def main():
global args, DEBUG
args = parser.parse_args()
DEBUG = args.debug
print_debug(DEBUG)
for dataset in ['test', 'train']:
do_dataset(dataset)
def main():
global args, DEBUG, FRAC, PREDICTORS
args = parser.parse_args()
DEBUG = args.debug
FRAC = args.frac
print_debug(DEBUG)
if DEBUG:
storename = '../processed_features_debug{}/{}_debug{}.h5'.format(DEBUG, 'train', DEBUG)
mat_filename = '../processed_features_debug{}/text_feature_kernel.pickle'.format(DEBUG)
else:
storename = '../processed_features/{}.h5'.format('train')
mat_filename = '../processed_features/text_feature_kernel.pickle'
PREDICTORS = get_predictors(storename)
boosting_type_list = ['gbdt','dart']
num_leaves_list = [7,9,31,63]
max_depth_list = [3,4,7,9]
for boosting_type in boosting_type_list:
for i in range(len(num_leaves_list)):
print ('==============================================================')
num_leaves = num_leaves_list[i]
max_depth = max_depth_list[i]
print('num leaves:', num_leaves)
print('max depth:', max_depth)
DO(mat_filename,storename,num_leaves,max_depth,1,boosting_type)
def main():
global args, DEBUG
args = parser.parse_args()
DEBUG = args.debug
print_debug(DEBUG)
for dataset in ['train', 'test']:
do_dataset(dataset)
write_all_feature_to_text()
def main():
global args, DEBUG, FRAC, PREDICTORS, TRAINMODE
args = parser.parse_args()
DEBUG = args.debug
FRAC = args.frac
TRAINMODE = args.trainmode
print_debug(DEBUG)
DO()
def main():
global args, DEBUG, DATASET
args = parser.parse_args()
DATASET = args.dataset
DEBUG = args.debug
print_debug(DEBUG)
if DEBUG:
todir = '../processed_features_debug{}/'.format(DEBUG)
else:
todir = '../processed_features/'
gen_aggregated_kernel(todir, '.pickle')
def main():
global args, DEBUG, FRAC, PREDICTORS, TRAINMODE, PREDICTORS, LOCAL_TUNE_RESULT
args = parser.parse_args()
DEBUG = args.debug
FRAC = args.frac
TRAINMODE = args.trainmode
# OPTION=args.option
print_debug(DEBUG)
if DEBUG:
dir_feature = '../processed_features_debug2/'
else:
dir_feature = '../processed_features/'
# boosting_list = ['gbdt', 'dart']
boosting_list = ['gbdt']
num_leave_list = [7, 9, 15, 31, 63, 128]
max_depth_list = [3, 4, 7, 15, 31, 64]
model_list = []
for i in range(len(num_leave_list)):
num_leave = num_leave_list[i]
max_depth = max_depth_list[i]
for boosting_type in boosting_list:
model_list = model_list + [
'{}_{}_{}'.format(boosting_type, num_leave, max_depth)
]
LOCAL_TUNE_RESULT = pd.DataFrame(
index=model_list,
columns=['running_time', 'num_round', 'train', 'val'])
if DEBUG: print(LOCAL_TUNE_RESULT)
option = 1
is_textadded = True
PREDICTORS = PREDICTORS_BASED
mat_filename = dir_feature + 'text_feature_kernel.pickle'
print_header('Option {}'.format(option))
print('is_textadded {} \n predictors {} \n mat filename {}'.format(
is_textadded, PREDICTORS, mat_filename))
for k in range(len(num_leave_list)):
i = len(num_leave_list) - k - 1
num_leave = num_leave_list[i]
max_depth = max_depth_list[i]
for boosting_type in boosting_list:
DO(option, is_textadded, mat_filename, dir_feature, num_leave,
max_depth, boosting_type)
print_header('FINAL SUMMARY')
print(LOCAL_TUNE_RESULT)
LOCAL_TUNE_RESULT.to_csv('csv/tune_params.csv', index=True)
def main():
global args, DEBUG, FRAC, PREDICTORS, TRAINMODE, OPTION
args = parser.parse_args()
