Resolving conflicts between branches

catalyst/data/_equities.pyx

@@ -220,6 +220,8 @@ cpdef _read_bcolz_data(ctable_t table,
             outbuf_as_float = outbuf.astype(float64) * .000000001
             outbuf_as_float[where_nan] = NAN
             results.append(outbuf_as_float)
+        elif column_name in ['volume']:
+            results.append(outbuf.astype(float64) * .000000001)
         else:
             results.append(outbuf)
     return results

catalyst/data/_minute_bar_internal.pyx

@@ -35,17 +35,6 @@ 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,
@@ -99,26 +88,6 @@ 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,
@@ -189,50 +158,3 @@ def find_last_traded_position_internal(
     # 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

@@ -60,10 +60,6 @@ class BaseBundle(object):
     def minutes_per_day(self):
         raise NotImplementedError()
 
-    @lazyval
-    def five_minutes_per_day(self):
-        raise NotImplementedError()
-
     @lazyval
     def frequencies(self):
         raise NotImplementedError()
@@ -115,7 +111,6 @@ class BaseBundle(object):
                environ,
                asset_db_writer,
                minute_bar_writer,
-               five_minute_bar_writer,
                daily_bar_writer,
                adjustment_writer,
                calendar,
@@ -162,7 +157,7 @@ class BaseBundle(object):
 
                 # 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.
+                # minute data.
                 metadata = self._post_process_metadata(
                     raw_metadata,
                     cache,
@@ -170,26 +165,6 @@ class BaseBundle(object):
                 )
                 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:

catalyst/data/bundles/base_pricing.py

@@ -47,10 +47,6 @@ class BaseCryptoPricingBundle(BasePricingBundle):
     def minutes_per_day(self):
         return 1440
 
-    @lazyval
-    def five_minutes_per_day(self):
-        return 288
-
     @property
     def splits(self):
         return []
@@ -68,10 +64,6 @@ class BaseEquityPricingBundle(BasePricingBundle):
     def minutes_per_day(self):
         return 390
 
-    @lazyval
-    def five_minutes_per_day(self):
-        return 78
-
     @property
     def splits(self):
         return self._splits

catalyst/data/bundles/core.py

@@ -17,10 +17,6 @@ from ..us_equity_pricing import (
     SQLiteAdjustmentReader,
     SQLiteAdjustmentWriter,
 )
-from ..five_minute_bars import (
-    BcolzFiveMinuteBarReader,
-    BcolzFiveMinuteBarWriter,
-)
 from ..minute_bars import (
     BcolzMinuteBarReader,
     BcolzMinuteBarWriter,
@@ -54,11 +50,6 @@ def minute_path(bundle_name, timestr, environ=None):
         environ=environ,
     )
 
-def five_minute_path(bundle_name, timestr, environ=None):
-    return pth.data_path(
-        five_minute_relative(bundle_name, timestr, environ),
-        environ=environ,
-    )
 
 def daily_path(bundle_name, timestr, environ=None):
     return pth.data_path(
@@ -92,8 +83,6 @@ def cache_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_relative(bundle_name, timestr, environ=None):
     return bundle_name, timestr, 'minute_equities.bcolz'
@@ -206,14 +195,13 @@ RegisteredBundle = namedtuple(
      'start_session',
      'end_session',
      'minutes_per_day',
-     'five_minutes_per_day',
      'ingest',
      'create_writers']
 )
 
 BundleData = namedtuple(
     'BundleData',
-    'asset_finder minute_bar_reader five_minute_bar_reader daily_bar_reader '
+    'asset_finder minute_bar_reader daily_bar_reader '
     'adjustment_reader',
 )
 
@@ -303,7 +291,6 @@ def _make_bundle_core():
             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,
@@ -316,7 +303,6 @@ def _make_bundle_core():
                  start_session=None,
                  end_session=None,
                  minutes_per_day=1440,
-                 five_minutes_per_day=288,
                  create_writers=True):
         """Register a data bundle ingest function.
 
@@ -397,7 +383,6 @@ 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,
         )
@@ -496,16 +481,6 @@ def _make_bundle_core():
                 # 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_relative(
                         name, timestr, environ=environ)
@@ -532,7 +507,6 @@ 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
@@ -544,7 +518,6 @@ def _make_bundle_core():
                 environ,
                 asset_db_writer,
                 minute_bar_writer,
-                five_minute_bar_writer,
                 daily_bar_writer,
                 adjustment_db_writer,
                 calendar,
@@ -631,9 +604,6 @@ def _make_bundle_core():
             minute_bar_reader=BcolzMinuteBarReader(
                 minute_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),
             ),

catalyst/data/bundles/poloniex.py

@@ -97,6 +97,8 @@ class PoloniexBundle(BaseCryptoPricingBundle):
                                end_date,
                                frequency):
 
