diff --git a/coverage.xml b/coverage.xml new file mode 100644 index 00000000..d2179403 --- /dev/null +++ b/coverage.xml @@ -0,0 +1,477 @@ + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + diff --git a/docs/index.rst b/docs/index.rst index 6629f7e8..5cd17a3b 100644 --- a/docs/index.rst +++ b/docs/index.rst @@ -3,9 +3,12 @@ You can adapt this file completely to your liking, but it should at least contain the root `toctree` directive. -Welcome to QSim's documentation! +Quantopian Simulator: QSim ================================ +Qsim runs backtests using asynchronous components and zeromq messaging for communication and coordination. + + Contents: .. toctree:: @@ -13,6 +16,7 @@ Contents: notes.rst modules.rst + messaging.rst diff --git a/qsim/simulator/qbt.py b/docs/messaging.rst similarity index 64% rename from qsim/simulator/qbt.py rename to docs/messaging.rst index 45247a4d..5ade0428 100644 --- a/qsim/simulator/qbt.py +++ b/docs/messaging.rst @@ -1,7 +1,3 @@ -""" -QBT - Quantopian Backtest -==================================== - qbt runs backtests using multiple processes and zeromq messaging for communication and coordination. Backtest is the primary process. It maintains both server and client sockets: @@ -27,41 +23,4 @@ zmq sockets for backtest clients: - event feed, ZMQ.RESP. Port = port_start + 6 - backtest will bind to this socket and respond to requests from client for more data. Response data will be the queue of events that transpired since the last request. - - -""" -import copy -import multiprocessing -import zmq - -import qsim.util as qutil -import qsim.simulator.sources as sources - - - -CONTROLLER_PORT = 9000 -DATA_SINK_PORT = 10000 -DATA_FEED_PORT = 30000 - -class Backtest(object): - - def __init__(self, db, logger): - qutil.logger = logger - self.db = db - self.feed = DataFeed(db, logger) - - def start_feed(self): - proc1 = multiprocessing.Process(target=feed.run) - proc1.start() - - def run(self): - # Prepare our context and sockets - self.context = zmq.Context() - - #create the feed sink. - self.feed_address = self.feed.data_address - self.feed_socket = self.context.connect(self.feed_address) - self.feed_socket.connect(zmq.PULL) - - - \ No newline at end of file + \ No newline at end of file diff --git a/etc/jenkins.sh b/etc/jenkins.sh index 56659efd..b45cab15 100755 --- a/etc/jenkins.sh +++ b/etc/jenkins.sh @@ -31,6 +31,7 @@ paver apidocs html nosetests #run pylint checks +cp ./pylint.rcfile /mnt/jenkins/.pylintrc #default location for config file... pylint -f parseable qsim | tee pylint.out #run sloccount analysis diff --git a/nosetests.xml b/nosetests.xml index 45278cc6..8557c4d9 100644 --- a/nosetests.xml +++ b/nosetests.xml @@ -1 +1 @@ - \ No newline at end of file + \ No newline at end of file diff --git a/pylint.rcfile b/pylint.rcfile new file mode 100644 index 00000000..b682c7fb --- /dev/null +++ b/pylint.rcfile @@ -0,0 +1,238 @@ +[MASTER] + +# Specify a configuration file. +#rcfile= + +# Python code to execute, usually for sys.path manipulation such as +# pygtk.require(). +#init-hook= + +# Profiled execution. +profile=no + +# Add to the black list. It should be a base name, not a +# path. You may set this option multiple times. +ignore=CVS + +# Pickle collected data for later comparisons. +persistent=yes + +# List of plugins (as comma separated values of python modules names) to load, +# usually to register additional checkers. +load-plugins= + + +[MESSAGES CONTROL] + +# Enable the message, report, category or checker with the given id(s). You can +# either give multiple identifier separated by comma (,) or put this option +# multiple time. +#enable= + +# Disable the message, report, category or checker with the given id(s). You +# can either give multiple identifier separated by comma (,) or put this option +# multiple time (only on the command line, not in the configuration file where +# it should appear only once). +#disable= + + +[REPORTS] + +# Set the output format. Available formats are text, parseable, colorized, msvs +# (visual studio) and html +output-format=text + +# Include message's id in output +include-ids=no + +# Put messages in a separate file for each module / package specified on the +# command line instead of printing them on stdout. Reports (if any) will be +# written in a file name "pylint_global.[txt|html]". +files-output=no + +# Tells whether to display a full report or only the messages +reports=yes + +# Python expression which should return a note less than 10 (10 is the highest +# note). You have access to the variables errors warning, statement which +# respectively contain the number of errors / warnings messages and the total +# number of statements analyzed. This is used by the global evaluation report +# (RP0004). +evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10) + +# Add a comment according to your evaluation note. This is used by the global +# evaluation report (RP0004). +comment=no + + +[BASIC] + +# Required attributes for module, separated by a comma +required-attributes= + +# List of builtins function names that should not be used, separated by a comma +bad-functions=map,filter,apply,input + +# Regular expression which should only match correct module names +module-rgx=(([a-z_][a-z0-9_]*)|([A-Z][a-zA-Z0-9]+))$ + +# Regular expression which should only match correct module level names +const-rgx=(([A-Z_][A-Z0-9_]*)|(__.