
+                'get spot value attempt {}: {}'.format(attempt_index, e)
+            )
+            if attempt_index < self.retry_get_spot_value:
+                sleep(self.retry_delay)
+                return self._get_spot_value(assets, field, dt, data_frequency,
+                                            attempt_index + 1)
+            else:
+                raise ExchangeBarDataError(
+                    data_type='spot',
+                    attempts=attempt_index,
+                    error=e
+                )
+
+    def get_spot_value(self, assets, field, dt, data_frequency):
+        return self._get_spot_value(assets, field, dt, data_frequency)
+
+    def get_adjusted_value(self, asset, field, dt,
+                           perspective_dt,
+                           data_frequency,
+                           spot_value=None):
+        # TODO: does this pertain to cryptocurrencies?
+        raise NotImplementedError("get_adjusted_value is not implemented yet!")

catalyst/exchange/exchange.py

@@ -0,0 +1,619 @@
+import abc
+import collections
+import random
+from abc import ABCMeta, abstractmethod, abstractproperty
+from time import sleep
+
+import numpy as np
+import pandas as pd
+from catalyst.assets._assets import TradingPair
+from logbook import Logger
+
+from catalyst.data.data_portal import BASE_FIELDS
+from catalyst.errors import (
+    SymbolNotFound,
+)
+from catalyst.exchange.exchange_errors import MismatchingBaseCurrencies, \
+    InvalidOrderStyle, BaseCurrencyNotFoundError
+from catalyst.exchange.exchange_execution import ExchangeStopLimitOrder, \
+    ExchangeLimitOrder, ExchangeStopOrder
+from catalyst.exchange.exchange_portfolio import ExchangePortfolio
+from catalyst.exchange.exchange_utils import get_exchange_symbols
+from catalyst.finance.order import ORDER_STATUS
+from catalyst.finance.transaction import Transaction
+
+log = Logger('Exchange')
+
+
+class Exchange:
+    __metaclass__ = ABCMeta
+
+    def __init__(self):
+        self.name = None
+        self.trading_pairs = None
+        self.assets = {}
+        self._portfolio = None
+        self.minute_writer = None
+        self.minute_reader = None
+        self.base_currency = None
+
+    @property
+    def positions(self):
+        return self.portfolio.positions
+
+    @property
+    def portfolio(self):
+        """
+        Return the Portfolio
+
+        :return:
+        """
+        if self._portfolio is None:
+            self._portfolio = ExchangePortfolio(
+                start_date=pd.Timestamp.utcnow()
+            )
+            self.synchronize_portfolio()
+
+        return self._portfolio
+
+    @abstractproperty
+    def account(self):
+        pass
+
+    @abstractproperty
+    def time_skew(self):
+        pass
+
+    def get_symbol(self, asset):
+        """
+        Get the exchange specific symbol of the given asset.
+
+        :param asset: Asset
+        :return: symbol: str
+        """
+        symbol = None
+
+        for key in self.assets:
+            if not symbol and self.assets[key].symbol == asset.symbol:
+                symbol = key
+
+        if not symbol:
+            raise ValueError('Currency %s not supported by exchange %s' %
+                             (asset['symbol'], self.name))
+
+        return symbol
+
+    def get_symbols(self, assets):
+        """
+        Get a list of symbols corresponding to each given asset.
+
+        :param assets: Asset[]
+        :return:
+        """
+        symbols = []
+
+        for asset in assets:
+            symbols.append(self.get_symbol(asset))
+
+        return symbols
+
+    def get_asset(self, symbol):
+        """
+        Find an Asset on the current exchange based on its Catalyst symbol
+        :param symbol: the [target]_[base] currency pair symbol
+        :return: Asset
+        """
+        asset = None
+
+        for key in self.assets:
+            if not asset and self.assets[key].symbol.lower() == symbol.lower():
+                asset = self.assets[key]
+
+        if not asset:
+            raise SymbolNotFound(symbol=symbol)
+
+        return asset
+
+    def fetch_symbol_map(self):
+        return get_exchange_symbols(self.name)
+
+    def load_assets(self):
+        """
+        Populate the 'assets' attribute with a dictionary of Assets.
+        The key of the resulting dictionary is the exchange specific
+        currency pair symbol. The universal symbol is contained in the
+        'symbol' attribute of each asset.
+
+
+        Notes
+        -----
+        The sid of each asset is calculated based on a numeric hash of the
+        universal symbol. This simple approach avoids maintaining a mapping
+        of sids.
+
+        This method can be overridden if an exchange offers equivalent data
+        via its api.
+        """
+
+        symbol_map = self.fetch_symbol_map()
+        for exchange_symbol in symbol_map:
+            asset = symbol_map[exchange_symbol]
+
+            if 'start_date' in asset:
+                start_date = pd.to_datetime(asset['start_date'], utc=True)
+            else:
+                start_date = None
+
+            if 'end_date' in asset:
+                end_date = pd.to_datetime(asset['end_date'], utc=True)
+            else:
+                end_date = None
+
+            if 'leverage' in asset:
+                leverage = asset['leverage']
+            else:
+                leverage = 1.0
+
+            if 'asset_name' in asset:
+                asset_name = asset['asset_name']
+            else:
+                asset_name = None
+
+            trading_pair = TradingPair(
+                symbol=asset['symbol'],
+                exchange=self.name,
+                start_date=start_date,
+                end_date=end_date,
+                leverage=leverage,
+                asset_name=asset_name
+            )
+
+            self.assets[exchange_symbol] = trading_pair
+
+    def check_open_orders(self):
+        """
+        Loop through the list of open orders in the Portfolio object.
+        For each executed order found, create a transaction and apply to the
+        Portfolio.
+
+        :return:
+        transactions: Transaction[]
+        """
+        transactions = list()
+        if self.portfolio.open_orders:
+            for order_id in list(self.portfolio.open_orders):
+                log.debug('found open order: {}'.format(order_id))
+
+                order, executed_price = self.get_order(order_id)
+                log.debug('got updated order {} {}'.format(
+                    order, executed_price))
+
+                if order.status == ORDER_STATUS.FILLED:
+                    transaction = Transaction(
+                        asset=order.asset,
+                        amount=order.amount,
+                        dt=pd.Timestamp.utcnow(),
+                        price=executed_price,
+                        order_id=order.id,
+                        commission=order.commission
+                    )
+                    transactions.append(transaction)
+
+                    self.portfolio.execute_order(order, transaction)
+
+                elif order.status == ORDER_STATUS.CANCELLED:
+                    self.portfolio.remove_order(order)
+
+                else:
+                    delta = pd.Timestamp.utcnow() - order.dt
+                    log.info(
+                        'order {order_id} still open after {delta}'.format(
+                            order_id=order_id,
+                            delta=delta
+                        )
+                    )
+        return transactions
+
+    def get_spot_value(self, assets, field, dt=None, data_frequency='minute'):
+        """
+        Public API method that returns a scalar value representing the value
+        of the desired asset's field at either the given dt.
+
+        Parameters
+        ----------
+        assets : Asset, ContinuousFuture, or iterable of same.
+            The asset or assets whose data is desired.
+        field : {'open', 'high', 'low', 'close', 'volume',
+                 'price', 'last_traded'}
+            The desired field of the asset.
+        dt : pd.Timestamp
+            The timestamp for the desired value.
+        data_frequency : str
+            The frequency of the data to query; i.e. whether the data is
+            'daily' or 'minute' bars
+
+        Returns
+        -------
+        value : float, int, or pd.Timestamp
+            The spot value of ``field`` for ``asset`` The return type is based
+            on the ``field`` requested. If the field is one of 'open', 'high',
+            'low', 'close', or 'price', the value will be a float. If the
+            ``field`` is 'volume' the value will be a int. If the ``field`` is
+            'last_traded' the value will be a Timestamp.
+
+        Bitfinex timeframes
+        -------------------
+        Available values: '1m', '5m', '15m', '30m', '1h', '3h', '6h', '12h',
+         '1D', '7D', '14D', '1M'
+        """
+        if field not in BASE_FIELDS:
+            raise KeyError('Invalid column: ' + str(field))
+
+        if isinstance(assets, collections.Iterable):
+            values = list()
+            for asset in assets:
+                value = self.get_single_spot_value(
+                    asset, field, data_frequency)
+                values.append(value)
+
+            return values
+        else:
+            return self.get_single_spot_value(
+                assets, field, data_frequency)
+
+    def get_single_spot_value(self, asset, field, data_frequency):
+        """
+        Similar to 'get_spot_value' but for a single asset
+
+        Note
+        ----
+        We're writing each minute bar to disk using zipline's machinery.
+        This is especially useful when running multiple algorithms
+        concurrently. By using local data when possible, we try to reaching
+        request limits on exchanges.
+
+        :param asset:
+        :param field:
+        :param data_frequency:
+        :return value: The spot value of the given asset / field
+        """
+        log.debug(
+            'fetching spot value {field} for symbol {symbol}'.format(
+                symbol=asset.symbol,
+                field=field
+            )
+        )
+
+        if field == 'price':
+            field = 'close'
+
+        # Don't use a timezone here
+        dt = pd.Timestamp.utcnow().floor('1 min')
+        value = None
+        if self.minute_reader is not None:
+            try:
+                # Slight delay to minimize the chances that multiple algos
+                # might try to hit the cache at the exact same time.
+                sleep_time = random.uniform(0.5, 0.8)
+                sleep(sleep_time)
+                # TODO: This does not always! Why is that? Open an issue with zipline.
+                # See: https://github.com/zipline-live/zipline/issues/26
+                value = self.minute_reader.get_value(
+                    sid=asset.sid,
+                    dt=dt,
+                    field=field
+                )
+            except Exception as e:
+                log.warn('minute data not found: {}'.format(e))
+
+        if value is None or np.isnan(value):
+            ohlc = self.get_candles(data_frequency, asset)
+            if field not in ohlc:
+                raise KeyError('Invalid column: %s' % field)
+
+            if self.minute_writer is not None:
+                df = pd.DataFrame(
+                    [ohlc],
+                    index=pd.DatetimeIndex([dt]),
+                    columns=['open', 'high', 'low', 'close', 'volume']
+                )
+
+                try:
+                    self.minute_writer.write_sid(
+                        sid=asset.sid,
+                        df=df
+                    )
+                    log.debug('wrote minute data: {}'.format(dt))
+                except Exception as e:
+                    log.warn(
+                        'unable to write minute data: {} {}'.format(dt, e))
+
+            value = ohlc[field]
+            log.debug('got spot value: {}'.format(value))
+        else:
+            log.debug('got spot value from cache: {}'.format(value))
+
+        return value
+
+    def get_history_window(self,
+                           assets,
+                           end_dt,
+                           bar_count,
+                           frequency,
+                           field,
+                           data_frequency,
+                           ffill=True):
+
+        """
+        Public API method that returns a dataframe containing the requested
+        history window.  Data is fully adjusted.
+
+        Parameters
+        ----------
+        assets : list of catalyst.data.Asset objects
+            The assets whose data is desired.
+
+        end_dt: not applicable to cryptocurrencies
+
+        bar_count: int
+            The number of bars desired.
+
+        frequency: string
+            "1d" or "1m"
+
+        field: string
+            The desired field of the asset.
+
+        data_frequency: string
+            The frequency of the data to query; i.e. whether the data is
+            'daily' or 'minute' bars.
+
+        # TODO: fill how?
+        ffill: boolean
+            Forward-fill missing values. Only has effect if field
+            is 'price'.
+
+        Returns
+        -------
+        A dataframe containing the requested data.
+        """
+
+        candles = self.get_candles(
+            data_frequency=frequency,
+            assets=assets,
+            bar_count=bar_count,
+        )
+
+        series = dict()
+        for asset in assets:
+            asset_candles = candles[asset]
+
+            values = map(lambda candle: candle[field], asset_candles)
+            dates = map(lambda candle: candle['last_traded'], asset_candles)
+
+            value_series = pd.Series(values, index=dates)
+            series[asset] = value_series
+
+        df = pd.concat(series)
+        return df
+
+    def synchronize_portfolio(self):
+        """
+        Update the portfolio cash and position balances based on the
+        latest ticker prices.
+
+        :return:
+        """
+        log.debug('synchronizing portfolio with exchange {}'.format(self.name))
+        balances = self.get_balances()
+
+        base_position_available = balances[self.base_currency] \
+            if self.base_currency in balances else None
+
+        if base_position_available is None:
+            raise BaseCurrencyNotFoundError(
+                base_currency=self.base_currency,
+                exchange=self.name
+            )
+
+        portfolio = self._portfolio
+        portfolio.cash = base_position_available
+        log.debug('found base currency balance: {}'.format(portfolio.cash))
+
+        if portfolio.starting_cash is None:
+            portfolio.starting_cash = portfolio.cash
+
+        if portfolio.positions:
+            assets = portfolio.positions.keys()
+            tickers = self.tickers(assets)
+
+            portfolio.positions_value = 0.0
+            for asset in tickers:
+                # TODO: convert if the position is not in the base currency
+                ticker = tickers[asset]
+                position = portfolio.positions[asset]
+                position.last_sale_price = ticker['last_price']
+                position.last_sale_date = ticker['timestamp']
+
+                portfolio.positions_value += \
+                    position.amount * position.last_sale_price
+                portfolio.portfolio_value = \
+                    portfolio.positions_value + portfolio.cash
+
+    @abstractmethod
+    def get_balances(self):
+        """
+        Retrieve wallet balances for the exchange
+        :return balances: A dict of currency => available balance
+        """
+        pass
+
+    @abstractmethod
+    def create_order(self, asset, amount, is_buy, style):
+        pass
+
+    def order(self, asset, amount, limit_price=None, stop_price=None,
+              style=None):
+        """Place an order.
+
+        Parameters
+        ----------
+        asset : Asset
+            The asset that this order is for.
+        amount : int
+            The amount of shares to order. If ``amount`` is positive, this is
+            the number of shares to buy or cover. If ``amount`` is negative,
+            this is the number of shares to sell or short.
+        limit_price : float, optional
+            The limit price for the order.
+        stop_price : float, optional
+            The stop price for the order.
+        style : ExecutionStyle, optional
+            The execution style for the order.
+
+        Returns
+        -------
+        order_id : str or None
+            The unique identifier for this order, or None if no order was
+            placed.
+
+        Notes
+        -----
+        The ``limit_price`` and ``stop_price`` arguments provide shorthands for
+        passing common execution styles. Passing ``limit_price=N`` is
+        equivalent to ``style=LimitOrder(N)``. Similarly, passing
+        ``stop_price=M`` is equivalent to ``style=StopOrder(M)``, and passing
+        ``limit_price=N`` and ``stop_price=M`` is equivalent to
+        ``style=StopLimitOrder(N, M)``. It is an error to pass both a ``style``
+        and ``limit_price`` or ``stop_price``.
+
+        See Also
+        --------
+        :class:`catalyst.finance.execution.ExecutionStyle`
+        :func:`catalyst.api.order_value`
+        :func:`catalyst.api.order_percent`
+        """
+        if amount == 0:
+            log.warn('skipping order amount of 0')
+            return None
+
+        if asset.base_currency != self.base_currency.lower():
+            raise MismatchingBaseCurrencies(
+                base_currency=asset.base_currency,
+                algo_currency=self.base_currency
+            )
+
+        is_buy = (amount > 0)
+
+        if limit_price is not None and stop_price is not None:
+            style = ExchangeStopLimitOrder(limit_price, stop_price,
+                                           exchange=self.name)
+        elif limit_price is not None:
+            style = ExchangeLimitOrder(limit_price, exchange=self.name)
+
+        elif stop_price is not None:
+            style = ExchangeStopOrder(stop_price, exchange=self.name)
+
+        elif style is not None:
+            raise InvalidOrderStyle(exchange=self.name,
+                                    style=style.__class__.__name__)
+        else:
+            raise ValueError('Incomplete order data.')
+
+        display_price = limit_price if limit_price is not None else stop_price
+        log.debug(
+            'issuing {side} order of {amount} {symbol} for {type}: {price}'.format(
+                side='buy' if is_buy else 'sell',
+                amount=amount,
+                symbol=asset.symbol,
+                type=style.__class__.__name__,
+                price='{}{}'.format(display_price, asset.base_currency)
+            )
+        )
+        order = self.create_order(asset, amount, is_buy, style)
+
+        self._portfolio.create_order(order)
+
+        return order.id
+
+    @abstractmethod
+    def get_open_orders(self, asset):
+        """Retrieve all of the current open orders.
+
+        Parameters
+        ----------
+        asset : Asset
+            If passed and not None, return only the open orders for the given
+            asset instead of all open orders.
+
+        Returns
+        -------
+        open_orders : dict[list[Order]] or list[Order]
+            If no asset is passed this will return a dict mapping Assets
+            to a list containing all the open orders for the asset.
+            If an asset is passed then this will return a list of the open
+            orders for this asset.
+        """
+        pass
+
+    @abstractmethod
+    def get_order(self, order_id):
+        """Lookup an order based on the order id returned from one of the
+        order functions.
+
+        Parameters
+        ----------
+        order_id : str
+            The unique identifier for the order.
+
+        Returns
+        -------
+        order : Order
+            The order object.
+        execution_price: float
+            The execution price per share of the order
+        """
+        pass
+
+    @abstractmethod
+    def cancel_order(self, order_param):
+        """Cancel an open order.
+
+        Parameters
+        ----------
+        order_param : str or Order
+            The order_id or order object to cancel.
+        """
+        pass
+
+    @abstractmethod
+    def get_candles(self, data_frequency, assets, bar_count=None):
+        """
+        Retrieve OHLCV candles for the given assets
+
+        :param data_frequency:
+        :param assets:
+        :param end_dt:
+        :param bar_count:
+        :param limit:
+        :return:
+        """
+        pass
+
+    @abc.abstractmethod
+    def tickers(self, assets):
+        """
+        Retrieve current tick data for the given assets
+
+        :param assets:
+        :return:
+        """
+        pass
+
+    @abc.abstractmethod
+    def get_account(self):
+        """
+        Retrieve the account parameters.
+        :return:
+        """
+        pass

