"""
利用决策树预测乳腺癌的例子（网格搜索算法优化）
sklearn.grid_search模块在0.18版本中被弃用，它所支持的类转移到model_selection 模板中。还要注意，新的CV迭代器的接口与这个模块的接口不同，sklearn.grid_search在0.20中被删除。
解决方法：将下面代码“from sklearn.grid_search import GridSearchCV”修改成：“from sklearn.model_selection import GridSearchCV”
程序来源：https://blog.csdn.net/guoyc439/article/details/123381908
20221113 byp
"""
from sklearn.model_selection import GridSearchCV, KFold, train_test_split
from sklearn.metrics import make_scorer, accuracy_score
from sklearn.tree import DecisionTreeClassifier
from sklearn.datasets import load_breast_cancer
import warnings
from sklearn.neighbors import KNeighborsClassifier as KNN

warnings.filterwarnings('ignore')

# load  data

data = load_breast_cancer()
print(data.data.shape)
print(data.target.shape)

# (569, 30)
# (569,)

X, y = data['data'] , data['target']
X_train, X_test, y_train, y_test = train_test_split(
    X, y, train_size=0.8, random_state=0
)

regressor = DecisionTreeClassifier(random_state=0)
parameters = {'max_depth': range(1, 6)}
scorin_fnc = make_scorer(accuracy_score)
kflod = KFold(n_splits=10)
# grid = GridSearchCV(regressor, parameters, scorin_fnc, cv=kflod)
grid = GridSearchCV(regressor, parameters, scoring=None, cv=kflod)
"""
GridSearchCV参数：
class sklearn.model_selection.GridSearchCV(estimator, param_grid, scoring=None,
fit_params=None, n_jobs=None, iid=’warn’, refit=True, cv=’warn’, verbose=0,
pre_dispatch=‘2*n_jobs’, error_score=’raise-deprecating’, return_train_score=’warn’)
"""
grid = grid.fit(X_train, y_train)
reg = grid.best_estimator_
print('best score:%f', grid.best_score_)
print('best parameters:')

for key in parameters.keys():

    print('%s:%d' % (key, reg.get_params()[key]))

print('test score : %f' % reg.score(X_test, y_test))

# import pandas as pd
# pd.DataFrame(grid.cv_results_).T

# 引入KNN训练方法
knn = KNN()

# 进行填充测试数据进行训练
knn.fit(X_train, y_train)
params = knn.get_params()
score = knn.score(X_test, y_test)
print("KNN 预测得分为：%s" % score)