def objective_function(self,x):
print("XGBRegressor优化中...")
train_x, test_x, train_y, test_y = util.get_train_test_split(self.src,int(np.round(x[0])),int(np.round(x[1])),with_rain=self.with_rain)
print(self.model_name)
self.tune_params = ['offset','period','max_depth',
# 'learning_rate',
'n_estimators',
'gasmma',
'min_child_weight','max_delta_step','subsample',
'colsample_bytree','colsample_bylevel','colsample_bynode','reg_alpha',
'reg_lambda','scale_pos_weight','base_score'
]
self.model.max_depth = int(x[2])
self.model.n_estimators = int(x[3])
self.model.gamma = x[4]
self.model.min_child_weight = int(x[5])
self.model.max_delta_step = int(x[6])
self.model.subsample = x[7]
self.model.colsample_bytree = x[8]
self.model.colsample_bylevel = x[9]
self.model.colsample_bynode = x[10]
self.model.reg_alpha = x[11]
self.model.reg_lambda = x[12]
self.model.scale_pos_weight = x[13]
self.model.base_score = x[14]
self.model.objective = 'reg:squarederror'
self.model.learning_rate = 0.001
self.model.fit(X=train_x,y=train_y)
y_hat = self.model.predict(test_x)
mse = mean_squared_error(y_hat,test_y)
return mse
def objective_function(self, x):
print("GradientBoostingRegressor优化中...")
self.tune_params = [
'offset', 'period', 'n_estimators', 'learning_rate', 'subsample',
'min_samples_split', 'min_samples_leaf',
'min_weight_fraction_leaf', 'max_depth', 'alpha'
]
print(self.model_name)
train_x, test_x, train_y, test_y = util.get_train_test_split(
self.src,
int(np.round(x[0])),
int(np.round(x[1])),
with_rain=self.with_rain)
self.model.n_estimators = int(x[2])
self.model.learning_rate = x[3]
self.model.subsample = x[4]
self.model.min_samples_split = int(x[5])
self.model.min_samples_leaf = int(x[6])
self.model.min_weight_fraction_leaf = x[7]
self.model.max_depth = int(x[8])
self.model.alpha = x[9]
self.model.fit(X=train_x, y=train_y)
y_hat = self.model.predict(test_x)
mse = mean_squared_error(y_hat, test_y)
return mse
def objective_function(self, x):
train_x, test_x, train_y, test_y = util.get_train_test_split(
self.src,
int(np.round(x[0])),
int(np.round(x[1])),
with_rain=self.with_rain)
self.model.fit(X=train_x, y=train_y)
y_hat = self.model.predict(test_x)
mse = mean_squared_error(y_hat, test_y)
return mse
def objective_function(self, x):
self.tune_params = ['offset', 'period']
print(self.model_name)
train_x, test_x, train_y, test_y = util.get_train_test_split(
self.src,
int(np.round(x[0])),
int(np.round(x[1])),
with_rain=self.with_rain)
self.model.fit(X=train_x, y=train_y)
y_hat = self.model.predict(test_x)
mse = mean_squared_error(y_hat, test_y)
return mse
def objective_function(self, x):
print("Ridge最优化中...")
self.tune_params = ['offset', 'period', 'alpha', 'max_iter', 'tol']
train_x, test_x, train_y, test_y = util.get_train_test_split(
self.src,
int(np.round(x[0])),
int(np.round(x[1])),
with_rain=self.with_rain)
self.model.alpha = x[2]
self.model.max_iter = x[3]
self.model.tol = x[4]
self.model.fit(X=train_x, y=train_y)
y_hat = self.model.predict(test_x)
mse = mean_squared_error(y_hat, test_y)
return mse
def objective_function(self, x):
print("RidgeCV最优化中...")
self.tune_params = [
'offset', 'period', 'alpha0', 'alpha1', 'alpha2', 'alpha3', 'cv'
]
print(self.model_name)
train_x, test_x, train_y, test_y = util.get_train_test_split(
self.src,
int(np.round(x[0])),
int(np.round(x[1])),
with_rain=self.with_rain)
self.model.alphas = [x[2], x[3], x[4], x[5]]
self.cv = int(x[6])
self.model.fit(X=train_x, y=train_y)
y_hat = self.model.predict(test_x)
mse = mean_squared_error(y_hat, test_y)
return mse
def objective_function(self, x):
print("BaggingRegressor优化中...")
self.tune_params = [
'offset', 'period', 'n_estimators', 'max_samples', 'max_features'
]
print(self.model_name)
train_x, test_x, train_y, test_y = util.get_train_test_split(
self.src,
int(np.round(x[0])),
int(np.round(x[1])),
with_rain=self.with_rain)
self.model.n_estimators = int(x[2])
self.model.max_samples = x[3]
self.model.max_features = x[4]
self.model.fit(X=train_x, y=train_y)
y_hat = self.model.predict(test_x)
mse = mean_squared_error(y_hat, test_y)
return mse
def objective_function(self, x):
print("AdaBoostRegressor优化中...")
