def extract_train_features():
start = time.time()
features = feature_extractor()
header = []
for h in features.features:
header.append(h[0])
print("Reading in the training data")
X = data_io.read_train_pairs()
y = data_io.read_train_target()
#X = X.iloc[1:7]
#y = y.iloc[1:7]
print("Extracting features: " + str(X.shape))
extracted = features.fit_transform(X, y,type_map = data_io.read_train_info());
elapsed = float(time.time() - start)
print("Features extracted in " + str(elapsed/60.0) + " Minutes")
print ("Saving features")
X = pd.DataFrame(extracted, index = X.index)
X.columns = header
data_io.save_train_features(X, y.Target)
return X
def extract_train_features():
start = time.time()
features = feature_extractor()
header = []
for h in features.features:
header.append(h[0])
print("Reading in the training data")
X = data_io.read_train_pairs()
y = data_io.read_train_target()
#X = X.iloc[1:7]
#y = y.iloc[1:7]
print("Extracting features: " + str(X.shape))
extracted = features.fit_transform(X,
y,
type_map=data_io.read_train_info())
elapsed = float(time.time() - start)
print("Features extracted in " + str(elapsed / 60.0) + " Minutes")
print("Saving features")
X = pd.DataFrame(extracted, index=X.index)
X.columns = header
data_io.save_train_features(X, y.Target)
return X
def main():
y = data_io.read_train_target()
X = data_io.load_train_features()
if(type(X) == type(None)):
print("No feature file found!")
exit(1)
X_old = data_io.load_features("./Models/old_csv/features_train_en_python.csv")
print X.shape
X = X_old.join(X)
print X.shape
#print X
data_io.save_train_features(X,y)
X = data_io.load_valid_features()
X_old = data_io.load_features("./Models/old_csv/features_valid_en_python.csv")
print X.shape
X = X_old.join(X)
print X.shape
data_io.save_valid_features(X)
def main():
y = data_io.read_train_target()
X = data_io.load_train_features()
if (type(X) == type(None)):
print("No feature file found!")
exit(1)
X_old = data_io.load_features(
"./Models/old_csv/features_train_en_python.csv")
print X.shape
X = X_old.join(X)
print X.shape
#print X
data_io.save_train_features(X, y)
X = data_io.load_valid_features()
X_old = data_io.load_features(
"./Models/old_csv/features_valid_en_python.csv")
print X.shape
X = X_old.join(X)
print X.shape
data_io.save_valid_features(X)
srch_length_of_stay_features.SrchLengthOfStayFeatures(self.X),
srch_booking_window_features.SrchBookingWindowFeatures(self.X),
]
return map(self.transformer, feature_list)
if __name__ == "__main__":
parser = argparse.ArgumentParser(description="Generate features using train/test data")
parser.add_argument("--test", action="store_true", default=False, help="Weather to use test data", required=False)
result = parser.parse_args()
if result.test:
print("Reading test data")
data = data_io.read_test()
else:
print("Reading training data")
data = data_io.read_train()
fm = FeatureExtractor(data)
derived_features = fm.feature_extractor()
data.fillna(0, inplace=True)
data = pandas.concat([data] + derived_features, axis=1)
if result.test:
data_io.save_test_features(data)
else:
data_io.save_train_features(data)
