Python编程作业【第十五周】（sklearn homework）

Sklearn

1. Create a classification dataset (n samples $\geq$ 1000, n features $\geq$ 10)
2. Split the dataset using 10-fold cross validation
3. Train the algorithms
4. Evaluate the cross-validated performance I Accuracy
5. Write a short report summarizing the methodology and the results

#1
from sklearn import datasets
dataset = datasets.make_classification(n_samples=1000, n_features=10,
            n_informative=2, n_redundant=2, n_repeated=0, n_classes=2)

#2
from sklearn import cross_validation
kf = cross_validation.KFold(len(iris.data), n_folds=10, shuffle=True)
for train_index, test_index in kf:
    X_train, y_train = iris.data[train_index], iris.target[train_index]
    X_test, y_test   = iris.data[test_index],  iris.target[test_index]

#3
# Naive Bayes
from sklearn.naive_bayes import GaussianNB
clf = GaussianNB()
clf.fit(X_train, y_train)
pred = clf.predict(X_test)

#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)

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

#4
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

#5
#随机森林算法、高斯朴素贝叶斯算法、SVM算法都是设立了训练集和检验集，通过检验集的检验来查看训练集的效果如何。经过反复的实验，随机森林算法的性能要高于高斯朴素贝叶斯和SVM算法。