class FluentWrapper(object):
""" Wraps nupic.fluent Model """
def __init__(self, dataPath):
"""
initializes nupic.fluent model with given sample data
:param str dataPath: Path to sample data file.
Must be a CSV file having 'ID and 'Sample' columns
"""
g_log.info("Initialize nupic.fluent")
# Initialize nupic.fluent model runner
self._fluent = FluentRunner(dataPath=dataPath,
resultsDir="",
experimentName="imbu_fingerprints",
load=False,
modelName="ClassificationModelFingerprint",
modelModuleName="fluent.models.classify_fingerprint",
numClasses=1, # must be >0 to go through training
plots=0,
orderedSplit=False,
trainSizes=[],
verbosity=0)
# Train model with given sample data
self._fluent.initModel()
self._fluent.setupData()
self._fluent.trainSize = len(self._fluent.samples)
self._fluent.encodeSamples()
self._fluent.resetModel(0)
for i in range(self._fluent.trainSize):
self._fluent.model.trainModel(i)
def query(self, text):
""" Queries fluent model and returns an ordered list of matching documents.
:param str text: The text to match.
:returns: a sequence of matching samples.
::
[
{"id": "1", "text": "sampleText", "score": "0.75"},
...
]
"""
results = []
if text:
g_log.info("Query model for : %s", text)
sampleIDs, sampleDists = self._fluent.model.queryModel(text, False)
for sID, dist in zip (sampleIDs, sampleDists):
results.append({"id": sID,
"text": self._fluent.dataDict[sID][0],
"score": dist.item()})
return results
class FluentWrapper(object):
""" Wraps nupic.fluent Model """
def __init__(self, dataPath):
"""
initializes nupic.fluent model with given sample data
:param str dataPath: Path to sample data file.
Must be a CSV file having 'ID and 'Sample' columns
"""
g_log.info("Initialize nupic.fluent")
# Initialize nupic.fluent model runner
self._fluent = FluentRunner(
dataPath=dataPath,
resultsDir="",
experimentName="imbu_fingerprints",
load=False,
modelName="ClassificationModelFingerprint",
modelModuleName="fluent.models.classify_fingerprint",
numClasses=1, # must be >0 to go through training
plots=0,
orderedSplit=False,
trainSizes=[],
verbosity=0,
)
# Train model with given sample data
self._fluent.initModel()
self._fluent.setupData()
self._fluent.trainSize = len(self._fluent.samples)
self._fluent.encodeSamples()
self._fluent.resetModel(0)
for i in range(self._fluent.trainSize):
self._fluent.model.trainModel(i)
def query(self, text):
""" Queries fluent model and returns an ordered list of matching documents.
:param str text: The text to match.
:returns: a sequence of matching samples.
::
[
{"id": "1", "text": "sampleText", "score": "0.75"},
...
]
"""
results = []
if text:
g_log.info("Query model for : %s", text)
sampleIDs, sampleDists = self._fluent.model.queryModel(text, False)
for sID, dist in zip(sampleIDs, sampleDists):
results.append({"id": sID, "text": self._fluent.dataDict[sID][0], "score": dist.item()})
return results
def run(args):
start = time.time()
root = os.path.dirname(os.path.realpath(__file__))
resultsDir = os.path.join(root, args.resultsDir)
runner = Runner(dataPath=args.dataPath,
resultsDir=resultsDir,
experimentName=args.experimentName,
load=args.load,
modelName=args.modelName,
modelModuleName=args.modelModuleName,
numClasses=args.numClasses,
plots=args.plots,
orderedSplit=args.orderedSplit,
trainSize=args.trainSize,
verbosity=args.verbosity)
runner.initModel()
print "Reading in data and preprocessing."
dataTime = time.time()
runner.setupData()
print ("Data setup complete; elapsed time is {0:.2f} seconds.\nNow encoding "
"the data".format(time.time() - dataTime))
encodeTime = time.time()
runner.encodeSamples()
print ("Encoding complete; elapsed time is {0:.2f} seconds.\nNow running the "
"experiment.".format(time.time() - encodeTime))
runner.runExperiment()
runner.calculateResults()
runner.save()
print "Experiment complete in {0:.2f} seconds.".format(time.time() - start)
if args.validation:
print "Validating experiment against expected classifications..."
print runner.validateExperiment(args.validation)