self.tune_params = [
'offset', 'period', 'n_estimators', 'learning_rate'
]
print(self.model_name)
train_x, test_x, train_y, test_y = util.get_train_test_split(
self.src,
int(np.round(x[0])),
int(np.round(x[1])),
with_rain=self.with_rain)
self.model.n_estimators = int(x[2])
self.model.learning_rate = x[3]
self.model.loss = 'square'
self.model.fit(X=train_x, y=train_y)
y_hat = self.model.predict(test_x)
mse = mean_squared_error(y_hat, test_y)
return mse
def objective_function(self, x):
print("LassoLarsCV最优化中...")
self.tune_params = [
'offset', 'period', 'max_iter', 'max_n_alphas', 'eps'
]
print(self.model_name)
train_x, test_x, train_y, test_y = util.get_train_test_split(
self.src,
int(np.round(x[0])),
int(np.round(x[1])),
with_rain=self.with_rain)
self.model.max_iter = x[2]
self.model.max_n_alphas = x[3]
self.model.eps = x[4]
self.model.fit(X=train_x, y=train_y)
y_hat = self.model.predict(test_x)
mse = mean_squared_error(y_hat, test_y)
return mse
def objective_function(self,x):
print("CatBoostRegressor优化中...")
train_x, test_x, train_y, test_y = util.get_train_test_split(self.src,int(np.round(x[0])),int(np.round(x[1])),with_rain=self.with_rain)
print(self.model_name)
self.tune_params = ['offset','period','max_depth','subsample','learning_rate','n_estimators',
'min_child_samples','max_leaves']
self.model.max_depth = int(x[2])
self.model.subsample = x[3]
self.model.learning_rate = x[4]
self.model.n_estimators = int(x[5])
self.model.min_child_samples = x[6]
self.model.max_leaves = x[7]
self.model.task_type = 'gpu'
self.model.iterations = 100
self.model.loss_function = 'MSE'
train_x,val_x,train_y,val_y = train_test_split(train_x,train_y,test_size=0.1)
self.model.fit(train_x,train_y,eval_set=(val_x,val_y),plot=True)
y_hat = self.model.predict(test_x)
mse = mean_squared_error(y_hat,test_y)
return mse
def objective_function(self, x):
print("BayesianRidge最优化中...")
self.tune_params = [
'offset', 'period', 'n_iter', 'tol', 'alpha_1', 'alpha_2',
'lambda_1', 'lambda_2'
]
print(self.model_name)
train_x, test_x, train_y, test_y = util.get_train_test_split(
self.src,
int(np.round(x[0])),
int(np.round(x[1])),
with_rain=self.with_rain)
self.model.n_iter = int(x[2])
self.model.tol = x[3]
self.model.alpha_1 = x[4]
self.model.alpha_2 = x[5]
self.model.lambda_1 = x[6]
self.model.lambda_2 = x[7]
self.model.fit(X=train_x, y=train_y)
y_hat = self.model.predict(test_x)
mse = mean_squared_error(y_hat, test_y)
return mse
def objective_function(self,x):
print("LightGBMRegressor优化中...")
train_x, test_x, train_y, test_y = util.get_train_test_split(self.src,int(np.round(x[0])),int(np.round(x[1])),with_rain=self.with_rain)
print(self.model_name)
self.tune_params = ['offset','period','num_leaves','learning_rate','feature_fraction','bagging_fraction','bagging_freq']
params = {
'task': 'train',
'boosting_type': 'gbdt', # 设置提升类型
'objective': 'regression', # 目标函数
'metric': {'mse'}, # 评估函数
'num_leaves': int(x[2]), # 叶子节点数
'learning_rate': x[3], # 学习速率
'feature_fraction': x[4], # 建树的特征选择比例
'bagging_fraction': x[5], # 建树的样本采样比例
'bagging_freq': int(x[6]), # k 意味着每 k 次迭代执行bagging
'verbose': 0, # <0 显示致命的, =0 显示错误 (警告), >0 显示信息
'device':'gpu'
}
train_x,val_x,train_y,val_y = train_test_split(train_x,train_y,test_size=0.1)
self.model = lgb.train(params,lgb.Dataset(train_x,train_y),num_boost_round=100,valid_sets=lgb.Dataset(val_x,val_y),early_stopping_rounds=5)
y_hat = self.model.predict(test_x,num_iteration=self.model.best_iteration)
mse = mean_squared_error(y_hat,test_y)
return mse
df, unique_labels = util.load_data(file_name)
auto_df, auto_unique_labels = util.load_data(auto_file_name)
print("df after loading (%ld rows):" % df.shape[0])
print(df.head(n=5))
# hash encode the data
df = util.hash_encoder(df, cols_to_hash, no_new_cols_per)
print("df after hashing (%ld rows):" % df.shape[0])
print(df.head(n=5))
auto_df = util.hash_encoder(auto_df, cols_to_hash, no_new_cols_per)
# separate into train/test X/y splits
df_train_X, df_train_y, df_test_X, df_test_y = util.get_train_test_split(df)
auto_df_test_X = auto_df
auto_df_test_y = auto_df_test_X.pop('delinquent')
auto_df_test_y = auto_df_test_y.astype(np.int32)
print("df train X:")
print(df_train_X.head(n=5))
print('df train X rows:')
print(df_train_X.shape[0])
print("df train y head:")
print(df_train_y.head(n=5))
print("df test y head:")
print(df_test_y.head(n=5))
print("auto df test y head:")