第五次作业

首先尝试了以下代码进行stacking模型融合，该代码是没有用第三方库，程序也比较老，有一些接口已经改变，在测试后后已经不能够运行，自己尝试修正，没有成功。

# coding=utf8


from sklearn import datasets
from sklearn.ensemble import RandomForestClassifier, ExtraTreesClassifier, GradientBoostingClassifier
from sklearn.cross_validation import train_test_split
from sklearn.cross_validation import StratifiedKFold
import numpy as np
from sklearn.metrics import roc_auc_score
from sklearn.datasets.samples_generator import make_blobs

'''创建训练的数据集'''
data, target = make_blobs(n_samples=50000, centers=2, random_state=0, cluster_std=0.60)

'''模型融合中使用到的各个单模型'''
clfs = [RandomForestClassifier(n_estimators=5, n_jobs=-1, criterion='gini'),
        RandomForestClassifier(n_estimators=5, n_jobs=-1, criterion='entropy'),
        ExtraTreesClassifier(n_estimators=5, n_jobs=-1, criterion='gini'),
        ExtraTreesClassifier(n_estimators=5, n_jobs=-1, criterion='entropy'),
        GradientBoostingClassifier(learning_rate=0.05, subsample=0.5, max_depth=6, n_estimators=5)]

'''切分一部分数据作为测试集'''
X, X_predict, y, y_predict = train_test_split(data, target, test_size=0.33, random_state=2017)


dataset_blend_train = np.zeros((X.shape[0], len(clfs)))
dataset_blend_test = np.zeros((X_predict.shape[0], len(clfs)))

'''5折stacking'''
n_folds = 5
skf = list(StratifiedKFold(y, n_folds))
for j, clf in enumerate(clfs):
    '''依次训练各个单模型'''
    # print(j, clf)
    dataset_blend_test_j = np.zeros((X_predict.shape[0], len(skf)))
    for i, (train, test) in enumerate(skf):
        '''使用第i个部分作为预测，剩余的部分来训练模型，获得其预测的输出作为第i部分的新特征。'''
        # print("Fold", i)
        X_train, y_train, X_test, y_test = X[train], y[train], X[test], y[test]
        clf.fit(X_train, y_train)
        y_submission = clf.predict_proba(X_test)[:, 1]
        dataset_blend_train[test, j] = y_submission
        dataset_blend_test_j[:, i] = clf.predict_proba(X_predict)[:, 1]
    '''对于测试集，直接用这k个模型的预测值均值作为新的特征。'''
    dataset_blend_test[:, j] = dataset_blend_test_j.mean(1)
    print("val auc Score: %f" % roc_auc_score(y_predict, dataset_blend_test[:, j]))
# clf = LogisticRegression()
clf = GradientBoostingClassifier(learning_rate=0.02, subsample=0.5, max_depth=6, n_estimators=30)
clf.fit(dataset_blend_train, y)
y_submission = clf.predict_proba(dataset_blend_test)[:, 1]

print("Linear stretch of predictions to [0,1]")
y_submission = (y_submission - y_submission.min()) / (y_submission.max() - y_submission.min())
print("blend result")
print("val auc Score: %f" % (roc_auc_score(y_predict, y_submission)))

来自github
尝试使用第三方库mlxtend实现stacking

clf1 = KNeighborsClassifier(n_neighbors=1)
clf2 = RandomForestClassifier(random_state=1)
clf3 = GaussianNB()
lr = LogisticRegression()
sclf = StackingClassifier(classifiers=[clf1, clf2, clf3],
                          use_probas=True,
                          average_probas=False,
                          meta_classifier=lr)

print('3-fold cross validation:\n')

for clf, label in zip([clf1, clf2, clf3, sclf], 
                      ['KNN', 
                       'Random Forest', 
                       'Naive Bayes',
                       'StackingClassifier']):

    scores =cross_val_score(clf, X, y,cv=3, scoring='accuracy')
    print("Accuracy: %0.2f (+/- %0.2f) [%s]" 
          % (scores.mean(), scores.std(), label))

集成学习还是要花费很长时间的，调参由于时间原因就没有进行。模型融合的效果并没有特别好。
看到其他博客有写道最开始对数据进行预处理时候词向量转化的参数不同对最后的结果影响很大。