[AI practice] xgb Xgbregression multioutputregressor parameter 2 (GPU training model)

xgb.XGBRegressor Multiple regression MultiOutputRegressor Adjustable parameter 2（GPU Training models ）

• Environmental Science

  • Ubuntu18.04
  • python3.6.9
  • TensorFlow 2.4.2
  • cuda 11.0
  • xgboost 1.5.2

• Dependency Library

  import pandas as pd
  from sklearn.model_selection import train_test_split
  from sklearn.model_selection import GridSearchCV # The grid search 
  from sklearn.metrics import make_scorer
  from sklearn.metrics import r2_score
  from sklearn.ensemble import GradientBoostingRegressor
  from sklearn.multioutput import MultiOutputRegressor
  import xgboost as xgb
  import joblib
  

• Call the core code

  def tune_parameter(train_data_path, test_data_path, n_input, n_output, version):
      #  Model parameter adjustment 
      
      x,y = load_data(version, 'train', train_data_path, n_input, n_output)
      train_x,test_x,train_y,test_y = train_test_split(x,y,test_size=0.2,random_state=2022)
      
      gsc = GridSearchCV(
              estimator=xgb.XGBRegressor(seed=42,
                               tree_method='gpu_hist',
                               gpu_id=3),
              param_grid={
        "learning_rate": [0.05, 0.10, 0.15],
                          "n_estimators":[400, 500, 600, 700],
                          "max_depth": [ 3, 5, 7],
                          "min_child_weight": [ 1, 3, 5, 7],
                          "gamma":[ 0.0, 0.1, 0.2],
                          "colsample_bytree":[0.7, 0.8, 0.9],
                          "subsample":[0.7, 0.8, 0.9],
                          },
                          cv=3, scoring='neg_mean_squared_error', verbose=0, n_jobs=4)
  
      grid_result = MultiOutputRegressor(gsc).fit(train_x, train_y)
  
      #best_params = grid_result.estimators_[0].best_params_
      print('-'*20)
      print('best_params:')
      for i in range(len(grid_result.estimators_)):
          print(i, grid_result.estimators_[i].best_params_)
      
      model = grid_result
      
      pre_y = model.predict(test_x)
      print('-'*20)
      # Calculate the decision coefficient r Fang 
      r2 = performance_metric(test_y, pre_y)  
      print('test_r2 = ', r2)
  
  def performance_metric(y_true, y_predict):
      
      score = r2_score(y_true,y_predict)
      
      MSE=np.mean(( y_predict- y_true)**2)
      print('RMSE: ',MSE**0.5)
      MAE=np.mean(np.abs( y_predict- y_true))
      print('MAE: ',MAE)
      
      return score
      
  

  Save the model after parameter adjustment , Add the following code

  joblib.dump(model, './ml_data/xgb_%d_%d_%s.model' %(n_input, n_output, version)) 
  

  Adjustable parameter ： modify param_grid Set your own parameters

  param_grid = {
        
  	"learning_rate": [0.05, 0.10, 0.15],
      "n_estimators":[400, 500, 600, 700],
      "max_depth": [ 3, 5, 7],
      "min_child_weight": [ 1, 3, 5, 7],
      "gamma":[ 0.0, 0.1, 0.2],
      "colsample_bytree":[0.7, 0.8, 0.9],
      "subsample":[0.7, 0.8, 0.9],
  }
  

  Number of tuning threads n_jobs=4 , It can be set according to your own machine , Set up n_jobs=-1 It's easy to report mistakes

  GPU Parameter setting ：

  estimator=xgb.XGBRegressor(seed=42,
  	                             tree_method='gpu_hist',
  	                             gpu_id=3)
  

  tree_method=‘gpu_hist’ Said the use of GPU Training models ,
  gpu_id=3 Indicates the setting of the second 3 block GPU,