*__))$ + +# Regular expression which should only match correct class names +class-rgx=[A-Z_][a-zA-Z0-9]+$ + +# Regular expression which should only match correct function names +function-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression which should only match correct method names +method-rgx=[a-z_][a-z0-9_]{2,30}$|setUp + +# Regular expression which should only match correct instance attribute names +attr-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression which should only match correct argument names +argument-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression which should only match correct variable names +variable-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression which should only match correct list comprehension / +# generator expression variable names +inlinevar-rgx=[A-Za-z_][A-Za-z0-9_]*$ + +# Good variable names which should always be accepted, separated by a comma +good-names=i,j,k,ex,Run,_ + +# Bad variable names which should always be refused, separated by a comma +bad-names=foo,bar,baz,toto,tutu,tata + +# Regular expression which should only match functions or classes name which do +# not require a docstring +no-docstring-rgx=__.*__ + + +[FORMAT] + +# Maximum number of characters on a single line. +max-line-length=125 + +# Maximum number of lines in a module +max-module-lines=1000 + +# String used as indentation unit. This is usually " " (4 spaces) or "\t" (1 +# tab). +indent-string=' ' + + +[MISCELLANEOUS] + +# List of note tags to take in consideration, separated by a comma. +notes=FIXME,XXX,TODO + + +[SIMILARITIES] + +# Minimum lines number of a similarity. +min-similarity-lines=4 + +# Ignore comments when computing similarities. +ignore-comments=yes + +# Ignore docstrings when computing similarities. +ignore-docstrings=yes + + +[TYPECHECK] + +# Tells whether missing members accessed in mixin class should be ignored. A +# mixin class is detected if its name ends with "mixin" (case insensitive). +ignore-mixin-members=yes + +# List of classes names for which member attributes should not be checked +# (useful for classes with attributes dynamically set). +ignored-classes=SQLObject + +# When zope mode is activated, add a predefined set of Zope acquired attributes +# to generated-members. +zope=no + +# List of members which are set dynamically and missed by pylint inference +# system, and so shouldn't trigger E0201 when accessed. +generated-members=REQUEST,acl_users,aq_parent + + +[VARIABLES] + +# Tells whether we should check for unused import in __init__ files. +init-import=no + +# A regular expression matching the beginning of the name of dummy variables +# (i.e. not used). +dummy-variables-rgx=_|dummy + +# List of additional names supposed to be defined in builtins. Remember that +# you should avoid to define new builtins when possible. +additional-builtins= + + +[CLASSES] + +# List of interface methods to ignore, separated by a comma. This is used for +# instance to not check methods defines in Zope's Interface base class. +ignore-iface-methods=isImplementedBy,deferred,extends,names,namesAndDescriptions,queryDescriptionFor,getBases,getDescriptionFor,getDoc,getName,getTaggedValue,getTaggedValueTags,isEqualOrExtendedBy,setTaggedValue,isImplementedByInstancesOf,adaptWith,is_implemented_by + +# List of method names used to declare (i.e. assign) instance attributes. +defining-attr-methods=__init__,__new__,setUp + + +[DESIGN] + +# Maximum number of arguments for function / method +max-args=5 + +# Argument names that match this expression will be ignored. Default to name +# with leading underscore +ignored-argument-names=_.* + +# Maximum number of locals for function / method body +max-locals=15 + +# Maximum number of return / yield for function / method body +max-returns=6 + +# Maximum number of branch for function / method body +max-branchs=12 + +# Maximum number of statements in function / method body +max-statements=50 + +# Maximum number of parents for a class (see R0901). +max-parents=7 + +# Maximum number of attributes for a class (see R0902). +max-attributes=7 + +# Minimum number of public methods for a class (see R0903). +min-public-methods=2 + +# Maximum number of public methods for a class (see R0904). +max-public-methods=20 + + +[IMPORTS] + +# Deprecated modules which should not be used, separated by a comma +deprecated-modules=regsub,string,TERMIOS,Bastion,rexec + +# Create a graph of every (i.e. internal and external) dependencies in the +# given file (report RP0402 must not be disabled) +import-graph= + +# Create a graph of external dependencies in the given file (report RP0402 must +# not be disabled) +ext-import-graph= + +# Create a graph of internal dependencies in the given file (report RP0402 must +# not be disabled) +int-import-graph= diff --git a/qsim/messaging.py b/qsim/messaging.py index 5b512b6a..2e6e50cd 100644 --- a/qsim/messaging.py +++ b/qsim/messaging.py @@ -5,7 +5,7 @@ import json import uuid import zmq -import util as qutil +import