def generateStats(filename, statsInfo, maxSamples = None, filters=[], cache=True):
"""Generate requested statistics for a dataset and cache to a file.
If filename is None, then don't cache to a file"""
# Sanity checking
if not isinstance(statsInfo, dict):
raise RuntimeError("statsInfo must be a dict -- "
"found '%s' instead" % type(statsInfo))
filename = findDataset(filename)
if cache:
statsFilename = getStatsFilename(filename, statsInfo, filters)
# Use cached stats if found AND if it has the right data
if os.path.exists(statsFilename):
try:
r = pickle.load(open(statsFilename, "rb"))
except:
# Ok to ignore errors -- we will just re-generate the file
print "Warning: unable to load stats for %s -- " \
"will regenerate" % filename
r = dict()
requestedKeys = set([s for s in statsInfo])
availableKeys = set(r.keys())
unavailableKeys = requestedKeys.difference(availableKeys)
if len(unavailableKeys ) == 0:
return r
else:
print "generateStats: re-generating stats file %s because " \
"keys %s are not available" % \
(filename, str(unavailableKeys))
os.remove(filename)
print "Generating statistics for file '%s' with filters '%s'" % (filename, filters)
sensor = RecordSensor()
sensor.dataSource = FileRecordStream(filename)
sensor.preEncodingFilters = filters
# Convert collector description to collector object
stats = []
for field in statsInfo:
# field = key from statsInfo
if statsInfo[field] == "number":
# This wants a field name e.g. consumption and the field type as the value
statsInfo[field] = NumberStatsCollector()
elif statsInfo[field] == "category":
statsInfo[field] = CategoryStatsCollector()
else:
raise RuntimeError("Unknown stats type '%s' for field '%s'" % (statsInfo[field], field))
# Now collect the stats
if maxSamples is None:
maxSamples = 500000
for i in xrange(maxSamples):
try:
record = sensor.getNextRecord()
except StopIteration:
break
for (name, collector) in statsInfo.items():
collector.add(record[name])
del sensor
# Assemble the results and return
r = dict()
for (field, collector) in statsInfo.items():
stats = collector.getStats()
if field not in r:
r[field] = stats
else:
r[field].update(stats)
if cache:
f = open(statsFilename, "wb")
pickle.dump(r, f)
f.close()
# caller may need to know name of cached file
r["_filename"] = statsFilename
return r
def generateStats(filename, statsInfo, maxSamples = None, filters=[], cache=True):
"""Generate requested statistics for a dataset and cache to a file.
If filename is None, then don't cache to a file"""
# Sanity checking
if not isinstance(statsInfo, dict):
raise RuntimeError("statsInfo must be a dict -- "
"found '%s' instead" % type(statsInfo))
filename = findDataset(filename)
if cache:
statsFilename = getStatsFilename(filename, statsInfo, filters)
# Use cached stats if found AND if it has the right data
if os.path.exists(statsFilename):
try:
r = pickle.load(open(statsFilename, "rb"))
except:
# Ok to ignore errors -- we will just re-generate the file
print "Warning: unable to load stats for %s -- " \
"will regenerate" % filename
r = dict()
requestedKeys = set([s for s in statsInfo])
availableKeys = set(r.keys())
unavailableKeys = requestedKeys.difference(availableKeys)
if len(unavailableKeys ) == 0:
return r
else:
print "generateStats: re-generating stats file %s because " \
"keys %s are not available" % \
(filename, str(unavailableKeys))
os.remove(filename)
print "Generating statistics for file '%s' with filters '%s'" % (filename, filters)
sensor = RecordSensor()
