def run(self):
print "Reading in the data"
dataset = self.getDataset()
featureNames = [i[0] for i in self.dataToWrite]
if self.ignoreFeatures != []:
if self.getTrain:
intermediate = data_io.read_intermediate_train()
else:
intermediate = data_io.read_intermediate_valid()
for i in self.ignoreFeatures:
dataset[i] = intermediate[i]
for element in self.dataToWrite:
if element[0] in self.ignoreFeatures:
element[1] = element[0]
element[2] = f.SimpleTransform(transformer=f.ff.identity)
print "Extracting features and transforming"
featureMapper = f.FeatureMapper(self.dataToWrite)
transformedDataset = featureMapper.transform(dataset)
print "Saving the data"
if self.getTrain:
data_io.write_intermediate_train(featureNames, transformedDataset,
dataset)
else:
data_io.write_intermediate_valid(featureNames, transformedDataset,
dataset)
def run(self):
print "Reading in the data"
dataset = self.getDataset()
featureNames = [i[0] for i in self.dataToWrite]
if self.ignoreFeatures != []:
if self.getTrain:
intermediate = data_io.read_intermediate_train()
else:
intermediate = data_io.read_intermediate_valid()
for i in self.ignoreFeatures:
dataset[i] = intermediate[i]
for element in self.dataToWrite:
if element[0] in self.ignoreFeatures:
element[1] = element[0]
element[2] = f.SimpleTransform(transformer=f.ff.identity)
print "Extracting features and transforming"
featureMapper = f.FeatureMapper(self.dataToWrite)
transformedDataset = featureMapper.transform(dataset)
print "Saving the data"
if self.getTrain:
data_io.write_intermediate_train(featureNames, transformedDataset, dataset)
else:
data_io.write_intermediate_valid(featureNames, transformedDataset, dataset)
def run(self):
features = f.features
train = self.getTrainingDataset()
print "Reading preprocessed features"
if f.preprocessedFeatures != []:
intermediate = data_io.read_intermediate_train()
for i in f.preprocessedFeatures:
train[i] = intermediate[i]
for i in features:
if i[0] in f.preprocessedFeatures:
i[1] = i[0]
i[2] = f.SimpleTransform(transformer=f.ff.identity)
print "Reading targets"
target = data_io.read_train_target()
print "Extracting features and training model"
classifier = self.getPipeline(features)
if self.directionForward:
finalTarget = [x * (x + 1) / 2 for x in target.Target]
else:
finalTarget = [-x * (x - 1) / 2 for x in target.Target]
classifier.fit(train, finalTarget)
print classifier.steps[-1][1].feature_importances_
print "Saving the classifier"
data_io.save_model(classifier)
def run(self):
features = f.features
train = self.getTrainingDataset()
print "Reading preprocessed features"
if f.preprocessedFeatures != []:
intermediate = data_io.read_intermediate_train()
for i in f.preprocessedFeatures:
train[i] = intermediate[i]
for i in features:
if i[0] in f.preprocessedFeatures:
i[1] = i[0]
i[2] = f.SimpleTransform(transformer=f.ff.identity)
print "Reading targets"
target = data_io.read_train_target()
print "Extracting features and training model"
classifier = self.getPipeline(features)
if self.directionForward:
finalTarget = [x * (x + 1) / 2 for x in target.Target]
else:
finalTarget = [-x * (x - 1) / 2 for x in target.Target]
classifier.fit(train, finalTarget)
print classifier.steps[-1][1].feature_importances_
print "Saving the classifier"
data_io.save_model(classifier)