+        # TODO: replace this with direct exchange call
+        # The end date and frequency should be used to calculate the number of bars
         if(frequency == 'minute'):
             pc = PoloniexCurator()
             raw = pc.onemin_to_dataframe(symbol, start_date, end_date)
@@ -146,7 +148,6 @@ class PoloniexBundle(BaseCryptoPricingBundle):
                          data_frequency):
         period_map = {
             'daily': 86400,
-#            '5-minute': 300,
         }
 
         try:
@@ -165,6 +166,7 @@ class PoloniexBundle(BaseCryptoPricingBundle):
         return self._format_polo_query(query_params)
     
     def _format_polo_query(self, query_params):
+        # TODO: got against the exchange object
         return 'https://poloniex.com/public?{query}'.format(
             query=urlencode(query_params),
         )

catalyst/data/data_portal.py

@@ -42,7 +42,6 @@ from catalyst.assets.roll_finder import (
 )
 from catalyst.data.dispatch_bar_reader import (
     AssetDispatchMinuteBarReader,
-    AssetDispatchFiveMinuteBarReader,
     AssetDispatchSessionBarReader
 )
 from catalyst.data.resample import (
@@ -120,10 +119,6 @@ class DataPortal(object):
         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.
-    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
@@ -150,7 +145,6 @@ class DataPortal(object):
                  trading_calendar,
                  first_trading_day,
                  daily_reader=None,
-                 five_minute_reader=None,
                  minute_reader=None,
                  future_daily_reader=None,
                  future_minute_reader=None,
@@ -202,7 +196,6 @@ class DataPortal(object):
                 reader.last_available_dt
                 for reader in [
                     minute_reader,
-                    five_minute_reader,
                     future_minute_reader,
                 ]
                 if reader is not None
@@ -214,8 +207,6 @@ class DataPortal(object):
 
         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(
@@ -229,13 +220,10 @@ class DataPortal(object):
         }
 
         aligned_minute_readers = {}
-        aligned_five_minute_readers = {}
         aligned_session_readers = {}
 
         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
 
@@ -267,13 +255,6 @@ 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,
@@ -283,7 +264,6 @@ class DataPortal(object):
 
         self._pricing_readers = {
             'minute': _dispatch_minute_reader,
-            '5-minute': _dispatch_five_minute_reader,
             'daily': _dispatch_session_reader,
         }
 
@@ -719,17 +699,6 @@ class DataPortal(object):
             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,

catalyst/data/dispatch_bar_reader.py

@@ -138,12 +138,6 @@ 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/loader.py

@@ -12,41 +12,36 @@
 # 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 datetime
 import os
 from collections import OrderedDict
 
 import logbook
 import pandas as pd
-import numpy as np
-from pandas_datareader.data import DataReader
-import datetime
-import time
 import pytz
+from pandas_datareader.data import DataReader
 from six import iteritems
 from six.moves.urllib_error import HTTPError
 
-from .benchmarks import get_benchmark_returns
+from catalyst.utils.calendars import get_calendar
 from . import treasuries, treasuries_can
+from .benchmarks import get_benchmark_returns
+from ..utils.deprecate import deprecated
 from ..utils.paths import (
     cache_root,
     data_root,
 )
-from ..utils.deprecate import deprecated
-
-from catalyst.data.bundles.poloniex import PoloniexBundle
-from catalyst.utils.calendars import get_calendar
-
 
 logger = logbook.Logger('Loader')
 
 # Mapping from index symbol to appropriate bond data
 INDEX_MAPPING = {
     'SPY':
-    (treasuries, 'treasury_curves.csv', 'www.federalreserve.gov'),
+        (treasuries, 'treasury_curves.csv', 'www.federalreserve.gov'),
     '^GSPTSE':
-    (treasuries_can, 'treasury_curves_can.csv', 'bankofcanada.ca'),
+        (treasuries_can, 'treasury_curves_can.csv', 'bankofcanada.ca'),
     '^FTSE':  # use US treasuries until UK bonds implemented
-    (treasuries, 'treasury_curves.csv', 'www.federalreserve.gov'),
+        (treasuries, 'treasury_curves.csv', 'www.federalreserve.gov'),
 }
 
 ONE_HOUR = pd.Timedelta(hours=1)
@@ -94,18 +89,27 @@ def has_data_for_dates(series_or_df, first_date, last_date):
     if not isinstance(dts, pd.DatetimeIndex):
         raise TypeError("Expected a DatetimeIndex, but got %s." % type(dts))
     first, last = dts[[0, -1]].tz_localize(None)
-    return (first <= first_date.tz_localize(None)) and (last >= last_date.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=None, bundle=None, bundle_data=None,
+                            environ=None, exchange=None, start_dt=None,
+                            end_dt=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[1]
-    now = pd.Timestamp.utcnow()
+    # TODO: consider making configurable
+    bm_symbol = 'btc_usdt'
+    # if trading_days is None:
+    #    trading_days = get_calendar('OPEN').schedule
+
+    if start_dt is None:
+        start_dt = get_calendar('OPEN').first_trading_session
+
+    if end_dt is None:
+        end_dt = pd.Timestamp.utcnow()
 