catalyst/exchange/exchange_clock.py

@@ -0,0 +1,60 @@
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+from time import sleep
+
+import pandas as pd
+from catalyst.gens.sim_engine import (
+    BAR,
+    SESSION_START,
+    MINUTE_END,
+    SESSION_END
+)
+from logbook import Logger
+
+log = Logger('ExchangeClock')
+
+
+class ExchangeClock(object):
+    """Realtime clock for live trading.
+
+    This class is a drop-in replacement for
+    :class:`zipline.gens.sim_engine.MinuteSimulationClock`.
+
+    This is a stripped down version because crypto exchanges run around the clock.
+
+    The :param:`time_skew` parameter represents the time difference between
+    the Broker and the live trading machine's clock.
+    """
+
+    def __init__(self, sessions, time_skew=pd.Timedelta("0s")):
+
+        self.sessions = sessions
+        self.time_skew = time_skew
+        self._last_emit = None
+        self._before_trading_start_bar_yielded = True
+
+    def __iter__(self):
+        yield pd.Timestamp.utcnow(), SESSION_START
+
+        while True:
+            current_time = pd.Timestamp.utcnow()
+            current_minute = current_time.floor('1 min')
+
+            if self._last_emit is None or current_minute > self._last_emit:
+                log.debug('emitting minutely bar: {}'.format(current_minute))
+
+                self._last_emit = current_minute
+                yield current_minute, BAR
+            else:
+                sleep(1)

