def stacking_pred(x_train,
y_train,
x_valid,
kf,
clf_list,
label_split=None,
clf_fin='lgb',
if_concat_origin=True):
for k, clf_list in enumerate(clf_list):
clf_list = [clf_list]
column_list = []
train_data_list = []
test_data_list = []
for clf in clf_list:
train_data, test_data, clf_name = clf(x_train,
y_train,
x_valid,
kf,
label_split=label_split)
train_data_list.append(train_data)
test_data_list.append(test_data)
column_list.append("clf_%s" % (clf_name))
train = np.concatenate(train_data_list, axis=1)
test = np.concatenate(test_data_list, axis=1)
if if_concat_origin:
train = np.concatenate([x_train, train], axis=1)
test = np.concatenate([x_valid, test], axis=1)
print(x_train.shape)
print(train.shape)
print(clf_name)
print(clf_name in ['lgb'])
if clf_fin in ['rf', 'ada', 'gb', 'et', 'lr', 'lsvc', 'knn']:
if clf_fin in ['rf']:
clf = RandomForestRegressor(n_estimators=600,
max_depth=20,
n_jobs=-1,
random_state=2017,
max_features='auto',
verbose=1)
elif clf_fin in ['ada']:
clf = AdaBoostRegressor(n_estimators=30,
random_state=2017,
learning_rate=0.01)
elif clf_fin in ['gb']:
clf = GradientBoostingRegressor(learning_rate=0.04,
n_estimators=100,
subsample=0.8,
random_state=2017,
max_depth=5,
verbose=1)
elif clf_fin in ['et']:
clf = ExtraTreesRegressor(n_estimators=600,
max_depth=35,
max_features='auto',
n_jobs=-1,
random_state=2017,
verbose=-1)
elif clf_fin in ['lr']:
clf = LinearRegression(n_jobs=-1)
clf.fit(train, y_train)
pre = clf.predict(test).reshape(-1, 1)
return pre
elif clf_fin in ['xgb']:
clf = xgboost
train_matrix = clf.DMatrix(train, label=y_train, missing=-1)
test_matrix = clf.DMatrix(train, label=y_train, missing=-1)
params = {
'booster': 'gbtree',
'eval_metric': 'rmse',
'gamma': 1,
'min_child_weight': 1.5,
'max_depth': 5,
'lambda': 10,
'subsample': 0.7,
'colsample_bytree': 0.7,
'colsample_bylevel': 0.7,
'eta': 0.03,
'tree_method': 'extra',
'seed': 2017,
'nthread': 12
}
num_round = 10000
early_stopping_rounds = 100
watchlist = [(train_matrix, 'train'), (test_matrix, 'eval')]
model = clf.train(params,
train_matrix,
num_boost_round=num_round,
evals=watchlist,
early_stopping_rounds=early_stopping_rounds)
pre = model.predict(test,
ntree_limit=model.best_ntree_limit).reshape(
-1, 1)
return pre
elif clf_fin in ['lgb']:
print(clf_name)
clf = lightgbm
train_matrix = clf.Dataset(train, label=y_train)
test_matrix = clf.Dataset(train, label=y_train)
params = {
'boosting_type': 'gbdt',
'objective': 'regression_l2',
'metric': 'mse',
'min_child_weight': 1.5,
'num_leaves': 2**5,
'lambda_l2': 10,
'subsample': 0.7,
'colsample_bytree': 0.7,
'colsample_bylevel': 0.7,
'learning_rate': 0.03,
'tree_method': 'extract',
'seed': 2017,
'nthread': 12,
'silent': True
}
num_round = 10000
early_stopping_rounds = 100
model = clf.train(params,
train_matrix,
num_round,
valid_sets=test_matrix,
early_stopping_rounds=early_stopping_rounds)
pre = model.predict(test,
num_iteration=model.best_iteration).reshape(
-1, 1)
return pre