     # We expect to have benchmark and treasury data that's current up until
     # **two** full trading days prior to the most recently completed trading
@@ -121,6 +125,7 @@ def load_crypto_market_data(trading_day=None, trading_days=None, bm_symbol='USDT
 
     # We'll attempt to download new data if the latest entry in our cache is
     # before this date.
+    '''
     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
@@ -129,31 +134,44 @@ def load_crypto_market_data(trading_day=None, trading_days=None, bm_symbol='USDT
         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,
-        first_date,
-        last_date,
-        now,
-        # 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,
-    )
+    '''
+    last_date = trading_days[trading_days.get_loc(end_dt, method='ffill') - 1]
+
+    if exchange is None:
+        # This is exceptional, since placing the import at the module scope
+        #  breaks things and it's only needed here
+        from catalyst.exchange.poloniex.poloniex import Poloniex
+        exchange = Poloniex('', '', '')
+
+    benchmark_asset = exchange.get_asset(bm_symbol)
+
+    # exchange.get_history_window() already ensures that we have the right data
+    # for the right dates
+    br = exchange.get_history_window(
+        assets=[benchmark_asset],
+        end_dt=last_date,
+        bar_count=pd.Timedelta(last_date - start_dt).days,
+        frequency='1d',
+        field='close',
+        data_frequency='daily')
+    br.columns = ['close']
+    br = br.pct_change(1).iloc[1:]
+    br.loc[start_dt] = 0
+    br = br.sort_index()
+
     # 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') 
+    first_date_treasury = pd.Timestamp('1990-01-02', tz='UTC')
     tc = ensure_treasury_data(
         bm_symbol,
         first_date_treasury,
         last_date,
-        now,
+        end_dt,
         environ,
     )
-    benchmark_returns = br[br.index.slice_indexer(first_date, last_date)]
-    treasury_curves = tc[tc.index.slice_indexer(first_date_treasury, last_date)]
+    benchmark_returns = br[br.index.slice_indexer(start_dt, last_date)]
+    treasury_curves = tc[
+        tc.index.slice_indexer(first_date_treasury, last_date)]
     return benchmark_returns, treasury_curves
 
 
@@ -251,12 +269,11 @@ def ensure_crypto_benchmark_data(symbol,
                                  bundle,
                                  bundle_data,
                                  environ=None):
-
     filename = get_benchmark_filename(symbol)
 
     logger.info(
         ('Loading benchmark data for {symbol!r} '
-            'from {first_date} to {last_date}'),
+         'from {first_date} to {last_date}'),
         symbol=symbol,
         first_date=first_date,
         last_date=last_date
@@ -277,7 +294,7 @@ def ensure_crypto_benchmark_data(symbol,
     # If no cached data was found or it was missing any dates then download the
     # necessary data.
 
-    if(bundle == 'poloniex'):
+    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.
@@ -285,43 +302,51 @@ def ensure_crypto_benchmark_data(symbol,
         prevents users abroad from getting Catalyst to work
         '''
         logger.info(
-            ('Retrieving benchmark data from bundle for {symbol!r} from {first_date} to {last_date}'),
+            (
+                'Retrieving benchmark data from bundle for {symbol!r} from {first_date} to {last_date}'),
             symbol=symbol, first_date=first_date, last_date=last_date)
 
-        asset = bundle_data.asset_finder.lookup_symbol(symbol=symbol,as_of_date=None)
+        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')
+            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)]
+        bench_raw = bench_raw[
+                    pd.to_datetime(first_date - trading_day):pd.to_datetime(
+                        last_date)]
 
     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}'),
+            (
+                'Downloading benchmark data for {symbol!r} from {first_date} to {last_date}'),
             symbol=symbol, first_date=first_date, last_date=last_date)
 
+        raise DeprecationWarning('poloniex bundle deprecated')
         # Load benchmark symbol from Poloniex API
-        try:
-            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 fetch new crypto benchmark returns')
-            raise
+        # try:
+        #     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 fetch new crypto benchmark returns')
+        #     raise
 