catalyst/exchange/exchange_errors.py

@@ -0,0 +1,113 @@
+from catalyst.errors import ZiplineError
+
+
+class ExchangeRequestError(ZiplineError):
+    msg = (
+        'Request failed: {error}'
+    ).strip()
+
+
+class ExchangeRequestErrorTooManyAttempts(ZiplineError):
+    msg = (
+        'Request failed: {error}, giving up after {attempts} attempts'
+    ).strip()
+
+
+class ExchangeBarDataError(ZiplineError):
+    msg = (
+        'Unable to retrieve bar data: {data_type}, ' +
+        'giving up after {attempts} attempts: {error}'
+    ).strip()
+
+
+class ExchangePortfolioDataError(ZiplineError):
+    msg = (
+        'Unable to retrieve portfolio data: {data_type}, ' +
+        'giving up after {attempts} attempts: {error}'
+    ).strip()
+
+
+class ExchangeTransactionError(ZiplineError):
+    msg = (
+        'Unable to execute transaction: {transaction_type}, ' +
+        'giving up after {attempts} attempts: {error}'
+    ).strip()
+
+
+class ExchangeAuthNotFound(ZiplineError):
+    msg = (
+        'Please create an auth.json file containing the api token and key for '
+        'exchange {exchange}. Place the file here: {filename}'
+    ).strip()
+
+
+class ExchangeSymbolsNotFound(ZiplineError):
+    msg = (
+        'Unable to download or find a local copy of symbols.json for exchange '
+        '{exchange}. The file should be here: {filename}'
+    ).strip()
+
+
+class AlgoPickleNotFound(ZiplineError):
+    msg = (
+        'Pickle not found for algo {algo} in path {filename}'
+    ).strip()
+
+
+class InvalidHistoryFrequencyError(ZiplineError):
+    msg = (
+        'History frequency {frequency} not supported by the exchange.'
+    ).strip()
+
+
+class InvalidSymbolError(ZiplineError):
+    msg = (
+        'Invalid trading pair symbol: {symbol}. '
+        'Catalyst symbols must follow this convention: '
+        '[Market Currency]_[Base Currency]. For example: eth_usd, btc_usd, '
+        'neo_eth, ubq_btc. Error details: {error}'
+    ).strip()
+
+
+class InvalidOrderStyle(ZiplineError):
+    msg = (
+        'Order style {style} not supported by exchange {exchange}.'
+    ).strip()
+
+
+class CreateOrderError(ZiplineError):
+    msg = (
+        'Unable to create order on exchange {exchange} {error}.'
+    ).strip()
+
+
+class OrderNotFound(ZiplineError):
+    msg = (
+        'Order {order_id} not found on exchange {exchange}.'
+    ).strip()
+
+
+class OrderCancelError(ZiplineError):
+    msg = (
+        'Unable to cancel order {order_id} on exchange {exchange} {error}.'
+    ).strip()
+
+
+class SidHashError(ZiplineError):
+    msg = (
+        'Unable to hash sid from symbol {symbol}.'
+    ).strip()
+
+
+class BaseCurrencyNotFoundError(ZiplineError):
+    msg = (
+        'Algorithm base currency {base_currency} not found in exchange '
+        '{exchange}.'
+    ).strip()
+
+
+class MismatchingBaseCurrencies(ZiplineError):
+    msg = (
+        'Unable to trade with base currency {base_currency} when the '
+        'algorithm uses {algo_currency}.'
+    ).strip()

catalyst/exchange/exchange_execution.py

@@ -0,0 +1,39 @@
+from catalyst.finance.execution import LimitOrder, StopOrder, StopLimitOrder
+
+
+class ExchangeLimitOrder(LimitOrder):
+    def get_limit_price(self, is_buy):
+        """
+        We may be trading Satoshis with 8 decimals, we cannot round numbers
+        :param is_buy:
+        :return:
+        """
+        return self.limit_price
+
+
+class ExchangeStopOrder(StopOrder):
+    def get_stop_price(self, is_buy):
+        """
+        We may be trading Satoshis with 8 decimals, we cannot round numbers
+        :param is_buy:
+        :return:
+        """
+        return self.stop_price
+
+
+class ExchangeStopLimitOrder(StopLimitOrder):
+    def get_limit_price(self, is_buy):
+        """
+        We may be trading Satoshis with 8 decimals, we cannot round numbers
+        :param is_buy:
+        :return:
+        """
+        return self.limit_price
+
+    def get_stop_price(self, is_buy):
+        """
+        We may be trading Satoshis with 8 decimals, we cannot round numbers
+        :param is_buy:
+        :return:
+        """
+        return self.stop_price

catalyst/exchange/exchange_portfolio.py

@@ -0,0 +1,87 @@
+import numpy as np
+from logbook import Logger
+
+from catalyst.protocol import Portfolio, Positions, Position
+
+log = Logger('ExchangePortfolio')
+
+
+class ExchangePortfolio(Portfolio):
+    """
+    Since the goal is to support multiple exchanges, it makes sense to
+    include additional stats in the portfolio object.
+
+    Instead of relying on the performance tracker, each exchange portfolio
+    tracks its own holding. This offers a separation between tracking an
+    exchange and the statistics of the algorithm.
+    """
+
+    def __init__(self, start_date, starting_cash=None):
+        self.capital_used = 0.0
+        self.starting_cash = starting_cash
+        self.portfolio_value = starting_cash
+        self.pnl = 0.0
+        self.returns = 0.0
+        self.cash = starting_cash
+        self.positions = Positions()
+        self.start_date = start_date
+        self.positions_value = 0.0
+        self.open_orders = dict()
+
+    def calculate_pnl(self):
+        log.debug('calculating pnl')
+
+    def create_order(self, order):
+        log.debug('creating order {}'.format(order.id))
+        self.open_orders[order.id] = order
+
+        order_position = self.positions[order.asset] \
+            if order.asset in self.positions else None
+
+        if order_position is None:
+            order_position = Position(order.asset)
+            self.positions[order.asset] = order_position
+
+        order_position.amount += order.amount
+        log.debug('open order added to portfolio')
+
+    def execute_order(self, order, transaction):
+        log.debug('executing order {}'.format(order.id))
+        del self.open_orders[order.id]
+
+        order_position = self.positions[order.asset] \
+            if order.asset in self.positions else None
+
+        if order_position is None:
+            raise ValueError(
+                'Trying to execute order for a position not held: %s' % order.id
+            )
+
+        self.capital_used += order.amount * transaction.price
+
+        if order.amount > 0:
+            if order_position.cost_basis > 0:
+                order_position.cost_basis = np.average(
+                    [order_position.cost_basis, transaction.price],
+                    weights=[order_position.amount, order.amount]
+                )
+            else:
+                order_position.cost_basis = transaction.price
+
+        log.debug('updated portfolio with executed order')
+
+    def remove_order(self, order):
+        log.info('removing cancelled order {}'.format(order.id))
+        del self.open_orders[order.id]
+
+        order_position = self.positions[order.asset] \
+            if order.asset in self.positions else None
+
+        if order_position is None:
+            raise ValueError(
+                'Trying to remove order for a position not held: %s' % order.id
+            )
+
+        order_position.amount -= order.amount
+
+        log.debug('removed order from portfolio')

catalyst/exchange/exchange_utils.py

@@ -0,0 +1,134 @@
+import json
+import os
+import pickle
+import urllib
+from datetime import date, datetime
+
+from catalyst.exchange.exchange_errors import ExchangeAuthNotFound, \
+    ExchangeSymbolsNotFound
+from catalyst.utils.paths import data_root, ensure_directory
+
+# TODO: move to aws
+SYMBOLS_URL = 'https://raw.githubusercontent.com/enigmampc/catalyst/' \
+              'master/catalyst/exchange/{exchange}/symbols.json'
+
+
+def get_exchange_folder(exchange_name, environ=None):
+    if not environ:
+        environ = os.environ
+
+    root = data_root(environ)
+    exchange_folder = os.path.join(root, 'exchanges', exchange_name)
+    ensure_directory(exchange_folder)
+
+    return exchange_folder
+
+
+def download_exchange_symbols(exchange_name, environ=None):
+    exchange_folder = get_exchange_folder(exchange_name, environ)
+    filename = os.path.join(exchange_folder, 'symbols.json')
+
+    url = SYMBOLS_URL.format(exchange=exchange_name)
+    response = urllib.urlretrieve(url=url, filename=filename)
+    return response
+
+
+def get_exchange_symbols(exchange_name, environ=None):
+    exchange_folder = get_exchange_folder(exchange_name, environ)
+    filename = os.path.join(exchange_folder, 'symbols.json')
+
+    if not os.path.isfile(filename):
+        download_exchange_symbols(exchange_name, environ)
+
+    if os.path.isfile(filename):
+        with open(filename) as data_file:
+            data = json.load(data_file)
+            return data
+    else:
+        raise ExchangeSymbolsNotFound(
+            exchange=exchange_name,
+            filename=filename
+        )
+
+
+def get_exchange_auth(exchange_name, environ=None):
+    exchange_folder = get_exchange_folder(exchange_name, environ)
+    filename = os.path.join(exchange_folder, 'auth.json')
+
+    if os.path.isfile(filename):
+        with open(filename) as data_file:
+            data = json.load(data_file)
+            return data
+    else:
+        raise ExchangeAuthNotFound(
+            exchange=exchange_name,
+            filename=filename
+        )
+
+
+def get_algo_folder(algo_name, environ=None):
+    if not environ:
+        environ = os.environ
+
+    root = data_root(environ)
+    algo_folder = os.path.join(root, 'live_algos', algo_name)
+    ensure_directory(algo_folder)
+
+    return algo_folder
+
+
+def get_algo_object(algo_name, key, environ=None, rel_path=None):
+    folder = get_algo_folder(algo_name, environ)
+
+    if rel_path is not None:
+        folder = os.path.join(folder, rel_path)
+
+    filename = os.path.join(folder, key + '.p')
+
+    if os.path.isfile(filename):
+        try:
+            with open(filename, 'rb') as handle:
+                return pickle.load(handle)
+        except Exception as e:
+            return None
+    else:
+        return None
+
+
+def save_algo_object(algo_name, key, obj, environ=None, rel_path=None):
+    folder = get_algo_folder(algo_name, environ)
+
+    if rel_path is not None:
+        folder = os.path.join(folder, rel_path)
+        ensure_directory(folder)
+
+    filename = os.path.join(folder, key + '.p')
+
+    with open(filename, 'wb') as handle:
+        pickle.dump(obj, handle, protocol=pickle.HIGHEST_PROTOCOL)
+
+
+def append_algo_object(algo_name, key, obj, environ=None):
+    algo_folder = get_algo_folder(algo_name, environ)
+    filename = os.path.join(algo_folder, key + '.p')
+
+    mode = 'a+b' if os.path.isfile(filename) else 'wb'
+    with open(filename, mode) as handle:
+        pickle.dump(obj, handle, protocol=pickle.HIGHEST_PROTOCOL)
+
+
+def get_exchange_minute_writer_root(exchange_name, environ=None):
+    exchange_folder = get_exchange_folder(exchange_name, environ)
+
+    minute_data_folder = os.path.join(exchange_folder, 'minute_data')
+    ensure_directory(minute_data_folder)
+
+    return minute_data_folder
+
+
+def perf_serial(obj):
+    """JSON serializer for objects not serializable by default json code"""
+
+    if isinstance(obj, (datetime, date)):
+        return obj.isoformat()
+    raise TypeError("Type %s not serializable" % type(obj))

