import numpy as np
import pandas as pd 
import matplotlib.pyplot as plt
plt.style.use("ggplot")
%matplotlib inline
import seaborn as sns

from sklearn import datasets 
from sklearn.datasets import make_blobs
from sklearn.model_selection import train_test_split
data, target = make_blobs(n_samples=10000, centers=2, random_state=1, cluster_std=1.0 )
## 創(chuàng)建訓(xùn)練集和測(cè)試集
X_train1,X_test,y_train1,y_test = train_test_split(data, target, test_size=0.2, random_state=1)
## 創(chuàng)建訓(xùn)練集和驗(yàn)證集
X_train,X_val,y_train,y_val = train_test_split(X_train1, y_train1, test_size=0.3, random_state=1)
print("The shape of training X:",X_train.shape)
print("The shape of training y:",y_train.shape)
print("The shape of test X:",X_test.shape)
print("The shape of test y:",y_test.shape)
print("The shape of validation X:",X_val.shape)
print("The shape of validation y:",y_val.shape)
 

from sklearn.svm import SVC
from sklearn.ensemble import RandomForestClassifier
from sklearn.neighbors import KNeighborsClassifier

clfs = [SVC(probability=True),RandomForestClassifier(n_estimators=5,n_jobs=-1,criterion='gini'),KNeighborsClassifier()]

from sklearn.linear_model import LinearRegression
lr = LinearRegression()

val_features = np.zeros((X_val.shape[0],len(clfs)))
test_features = np.zeros((X_test.shape[0],len(clfs)))

for i,clf in enumerate(clfs):
    clf.fit(X_train,y_train)
    val_feature = clf.predict_proba(X_val)[:,1]
    test_feature = clf.predict_proba(X_test)[:,1]
    val_features[:,i] = val_feature
    test_features[:,i] = test_feature

lr.fit(val_features,y_val)

lr.fit(val_features,y_val)
from sklearn.model_selection import cross_val_score
cross_val_score(lr,test_features,y_test,cv=5)