题目要求:
Create a classification dataset (n samples 1000, n features 10)2 Split the dataset using 10-fold cross validation
3 Train the algorithms
I GaussianNB
I SVC (possible C values [1e-02, 1e-01, 1e00, 1e01, 1e02], RBF kernel)
I RandomForestClassifier (possible n estimators values [10, 100, 1000])
4 Evaluate the cross-validated performance
I Accuracy
I F1-score
I AUC ROC
5 Write a short report summarizing the methodology and the results
代码:
from sklearn import datasets
from sklearn import metrics
from sklearn import cross_validation
from sklearn.svm import SVC
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier
dataset = datasets.make_classification(n_samples=1000, n_features=10, n_informative=2, n_redundant=2, n_repeated=0, n_classes=2)
kf = cross_validation.KFold(1000, n_folds=10, shuffle=True)
for train_index, test_index in kf:
X_train, y_train = dataset[0][train_index], dataset[1][train_index]
X_test, y_test = dataset[0][test_index], dataset[1][test_index]
clf = GaussianNB()
clf.fit(X_train, y_train)
print('GaussianNB:')
print('Predict:',clf.predict(X_test),sep='\n')
print('y_test:',y_test,sep='\n')
clf = SVC(C=1e-01, kernel='rbf' , gamma=0.1)
clf.fit(X_train, y_train)
print('SVC:')
print('Predict:',clf.predict(X_test),sep='\n')
print('y_test:',y_test,sep='\n')
clf = RandomForestClassifier(n_estimators=6)
clf.fit(X_train, y_train)
print('Random Forest:')
print('Predict:',clf.predict(X_test),sep='\n')
print('y_test:',y_test,sep='\n')
print('Accuracy:',metrics.accuracy_score(y_test, clf.predict(X_test)))
print('F1-score:',metrics.f1_score(y_test, clf.predict(X_test)))
print('AUC ROC:',metrics.roc_auc_score(y_test, clf.predict(X_test)))