catalyst/exchange/stats_utils.py

@@ -0,0 +1,47 @@
+import pandas as pd
+
+
+def get_pretty_stats(stats_df, num_rows=10):
+    """
+    Format and print the last few rows of a statistics DataFrame.
+    See the pyfolio project for the data structure.
+
+    :param stats_df:
+    :param num_rows:
+    :return:
+    """
+    stats_df.set_index('period_close', drop=True, inplace=True)
+    stats_df.dropna(axis=1, how='all', inplace=True)
+
+    pd.set_option('display.expand_frame_repr', False)
+    pd.set_option('precision', 3)
+    pd.set_option('display.width', 1000)
+    pd.set_option('display.max_colwidth', 1000)
+
+    columns = ['starting_cash', 'ending_cash', 'portfolio_value',
+               'pnl', 'long_exposure', 'short_exposure', 'orders',
+               'transactions', 'positions']
+
+    def format_positions(positions):
+        parts = []
+        for position in positions:
+            msg = '{amount:.2f}{market} cost basis {cost_basis:.4f}{base}'.format(
+                amount=position['amount'],
+                market=position['sid'].market_currency,
+                cost_basis=position['cost_basis'],
+                base=position['sid'].base_currency
+            )
+            parts.append(msg)
+        return ', '.join(parts)
+
+    formatters = {
+        'orders': lambda orders: len(orders),
+        'transactions': lambda transactions: len(transactions),
+        'returns': lambda returns: "{0:.4f}".format(returns),
+        'positions': format_positions
+    }
+
+    return stats_df.tail(num_rows).to_string(
+        columns=columns,
+        formatters=formatters
+    )

catalyst/finance/performance/tracker.py

@@ -111,6 +111,21 @@ class PerformanceTracker(object):
                     self.treasury_curves,
                     self.trading_calendar
                 )
+        elif self.emission_rate == '5-minute':
+            self.all_benchmark_returns = pd.Series(
+                index=pd.date_range(
+                    self.sim_params.first_open,
+                    self.sim_params.last_close,
+                    freq='5min'
+                ),
+            )
+            self.cumulative_risk_metrics = \
+                risk.RiskMetricsCumulative(
+                    self.sim_params,
+                    self.treasury_curves,
+                    self.trading_calendar,
+                    create_first_day_stats=True,
+                )
         elif self.emission_rate == 'minute':
             self.all_benchmark_returns = pd.Series(index=pd.date_range(
                 self.sim_params.first_open, self.sim_params.last_close,

catalyst/finance/risk/risk.py

@@ -158,7 +158,7 @@ def choose_treasury(select_treasury, treasury_curves, start_session,
                 )
                 break
 
-        if search_day:
+        if search_day and trading_calendar.name != 'OPEN':          # Supress warning for 'OPEN' calendar
             if (search_dist is None or search_dist > 1) and \
                     search_days[0] <= end_session <= search_days[-1]:
                 message = "No rate within 1 trading day of end date = \

catalyst/gens/sim_engine.pyx

@@ -20,7 +20,9 @@ cimport cython
 from cpython cimport bool
 
 cdef np.int64_t _nanos_in_minute = 60000000000
+cdef np.int64_t _nanos_in_five_minutes = 5 * _nanos_in_minute
 NANOS_IN_MINUTE = _nanos_in_minute
+NANOS_IN_FIVE_MINUTES = _nanos_in_five_minutes
 
 cpdef enum:
     BAR = 0
@@ -115,3 +117,24 @@ cdef class MinuteSimulationClock:
             yield minute, BAR
             if minute_emission:
                 yield minute, MINUTE_END
+
+cdef class FiveMinuteSimulationClock(MinuteSimulationClock):
+    @cython.boundscheck(False)
+    @cython.wraparound(False)
+    cdef dict calc_minutes_by_session(self):
+        cdef dict five_minutes_by_session
+        cdef int session_idx
+        cdef np.int64_t session_nano
+        cdef np.ndarray[np.int64_t, ndim=1] five_minutes_nanos
+
+        five_minutes_by_session = {}
+        for session_idx, session_nano in enumerate(self.sessions_nanos):
+            five_minutes_nanos = np.arange(
+                self.market_opens_nanos[session_idx],
+                self.market_closes_nanos[session_idx],
+                _nanos_in_five_minutes
+            )
+            five_minutes_by_session[session_nano] = pd.to_datetime(
+                five_minutes_nanos, utc=True, box=True
+            )
+        return five_minutes_by_session

catalyst/gens/tradesimulation.py

@@ -34,6 +34,7 @@ class AlgorithmSimulator(object):
 
     EMISSION_TO_PERF_KEY_MAP = {
         'minute': 'minute_perf',
+        '5-minute': '5_minute_perf',
         'daily': 'daily_perf'
     }
 
@@ -201,7 +202,7 @@ class AlgorithmSimulator(object):
             stack.enter_context(self.processor)
             stack.enter_context(ZiplineAPI(self.algo))
 
-            if algo.data_frequency == 'minute':
+            if algo.data_frequency in set(('minute', '5-minute')):
                 def execute_order_cancellation_policy():
                     algo.blotter.execute_cancel_policy(SESSION_END)
 

catalyst/pipeline/loaders/crypto_pricing_loader.py

@@ -33,13 +33,30 @@ class CryptoPricingLoader(PipelineLoader):
     Delegates loading of baselines and adjustments.
     """
 
-    def __init__(self, raw_price_loader, dataset):
-        self.raw_price_loader = raw_price_loader
-        self._columns = dataset.columns
+    def __init__(self, bundle, data_frequency, dataset):
 
         cal = get_calendar('OPEN')
 
-        self._all_sessions = cal.all_sessions
+        if data_frequency == 'daily':
+            reader = bundle.daily_bar_reader
+            all_sessions = cal.all_sessions
+
+        elif data_frequency == '5-minute':
+            reader = bundle.five_minute_bar_reader
+            all_sessions = cal.all_five_minutes
+
+        elif data_frequency == 'minute':
+            reader = bundle.minute_bar_reader
+            all_sessions = cal.all_minutes
+
+        else:
+            raise ValueError(
+                'Invalid data frequency: {}'.format(data_frequency)
+            )
+
+        self.raw_price_loader = reader
+        self._columns = dataset.columns
+        self._all_sessions = all_sessions
 
     @classmethod
     def from_files(cls, pricing_path):
@@ -89,6 +106,7 @@ class CryptoPricingLoader(PipelineLoader):
 
 
 def _shift_dates(dates, start_date, end_date, shift):
+
     try:
         start = dates.get_loc(start_date)
     except KeyError:

catalyst/pipeline/loaders/equity_pricing_loader.py

@@ -36,15 +36,34 @@ class USEquityPricingLoader(PipelineLoader):
     Delegates loading of baselines and adjustments.
     """
 
-    def __init__(self, raw_price_loader, adjustments_loader, dataset):
-        self.raw_price_loader = raw_price_loader
-        self.adjustments_loader = adjustments_loader
+    def __init__(self, bundle, data_frequency, dataset):
+
+        if data_frequency == 'daily':
+            reader = bundle.daily_bar_reader
+        elif data_frequency == '5-minute':
+            reader = bundle.five_minute_bar_reader
+        elif daily_bar_reader == 'minute':
+            reader = bundle.minute_bar_reader
+        else:
+            raise ValueError(
+                'Invalid data frequency: {}'.format(data_frequency)
+            )
+
+        cal = reader.trading_calendar or get_calendar('NYSE')
+
+        if data_frequency == 'daily':
+            all_sessions = cal.all_sessions
+        elif data_frequency == '5-minute':
+            reader = bundle.five_minute_bar_reader
+            all_sessions = cal.all_five_minutes
+        elif daily_bar_reader == 'minute':
+            reader = bundle.minute_bar_reader
+            all_sessions = cal.all_minutes
+
+        self.raw_price_loader = reader
+        self.adjustments_loader = bundle.adjustments_loader
         self._columns = dataset.columns
-
-        cal = self.raw_price_loader.trading_calendar or \
-            get_calendar("NYSE")
-
-        self._all_sessions = cal.all_sessions
+        self._all_sessions = all_sessions
 
     @classmethod
     def from_files(cls, pricing_path, adjustments_path):

catalyst/sources/benchmark_source.py

@@ -65,6 +65,19 @@ class BenchmarkSource(object):
                 )
 
                 self._precalculated_series = minute_series
+            elif self.emission_rate == '5-minute':
+                five_minutes = \
+                    trading_calendar.five_minutes_for_sessions_in_range(
+                        sessions[0],
+                        sessions[-1],
+                    )
+
+                five_minute_series = daily_series.reindex(
+                    index=five_minutes,
+                    method='ffill',
+                )
+                
+                self._precalculated_series = five_minute_series
             else:
                 self._precalculated_series = daily_series
         else:
@@ -155,6 +168,21 @@ class BenchmarkSource(object):
                 ffill=True
             )[asset]
 
