- Create a classification dataset (n samples ! 1000, n features ! 10)
- Split the dataset using 10-fold cross validation
- Train the algorithms
GaussianNB
SVC (possible C values [1e-02, 1e-01, 1e00, 1e01, 1e02], RBF kernel)
RandomForestClassifier (possible n estimators values [10, 100, 1000])- Evaluate the cross-validated performance
Accuracy
F1-score
AUC ROC- Write a short report summarizing the methodology and the results
只要按照ppt上的教程写代码即可,通过datasets.make_classification生成数据集,通过cross_validation.KFold将数据集划分为训练集和测试集,通过metrics.accuracy_score、metrics.f1_score、metrics.roc_auc_score获得结果。
from sklearn import metrics
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
# Datasets
dataset = datasets.make_classification(n_samples=1000, n_features=10)
# Cross-validation
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]
# GaussianNB
GaussianNB_clf = GaussianNB()
GaussianNB_clf.fit(X_train, y_train)
GaussianNB_pred = GaussianNB_clf.predict(X_test)
# SVM
SVC_clf = SVC(C=1e-01, kernel='rbf', gamma=0.1)
SVC_clf.fit(X_train, y_train)
SVC_pred = SVC_clf.predict(X_test)
# Random Forest
Random_Forest_clf = RandomForestClassifier(n_estimators=6)
Random_Forest_clf.fit(X_train, y_train)
Random_Forest_pred = Random_Forest_clf.predict(X_test)
# Evaluate the cross-validated performance
# GaussianNB
GaussianNB_accuracy_score = metrics.accuracy_score(y_test, GaussianNB_pred)
GaussianNB_f1_score = metrics.f1_score(y_test, GaussianNB_pred)
GaussianNB_roc_auc_score = metrics.roc_auc_score(y_test, GaussianNB_pred)
print(" GaussianNB_accuracy_score: ", GaussianNB_accuracy_score)
print(" GaussianNB_f1_score: ", GaussianNB_f1_score)
print(" GaussianNB_roc_auc_score: ", GaussianNB_roc_auc_score)
# SVC
SVC_accuracy_score = metrics.accuracy_score(y_test, SVC_pred)
SVC_f1_score = metrics.f1_score(y_test, SVC_pred)
SVC_roc_auc_score = metrics.roc_auc_score(y_test, SVC_pred)
print("\n SVC_accuracy_score: ", SVC_accuracy_score)
print(" SVC_f1_score: ", SVC_f1_score)
print(" SVC_roc_auc_score: ", SVC_roc_auc_score)
# Random_Forest
Random_Forest_accuracy_score = metrics.accuracy_score(y_test, Random_Forest_pred)
Random_Forest_f1_score = metrics.f1_score(y_test, Random_Forest_pred)
Random_Forest_roc_auc_score = metrics.roc_auc_score(y_test, Random_Forest_pred)
print("\n Random_Forest_accuracy_score: ", Random_Forest_accuracy_score)
print(" Random_Forest_f1_score: ", Random_Forest_f1_score)
print(" Random_Forest_roc_auc_score: ", Random_Forest_roc_auc_score)