模型融合

一、 Stacking

代码如下：

# 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=2018)


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)))

二、 blending

bending主要思路是把原始的训练集先分成两部分，比如70%的数据作为新的训练集，剩下30%的数据作为测试集。第一层我们在这70%的数据上训练多个模型，然后去预测那30%数据的label。在第二层里，我们就直接用这30%数据在第一层预测的结果做为新特征继续训练即可。

代码如下：

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=2018)

'''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=2018)
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)))

参考GitHub