+            return benchmark_series.pct_change()[1:]
+        elif self.emission_rate == '5-minute':
+            five_minutes = trading_calendar.five_minutes_for_sessions_in_range(
+                self.sessions[0], self.sessions[-1]
+            )
+            benchmark_series = data_portal.get_history_window(
+                [asset],
+                five_minutes[-1],
+                bar_count=len(five_minutes) + 1,
+                frequency='5m',
+                field='price',
+                data_frequency=self.emission_rate,
+                ffill=True,
+            )[asset]
+
             return benchmark_series.pct_change()[1:]
         else:
             start_date = asset.start_date

catalyst/utils/calendars/calendar_utils.py

@@ -25,7 +25,7 @@ _default_calendar_factories = {
     'us_futures': QuantopianUSFuturesCalendar,
 }
 _default_calendar_aliases = {
-    'CATX': 'OPEN',
+    'POLO': 'OPEN',
     'NASDAQ': 'NYSE',
     'BATS': 'NYSE',
     'CBOT': 'CME',

catalyst/utils/calendars/exchange_calendar_open.py

@@ -1,6 +1,7 @@
 from datetime import time
 from pytz import timezone
 
+from pandas import Timestamp
 from pandas.tseries.offsets import DateOffset
 
 from catalyst.utils.memoize import lazyval
@@ -28,3 +29,6 @@ class OpenExchangeCalendar(TradingCalendar):
     @lazyval
     def day(self):
         return DateOffset(days=1)
+
+    def __init__(self, *args, **kwargs):
+        super(OpenExchangeCalendar, self).__init__(start=Timestamp('2015-03-01', tz='UTC'), **kwargs)

catalyst/utils/calendars/trading_calendar.py

@@ -118,6 +118,9 @@ class TradingCalendar(with_metaclass(ABCMeta)):
         self._trading_minutes_nanos = self.all_minutes.values.\
             astype(np.int64)
         
+        self._trading_five_minutes_nanos = self.all_five_minutes.values.\
+            astype(np.int64)
+
         self.first_trading_session = _all_days[0]
         self.last_trading_session = _all_days[-1]
 
@@ -179,6 +182,18 @@ class TradingCalendar(with_metaclass(ABCMeta)):
         """
         return int(self._minutes_per_session[start_session:end_session].sum())
 
+    @lazyval
+    def _five_minutes_per_session(self):
+        diff = self.schedule.market_close - self.schedule.market_open
+        diff = diff.astype('timedelta64[m]')
+        return (diff + 1) // 5
+
+    def five_minutes_count_for_sessions_in_range(self,
+                                                 start_session,
+                                                 end_session):
+        five_mins = self._five_minutes_per_session[start_session:end_session]
+        return int(five_mins.sum())
+
     @property
     def regular_holidays(self):
         """
@@ -371,6 +386,10 @@ class TradingCalendar(with_metaclass(ABCMeta)):
         idx = next_divider_idx(self._trading_minutes_nanos, dt.value)
         return self.all_minutes[idx]
 
+    def next_five_minute(self, dt):
+        idx = next_divider_idx(self._trading_five_minutes_nanos, dt.values)
+        return self.all_five_mintutes[idx]
+
     def previous_minute(self, dt):
         """
         Given a dt, return the previous exchange minute.
@@ -465,6 +484,12 @@ class TradingCalendar(with_metaclass(ABCMeta)):
             end_minute=self.schedule.at[session_label, 'market_close'],
         )
 
+    def five_minutes_for_session(self, session_label):
+        return self.five_minutes_in_range(
+            start_five_minute=self.schedule.at[session_label, 'market_open'],
+            end_five_minute=self.schedule.at[session_label, 'market_close'],
+        )
+
     def minutes_window(self, start_dt, count):
         start_dt_nanos = start_dt.value
         all_minutes_nanos = self._trading_minutes_nanos
@@ -566,6 +591,20 @@ class TradingCalendar(with_metaclass(ABCMeta)):
 
         return abs(end_idx - start_idx)
 
+    def five_minutes_in_range(self, start_five_minute, end_five_minute):
+        start_idx = searchsorted(self._trading_five_minutes_nanos,
+                                 start_five_minute.value)
+
+        end_idx = searchsorted(self._trading_five_minutes_nanos,
+                               end_five_minute.value)
+
+        if end_five_minute.value == self._trading_five_minutes_nanos[end_idx]:
+            # if the end minute is a market minute, increase by 1
+            end_idx += 1
+
+        return self.all_five_minutes[start_idx:end_idx]
+        
+
     def minutes_in_range(self, start_minute, end_minute):
         """
         Given start and end minutes, return all the calendar minutes
@@ -623,6 +662,15 @@ class TradingCalendar(with_metaclass(ABCMeta)):
 
         return self.minutes_in_range(first_minute, last_minute)
 
+    def five_minutes_for_sessions_in_range(self,
+                                           start_session_label,
+                                           end_session_label):
+
+        first_minute, _ = self.open_and_close_for_session(start_session_label)
+        _, last_minute = self.open_and_close_for_session(end_session_label)
+
+        return self.five_minutes_in_range(first_minute, last_minute)
+
     def open_and_close_for_session(self, session_label):
         """
         Returns a tuple of timestamps of the open and close of the session
@@ -690,8 +738,7 @@ class TradingCalendar(with_metaclass(ABCMeta)):
     def execution_time_from_close(self, close_dates):
         return close_dates
 
-    @lazyval
-    def all_minutes(self):
+    def _all_minutes_with_interval(self, interval):
         """
         Returns a DatetimeIndex representing all the minutes in this calendar.
         """
@@ -703,8 +750,10 @@ class TradingCalendar(with_metaclass(ABCMeta)):
 
         deltas = closes_in_ns - opens_in_ns
 
+        nanos_in_interval = interval * NANOS_IN_MINUTE
+
         # + 1 because we want 390 days per standard day, not 389
-        daily_sizes = (deltas / NANOS_IN_MINUTE) + 1
+        daily_sizes = (deltas / nanos_in_interval) + 1
         num_minutes = np.sum(daily_sizes).astype(np.int64)
 
         # One allocation for the entire thing. This assumes that each day
@@ -721,13 +770,27 @@ class TradingCalendar(with_metaclass(ABCMeta)):
                 np.arange(
                     opens_in_ns[day_idx],
                     closes_in_ns[day_idx] + NANOS_IN_MINUTE,
-                    NANOS_IN_MINUTE
+                    nanos_in_interval
                 )
 
             idx += size_int
 
         return DatetimeIndex(all_minutes).tz_localize("UTC")
 
+    @lazyval
+    def all_five_minutes(self):
+        """
+        Returns a DatetimeIndex representing all the five minutes in this calendar.
+        """
+        return self._all_minutes_with_interval(5) 
+
+    @lazyval
+    def all_minutes(self):
+        """
+        Returns a DatetimeIndex representing all the minutes in this calendar.
+        """
+        return self._all_minutes_with_interval(1)
+
     @preprocess(dt=coerce(pd.Timestamp, attrgetter('value')))
     def minute_to_session_label(self, dt, direction="next"):
         """

catalyst/utils/cli.py

@@ -1,10 +1,34 @@
+from itertools import count
+
 import click
 import pandas as pd
 
 from .context_tricks import CallbackManager
 
+DEFAULT_BAR_TEMPLATE = '    [%(bar)s]  %(label)s:  %(info)s'
+DEFAULT_EMPTY_CHAR = ' '
+DEFAULT_FILL_CHAR = '='
 
-def maybe_show_progress(it, show_progress, **kwargs):
+def item_show_count(total=None):
+    def maybe_show_total(index):
+        if total is not None:
+            return '{0}/{1}'.format(index, total)
+        return str(index)
+
+    def item_show_func(item, _it=iter(count())):
+        if item is not None:
+            starting = False
+            return maybe_show_total(next(_it))
+        return 'DONE'
+
+    return item_show_func
+
+def maybe_show_progress(it,
+                        show_progress,
+                        empty_char=DEFAULT_EMPTY_CHAR,
+                        fill_char=DEFAULT_FILL_CHAR,
+                        bar_template=DEFAULT_BAR_TEMPLATE,
+                        **kwargs):
     """Optionally show a progress bar for the given iterator.
 
     Parameters
@@ -30,6 +54,9 @@ def maybe_show_progress(it, show_progress, **kwargs):
                 ...
     """
     if show_progress:
+        kwargs['bar_template'] = bar_template
+        kwargs['empty_char'] = empty_char
+        kwargs['fill_char'] = fill_char
         return click.progressbar(it, **kwargs)
 
     # context manager that just return `it` when we enter it

catalyst/utils/events.py

@@ -602,6 +602,7 @@ class date_rules(object):
 class time_rules(object):
     market_open = AfterOpen
     market_close = BeforeClose
+    every_5_minutes = Always
     every_minute = Always
 
 

catalyst/utils/run_algo.py

@@ -3,12 +3,20 @@ import re
 from runpy import run_path
 import sys
 import warnings
+from time import sleep
+from datetime import timedelta
+
+import pandas as pd
 
 import click
+
+from catalyst.exchange.bittrex.bittrex import Bittrex
+
 try:
     from pygments import highlight
     from pygments.lexers import PythonLexer
     from pygments.formatters import TerminalFormatter
+
     PYGMENTS = True
 except:
     PYGMENTS = False
@@ -29,6 +37,21 @@ from catalyst.utils.calendars import get_calendar
 from catalyst.utils.factory import create_simulation_parameters
 import catalyst.utils.paths as pth
 
+from catalyst.exchange.algorithm_exchange import ExchangeTradingAlgorithm
+from catalyst.exchange.data_portal_exchange import DataPortalExchange
+from catalyst.exchange.bitfinex.bitfinex import Bitfinex
+from catalyst.exchange.asset_finder_exchange import AssetFinderExchange
+from catalyst.exchange.exchange_portfolio import ExchangePortfolio
+from catalyst.exchange.exchange_errors import (
+    ExchangeRequestError,
+    ExchangeRequestErrorTooManyAttempts,
+    BaseCurrencyNotFoundError)
+from catalyst.exchange.exchange_utils import get_exchange_auth, \
+    get_algo_object
+from logbook import Logger
+
+log = Logger('run_algo')
+
 
 class _RunAlgoError(click.ClickException, ValueError):
     """Signal an error that should have a different message if invoked from
@@ -68,7 +91,11 @@ def _run(handle_data,
          output,
          print_algo,
          local_namespace,
-         environ):
+         environ,
+         live,
+         exchange,
+         algo_namespace,
+         base_currency):
     """Run a backtest for the given algorithm.
 
