def extractFeatures(self, train_data, test_data):
# Construct Feature Extractor
fe = FeatureExtractor()
fe.buildVectorizer(train_data, self.config['featureKwargs'])
# Make feature path if it doesnt exist
if not os.path.exists(self.feature_path):
os.mkdir(self.feature_path)
# Check if train vectors already exist
if os.path.exists(os.path.join(self.feature_path, 'train_vectors.npz')):
# If it does, load them
train_vectors = load_npz(os.path.join(self.feature_path, 'train_vectors.npz'))
else:
# Make the train vectors
train_vectors = [fe.process(feature, train_data) for feature in self.config['features']]
if len(train_vectors) > 1:
train_vectors = numpy.concatenate(train_vectors, axis=1)
else:
train_vectors = train_vectors[0]
# Save the train vectors
save_npz(os.path.join(self.feature_path, 'train_vectors.npz'), train_vectors)
# Check if test vectors already exist
if os.path.exists(os.path.join(self.feature_path, 'test_vectors.npz')):
# If it does, load them
test_vectors = load_npz(os.path.join(self.feature_path, 'test_vectors.npz'))
else:
# Make the test vectors
test_vectors = [fe.process(feature, test_data) for feature in self.config['features']]
if len(test_vectors) > 1:
test_vectors = numpy.concatenate(test_vectors, axis=1)
else:
test_vectors = test_vectors[0]
# Save the test vectors
save_npz(os.path.join(self.feature_path, 'test_vectors.npz'), test_vectors)
return train_vectors, test_vectors
def extractFeatures(self, train_data, test_data):
#Extract Features and pass them as concatenated arrays
fe = FeatureExtractor(self.config['features'],
self.config['featurePath'],
self.config['featureKwargs'])
fe.buildVectorizer(train_data)
#Check for ALready done work
if path.exists(self.config['featurePath'] + "train_data.pickle"):
print("here's the error?")
with open(self.config['featurePath'] + "train_data.pickle",
"rb") as file:
train_vectors = pickle.load(file)
else:
train_vectors = fe.process(train_data)
with open(self.config['featurePath'] + "train_data.pickle",
"wb+") as file:
pickle.dump(train_vectors, file)
if len(train_vectors) > 1:
print("took option A")
train_vectors = numpy.concatenate(train_vectors, axis=1)
else:
print("took option B")
train_vectors = train_vectors[0]
print(train_vectors.shape)
print(train_vectors[1, :])
#Check for ALready done work
if path.exists(self.config['featurePath'] + "test_data.pickle"):
with open(self.config['featurePath'] + "test_data.pickle",
"rb") as file:
test_vectors = pickle.load(file)
else:
test_vectors = fe.process(test_data)
with open(self.config['featurePath'] + "test_data.pickle",
"wb+") as file:
pickle.dump(test_vectors, file)
if len(test_vectors) > 1:
test_vectors = numpy.concatenate(test_vectors, axis=1)
else:
test_vectors = test_vectors[0]
return train_vectors.toarray(), test_vectors.toarray()