qsim.util as qutil class ParallelBuffer(object): """ holds several queues of events by key, allows retrieval in date order @@ -20,13 +20,16 @@ class ParallelBuffer(object): self.data_buffer[key] = [] def __len__(self): + """buffer's length is same as internal map holding separate sorted arrays of events keyed by source id""" return len(self.data_buffer) - def append(self, key, value): - self.data_buffer[key].append(value) + def append(self, source_id, value): + """add an event to the buffer for the source specified by source_id""" + self.data_buffer[source_id].append(value) self.received_count += 1 def next(self): + """Get the next message in chronological order""" if(not(self.is_full() or self.draining)): return @@ -43,12 +46,14 @@ class ParallelBuffer(object): return earliest.pop(0) def is_full(self): + """indicates whether the buffer has messages in buffer for all un-DONE sources""" for source, events in self.data_buffer.iteritems(): if (len(events) == 0): return False return True def pending_messages(self): + """""" total = 0 for source, events in self.data_buffer.iteritems(): total += len(events) diff --git a/qsim/test/test_messaging.py b/qsim/test/test_messaging.py index 6636812c..7e2e794a 100644 --- a/qsim/test/test_messaging.py +++ b/qsim/test/test_messaging.py @@ -1,7 +1,9 @@ +""" +Test suite for the messaging infrastructure of QSim. +""" +#don't worry about excessive public methods pylint: disable=R0904 + import unittest2 as unittest -import zmq -import logging -import tornado import multiprocessing from qsim.simulator.feed import DataFeed @@ -12,9 +14,12 @@ import qsim.util as qutil from qsim.test.client import TestClient -class MessagingTestCase(unittest.TestCase): +class MessagingTestCase(unittest.TestCase): + """Tests the message passing: datasources -> feed -> transforms -> merge -> client""" def setUp(self): + """generate some config objects for the datafeed, sources, and transforms.""" + qutil.configure_logging() qutil.logger.info("testing...") self.total_data_count = 800 @@ -25,9 +30,12 @@ class MessagingTestCase(unittest.TestCase): self.config = {} self.config['name'] = '**merged feed**' - self.config['transforms'] = [{'name':'mavg1', 'class':'MovingAverage', 'hours':1},{'name':'mavg2', 'class':'MovingAverage', 'hours':2}] + self.config['transforms'] = [{'name':'mavg1', 'class':'MovingAverage', 'hours':1}, + {'name':'mavg2', 'class':'MovingAverage', 'hours':2}] - def test_client(self): + def test_client(self): + """directly connect the test client to the feed, using two random data sources""" + #subscribe a client to the multiplexed feed client = TestClient(self.feed, self.feed.feed_address) @@ -36,11 +44,18 @@ class MessagingTestCase(unittest.TestCase): client.run() - self.assertEqual(self.feed.data_buffer.pending_messages(), 0, "The feed should be drained of all messages, found {n} remaining.".format(n=self.feed.data_buffer.pending_messages())) - self.assertEqual(self.total_data_count, client.received_count, "The client should have received ({n}) the same number of messages as the feed sent ({m}).".format(n=client.received_count, m=self.total_data_count)) + self.assertEqual(self.feed.data_buffer.pending_messages(), 0, + "The feed should be drained of all messages, found {n} remaining." + .format(n=self.feed.data_buffer.pending_messages())) + self.assertEqual(self.total_data_count, client.received_count, + "The client should have received ({n}) the same number of messages as the feed sent ({m})." + .format(n=client.received_count, m=self.total_data_count)) def dtest_moving_average_to_client(self): + """2 datasources -> feed -> moving average transform -> testclient + verify message count at client.""" + mavg = MovingAverage(self.feed, self.config['transforms'][0], result_address="tcp://127.0.0.1:20202") mavg_proc = multiprocessing.Process(target=mavg.run) mavg_proc.start() @@ -52,9 +67,14 @@ class MessagingTestCase(unittest.TestCase): client.run() self.assertEqual(self.feed.data_buffer.pending_messages(), 0, "The feed should be drained of all messages.") - self.assertEqual(self.total_data_count, client.received_count, "The client should have received the same number of messages as the feed sent.") + self.assertEqual(self.total_data_count, client.received_count, + "The client should have received the same number of messages as the feed sent.") def dtest_merged_to_client(self): + """ + 2 datasources -> feed -> 2 moving average transforms -> transform merge -> testclient + verify message count at client. + """ merger = MergedTransformsFeed(self.feed, self.config) merger_proc = multiprocessing.Process(target=merger.run) merger_proc.start() @@ -66,5 +86,6 @@ class MessagingTestCase(unittest.TestCase): client.run() self.assertEqual(self.feed.data_buffer.pending_messages(), 0, "The feed should be drained of all messages.") - self.assertEqual(self.total_data_count, client.received_count, "The client should have received the same number of messages as the feed sent.") + self.assertEqual(self.total_data_count, client.received_count, + "The client should have received the same number of messages as the feed sent.") diff --git a/sloccount.sc b/sloccount.sc new file mode 100644 index 00000000..e69de29b