     This is shared between the cli and :func:`catalyst.run_algo`.
@@ -117,7 +144,110 @@ def _run(handle_data,
         else:
             click.echo(algotext)
 
-    if bundle is not None:
+    mode = 'live' if live else 'backtest'
+    log.info('running algo in {mode} mode'.format(mode=mode))
+
+    if live and exchange is not None:
+        exchange_name = exchange
+        start = pd.Timestamp.utcnow()
+        end = start + timedelta(minutes=1439)
+
+        portfolio = get_algo_object(
+            algo_name=algo_namespace,
+            key='portfolio_{}'.format(exchange_name),
+            environ=environ
+        )
+        if portfolio is None:
+            portfolio = ExchangePortfolio(
+                start_date=pd.Timestamp.utcnow()
+            )
+
+        exchange_auth = get_exchange_auth(exchange_name)
+        if exchange_name == 'bitfinex':
+            exchange = Bitfinex(
+                key=exchange_auth['key'],
+                secret=exchange_auth['secret'],
+                base_currency=base_currency,
+                portfolio=portfolio
+            )
+        elif exchange_name == 'bittrex':
+            exchange = Bittrex(
+                key=exchange_auth['key'],
+                secret=exchange_auth['secret'],
+                base_currency=base_currency,
+                portfolio=portfolio
+            )
+        else:
+            raise NotImplementedError(
+                'exchange not supported: %s' % exchange_name)
+
+    open_calendar = get_calendar('OPEN')
+    sim_params = create_simulation_parameters(
+        start=start,
+        end=end,
+        capital_base=capital_base,
+        data_frequency=data_frequency,
+        emission_rate=data_frequency,
+    )
+
+    if live and exchange is not None:
+        env = TradingEnvironment(
+            environ=environ,
+            exchange_tz='UTC',
+            asset_db_path=None
+        )
+        env.asset_finder = AssetFinderExchange(exchange)
+
+        data = DataPortalExchange(
+            exchange=exchange,
+            asset_finder=env.asset_finder,
+            trading_calendar=open_calendar,
+            first_trading_day=pd.to_datetime('today', utc=True)
+        )
+        choose_loader = None
+
+        def fetch_capital_base(attempt_index=0):
+            """
+            Fetch the base currency amount required to bootstrap
+            the algorithm against the exchange.
+
+            The algorithm cannot continue without this value.
+
+            :param attempt_index:
+            :return capital_base: the amount of base currency available for
+            trading
+            """
+            try:
+                log.debug('retrieving capital base in {} to bootstrap '
+                          'exchange {}'.format(base_currency, exchange_name))
+                balances = exchange.get_balances()
+            except ExchangeRequestError as e:
+                if attempt_index < 20:
+                    sleep(5)
+                    return fetch_capital_base(attempt_index + 1)
+                else:
+                    raise ExchangeRequestErrorTooManyAttempts(
+                        attempts=attempt_index,
+                        error=e
+                    )
+
+            if base_currency in balances:
+                return balances[base_currency]
+            else:
+                raise BaseCurrencyNotFoundError(
+                    base_currency=base_currency,
+                    exchange=exchange_name
+                )
+
+        sim_params = create_simulation_parameters(
+            start=start,
+            end=end,
+            capital_base=fetch_capital_base(),
+            emission_rate='minute',
+            data_frequency='minute'
+        )
+
+    elif bundle is not None:
         bundles = bundle.split(',')
 
         def get_trading_env_and_data(bundles):
@@ -146,25 +276,23 @@ def _run(handle_data,
                     str(bundle_data.asset_finder.engine.url),
                 )
 
-            open_calendar = get_calendar('OPEN')
-
             env = TradingEnvironment(
-                load=partial(load_crypto_market_data, environ=environ),
+                load=partial(load_crypto_market_data, bundle=b, bundle_data=bundle_data, environ=environ),
                 bm_symbol='USDT_BTC',
                 trading_calendar=open_calendar,
                 asset_db_path=connstr,
                 environ=environ,
             )
 
-            first_trading_day =\
-                bundle_data.equity_minute_bar_reader.first_trading_day
+            first_trading_day = bundle_data.minute_bar_reader.first_trading_day
 
             data = DataPortal(
                 env.asset_finder,
                 open_calendar,
                 first_trading_day=first_trading_day,
-                equity_minute_reader=bundle_data.equity_minute_bar_reader,
-                equity_daily_reader=bundle_data.equity_daily_bar_reader,
+                minute_reader=bundle_data.minute_bar_reader,
+                five_minute_reader=bundle_data.five_minute_bar_reader,
+                daily_reader=bundle_data.daily_bar_reader,
                 adjustment_reader=bundle_data.adjustment_reader,
             )
 
@@ -179,15 +307,16 @@ def _run(handle_data,
 
             if b == 'poloniex':
                 return CryptoPricingLoader(
-                           bundle_data.equity_daily_bar_reader,
-                           CryptoPricing,
-                       )
-            elif b == 'quantopian-quandl':
+                    bundle_data,
+                    data_frequency,
+                    CryptoPricing,
+                )
+            elif b == 'quandl':
                 return USEquityPricingLoader(
-                           bundle_data.equity_daily_bar_reader,
-                           bundle_data.adjustment_reader,
-                           USEquityPricing,
-                       )
+                    bundle_data,
+                    data_frequency,
+                    USEquityPricing,
+                )
             raise ValueError(
                 "No PipelineLoader registered for bundle %s." % b
             )
@@ -207,16 +336,16 @@ def _run(handle_data,
         env = TradingEnvironment(environ=environ)
         choose_loader = None
 
-    perf = TradingAlgorithm(
+    TradingAlgorithmClass = (
+        partial(ExchangeTradingAlgorithm, exchange=exchange,
+                algo_namespace=algo_namespace)
+        if live and exchange else TradingAlgorithm)
+
+    perf = TradingAlgorithmClass(
         namespace=namespace,
         env=env,
         get_pipeline_loader=choose_loader,
-        sim_params=create_simulation_parameters(
-            start=start,
-            end=end,
-            capital_base=capital_base,
-            data_frequency=data_frequency,
-        ),
+        sim_params=sim_params,
         **{
             'initialize': initialize,
             'handle_data': handle_data,
@@ -292,10 +421,10 @@ def load_extensions(default, extensions, strict, environ, reload=False):
             _loaded_extensions.add(ext)
 
 
-def run_algorithm(start,
-                  end,
-                  initialize,
-                  capital_base,
+def run_algorithm(initialize,
+                  capital_base=None,
+                  start=None,
+                  end=None,
                   handle_data=None,
                   before_trading_start=None,
                   analyze=None,
@@ -306,7 +435,11 @@ def run_algorithm(start,
                   default_extension=True,
                   extensions=(),
                   strict_extensions=True,
-                  environ=os.environ):
+                  environ=os.environ,
+                  live=False,
+                  exchange_name=None,
+                  base_currency=None,
+                  algo_namespace=None):
     """Run a trading algorithm.
 
     Parameters
@@ -360,6 +493,12 @@ def run_algorithm(start,
     environ : mapping[str -> str], optional
         The os environment to use. Many extensions use this to get parameters.
         This defaults to ``os.environ``.
+    live: execute live trading
+    exchange_conn: The exchange connection parameters
+
+    Supported Exchanges
+    -------------------
+    bitfinex
 
     Returns
     -------
@@ -372,25 +511,25 @@ def run_algorithm(start,
     """
     load_extensions(default_extension, extensions, strict_extensions, environ)
 
-    non_none_data = valfilter(bool, {
-        'data': data is not None,
-        'bundle': bundle is not None,
-    })
-    if not non_none_data:
-        # if neither data nor bundle are passed use 'quantopian-quandl'
-        bundle = 'quantopian-quandl'
+    if not live:
+        non_none_data = valfilter(bool, {
+            'data': data is not None,
+            'bundle': bundle is not None,
+        })
+        if not non_none_data:
+            # if neither data nor bundle are passed use 'quantopian-quandl'
+            bundle = 'quantopian-quandl'
 
-    elif len(non_none_data) != 1:
-        raise ValueError(
-            'must specify one of `data`, `data_portal`, or `bundle`,'
-            ' got: %r' % non_none_data,
-        )
-
-    elif 'bundle' not in non_none_data and bundle_timestamp is not None:
-        raise ValueError(
-            'cannot specify `bundle_timestamp` without passing `bundle`',
-        )
+        elif len(non_none_data) != 1:
+            raise ValueError(
+                'must specify one of `data`, `data_portal`, or `bundle`,'
+                ' got: %r' % non_none_data,
+            )
 
