import scipy

from sklearn.datasets import load_digits
from sklearn.metrics import classification_report
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.model_selection import GridSearchCV,RandomizedSearchCV

#模型选择参数优化随机搜索寻优RandomizedSearchCV模型
def test_RandomizedSearchCV():
    '''
    测试 RandomizedSearchCV 的用法。使用 LogisticRegression 作为分类器，主要优化 C、multi_class 等参数。其中 C 的分布函数为指数分布
    '''
    ### 加载数据
    digits = load_digits()
    X_train,X_test,y_train,y_test=train_test_split(digits.data, digits.target,test_size=0.25,random_state=0,stratify=digits.target)
    #### 参数优化 ######
    tuned_parameters ={  'C': scipy.stats.expon(scale=100), # 指数分布
                        'multi_class': ['ovr','multinomial']}
    clf=RandomizedSearchCV(LogisticRegression(penalty='l2',solver='lbfgs',tol=1e-6),tuned_parameters,cv=10,scoring="accuracy",n_iter=100)
    clf.fit(X_train,y_train)
    print("Best parameters set found:",clf.best_params_)
    print("Randomized Grid scores:")
#     for params, mean_score, scores in clf.fit_params,clf.mean_score,clf.score:
#         print("\t%0.3f (+/-%0.03f) for %s" % (mean_score, scores() * 2, params))
#     print("\t%0.3f (+/-%0.03f) for %s" % (clf.mean_score,clf.score * 2, clf.fit_params))
    print(clf)

    print("Optimized Score:",clf.score(X_test,y_test))
    print("Detailed classification report:")
    y_true, y_pred = y_test, clf.predict(X_test)
    print(classification_report(y_true, y_pred))
    
#调用RandomizedSearchCV()
test_RandomizedSearchCV()