第十五周作业 —— sklearn

Train the algorithms

GaussianNB

iris = datasets. load_iris ()

dataset = datasets. make_classification ( n_samples = 1000 , n_features = 10 ,

n_informative = 2 , n_redundant = 2 , n_repeated = 0 , n_classes = 2 )

#10 - fold 交叉检验

kf = cross_validation. KFold ( 1000 , n_folds = 10 , shuffle = True )

#获取数据

for train_index, test_index in kf:

X_train, X_test = dataset [ 0 ][train_index ],dataset [ 0 ][test_index ]

y_train, y_test = dataset [ 1 ][train_index ],dataset [ 1 ][test_index ]

#高斯朴素贝叶斯

clf = GaussianNB ()

clf. fit (X_train, y_train)

pred = clf. predict (X_test)

acc = metrics. accuracy_score (y_test, pred)

f1 = metrics. f1_score (y_test, pred)

auc = metrics. roc_auc_score (y_test, pred)

结果如下：

SVC (possible C values [1e-02, 1e-01, 1e00, 1e01, 1e02], RBF kernel)

def rbf_svm( X_train, y_train, X_test, C):

clf = SVC ( C = C, kernel = ' rbf ' , class_weight = ' balanced ' )

clf. fit (X_train,y_train)

return clf. predict (X_test)

#样本数量

n_sam = 1000

iris = datasets. load_iris ()

dataset = datasets. make_classification ( n_samples = n_sam , n_features = 10 ,

n_informative = 2 , n_redundant = 2 , n_repeated = 0 , n_classes = 2 )

#使用10fold交叉检验

kf = cross_validation. KFold (n_sam , n_folds = 10 , shuffle = True )

accuracy = []

f1 = []

auc_roc = []

for train_index, test_index in kf:

X_train, X_test = dataset [ 0 ][train_index ],dataset [ 0 ][test_index ]

y_train, y_test = dataset [ 1 ][train_index ],dataset [ 1 ][test_index ]

nn = len (X_train)

bestC = None

Cvalues = [ 1e-2, 1e-1, 1e0, 1e1, 1e2 ]

innerscore = []

#用不同的参数C来对数据集进行训练

for C in Cvalues:

#内部使用5fold交叉检验

ikf = cross_validation. KFold (nn, n_folds = 5 , shuffle = True , random_state = 5678 )

innerf1 = []

for t_index, v_index in ikf:

X_t, X_v = X_train [t_index ], X_train [v_index ]

y_t, y_v = y_train [t_index ], y_train [v_index ]

ipred = rbf_svm (X_t, y_t, X_v, C)

#对检验的f1score进行保存

innerf1. append (metrics. f1_score (y_v, ipred))

innerscore. append ( sum (innerf1) / len (innerf1))

#选出能得出最好的f1score的C

bestC = Cvalues [np. argmax (innerscore)]

#预测分类结果

pred = rbf_svm (X_train, y_train, X_test, bestC)

accuracy. append (metrics. accuracy_score (y_test,pred))

f1. append (metrics. f1_score (y_test,pred))

auc_roc. append (metrics. roc_auc_score (y_test, pred))

结果如下：

RandomForestClassifier (possible n estimators values [10, 100, 1000])

#用不同参数构建分类器

def rbf_ranf( X_train, y_train, X_test, nest):

clf = RandomForestClassifier ( n_estimators = nest)

clf. fit (X_train,y_train)

return clf. predict (X_test)

#样本数量

n_sam = 1000

iris = datasets. load_iris ()

dataset = datasets. make_classification ( n_samples = n_sam , n_features = 10 ,

n_informative = 2 , n_redundant = 2 , n_repeated = 0 , n_classes = 2 )

#使用10fold交叉检验

kf = cross_validation. KFold (n_sam , n_folds = 10 , shuffle = True )

accuracy = []

f1 = []

auc_roc = []

for train_index, test_index in kf:

X_train, X_test = dataset [ 0 ][train_index ],dataset [ 0 ][test_index ]

y_train, y_test = dataset [ 1 ][train_index ],dataset [ 1 ][test_index ]

nn = len (X_train)

bestN = None

N_est = [ 10, 100, 1000 ]

innerscore = []

#用不同的参数n_estimator来对数据集进行训练

for nest in N_est:

ikf = cross_validation. KFold (nn, n_folds = 5 , shuffle = True , random_state = 5678 )

innerf1 = []

for t_index, v_index in ikf:

X_t, X_v = X_train [t_index ], X_train [v_index ]

y_t, y_v = y_train [t_index ], y_train [v_index ]

ipred = rbf_ranf (X_t, y_t, X_v, nest)

innerf1. append (metrics. f1_score (y_v, ipred))

innerscore. append ( sum (innerf1) / len (innerf1))

bestN = N_est [np. argmax (innerscore)]

#预测分类结果

pred = rbf_ranf (X_train, y_train, X_test, bestN)

accuracy. append (metrics. accuracy_score (y_test,pred))

f1. append (metrics. f1_score (y_test,pred))

auc_roc. append (metrics. roc_auc_score (y_test, pred))

结果如下：

结论，从结果来看，随机森林训练法最好