+        elif 'bundle' not in non_none_data and bundle_timestamp is not None:
+            raise ValueError(
+                'cannot specify `bundle_timestamp` without passing `bundle`',
+            )
     return _run(
         handle_data=handle_data,
         initialize=initialize,
@@ -410,4 +549,8 @@ def run_algorithm(start,
         print_algo=False,
         local_namespace=False,
         environ=environ,
+        live=live,
+        exchange=exchange_name,
+        algo_namespace=algo_namespace,
+        base_currency=base_currency
     )

docs/live-trading-blueprint.md

@@ -0,0 +1,207 @@
+<h1>Live Trading Blueprint</h1>
+The purpose of this document is to allow project contributors navigate
+through the ongoing live trading implementation.
+
+<h2>Components</h2>
+At a high level, the following components have been implemented to coerce
+zipline into live trading.
+
+<h3>Exchange</h3>
+
+*catalyst/exchange*
+
+Exchange is a new package introducing cryptocurrency
+exchanges to zipline. The package contains mostly new implementations
+of existing components, adapted to characteristics of exchanges.
+
+Here are some key characteristics which make cryptocurrency exchanges
+exchanges different compared to equity brokers.
+* They trade around the clock.
+* Currency symbols are inconsistent across exchanges.
+* They trade currency pairs (i.e. the base currency is not always be USD).
+This is a paradigm shift in context of zipline. Additional
+business logic will be required to manage the portfolio data and orders.
+* The price of a single asset might vary across exchanges. This means
+arbitrage opportunities. Consequently, to extract maximum alpha, the
+platform should not only support multiple exchanges, but also multiple
+exchanges per algorithm.
+* The fee model is usually more complex than that of an equity broker.
+It can vary drastically between exchanges.
+* There are no splits, mergers, etc. to worry about.
+* A complete order book is usually available, the platform should
+offer access to it order to help traders reduce slippage.
+
+<h3>New Components</h3>
+These components of the exchange package were added to the zipline
+sources.
+
+<h4>Exchange</h4>
+
+*catalyst/exchange/exchange.py*
+
+Abstract class which acts as an interface for the implementation of
+various exchanges. It also contains logic common to all exchanges.
+
+<h4>Bitfinex</h4>
+
+*catalyst/exchange/bitfinex.py*
+
+The Bitfinex exchange implementation. It extends the Exchange class.
+
+<h4>DataPortalExchange</h4>
+
+*catalyst/exchange/data_portal_exchange.py*
+
+Extends the zipline DataPortal to route spot data to the exchange.
+This is critical because it allows the algoritm to request data in
+real-time.
+
+For example, `data.current(asset, 'price')` retrieves the current price
+of the asset, not the price at the time of yielding the bar this
+is critical to minimize slippage.
+
+At the time of writing, it only supports spot data but I believe that
+it should be extended to historical data as well. Some exchanges
+have better historical data APIs than others. This will need to
+be considered during each individual implementation.
+
+<h4>ExchangeClock</h4>
+
+*catalyst/exchange/exchange_clock.py*
+
+An implementation to the zipline Clock which runs 24/7. It yields a
+bar every minute.
+
+<h4>AssetFinderExchange</h4>
+
+*catalyst/exchange/asset_finder_exchange.py*
+
+An alternate implementation of AssetFinder which locates each asset
+against the exchanges instead of bundle databases.
+
+For example, `symbol('eth_usd')` should return an Ethereum/USD asset
+regardless of currency notation of the target exchange.
+
+To acheive this, I have created a dictionary of currencies for the
+Bitfinex exchange. Here is what it looks like.
+* Each key represents the exchange specific symbol.
+* The symbol attribute represents the abstract symbol common across
+all exchanges for the given currency.
+* The start_date attribute should correspond to its first trading day
+on the exchange.
+
+```json
+{
+  "btcusd": {
+    "symbol": "btc_usd",
+    "start_date": "2010-01-01"
+  },
+  "ltcusd": {
+    "symbol": "ltc_usd",
+    "start_date": "2010-01-01"
+  },
+  "ltcbtc": {
+    "symbol": "ltc_btc",
+    "start_date": "2010-01-01"
+  },
+  "ethusd": {
+    "symbol": "eth_usd",
+    "start_date": "2010-01-01"
+  },
+  "ethbtc": {
+    "symbol": "eth_btc",
+    "start_date": "2010-01-01"
+  }
+}
+```
+
+<h4>ExchangeTradingAlgorithm</h4>
+
+*catalyst/exchange/algorithm_exchange.py*
+
+Extends the TradingAlgorithm class which orchestrates the api
+operations. This class brings together most of the components
+described above.
+
+<h3>Modified Components</h3>
+
+The following components have been modified to include conditional
+business logic to enable live trading.
+
+<h4>run_algorithm</h4>
+
+*catalyst/utils/run_algo.py*
+
+The run_algorithm interface is an entry point to execute an
+algorithm in zipline. This component was already modified for
+the catalyst concurrency bundles. I added conditional logic
+which should not interfere with backtesting.
+
+In a nutshell, the run_algorithm method now contains three additional
+parameters:
+* live: If True, zipline will attempt to trade live. If False or not
+specified, it will run a backtest as normal.
+* algo_namespace: An arbitrary namespace for the current algorithm.
+It will be used to persist data between runs.
+* exchange_conn: A dictionary containing the attributes required
+to instantiate an exchange. Here is an example for Bitfinex:
+
+```python
+exchange_conn = dict(
+    name='bitfinex',
+    key='',
+    secret=b'',
+    base_currency='usd'
+)
+```
+
+The following sample algorithm uses the run_algorithm interface:
+
+*catalyst/examples/buy_and_hold_live.py*
+
+<h2>Portfolio Management</h2>
+
+Zipline has a Portfolio class containing key metrics used by zipline
+for, but not only, these reasons:
+
+* Placing orders: When placing orders (e.g. order_target_percent),
+zipline queries the portfolio to assess the size of current positions,
+cash available, etc.
+* Measuring performance: The portfolio contains attributes like
+cost basis of each asset, p&l, etc. which zipline uses to compute all
+of its performance criteria.
+
+When backtesting, zipline automatically updates the Portfolio object
+of its corresponding algorithm. When live trading, these updates should
+be the responsibility of the exchange as it holds the truth for:
+
+* Executed price of each order (including fees and slippage)
+* Partial / failed orders
+* Cash (i.e. base currency) available
+* Cost basis of each position
+
+If each exchange account had a one-to-one relationship with an
+algorithm, portfolio metrics could be retrieved directly from the
+exchange without persisting any data to the algorithm. However,
+doing this would have at least the following drawbacks:
+
+* It may not be reasonable to ask users to dedicate an
+exchange account to a single algorithm. Exchanges are not easy
+to partition.
+* If an exchange account contains existing positions, the calculated
+cost basis would correspond to all positions, not just those
+initiated by the algorithm.
+* It would not be possible impose trading limits on algorithms.
+
+It follows that Portfolio metrics should be calculated using a strategic
+combination of the exchange data and algorithm activity. While tracking
+the activity of an algorithm works well in backtesting, it is more
+challenging during live trading. A live algorithm might run over
+several months. It might have to stop and start for many reasons.
+This means that the platform should have the ability to persist
+algorithm activity in order to be reliable.
+
+In the interest of time, I will start by persisting algorithm
+activity in memory. Data will be lost when the algorithm execution stops.
+The intent it to offer a simple basis from which to implement data
+persistence strategies in the future.

docs/live-trading-wiki.md

@@ -0,0 +1,105 @@
+<h1>Live Trading</h1>
+This document explains how to get started with live trading.
+
+<h2>Supported Exchanges</h2>
+Catalyst can trade against these exchanges:
+
+* Bitfinex, id=`bitfinex`
+* Bittrex, id=`bittrex`
+
+<h3>Authentication</h3>
+Most exchanges require key/token combination for authentication. By
+convention, Catalyst uses an "auth.json" file to hold this data.
+
+This example illustrates the convention using the Bitfinex exchange.
+Here is how to generate key and secret values for bitfinex:
+https://docs.bitfinex.com/v1/docs/api-access. Most exchanges follow
+a similar process.
+
+The auth.json file:
+```json
+{
+  "name": "bitfinex",
+  "key": "my-key",
+  "secret": "my-secret"
+}
+```
+
+The file goes here:
+```
+~/.catalyst/data/exchanges/bitfinex/auth.json
+```
+
+Note that the 'bitfinex' directory corresponds to the id of the Bitfinex
+exchange as defined in the "Supported Exchanges" section above.
+Attempting to run an algorithm where the targeted exchange is missing
+its "auth.json" file will create the directory structure but result
+in an error.
+
+<h3>Currency Symbols</h3>
+Catalyst introduces a universal convention to reference
+trading pairs and individual currencies. This
+is required to ensure that the `symbol()` api predictably
+returns the correct asset regardless of the targeted exchange.
+
+Exchanges tend to use their own convention to represent currencies
+(e.g. XBT and BTC both represent Bitcoin on different exchanges).
+Trading pairs are also inconsistent. For example, Bitfinex
+puts the market currency before the base currency without a
+separator, Bittrex puts the base currency first and uses a dash
+seperator.
+
+Here is the Catalyst convention:
+
+*[Market Currency]_[Base Currency]* all lowercase.
+
+Currency symbols (e.g. btc, eth, ltc) follow the Bittrex convention.
+
+Here are some examples:
+```python
+# With Bitfinex
+bitcoin_usd_asset = symbol('btc_usd')
+ethereum_bitcoin_asset = symbol('eth_btc')
+
+# With Bittrex
+ethereum_bitcoin_asset = symbol('eth_btc')
+neo_ethereum_asset = symbol('neo_eth)
+```
+
+Note that the trading pairs are always referenced in the same manner.
+However, not all trading pairs are available on all exchanges. An
+error will occur if the specified trading pair is not trading
+on the exchange.
+
+<h2>Trading an Algorithm</h2>
+There is no special convention to follow when writing an
+algorithm for live trading. The same algorithm should work in
+backtest and live execution mode without modification.
+
+What differs are the arguments provided to the catalyst client or
+`run_algorithm()` interface. Here is example:
+
+```python
+run_algorithm(
+    initialize=initialize,
+    handle_data=handle_data,
+    analyze=analyze,
+    exchange_name='bitfinex',
+    live=True,
+    algo_namespace='my_algo_trading_xrp',
+    base_currency='btc'
+)
+```
+
+Here is the breakdown of the new arguments:
+* live: Boolean flag which enables live trading.
+* exchange_name: The name of the targeted exchange
+    (supported values: *bitfinex*, *bittrex*).
+* algo_namespace: A arbitrary label assigned to your algorithm for
+    data storage purposes.
+* base_currency: The base currency used to calculate the
+    statistics of your algorithm. Currently, the base currency of all
+    trading pairs of your algorithm must match this value.
+
+Here is a complete algorithm for reference:
+[Buy Low and Sell High](../catalyst/examples/buy_low_sell_high_live.py)

etc/requirements.txt

@@ -9,7 +9,9 @@ Logbook==0.12.5
 # Scientific Libraries
 
 pytz==2016.4
-numpy==1.11.1
+
+# FF: Upgraded numpy because of errors with version 1.11
+numpy==1.13.1
 
