def main():
# Read input data
train_df = pd.read_csv('input/train.csv')
test_df = pd.read_csv('input/test.csv')
# This prints out (rows, columns) in each dataframe
print('original train shape: %s' % str(train_df.shape))
print('original test shape: %s' % str(test_df.shape))
train_df, test_df = fillna(train_df, test_df)
train_df, test_df = count_encoding(train_df, test_df, replace=False)
train_df, test_df = target_encoding(train_df, test_df, replace=False)
train_df, test_df = high_diff_corr_pca(train_df, test_df, n_features=5)
train_df, test_df = sum_of_na(train_df, test_df)
train_df, test_df = drop_calc(train_df, test_df)
# This prints out (rows, columns) in each dataframe
print('Train shape: %s' % str(train_df.shape))
print('Test shape: %s' % str(test_df.shape))
params = {
'lambda': 1e-5,
'factor': 6,
'iteration': 100,
'patience': 10,
'eta': 0.2,
'nr_threads': 1,
'seed': 41
}
train_predict(train_df, test_df, params)
def main():
# Read input data
train_df = pd.read_csv('input/train.csv')
test_df = pd.read_csv('input/test.csv')
# This prints out (rows, columns) in each dataframe
print('original train shape: %s' % str(train_df.shape))
print('original test shape: %s' % str(test_df.shape))
# Fill NA
train_df, test_df = fillna(train_df, test_df)
# Count encoding
train_df, test_df = count_encoding(train_df, test_df, replace=False)
# Target encoding
train_df, test_df = target_encoding(train_df, test_df, replace=False)
# Dummy encoding
train_df, test_df = dummy_encoding(train_df, test_df)
# high_diff_corr_pca
train_df, test_df = high_diff_corr_pca(train_df, test_df, n_features=5)
# Sum of NA
train_df, test_df = sum_of_na(train_df, test_df)
# drop calc
train_df, test_df = drop_calc(train_df, test_df)
# This prints out (rows, columns) in each dataframe
print('Train shape: %s' % str(train_df.shape))
print('Test shape: %s' % str(test_df.shape))
params = {
'max_leaf': 1000,
'algorithm': 'RGF',
'loss': 'Log',
'l2': 0.01,
'sl2': 0.01,
'normalize': False,
'min_samples_leaf': 10,
'n_iter': None,
'opt_interval': 100,
'learning_rate': 0.5,
'calc_prob': 'sigmoid',
'n_jobs': -1,
'memory_policy': 'generous',
'verbose': True
}
train_predict(train_df, test_df, params)
def main():
# Read input data
train_df = pd.read_csv('input/train.csv')
test_df = pd.read_csv('input/test.csv')
# This prints out (rows, columns) in each dataframe
print('original train shape: %s' % str(train_df.shape))
print('original test shape: %s' % str(test_df.shape))
train_df, test_df = fillna(train_df, test_df)
train_df, test_df = count_encoding(train_df, test_df, replace=False)
train_df, test_df = target_encoding(train_df, test_df, replace=False)
train_df, test_df = dummy_encoding(train_df, test_df)
train_df, test_df = high_diff_corr_pca(train_df, test_df, n_features=5)
train_df, test_df = sum_of_na(train_df, test_df)
train_df, test_df = drop_calc(train_df, test_df)
# This prints out (rows, columns) in each dataframe
print('Train shape: %s' % str(train_df.shape))
print('Test shape: %s' % str(test_df.shape))
params = {
'bagging_temperature': 1,
'name': 'experiment',
'random_strength': 1,
'has_time': False,
'store_all_simple_ctr': False,
'verbose': True,
'use_best_model': True,
'random_seed': 41,
'thread_count': 2,
'od_type': 'IncToDec',
'od_wait': 20,
'od_pval': 0.01,
'feature_border_type': 'MinEntropy',
'loss_function': 'Logloss',
'rsm': 1,
'l2_leaf_reg': 23,
'depth': 6,
'learning_rate': 0.057,
'iterations': 10000,
'leaf_estimation_method': 'Newton'
}
train_predict(train_df, test_df, params)
def main():
# Read input data
train_df = pd.read_csv('input/train.csv')
test_df = pd.read_csv('input/test.csv')
# This prints out (rows, columns) in each dataframe
print('original train shape: %s' % str(train_df.shape))
print('original test shape: %s' % str(test_df.shape))
train_df, test_df = fillna(train_df, test_df)
train_df, test_df = count_encoding(train_df, test_df, replace=False)
train_df, test_df = target_encoding(train_df, test_df, replace=False)
train_df, test_df = dummy_encoding(train_df, test_df)
train_df, test_df = high_diff_corr_pca(train_df, test_df, n_features=5)
train_df, test_df = sum_of_na(train_df, test_df)
train_df, test_df = drop_calc(train_df, test_df)
l1_models = ['l1_rgf.csv.gz', 'l1_ffm.csv.gz', 'l1_catb.csv.gz']
# This prints out (rows, columns) in each dataframe
print('Train shape: %s' % str(train_df.shape))
print('Test shape: %s' % str(test_df.shape))
params = {
'application': 'binary',
'num_threads': 2,
'boosting': 'gbdt',
'max_bin': 16,
'learning_rate': 0.025,
'num_leaves': 52,
'feature_fraction': 0.45,
'bagging_fraction': 0.75,
'bagging_freq': 16,
'min_data_in_leaf': 740,
'min_child_weight': 2.0
}
train_predict(train_df, test_df, l1_models, params)
def main():
# Read input data
train_df = pd.read_csv('input/train.csv')
test_df = pd.read_csv('input/test.csv')
# This prints out (rows, columns) in each dataframe
print('original train shape: %s' % str(train_df.shape))
print('original test shape: %s' % str(test_df.shape))
train_df, test_df = fillna(train_df, test_df)
train_df, test_df = count_encoding(train_df, test_df, replace=False)
train_df, test_df = target_encoding(train_df, test_df, replace=False)
train_df, test_df = dummy_encoding(train_df, test_df)
train_df, test_df = high_diff_corr_pca(train_df, test_df, n_features=5)
train_df, test_df = sum_of_na(train_df, test_df)
train_df, test_df = drop_calc(train_df, test_df)
# This prints out (rows, columns) in each dataframe
print('Train shape: %s' % str(train_df.shape))
print('Test shape: %s' % str(test_df.shape))
params = {
'booster': 'gbtree',
'objective': 'binary:logistic',
'eval_metric': 'auc',
'seed': 41,
'nthread': 32,
'silent': True,
'eta': 0.025,
'max_depth': 5,
'min_child_weight': 9.15,
'gamma': 0.59,
'subsample': 0.8,
'colsample_bytree': 0.8
}
train_predict(train_df, test_df, params)