def test_pca_logistic2():
"""
According to the PCA first 3 component test, the selected index:
3,8,5,9,7,10,2,1,6,0,4
0-10
:return:
"""
print('Submission added test full')
b_time = datetime.datetime.now()
print('Begining reading data')
DATA_TRAIN_PATH = get_filepath('train')
y, tX, ids = load_csv_data(DATA_TRAIN_PATH)
print("Finish loading in {s} seconds".format(s=(datetime.datetime.now() -
b_time).total_seconds()))
data, x_mean, x_std = standardize(tX)
print("test bias")
test_bias(y)
nb_pc = 5
print("test the PCA with {} elements".format(nb_pc))
pcs, pc_data = pca_transform(data, nb_pc, concatenate=False)
print("get interactions")
interaction = interactions(data, range(0, 10))
interaction, _, _ = standardize(interaction)
print("select first 10 data entry with pc data")
data = np.c_[data[:, 0:10], pc_data]
data = np.c_[data, interaction]
# Begin the least square sgd
e_time = datetime.datetime.now()
print("Finish data reading in {s} seconds".format(
s=(e_time - b_time).total_seconds()))
# logistic = LogisticRegression((y, tX))
logistic = LogisticRegression((y, data),
regularizer="Lasso",
regularizer_p=0.)
# result = logistic.train(lr=0.1, batch_size=32, max_iters=6000)
result = logistic.cross_validation(4, [0.5],
'regularizer_p',
lr=0.1,
batch_size=32,
max_iters=1000,
early_stop=1000,
skip=True)
weight = result[0]
_, test_x, test_ids = load_test_data(clean=False)
test_data, x_mean, x_std = standardize(test_x)
pcs, pc_data = pca_transform(test_data, nb_pc, concatenate=False)
print("get interactions")
interaction = interactions(test_data, range(0, 10))
interaction, _, _ = standardize(interaction)
print("select first 10 data entry with pc data")
test_data = np.c_[test_data[:, 0:10], pc_data]
test_data = np.c_[test_data, interaction]
y_pred = []
for w in weight:
_y_pred = logistic.__call__(test_data, w)
y_pred.append(_y_pred)
y_pred = np.average(y_pred, axis=0)
y_pred[np.where(y_pred <= 0.5)] = -1
y_pred[np.where(y_pred > 0.5)] = 1
output_path = get_dataset_dir() + \
'/submission/pca_test{}.csv'.format(
datetime.datetime.now().__str__())
create_csv_submission(test_ids, y_pred, output_path)
def test_final():
b_time = datetime.datetime.now()
print('Begining reading data')
DATA_TRAIN_PATH = get_filepath('train')
y, tX, ids = load_csv_data(DATA_TRAIN_PATH)
print("Finish loading in {s} seconds".format(s=(datetime.datetime.now() -
b_time).total_seconds()))
data, _, _ = standardize(tX)
nb_pc = 5
print("test the PCA with {} elements".format(nb_pc))
pcs, pc_data = pca_transform(data, nb_pc, concatenate=False)
print("get interactions")
interaction = interactions(data, range(0, 10))
interaction, _, _ = standardize(interaction)
print("select first 10 data entry with pc data")
data = np.c_[data[:, 0:10], pc_data]
data = np.c_[data, interaction]
# Begin the least square sgd
e_time = datetime.datetime.now()
print("Finish data reading in {s} seconds".format(
s=(e_time - b_time).total_seconds()))
# train, valid = split_train_valid(0.8, data, labels=y)
logistic = LogisticRegression((y, data),
regularizer='Lasso',
regularizer_p=0.)
result = logistic.cross_validation(4, [0.],
'regularizer_p',
lr=0.1,
batch_size=32,
max_iters=1200,
early_stop=400)
weight = result[0]
print("loading the test set")
_, test_data, test_ids = load_test_data(clean=False)
# Feature transform
data, _, _ = standardize(test_data)
nb_pc = 5
print("test the PCA with {} elements".format(nb_pc))
pcs, pc_data = pca_transform(data, nb_pc, concatenate=False)
print("get interactions")
interaction = interactions(data, range(0, 10))
interaction, _, _ = standardize(interaction)
print("select first 10 data entry with pc data")
data = np.c_[data[:, 0:10], pc_data]
data = np.c_[data, interaction]
# Begin the least square sgd
e_time = datetime.datetime.now()
print("Finish data reading in {s} seconds".format(
s=(e_time - b_time).total_seconds()))
y_pred = []
for w in weight:
_y_pred = logistic.__call__(data, w)
y_pred += _y_pred
y_pred = np.average(y_pred)
y_pred[np.where(y_pred <= 0.5)] = -1
y_pred[np.where(y_pred > 0.5)] = 1
output_path = get_dataset_dir() + '/second_submission.csv'
create_csv_submission(test_ids, y_pred, output_path)