 # for pandas-datareader
 requests-file==1.4.1
@@ -77,3 +79,4 @@ lru-dict==1.1.4
 empyrical==0.2.1
 
 tables==3.3.0
+

setup.py

@@ -38,6 +38,7 @@ class LazyBuildExtCommandClass(dict):
     Lazy command class that defers operations requiring Cython and numpy until
     they've actually been downloaded and installed by setup_requires.
     """
+
     def __contains__(self, key):
         return (
             key == 'build_ext'
@@ -62,6 +63,7 @@ class LazyBuildExtCommandClass(dict):
             Custom build_ext command that lazily adds numpy's include_dir to
             extensions.
             """
+
             def build_extensions(self):
                 """
                 Lazily append numpy's include directory to Extension includes.
@@ -75,6 +77,7 @@ class LazyBuildExtCommandClass(dict):
                     ext.include_dirs.append(numpy_incl)
 
                 super(build_ext, self).build_extensions()
+
         return build_ext
 
 
@@ -100,7 +103,8 @@ ext_modules = [
     window_specialization('label'),
     Extension('catalyst.lib.rank', ['catalyst/lib/rank.pyx']),
     Extension('catalyst.data._equities', ['catalyst/data/_equities.pyx']),
-    Extension('catalyst.data._adjustments', ['catalyst/data/_adjustments.pyx']),
+    Extension('catalyst.data._adjustments',
+              ['catalyst/data/_adjustments.pyx']),
     Extension('catalyst._protocol', ['catalyst/_protocol.pyx']),
     Extension('catalyst.gens.sim_engine', ['catalyst/gens/sim_engine.pyx']),
     Extension(
@@ -117,7 +121,6 @@ ext_modules = [
     ),
 ]
 
-
 STR_TO_CMP = {
     '<': lt,
     '<=': le,
@@ -212,7 +215,7 @@ def read_requirements(path,
                       conda_format=False,
                       filter_names=None):
     """
-    Read a requirements.txt file, expressed as a path relative to Zipline root.
+    Read a requirements.txt file, expressed as a path relative to Catalyst root.
 
     Returns requirements with the pinned versions as lower bounds
     if `strict_bounds` is falsey.
@@ -264,6 +267,7 @@ def setup_requirements(requirements_path, module_names, strict_bounds,
         )
     return module_lines
 
+
 conda_build = os.path.basename(sys.argv[0]) in ('conda-build',  # unix
                                                 'conda-build-script.py')  # win
 
@@ -295,7 +299,7 @@ setup(
     ext_modules=ext_modules,
     include_package_data=True,
     package_data={root.replace(os.sep, '.'):
-                  ['*.pyi', '*.pyx', '*.pxi', '*.pxd']
+                      ['*.pyi', '*.pyx', '*.pxi', '*.pxd']
                   for root, dirnames, filenames in os.walk('catalyst')
                   if '__pycache__' not in root},
     license='Apache 2.0',

tests/exchange/base.py

@@ -0,0 +1,38 @@
+import unittest
+from abc import ABCMeta, abstractmethod
+
+
+class BaseExchangeTestCase():
+    __metaclass__ = ABCMeta
+
+    @abstractmethod
+    def test_order(self):
+        pass
+
+    @abstractmethod
+    def test_open_orders(self):
+        pass
+
+    @abstractmethod
+    def test_get_order(self):
+        pass
+
+    @abstractmethod
+    def test_cancel_order(self):
+        pass
+
+    @abstractmethod
+    def test_get_candles(self):
+        pass
+
+    @abstractmethod
+    def test_tickers(self):
+        pass
+
+    @abstractmethod
+    def test_get_balances(self):
+        pass
+
+    @abstractmethod
+    def test_get_account(self):
+        pass

tests/exchange/test_bitfinex.py

@@ -0,0 +1,70 @@
+from catalyst.exchange.bitfinex.bitfinex import Bitfinex
+from .base import BaseExchangeTestCase
+from logbook import Logger
+import pandas as pd
+from catalyst.finance.execution import (MarketOrder,
+                                        LimitOrder,
+                                        StopOrder,
+                                        StopLimitOrder)
+from catalyst.exchange.exchange_utils import get_exchange_auth
+
+log = Logger('test_bitfinex')
+
+
+class BitfinexTestCase(BaseExchangeTestCase):
+    @classmethod
+    def setup(self):
+        print ('creating bitfinex object')
+        auth = get_exchange_auth('bitfinex')
+        self.exchange = Bitfinex(
+            key=auth['key'],
+            secret=auth['secret'],
+            base_currency='usd'
+        )
+
+    def test_order(self):
+        log.info('creating order')
+        asset = self.exchange.get_asset('eth_usd')
+        order_id = self.exchange.order(
+            asset=asset,
+            style=LimitOrder(limit_price=200),
+            limit_price=200,
+            amount=0.5,
+            stop_price=None
+        )
+        log.info('order created {}'.format(order_id))
+        pass
+
+    def test_open_orders(self):
+        log.info('retrieving open orders')
+        orders = self.exchange.get_open_orders()
+        pass
+
+    def test_get_order(self):
+        log.info('retrieving order')
+        pass
+
+    def test_cancel_order(self):
+        log.info('cancel order')
+        pass
+
+    def test_get_candles(self):
+        log.info('retrieving candles')
+        pass
+
+    def test_tickers(self):
+        log.info('retrieving tickers')
+        tickers = self.exchange.tickers([
+            self.exchange.get_asset('eth_usd'),
+            self.exchange.get_asset('btc_usd')
+        ])
+        pass
+
+    def test_get_account(self):
+        log.info('retrieving account data')
+        pass
+
+    def test_get_balances(self):
+        log.info('testing exchange balances')
+        balances = self.exchange.get_balances()
+        pass

tests/exchange/test_bittrex.py

@@ -0,0 +1,83 @@
+from catalyst.exchange.bittrex.bittrex import Bittrex
+from catalyst.finance.order import Order
+from .base import BaseExchangeTestCase
+from logbook import Logger
+from catalyst.exchange.exchange_utils import get_exchange_auth
+
+log = Logger('test_bittrex')
+
+
+class BittrexTestCase(BaseExchangeTestCase):
+    @classmethod
+    def setup(self):
+        print ('creating bittrex object')
+        auth = get_exchange_auth('bittrex')
+        self.exchange = Bittrex(
+            key=auth['key'],
+            secret=auth['secret'],
+            base_currency='btc'
+        )
+
+    def test_order(self):
+        log.info('creating order')
+        asset = self.exchange.get_asset('neo_btc')
+        order_id = self.exchange.order(
+            asset=asset,
+            limit_price=0.0005,
+            amount=1,
+        )
+        log.info('order created {}'.format(order_id))
+        assert order_id is not None
+        pass
+
+    def test_open_orders(self):
+        log.info('retrieving open orders')
+        asset = self.exchange.get_asset('neo_btc')
+        orders = self.exchange.get_open_orders(asset)
+        pass
+
+    def test_get_order(self):
+        log.info('retrieving order')
+        order = self.exchange.get_order(
+            u'2c584020-9caf-4af5-bde0-332c0bba17e2')
+        assert isinstance(order, Order)
+        pass
+
+    def test_cancel_order(self, ):
+        log.info('cancel order')
+        self.exchange.cancel_order(u'dc7bcca2-5219-4145-8848-8a593d2a72f9')
+        pass
+
+    def test_get_candles(self):
+        log.info('retrieving candles')
+        ohlcv_neo = self.exchange.get_candles(
+            data_frequency='5m',
+            assets=self.exchange.get_asset('neo_btc')
+        )
+        ohlcv_neo_ubq = self.exchange.get_candles(
+            data_frequency='5m',
+            assets=[
+                self.exchange.get_asset('neo_btc'),
+                self.exchange.get_asset('ubq_btc')
+            ],
+            bar_count=14
+        )
+        pass
+
+    def test_tickers(self):
+        log.info('retrieving tickers')
+        tickers = self.exchange.tickers([
+            self.exchange.get_asset('ubq_btc'),
+            self.exchange.get_asset('neo_btc')
+        ])
+        assert len(tickers) == 2
+        pass
+
+    def test_get_balances(self):
+        log.info('testing wallet balances')
+        balances = self.exchange.get_balances()
+        pass
+
+    def test_get_account(self):
+        log.info('testing account data')
+        pass

tests/exchange/test_clock.py

@@ -0,0 +1,50 @@
+from unittest import TestCase
+from logbook import Logger
+from mock import patch, sentinel
+from catalyst.exchange.exchange_clock import ExchangeClock
+from catalyst.utils.calendars.trading_calendar import days_at_time
+from datetime import time
+from collections import defaultdict
+from catalyst.utils.calendars import get_calendar
+import pandas as pd
+
+log = Logger('ExchangeClockTestCase')
+
+
+class ExchangeClockTestCase(TestCase):
+    @classmethod
+    def setUpClass(cls):
+        cls.open_calendar = get_calendar("OPEN")
+
+        cls.sessions = pd.Timestamp.utcnow()
+
+    def setUp(self):
+        self.internal_clock = None
+        self.events = defaultdict(list)
+
+    def advance_clock(self, x):
+        """Mock function for sleep. Advances the internal clock by 1 min"""
+        # The internal clock advance time must be 1 minute to match
+        # MinutesSimulationClock's update frequency
+        self.internal_clock += pd.Timedelta('1 min')
+
+    def get_clock(self, arg, *args, **kwargs):
+        """Mock function for pandas.to_datetime which is used to query the
+        current time in RealtimeClock"""
+        assert arg == "now"
+        return self.internal_clock
+
+    def test_clock(self):
+        with patch('catalyst.exchange.exchange_clock.pd.to_datetime') as to_dt, \
+                patch('catalyst.exchange.exchange_clock.sleep') as sleep:
+            clock = ExchangeClock(sessions=self.sessions)
+            to_dt.side_effect = self.get_clock
+            sleep.side_effect = self.advance_clock
+            start_time = pd.Timestamp.utcnow()
+            self.internal_clock = start_time
+
+            events = list(clock)
+
+            # Event 0 is SESSION_START which always happens at 00:00.
+            ts, event_type = events[1]
+        pass