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):
valid = self.getValidationDataset()
if f.preprocessedFeatures != []:
intermediate = data_io.read_intermediate_valid()
for i in f.preprocessedFeatures:
valid[i] = intermediate[i]
print "Loading the classifier"
classifier = data_io.load_model()
print "Making predictions"
predictions = classifier.predict(valid)
predictions = predictions.flatten()
print "Writing predictions to file"
data_io.write_submission(predictions)
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)