sensor.dataSource = FileRecordStream(filename)
sensor.preEncodingFilters = filters
# Convert collector description to collector object
stats = []
for field in statsInfo:
# field = key from statsInfo
if statsInfo[field] == "number":
# This wants a field name e.g. consumption and the field type as the value
statsInfo[field] = NumberStatsCollector()
elif statsInfo[field] == "category":
statsInfo[field] = CategoryStatsCollector()
else:
raise RuntimeError("Unknown stats type '%s' for field '%s'" % (statsInfo[field], field))
# Now collect the stats
if maxSamples is None:
maxSamples = 500000
for i in xrange(maxSamples):
try:
record = sensor.getNextRecord()
except StopIteration:
break
for (name, collector) in statsInfo.items():
collector.add(record[name])
del sensor
# Assemble the results and return
r = dict()
for (field, collector) in statsInfo.items():
stats = collector.getStats()
if field not in r:
r[field] = stats
else:
r[field].update(stats)
if cache:
f = open(statsFilename, "wb")
pickle.dump(r, f)
f.close()
# caller may need to know name of cached file
r["_filename"] = statsFilename
return r
def testDeltaFilter(self):
"""
data looks like: should generate deltas
"t" "s" "dt" "ds"
t 10 X
t+1s 20 1s 10
t+1d 50 86399 30
r t+1d+1s 60 X
r+1d+3s 65 2s 5
"""
r = RecordSensor()
filename = findDataset("extra/qa/delta.csv")
datasource = FileRecordStream(filename)
r.dataSource = datasource
n = 50
encoder = MultiEncoder({
'blah':
dict(fieldname="s",
type='ScalarEncoder',
n=n,
w=11,
minval=0,
maxval=100)
})
r.encoder = encoder
# Test #1 -- no deltas
# Make sure we get a reset when the gym changes
resetOut = numpy.zeros((1, ), dtype='float')
sequenceIdOut = numpy.zeros((1, ), dtype='float')
dataOut = numpy.zeros((n, ), dtype='float')
sourceOut = numpy.zeros((1, ), dtype='float')
categoryOut = numpy.zeros((1, ), dtype='float')
outputs = dict(resetOut=resetOut,
sourceOut=sourceOut,
sequenceIdOut=sequenceIdOut,
dataOut=dataOut,
categoryOut=categoryOut)
inputs = dict()
r.verbosity = 0
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(
lr['t'],
datetime(year=2011, month=2, day=24, hour=16, minute=8, second=0))
self.assertEqual(lr['s'], 10)
self.assertEqual(lr['_reset'], 1)
self.assertTrue('dt' not in lr)
self.assertTrue('ds' not in lr)
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(
lr['t'],
datetime(year=2011, month=2, day=24, hour=16, minute=8, second=1))
self.assertEqual(lr['s'], 20)
self.assertEqual(lr['_reset'], 0)
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(
lr['t'],
datetime(year=2011, month=2, day=25, hour=16, minute=8, second=0))
self.assertEqual(lr['s'], 50)
self.assertEqual(lr['_reset'], 0)
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(
lr['t'],
datetime(year=2011, month=2, day=25, hour=16, minute=8, second=1))
self.assertEqual(lr['s'], 60)
self.assertEqual(lr['_reset'], 1)
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(
lr['t'],
datetime(year=2011, month=2, day=25, hour=16, minute=8, second=3))
self.assertEqual(lr['s'], 65)
self.assertEqual(lr['_reset'], 0)
# Add filters
r.preEncodingFilters = [DeltaFilter("s", "ds"), DeltaFilter("t", "dt")]
r.rewind()
# skip first record, which has a reset
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(
lr['t'],
datetime(year=2011, month=2, day=24, hour=16, minute=8, second=1))
self.assertEqual(lr['s'], 20)
self.assertEqual(lr['_reset'],
1) # this record should have a reset since
# it is first of a sequence
self.assertEqual(lr['dt'], 1)
self.assertEqual(lr['ds'], 10)
