def main(argv):
options, remainder = getopt.getopt(argv, "o:v", ["train_file="])
# Parse the arguments
for opt, arg in options:
if opt == "--train_file":
train_file = arg
# Featurize the train_file:
global templated_data
global y_list
templated_data, y_list = featurize_file(train_file)
# Initialize the sparse weights vector:
global w_vec
w_vec = np.zeros((1, n_features))
# w_vec[0,13] = 1
# w_vec[0,18] = 1
# w_vec[0,7] = 1
# w_vec[0,11] = 1
# w_vec[0,100]=45
# Train:
# train(templated_data, hashed_feature_matrix)
train(1, templated_data)
def main(argv):
options, remainder = getopt.getopt(argv, 'o:v', ['train_file=',])
# Parse the arguments
for opt, arg in options:
if opt == '--train_file':
train_file = arg
# print train_file
# Featurize the train_file:
# templated_data, hashed_feature_matrix = featurize_file(train_file)
global templated_data
global y_list
templated_data, y_list = featurize_file(train_file)
# print templated_data
# print y_list
# exit()
# Initialize the sparse weights vector:
global w_vec
# w_vec = lil_matrix((1,n_features))
# w_vec = np.ones((1,n_features))
# w_vec = np.full((1,n_features),0.1)
w_vec = np.zeros((1,n_features))
# w_vec[0,13] = 1
# w_vec[0,18] = 1
# w_vec[0,7] = 1
# w_vec[0,11] = 1
# print w_vec
# w_vec[0,100]=45
# w_vec = sparse.csr_matrix(w_vec)
# exit()
# Debug:
# Sentence 0, token 1's features
# print templated_data[0][1]['F']
# print templated_data[0][1]
# Sentence 0, token 1's hashed features
# print hashed_feature_matrix
# exit()
# Train:
# train(templated_data, hashed_feature_matrix)
train(templated_data)
exit()
# Train using the SGD:
SGD(5, templated_data)
