高级编程技术 第十五周 sklearn 学习

题目：

代码：

#sklearn chinese document
#http://cwiki.apachecn.org/display/sklearn/Index

from sklearn import datasets
from sklearn import cross_validation
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn import metrics

#step1 - Create a classification dataset (n samples >= 1000, n features >=10)
dataset = datasets.make_classification(n_samples = 1500,n_features = 15);

#step2 - Split the dataset using 10-fold cross validation
k_fold = cross_validation.KFold(n = 1500 ,n_folds = 10,shuffle=True)

for train_index,test_index in k_fold:
	x_train,y_train = dataset[0][train_index],dataset[1][train_index]
	x_test,y_test = dataset[0][test_index],dataset[1][test_index]
	
#step4 - Evaluate the cross-validated performance
def evaluate(y_test,perd,name):
	print(name+': ')
	acc = metrics.accuracy_score(y_test,pred)
	print('Accuracy: ',acc)
	f1 = metrics.f1_score(y_test,pred)
	print('F1_score: ',f1)
	auc = metrics.roc_auc_score(y_test,pred)
	print('AUC ROC: ',auc)
	
#step3 - Train the algorithms:GaussianNB,SVC,RandomForestClassifier

#3-1 GaussianNB
clf = GaussianNB()
clf.fit(x_train,y_train)
pred = clf.predict(x_test)
evaluate(y_test,pred,'GaussianNB')

#3-2 SVC	
C_values = [1e-02, 1e-01, 1e00, 1e01, 1e02]
for C_value in C_values:
	clf = SVC(C=C_value, kernel='rbf', gamma=0.1)
	clf.fit(x_train, y_train)
	pred = clf.predict(x_test)
	evaluate(y_test,pred,"SVC, C_value= %s" % str(C_value))

#3-3 RandomForestClassifier
clf = RandomForestClassifier(n_estimators = 6)
clf.fit(x_train,y_train)
pred = clf.predict(x_test)
evaluate(y_test,pred,'RandomForestClassifier')

性能评估：