if __name__ == '__main__':
train_df, test_df = fe.read_df()
sub_df = pd.read_csv('data/sample_submit.csv', header=None)
sub_df.iloc[:, 1] = np.zeros(len(sub_df))
train_df = preprocess(train_df)
test_df = preprocess(test_df)
features = [
'duration', 'goal_min', 'goal_max',
'country_encoding', 'category1_encoding', 'category2_encoding'
]
target = 'state'
cv = 10
train_dfs, valid_dfs, test_dfs = training.cv(train_df, cv)
scores = list()
params = None
tune = True
name = 'target_encoding'
for cv_idx in range(cv):
'prepare'
x_train, y_train = train_dfs[cv_idx][features], train_dfs[cv_idx][target]
x_valid, y_valid = valid_dfs[cv_idx][features], valid_dfs[cv_idx][target]
x_test, y_test = test_dfs[cv_idx][features], test_dfs[cv_idx][target]
# add feature from baseline
x_train, x_valid, x_test, x_sub = add_group_feature(x_train, x_valid, x_test, test_df[features], y_train)
lgb_train, lgb_valid = lgb.Dataset(x_train, y_train, categorical_feature=[3, 4, 5], free_raw_data=False), lgb.Dataset(x_valid, y_valid, categorical_feature=[3, 4, 5], free_raw_data=False)
# train_df = preprocess(train_df)
train_feature = fe.bert_feature(train_df)
train_feature['state'] = train_df.state
test_feature = fe.bert_feature(test_df)
# test_df = preprocess(test_df)
# features = [
# 'html_content'
# ]
features = list(test_feature.columns)
target = 'state'
print(train_feature.shape, test_feature.shape)
cv = 10
train_dfs, valid_dfs, test_dfs = training.cv(train_feature, cv)
scores = list()
params = None
tune = True
name = 'bert_feature'
for cv_idx in range(cv):
'prepare'
x_train, y_train = train_dfs[cv_idx][features], train_dfs[cv_idx][target]
x_valid, y_valid = valid_dfs[cv_idx][features], valid_dfs[cv_idx][target]
x_test, y_test = test_dfs[cv_idx][features], test_dfs[cv_idx][target]
lgb_train, lgb_valid = lgb.Dataset(x_train, y_train, free_raw_data=False), lgb.Dataset(x_valid, y_valid, free_raw_data=False)
'train'
if tune:
params = training.tuning(lgb_train, lgb_valid, 100)