def main():
X = data_io.load_train_features()
if (type(X) == type(None)):
print("No feature file found!")
exit(1)
y = data_io.read_train_target()
#min_max_scaler = preprocessing.MinMaxScaler()
#X = min_max_scaler.fit_transform(X)
get_top_features(X, y.Target, 20)
def main():
X = data_io.load_train_features()
if(type(X) == type(None)):
print("No feature file found!")
exit(1)
y = data_io.read_train_target()
#min_max_scaler = preprocessing.MinMaxScaler()
#X = min_max_scaler.fit_transform(X)
get_top_features(X,y.Target,20)
def grid_search():
X = data_io.load_train_features()
if(type(X) == type(None)):
print("No feature file found!")
exit(1)
y = data_io.read_train_target()
tree_depth = [5, 7, 9 , 10, 12, 14]
learning_rate = [0.01, 0.05, 0.1, 0.2]
scorer = Scorer(X,y)
for d in tree_depth:
for l in learning_rate:
r = scorer.score([d,l])
print "Score", d,l,r
def grid_search():
X = data_io.load_train_features()
if (type(X) == type(None)):
print("No feature file found!")
exit(1)
y = data_io.read_train_target()
tree_depth = [5, 7, 9, 10, 12, 14]
learning_rate = [0.01, 0.05, 0.1, 0.2]
scorer = Scorer(X, y)
for d in tree_depth:
for l in learning_rate:
r = scorer.score([d, l])
print "Score", d, l, r
def main():
fp.n_threads = int(data_io.get_json()["feature_extraction_threads"])
print("extracting train data set features")
X = data_io.load_train_features()
if(X is None):
extract_train_features()
else:
print("Feature already extracted!")
print("extracting valid data set features")
X = data_io.load_valid_features()
if(X is None):
extract_valid_features()
else:
print("Feature already extracted!")
def main():
fp.n_threads = int(data_io.get_json()["feature_extraction_threads"])
print("extracting train data set features")
X = data_io.load_train_features()
if (X is None):
extract_train_features()
else:
print("Feature already extracted!")
print("extracting valid data set features")
X = data_io.load_valid_features()
if (X is None):
extract_valid_features()
else:
print("Feature already extracted!")
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)
def main(valid):
X_train = data_io.load_train_features()
X_valid = data_io.load_valid_features()
t_file = merge("train", X_train)
v_file = merge(valid, X_valid)
def main(valid):
X_train = data_io.load_train_features()
X_valid = data_io.load_valid_features()
t_file = merge("train", X_train)
v_file = merge(valid, X_valid)
