高级编程作业 sklearn练习

Step1

from sklearn.datasets import make_classification
dataset = make_classification(n_samples=1000, n_features=10, n_informative=2, n_redundant=2, n_repeated=0, n_classes=2)
print("data")
print(dataset[0])
print("target")
print(dataset[1])

输出结果

Step2

from sklearn.cross_validation import KFold
kf = KFold(len(dataset[0]), 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]

Step3,4

GaussianNB

# 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
print("acc = ")
acc = metrics.accuracy_score(y_test, pred)
print(acc)
print("f1 = ")
f1 = metrics.f1_score(y_test, pred)
print(f1)
print("auc = ")
auc = metrics.roc_auc_score(y_test, pred)
print(auc)

输出结果

SVC

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

输出结果

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
print("acc = ")
acc = metrics.accuracy_score(y_test, pred)
print(acc)
print("f1 = ")
f1 = metrics.f1_score(y_test, pred)
print(f1)
print("auc = ")
auc = metrics.roc_auc_score(y_test, pred)
print(auc)

输出结果