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(
lr['t'],
datetime(year=2011, month=2, day=25, hour=16, minute=8, second=0))
self.assertEqual(lr['s'], 50)
self.assertEqual(lr['_reset'], 0)
self.assertEqual(lr['dt'], 3600 * 24 - 1)
self.assertEqual(lr['ds'], 30)
# next reset record is skipped
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(
lr['t'],
datetime(year=2011, month=2, day=25, hour=16, minute=8, second=3))
self.assertEqual(lr['s'], 65)
self.assertEqual(lr['_reset'], 1)
self.assertEqual(lr['dt'], 2)
self.assertEqual(lr['ds'], 5)
def testDeltaFilter(self):
"""
data looks like: should generate deltas
"t" "s" "dt" "ds"
t 10 X
t+1s 20 1s 10
t+1d 50 86399 30
r t+1d+1s 60 X
r+1d+3s 65 2s 5
"""
r = RecordSensor()
filename = findDataset("extra/qa/delta.csv")
datasource = FileRecordStream(filename)
r.dataSource = datasource
n = 50
encoder = MultiEncoder({'blah': dict(fieldname="s", type='ScalarEncoder',
n=n, w=11, minval=0, maxval=100)})
r.encoder = encoder
# Test #1 -- no deltas
# Make sure we get a reset when the gym changes
resetOut = numpy.zeros((1,), dtype='float')
sequenceIdOut = numpy.zeros((1,), dtype='float')
dataOut = numpy.zeros((n,), dtype='float')
sourceOut = numpy.zeros((1,), dtype='float')
categoryOut = numpy.zeros((1,), dtype='float')
outputs = dict(resetOut=resetOut,
sourceOut = sourceOut,
sequenceIdOut = sequenceIdOut,
dataOut = dataOut,
categoryOut = categoryOut)
inputs = dict()
r.verbosity=0
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(lr['t'], datetime(year=2011, month=2, day=24, hour=16,
minute=8, second=0))
self.assertEqual(lr['s'], 10)
self.assertEqual(lr['_reset'], 1)
self.assertTrue('dt' not in lr)
self.assertTrue('ds' not in lr)
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(lr['t'], datetime(year=2011, month=2, day=24, hour=16,
minute=8, second=1))
self.assertEqual(lr['s'], 20)
self.assertEqual(lr['_reset'], 0)
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(lr['t'], datetime(year=2011, month=2, day=25, hour=16,
minute=8, second=0))
self.assertEqual(lr['s'], 50)
self.assertEqual(lr['_reset'], 0)
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(lr['t'], datetime(year=2011, month=2, day=25, hour=16,
minute=8, second=1))
self.assertEqual(lr['s'], 60)
self.assertEqual(lr['_reset'], 1)
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(lr['t'], datetime(year=2011, month=2, day=25, hour=16,
minute=8, second=3))
self.assertEqual(lr['s'], 65)
self.assertEqual(lr['_reset'], 0)
# Add filters
r.preEncodingFilters = [DeltaFilter("s", "ds"), DeltaFilter("t", "dt")]
r.rewind()
# skip first record, which has a reset
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(lr['t'], datetime(year=2011, month=2, day=24, hour=16,
minute=8, second=1))
self.assertEqual(lr['s'], 20)
self.assertEqual(lr['_reset'], 1) # this record should have a reset since
# it is first of a sequence
self.assertEqual(lr['dt'], 1)
self.assertEqual(lr['ds'], 10)
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(lr['t'], datetime(year=2011, month=2, day=25, hour=16,
minute=8, second=0))
self.assertEqual(lr['s'], 50)
self.assertEqual(lr['_reset'], 0)
self.assertEqual(lr['dt'], 3600 * 24 - 1)
self.assertEqual(lr['ds'], 30)
# next reset record is skipped
r.compute(inputs, outputs)
lr = r.lastRecord
self.assertEqual(lr['t'], datetime(year=2011, month=2, day=25, hour=16,
minute=8, second=3))
self.assertEqual(lr['s'], 65)
self.assertEqual(lr['_reset'], 1)
self.assertEqual(lr['dt'], 2)
self.assertEqual(lr['ds'], 5)