def test_data_model():
title = 'complex_full_before_ddl_interactions_full'
print("Base line testing for model " + title)
b_time = datetime.datetime.now()
print('Beginning 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()))
_, test_x, test_ids = load_test_data(clean=False)
data = compose_interactions_for_transforms(tX)
t_data = compose_interactions_for_transforms(test_x)
# Test 1 Ridge 0.1
logistic = LogisticRegression((y, data),
regularizer='Ridge',
regularizer_p=0.1)
weight = logistic.train(lr=0.01,
decay=0.5,
max_iters=2000,
early_stop=1000,
decay_intval=100)
# weight, _, _ = logistic.cross_validation(4, [0.1, 0.5, 0.05], 'regularizer_p', max_iters=2000)
pred_label = predict_labels(weight, t_data)
create_csv_submission(
test_ids, pred_label,
get_dataset_dir() +
'/submission/removed_outlier_{}.csv'.format(title + 'Ridge01'))
# Test 2 Lasso 0.1
logistic = LogisticRegression((y, data),
regularizer='Lasso',
regularizer_p=0.1)
weight = logistic.train(lr=0.01,
decay=0.5,
max_iters=2000,
early_stop=1000,
decay_intval=100)
# weight, _, _ = logistic.cross_validation(4, [0.1, 0.5, 0.05], 'regularizer_p', max_iters=2000)
pred_label = predict_labels(weight, t_data)
create_csv_submission(
test_ids, pred_label,
get_dataset_dir() +
'/submission/removed_outlier_{}.csv'.format(title + '-Lasso0.1'))
# Test 3 No penalized
logistic = LogisticRegression((y, data))
weight = logistic.train(lr=0.01,
decay=0.5,
max_iters=2000,
early_stop=1000)
# weight, _, _ = logistic.cross_validation(4, [0.1, 0.5, 0.05], 'regularizer_p', max_iters=2000)
pred_label = predict_labels(weight, t_data)
create_csv_submission(
test_ids, pred_label,
get_dataset_dir() + '/submission/removed_outlier_{}.csv'.format(title))
def test_draw():
"""
Draw balanced sample, but result worse result.
"""
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)
# 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()))
data, _, _ = compose_complex_features_further(tX,
intercept=True,
interaction=True,
log=True,
sqrt=True,
power=True,
pca=True)
train, valid = draw_balanced_subsample(y, data, trainsize=6000)
# t_data, _, _ = compose_complex_features_further(test_x, intercept=True,
# interaction=True,
# log=True,
# sqrt=True,
# power=True,
# pca=True)
logistic = LogisticRegression(train=train,
validation=valid,
regularizer='Lasso',
regularizer_p=0.5)
result = logistic.train(lr=0.01, decay=0.5, early_stop=400, max_iters=2000)
print(result)
def test_logistic():
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()))
tX = standardize(tX)
# 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[0]),
regularizer="Lasso",
regularizer_p=0.1)
result = logistic.train(lr=0.05, batch_size=128, max_iters=1000)
print(result)
def test_baseline():
print("base line testing")
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 = baseline_logistic(tX)
logistic = LogisticRegression((y, data))
weight = logistic.train(lr=0.01, decay=1)
plot = True
if plot:
from plots import cross_validation_visualization
_, test_x, test_ids = load_test_data(clean=False)
t_data = baseline_logistic(test_x)
pred_label = predict_labels(weight, t_data)
create_csv_submission(
test_ids, pred_label,
get_dataset_dir() + '/submission/logistic_baseline.csv')
labels = unpickle('../data/meta')
interesting_coarse_labels = [0, 1] # Aquatic mammals and Fish
train = []
y = []
test = []
y_test = []
for i in range(len(train_data[b'coarse_labels'])):
for j in interesting_coarse_labels:
if train_data[b'coarse_labels'][i] == j:
train.append(train_data[b'data'][i])
y.append(j)
break
for i in range(len(test_data[b'coarse_labels'])):
for j in interesting_coarse_labels:
if test_data[b'coarse_labels'][i] == j:
test.append(test_data[b'data'][i])
y_test.append(j)
break
train = np.array(train)
y = np.array(y)
test = np.array(test)
y_test = np.array(y_test)
weight_matrix, losses = LogisticRegression.train(train, y,
iteration=1, learning_rate=0.1)
LogisticRegression.accuracy(weight_matrix, test, y_test)
