import xgboost as xgb
from sklearn.model_selection import GridSearchCV
from sklearn.metrics import make_scorer
from sklearn.metrics import accuracy_score
from sklearn.datasets import load_breast_cancer
from sklearn.model_selection import train_test_split
from sklearn.model_selection import ParameterGrid
from sklearn.model_selection import ParameterSampler
from scipy.stats.distributions import expon
import numpy as np #从给定分布中生成采样参数
np.random.seed(0)
param = {"a":[1,2],"b":expon()}
param = list(ParameterSampler(param,n_iter=4)) ################################################################################## def get_model_GridSearchCV(estimator,parameters,X_train,y_train,scoring,cv=5):
"""
return:返回训练过的最好模型
""" #refit:Refit an estimator using the best found parameters on the whole dataset.
model = GridSearchCV(estimator=estimator,param_grid=parameters,scoring=scoring,cv=5,refit=True) model.fit(X_train, y_train) #打印结果
print("best score in GridSearchCV:\n",model.best_score_)
print("best param in GridSearchCV:\n",model.best_params_) return model.best_estimator_ #########################################测试######################################## X,y = load_breast_cancer(return_X_y=True) #分隔训练集和测试集
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.3,random_state=0,stratify=y) #配置参数
param = [{
"learning_rate":[0.1,0.3,0.6],
"max_depth":[5,6,7],
"n_estimators":[100,200,300],
}] #scoring = make_scorer(accuracy_score, greater_is_better=True) estimator = xgb.XGBClassifier(objective="reg:logistic") #训练模型
model = get_model_GridSearchCV(estimator=estimator,
parameters=param,
cv=5,
X_train=X_train,
y_train=y_train,
scoring="roc_auc") #采用训练得模型做测试
"""
decision_function(*args, **kwargs) Call decision_function on the estimator with the best found parameters.
fit(X[, y, groups]) Run fit with all sets of parameters.
get_params([deep]) Get parameters for this estimator.
inverse_transform(*args, **kwargs) Call inverse_transform on the estimator with the best found params.
predict(*args, **kwargs) Call predict on the estimator with the best found parameters.
predict_log_proba(*args, **kwargs) Call predict_log_proba on the estimator with the best found parameters.
predict_proba(*args, **kwargs) Call predict_proba on the estimator with the best found parameters.
score(X[, y]) Returns the score on the given data, if the estimator has been refit.
set_params(**params) Set the parameters of this estimator.
transform(*args, **kwargs) Call transform on the estimator with the best found parameters.
"""
y_pred = model.predict(X_test) #模型评价
print(accuracy_score(y_test,y_pred))