def _sortChunk(records, key, chunkIndex, fields):
"""Sort in memory chunk of records
records - a list of records read from the original dataset
key - a list of indices to sort the records by
chunkIndex - the index of the current chunk
The records contain only the fields requested by the user.
_sortChunk() will write the sorted records to a standard File
named "chunk_<chunk index>.csv" (chunk_0.csv, chunk_1.csv,...).
"""
title(additional='(key=%s, chunkIndex=%d)' % (str(key), chunkIndex))
assert len(records) > 0
# Sort the current records
records.sort(key=itemgetter(*key))
# Write to a chunk file
if chunkIndex is not None:
filename = 'chunk_%d.csv' % chunkIndex
with FileRecordStream(filename, write=True, fields=fields) as o:
for r in records:
o.appendRecord(r)
assert os.path.getsize(filename) > 0
return records
def _step(self): """Run the network for one iteration.""" title() self.runCount = 1 self.experiment.pause = False self._runExperiment() self.pause = True
def onPhaseTeardown(self, exp):
title()
index = exp.position.phase
# Last phase
if index == len(exp.workflow) - 1:
self.done = True
def _step(self):
"""Run the network for one iteration."""
title()
self.runCount = 1
self.experiment.pause = False
self._runExperiment()
self.pause = True
def onPhaseTeardown(self, exp):
title()
index = exp.position.phase
# Last phase
if index == len(exp.workflow) - 1:
self.done = True
def onIter(self, exp, i):
""" """
title(additional='(), self.pause = ' + str(self.pause))
self.iteration += 1
# check if the pause button was clicked
if self.pause:
exp.pause = True
elif self.runCount is not None:
self.runCount -= 1
if self.runCount == 0:
exp.pause = True
runtimelistener.listenersEnabled = exp.pause
def onIter(self, exp, i):
""" """
title(additional='(), self.pause = ' + str(self.pause))
self.iteration += 1
# check if the pause button was clicked
if self.pause:
exp.pause = True
elif self.runCount is not None:
self.runCount -= 1
if self.runCount == 0:
exp.pause = True
runtimelistener.listenersEnabled = exp.pause
def onPhaseSetup(self, exp):
title()
self.iteration = 0
self.phase = self._getPhase(exp)
phase = self.phase[1]
self.iterationCount = phase[0]['iterationCount'] if len(phase) > 0 else 0
if self.pauseAtNextStep and self.pauseAtPhaseSetup:
#if self.pauseAtNextStep:
#from dbgp.client import brk; brk(port=9011)
exp.pause = True
self.pause = True
self.pauseAtPhaseSetup = False
else:
self.pauseAtPhaseSetup = True
def onPhaseSetup(self, exp):
title()
self.iteration = 0
self.phase = self._getPhase(exp)
phase = self.phase[1]
self.iterationCount = phase[0]['iterationCount'] if len(
phase) > 0 else 0
if self.pauseAtNextStep and self.pauseAtPhaseSetup:
#if self.pauseAtNextStep:
#from dbgp.client import brk; brk(port=9011)
exp.pause = True
self.pause = True
self.pauseAtPhaseSetup = False
else:
self.pauseAtPhaseSetup = True
def _mergeFiles(key, chunkCount, outputFile, fields):
"""Merge sorted chunk files into a sorted output file
chunkCount - the number of available chunk files
outputFile the name of the sorted output file
_mergeFiles()
"""
title()
# Open all chun files
files = [FileRecordStream('chunk_%d.csv' % i) for i in range(chunkCount)]
# Open output file
with FileRecordStream(outputFile, write=True, fields=fields) as o:
# Open all chunk files
files = [
FileRecordStream('chunk_%d.csv' % i) for i in range(chunkCount)
]
records = [f.getNextRecord() for f in files]
# This loop will run until all files are exhausted
while not all(r is None for r in records):
# Cleanup None values (files that were exhausted)
indices = [i for i, r in enumerate(records) if r is not None]
records = [records[i] for i in indices]
files = [files[i] for i in indices]
# Find the current record
r = min(records, key=itemgetter(*key))
# Write it to the file
o.appendRecord(r)
# Find the index of file that produced the current record
index = records.index(r)
# Read a new record from the file
records[index] = files[index].getNextRecord()
# Cleanup chunk files
for i, f in enumerate(files):
f.close()
os.remove('chunk_%d.csv' % i)
def _mergeFiles(key, chunkCount, outputFile, fields):
"""Merge sorted chunk files into a sorted output file
chunkCount - the number of available chunk files
outputFile the name of the sorted output file
_mergeFiles()
"""
title()
# Open all chun files
files = [FileRecordStream('chunk_%d.csv' % i) for i in range(chunkCount)]
# Open output file
with FileRecordStream(outputFile, write=True, fields=fields) as o:
# Open all chunk files
files = [FileRecordStream('chunk_%d.csv' % i) for i in range(chunkCount)]
records = [f.getNextRecord() for f in files]
# This loop will run until all files are exhausted
while not all(r is None for r in records):
# Cleanup None values (files that were exhausted)
indices = [i for i,r in enumerate(records) if r is not None]
records = [records[i] for i in indices]
files = [files[i] for i in indices]
# Find the current record
r = min(records, key=itemgetter(*key))
# Write it to the file
o.appendRecord(r)
# Find the index of file that produced the current record
index = records.index(r)
# Read a new record from the file
records[index] = files[index].getNextRecord()
# Cleanup chunk files
for i, f in enumerate(files):
f.close()
os.remove('chunk_%d.csv' % i)
