from sklearn.datasets import load_iris
from sklearn.svm import SVC
from sklearn.model_selection import train_test_splitiris = load_iris()
X_train,X_test,y_train,y_test = train_test_split(iris.data,iris.target,random_state=0)
print("Size of training set:{} size of testing set:{}".format(X_train.shape[0],X_test.shape[0]))####   grid search start
best_score = 0
for gamma in [0.001,0.01,0.1,1,10,100]:for C in [0.001,0.01,0.1,1,10,100]:svm = SVC(gamma=gamma,C=C)#对于每种参数可能的组合，进行一次训练；
        svm.fit(X_train,y_train)score = svm.score(X_test,y_test)if score > best_score:#找到表现最好的参数best_score = scorebest_parameters = {'gamma':gamma,'C':C}
####   grid search endprint("Best score:{:.2f}".format(best_score))
print("Best parameters:{}".format(best_parameters))

Size of training set:112 size of testing set:38
Best score:0.973684
Best parameters:{'gamma': 0.001, 'C': 100}

X_trainval,X_test,y_trainval,y_test = train_test_split(iris.data,iris.target,random_state=0)
X_train,X_val,y_train,y_val = train_test_split(X_trainval,y_trainval,random_state=1)
print("Size of training set:{} size of validation set:{} size of teseting set:{}".format(X_train.shape[0],X_val.shape[0],X_test.shape[0]))best_score = 0.0
for gamma in [0.001,0.01,0.1,1,10,100]:for C in [0.001,0.01,0.1,1,10,100]:svm = SVC(gamma=gamma,C=C)svm.fit(X_train,y_train)score = svm.score(X_val,y_val)if score > best_score:best_score = scorebest_parameters = {'gamma':gamma,'C':C}
svm = SVC(**best_parameters) #使用最佳参数，构建新的模型
svm.fit(X_trainval,y_trainval) #使用训练集和验证集进行训练，more data always results in good performance.
test_score = svm.score(X_test,y_test) # evaluation模型评估
print("Best score on validation set:{:.2f}".format(best_score))
print("Best parameters:{}".format(best_parameters))
print("Best score on test set:{:.2f}".format(test_score))

Size of training set:84 size of validation set:28 size of teseting set:38
Best score on validation set:0.96
Best parameters:{'gamma': 0.001, 'C': 10}
Best score on test set:0.92

from sklearn.model_selection import cross_val_scorebest_score = 0.0
for gamma in [0.001,0.01,0.1,1,10,100]:for C in [0.001,0.01,0.1,1,10,100]:svm = SVC(gamma=gamma,C=C)scores = cross_val_score(svm,X_trainval,y_trainval,cv=5) #5折交叉验证score = scores.mean() #取平均数if score > best_score:best_score = scorebest_parameters = {"gamma":gamma,"C":C}
svm = SVC(**best_parameters)
svm.fit(X_trainval,y_trainval)
test_score = svm.score(X_test,y_test)
print("Best score on validation set:{:.2f}".format(best_score))
print("Best parameters:{}".format(best_parameters))
print("Score on testing set:{:.2f}".format(test_score))

Best score on validation set:0.97
Best parameters:{'gamma': 0.01, 'C': 100}
Score on testing set:0.97

from sklearn.model_selection import GridSearchCV#把要调整的参数以及其候选值 列出来；
param_grid = {"gamma":[0.001,0.01,0.1,1,10,100],"C":[0.001,0.01,0.1,1,10,100]}
print("Parameters:{}".format(param_grid))grid_search = GridSearchCV(SVC(),param_grid,cv=5) #实例化一个GridSearchCV类
X_train,X_test,y_train,y_test = train_test_split(iris.data,iris.target,random_state=10)  # 在这里划分好数据后，下面的grid_search自动进行训练集和验证集划分并取出最优参数组合，返回的grid_search就是一个带该参数组合的模型
grid_search.fit(X_train,y_train) #训练，找到最优的参数，同时使用最优的参数实例化一个新的SVC estimator。
print("Test set score:{:.2f}".format(grid_search.score(X_test,y_test)))
print("Best parameters:{}".format(grid_search.best_params_))
print("Best score on train set:{:.2f}".format(grid_search.best_score_))

Parameters:{'gamma': [0.001, 0.01, 0.1, 1, 10, 100], 'C': [0.001, 0.01, 0.1, 1, 10, 100]}
Test set score:0.97
Best parameters:{'C': 10, 'gamma': 0.1}
Best score on train set:0.98