数据挖掘面试题之blending

原理：两层N个模型的blending原理

1，将训练集分为两部分（train1，train2），test。

2，第一层：对train1训练m个模型，预测train2 会得到m列预测值，组成新训练集X1

    预测test 会得到m列预测值，组成新测试集X2

3，用第一层输出的X1和train2的y作为第二层的训练集，训练一个模型后，预测X2

代码参考：

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)

'''5折stacking'''
n_folds = 5
skf = list(StratifiedKFold(y, n_folds))

'''切分训练数据集为d1,d2两部分'''
X_d1, X_d2, y_d1, y_d2 = train_test_split(X, y, test_size=0.5, random_state=2017)
dataset_d1 = np.zeros((X_d2.shape[0], len(clfs)))
dataset_d2 = np.zeros((X_predict.shape[0], len(clfs)))

for j, clf in enumerate(clfs):
    '''依次训练各个单模型'''
    # print(j, clf)
    '''使用第1个部分作为预测，第2部分来训练模型，获得其预测的输出作为第2部分的新特征。'''
    # X_train, y_train, X_test, y_test = X[train], y[train], X[test], y[test]
    clf.fit(X_d1, y_d1)
    y_submission = clf.predict_proba(X_d2)[:, 1]
    dataset_d1[:, j] = y_submission
    '''对于测试集，直接用这k个模型的预测值作为新的特征。'''
    dataset_d2[:, j] = clf.predict_proba(X_predict)[:, 1]
    print("val auc Score: %f" % roc_auc_score(y_predict, dataset_d2[:, j]))

'''融合使用的模型'''
# clf = LogisticRegression()
clf = GradientBoostingClassifier(learning_rate=0.02, subsample=0.5, max_depth=6, n_estimators=30)
clf.fit(dataset_d1, y_d2)
y_submission = clf.predict_proba(dataset_d2)[:, 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)))