python Datasets 作业

题目描述:
python Datasets 作业
代码：
from sklearn import cross_validation
from sklearn import datasets

#step1
d, t = datasets.make_classification(n_samples=1000, n_features=10, n_informative=2, n_redundant=2, n_repeated=0, n_classes=2)

#step2
kf = cross_validation.KFold(len(d), n_folds=10, shuffle=True)

for train_index, test_index in kf:
    X_train, y_train = d[train_index], t[train_index]
    X_test, y_test = d[test_index], t[test_index]
    print(X_train)
    print(y_train)
    print(X_test)
    print(y_test)

#step3 and 4
# Naive Bayes
from sklearn.naive_bayes import GaussianNB
clf = GaussianNB()
clf.fit(X_train, y_train)
pred = clf.predict(X_test)
print(pred)
print(y_test)

from sklearn import metrics
acc = metrics.accuracy_score(y_test, pred)
print(acc)
f1 = metrics.f1_score(y_test, pred)
print(f1)
auc = metrics.roc_auc_score(y_test, pred)
print(auc)

#SVM
from sklearn.svm import SVC
clf = SVC(C=1e-01, kernel='rbf', gamma=0.1)
clf.fit(X_train, y_train)
pred = clf.predict(X_test)
print(pred)
print(y_test)

from sklearn import metrics
acc = metrics.accuracy_score(y_test, pred)
print(acc)
f1 = metrics.f1_score(y_test, pred)
print(f1)
auc = metrics.roc_auc_score(y_test, pred)
print(auc)


# Random Forest
from sklearn.ensemble import RandomForestClassifier
clf = RandomForestClassifier(n_estimators=6)
clf.fit(X_train, y_train)
pred = clf.predict(X_test)

print(pred)
print(y_test)

from sklearn import metrics
acc = metrics.accuracy_score(y_test, pred)
print(acc)
f1 = metrics.f1_score(y_test, pred)
print(f1)
auc = metrics.roc_auc_score(y_test, pred)
print(auc)

#ignore step5