     # select close column and compute percent change between days
     daily_close = bench_raw[['close']]
@@ -380,7 +405,7 @@ def ensure_benchmark_data(symbol, first_date, last_date, now, trading_day,
     # necessary data.
     logger.info(
         ('Downloading benchmark data for {symbol!r} '
-            'from {first_date} to {last_date}'),
+         'from {first_date} to {last_date}'),
         symbol=symbol,
         first_date=first_date - trading_day,
         last_date=last_date
@@ -441,7 +466,7 @@ def ensure_benchmark_data(symbol, first_date, last_date, now, trading_day,
     # necessary data.
     logger.info(
         ('Downloading benchmark data for {symbol!r} '
-            'from {first_date} to {last_date}'),
+         'from {first_date} to {last_date}'),
         symbol=symbol,
         first_date=first_date - trading_day,
         last_date=last_date
@@ -525,7 +550,8 @@ def _load_cached_data(filename, first_date, last_date, now, resource_name,
             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')
+            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
 

catalyst/data/minute_bars.py

@@ -44,7 +44,6 @@ from catalyst.utils.calendars import get_calendar
 from catalyst.utils.cli import maybe_show_progress
 from catalyst.utils.memoize import lazyval
 
-
 logger = logbook.Logger('MinuteBars')
 
 US_EQUITIES_MINUTES_PER_DAY = 390
@@ -262,14 +261,14 @@ class BcolzMinuteBarMetadata(object):
             )
 
     def __init__(
-        self,
-        default_ohlc_ratio,
-        ohlc_ratios_per_sid,
-        calendar,
-        start_session,
-        end_session,
-        minutes_per_day,
-        version=FORMAT_VERSION,
+            self,
+            default_ohlc_ratio,
+            ohlc_ratios_per_sid,
+            calendar,
+            start_session,
+            end_session,
+            minutes_per_day,
+            version=FORMAT_VERSION,
     ):
         self.calendar = calendar
         self.start_session = start_session
@@ -342,10 +341,10 @@ class BcolzMinuteBarMetadata(object):
             'first_trading_day': str(self.start_session.date()),
             'market_opens': (
                 market_opens.values.astype('datetime64[m]').
-                astype(np.int64).tolist()),
+                    astype(np.int64).tolist()),
             'market_closes': (
                 market_closes.values.astype('datetime64[m]').
-                astype(np.int64).tolist()),
+                    astype(np.int64).tolist()),
         }
         with open(self.metadata_path(rootdir), 'w+') as fp:
             json.dump(metadata, fp)
@@ -914,10 +913,10 @@ class BcolzMinuteBarReader(MinuteBarReader):
         )
         self._schedule = self.calendar.schedule[slicer]
         self._market_opens = self._schedule.market_open
-        self._market_open_values = self._market_opens.values.\
+        self._market_open_values = self._market_opens.values. \
             astype('datetime64[m]').astype(np.int64)
         self._market_closes = self._schedule.market_close
-        self._market_close_values = self._market_closes.values.\
+        self._market_close_values = self._market_closes.values. \
             astype('datetime64[m]').astype(np.int64)
 
         self._default_ohlc_inverse = 1.0 / metadata.default_ohlc_ratio
@@ -1125,7 +1124,7 @@ class BcolzMinuteBarReader(MinuteBarReader):
             else:
                 return np.nan
 
-        #if field != 'volume':
+        # if field != 'volume':
         value *= self._ohlc_ratio_inverse_for_sid(sid)
         return value
 
@@ -1256,16 +1255,16 @@ class BcolzMinuteBarReader(MinuteBarReader):
                 if indices_to_exclude is not None:
                     for excl_start, excl_stop in indices_to_exclude[::-1]:
                         excl_slice = np.s_[
-                            excl_start - start_idx:excl_stop - start_idx + 1]
+                                     excl_start - start_idx:excl_stop - start_idx + 1]
                         values = np.delete(values, excl_slice)
 
                 where = values != 0
                 # first slice down to len(where) because we might not have
                 # written data for all the minutes requested
-                #if field != 'volume':
+                # if field != 'volume':
                 out[:len(where), i][where] = (
-                        values[where] * self._ohlc_ratio_inverse_for_sid(sid))
-                #else:
+                    values[where] * self._ohlc_ratio_inverse_for_sid(sid))
+                # else:
                 #    out[:len(where), i][where] = values[where]
 
             results.append(out)
@@ -1319,9 +1318,9 @@ class H5MinuteBarUpdateWriter(object):
 
     def __init__(self, path, complevel=None, complib=None):
         self._complevel = complevel if complevel \
-            is not None else self._COMPLEVEL
+                                       is not None else self._COMPLEVEL
         self._complib = complib if complib \
-            is not None else self._COMPLIB
+                                   is not None else self._COMPLIB
         self._path = path
 
     def write(self, frames):
@@ -1353,6 +1352,7 @@ class H5MinuteBarUpdateReader(MinuteBarUpdateReader):
     path : str
         The path of the HDF5 file from which to source data.
     """
+
     def __init__(self, path):
         self._panel = pd.read_hdf(path)