Gridsearchcv with k-fold cross validation and early stopping

gridsearchcv.py

#

... import xgboost.sklearn as xgb 
... from sklearn.model_selection import GridSearchCV 
... from sklearn.model_selection import TimeSeriesSplit 
...  
... cv = 2 
...  
... trainX= [[1], [2], [3], [4], [5]] 
... trainY = [1, 2, 1, 2, 1] 
...  
... # these are the evaluation sets 
... testX = trainX  
... testY = trainY 
...  
... paramGrid = {"subsample" : [0.5, 0.8]} 
...  
... fit_params={"early_stopping_rounds":42,  
...             "eval_metric" : "mae",  
...             "eval_set" : [[testX, testY]]} 
...  
... model = xgb.XGBRegressor() 
...  
... from sklearn.model_selection import StratifiedKFold 
... skf = StratifiedKFold(n_splits=cv, shuffle = True, random_state = 999) 
... gridsearch = GridSearchCV(model, paramGrid, verbose=1,              
...          cv=skf.split(trainX, trainY)) 
...  
... g = gridsearch.fit(trainX, trainY, **fit_params) 
... y_true, y_pred = testY, gridsearch.predict(testX) 
... from sklearn.metrics import r2_score  
... print(r2_score(y_true, y_pred)) 
... print(g.cv_results_)