DEBUG = args.debug
FRAC = args.frac
TRAINMODE = args.trainmode
OPTION = args.option
print_debug(DEBUG)
feature_train = get_good_local()
if DEBUG: print(feature_train)
PREDICTORS = PREDICTORS_BASED + feature_train
if DEBUG: print(PREDICTORS)
DO()
def main():
global args, DEBUG, FRAC, PREDICTORS, TRAINMODE, PREDICTORS, LOCAL_VALIDATION_RESULT
args = parser.parse_args()
DEBUG = args.debug
FRAC = args.frac
TRAINMODE = args.trainmode
# OPTION=args.option
print_debug(DEBUG)
done_feature_df = load_csv('csv/forward_selection.csv')
print(done_feature_df)
if DEBUG:
dir_feature = '../processed_features_debug2/'
else:
dir_feature = '../processed_features/'
option = 0
is_textadded = False
PREDICTORS = PREDICTORS_BASED
feature_list = ['base']
files = glob.glob(dir_feature + '*.pickle')
REMOVED_LIST = [
'cat_encode', 'len_feature_kernel', 'text_feature_kernel', 'time'
]
for file in files:
filename = os.path.basename(file)
feature = re.sub('\.pickle$', '', filename)
if is_added(filename, REMOVED_LIST):
feature_list = feature_list + [feature]
LOCAL_VALIDATION_RESULT = pd.DataFrame(
index=feature_list,
columns=['running_time', 'num_round', 'train', 'val', 'diff'])
if DEBUG:
print(feature_list)
print(LOCAL_VALIDATION_RESULT)
for feature in feature_list:
if feature == 'base':
PREDICTORS = PREDICTORS
else:
PREDICTORS = PREDICTORS + [feature]
DO(option, is_textadded, 'abc', dir_feature, 1988, feature)
if feature != 'base':
PREDICTORS.remove(feature)
print_header('FINAL SUMMARY')
print(LOCAL_VALIDATION_RESULT)
LOCAL_VALIDATION_RESULT.to_csv('forward_selection.csv', index=True)
def main():
global args, DEBUG, FRAC, PREDICTORS, TRAINMODE, PREDICTORS, LOCAL_VALIDATION_RESULT
args = parser.parse_args()
DEBUG = args.debug
FRAC = args.frac
TRAINMODE = args.trainmode
# OPTION=args.option
print_debug(DEBUG)
if DEBUG:
dir_feature = '../processed_features_debug2/'
else:
dir_feature = '../processed_features/'
option = 0
is_textadded = False
PREDICTORS = PREDICTORS_BASED
mat_filename = dir_feature + 'text_feature_kernel.pickle'
# seed_list = np.random.randint(2000, size=1000)
random.seed(1992)
seed_array = random.sample(range(0, 10000), 100)
seed_list = []
for seed in seed_array:
seed_list = seed_list + ['seed_' + str(seed)]
LOCAL_VALIDATION_RESULT = pd.DataFrame(index=seed_list,
columns=[
'seed', 'running_time',
'num_round', 'train', 'val',
'local_test', 'diff'
])
print(seed_list)
print(LOCAL_VALIDATION_RESULT)
for seed in seed_array:
DO(option, is_textadded, mat_filename, dir_feature, seed)
print_header('FINAL SUMMARY')
print(LOCAL_VALIDATION_RESULT)
LOCAL_VALIDATION_RESULT.to_csv('seed_select.csv', index=False)
def main():
global args, DEBUG, FRAC, PREDICTORS, TRAINMODE, PREDICTORS, LOCAL_VALIDATION_RESULT
args = parser.parse_args()
DEBUG = args.debug
FRAC = args.frac
TRAINMODE = args.trainmode
# OPTION=args.option
print_debug(DEBUG)
if DEBUG:
dir_feature = '../processed_features_debug2/'
else:
dir_feature = '../processed_features/'
option_list = []
for option in range(10):
option_list = option_list + ['option' + str(option)]
LOCAL_VALIDATION_RESULT = pd.DataFrame(
index=option_list,
columns=['running_time', 'num_round', 'train', 'val'])
if DEBUG:
print(option_list)
print(LOCAL_VALIDATION_RESULT)
test_list = [8]
for option in test_list:
# nothing here
if option == 0:
is_textadded = False
PREDICTORS = PREDICTORS_BASED
mat_filename = dir_feature + 'text_feature_kernel.pickle'
# kernel
elif option == 1:
is_textadded = True
PREDICTORS = PREDICTORS_BASED
mat_filename = dir_feature + 'text_feature_kernel.pickle'
# kernel max_feature = 1000
elif option == 2:
is_textadded = True
PREDICTORS = PREDICTORS_BASED
mat_filename = dir_feature + 'text_feature_kernel_1000.pickle'
# kernel max_feature = 30000
elif option == 3:
is_textadded = True
PREDICTORS = PREDICTORS_BASED
mat_filename = dir_feature + 'text_feature_kernel_30000.pickle'
# kernel max_feature = infinite
elif option == 4:
is_textadded = True
PREDICTORS = PREDICTORS_BASED
mat_filename = dir_feature + 'text_feature_kernel_-1.pickle'
# kernel max_feature = 18000 + 'good' feature
elif option == 5:
is_textadded = True
PREDICTORS = PREDICTORS_BASED + PREDICTORS_GOOD
mat_filename = dir_feature + 'text_feature_kernel.pickle'
# kernel max_feature = 18000 + not-checked feature
elif option == 6:
is_textadded = True
PREDICTORS = PREDICTORS_BASED + PREDICTORS_NOTCHECKED
mat_filename = dir_feature + 'text_feature_kernel.pickle'
elif option == 7:
is_textadded = True
PREDICTORS = PREDICTORS_BASED + PREDICTORS_OVERFIT
mat_filename = dir_feature + 'text_feature_kernel.pickle'
elif option == 8:
is_textadded = True
PREDICTORS = PREDICTORS_BASED + PREDICTORS_TRY
mat_filename = dir_feature + 'text_feature_kernel_30000.pickle'
if DEBUG:
print_header('Option {}'.format(option))
print('is_textadded {} \n predictors {} \n mat filename {}'.format(
is_textadded, PREDICTORS, mat_filename))
DO(option, is_textadded, mat_filename, dir_feature)
print_header('FINAL SUMMARY')
print(LOCAL_VALIDATION_RESULT)
def main():
global args, DEBUG, FRAC, PREDICTORS
args = parser.parse_args()
DEBUG = args.debug
FRAC = args.frac
print_debug(DEBUG)
print("\nData Load Stage")
target = TARGET
tabular_predictors = get_tabular_predictors()
# categorical = get_categorical(predictors)
if DEBUG:
mat_filename = '../processed_features_debug2/text_feature_kernel.pickle'
dir_feature = '../processed_features_debug2/'
else:
mat_filename = '../processed_features/text_feature_kernel.pickle'
dir_feature = '../processed_features/'
X, y, test, full_predictors, predictors = prepare_training(
mat_filename, dir_feature, tabular_predictors)
categorical = get_categorical(predictors)
predictors = get_predictors(predictors)
X_train, X_valid, y_train, y_valid = train_test_split(X,
y,
test_size=0.10,
random_state=SEED)
print(X.shape)
print("Light Gradient Boosting Regressor")
lgbm_params = {
'task': 'train',
'boosting_type': 'gbdt',
'objective': 'regression',
'metric': 'rmse',
'max_depth': 15,
# 'num_leaves': 31,
'feature_fraction': 0.7,
'bagging_fraction': 0.8,
# 'bagging_freq': 5,
'learning_rate': 0.019,
'verbose': 0
}
print(lgbm_params)
# LGBM Dataset Formatting
lgtrain = lgb.Dataset(X_train,
y_train,
feature_name=full_predictors,
categorical_feature=categorical)
lgvalid = lgb.Dataset(X_valid,
y_valid,
feature_name=full_predictors,
categorical_feature=categorical)
# Go Go Go
modelstart = time.time()
lgb_clf = lgb.train(lgbm_params,
lgtrain,
num_boost_round=16000,
valid_sets=[lgtrain, lgvalid],
valid_names=['train', 'valid'],
early_stopping_rounds=200,
verbose_eval=200)