2020-04-04

分类模型融合

from sklearn.datasets import make_blobs
from sklearn import datasets
from sklearn.tree import DecisionTreeClassifier
import numpy as np
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import VotingClassifier
from xgboost import XGBClassifier
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.model_selection import train_test_split
from sklearn.datasets import make_moons
from sklearn.metrics import accuracy_score,roc_auc_score
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import StratifiedKFold

#Voting投票机制：
'''
硬投票：对多个模型直接进行投票，不区分模型结果的相对重要度，最终投票数最多的类为最终被预测的类。
'''
iris = datasets.load_iris()

x=iris.data
y=iris.target
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3)

clf1 = XGBClassifier(learning_rate=0.1, n_estimators=150, max_depth=3, min_child_weight=2, subsample=0.7,
                     colsample_bytree=0.6, objective='binary:logistic')
clf2 = RandomForestClassifier(n_estimators=50, max_depth=1, min_samples_split=4,
                              min_samples_leaf=63,oob_score=True)
clf3 = SVC(C=0.1)

# 硬投票
eclf = VotingClassifier(estimators=[('xgb', clf1), ('rf', clf2), ('svc', clf3)], voting='hard')
for clf, label in zip([clf1, clf2, clf3, eclf], ['XGBBoosting', 'Random Forest', 'SVM', 'Ensemble']):
    scores = cross_val_score(clf, x, y, cv=5, scoring='accuracy')
    print("Accuracy: %0.2f (+/- %0.2f) [%s]" % (scores.mean(), scores.std(), label))
'''
软投票：和硬投票原理相同，增加了设置权重的功能，可以为不同模型设置不同权重，进而区别模型不同的重要度。
'''
x=iris.data
y=iris.target
x_train,x_test,y_train,y_test=train_test_split(x,y,test_size=0.3)

clf1 = XGBClassifier(learning_rate=0.1, n_estimators=150, max_depth=3, min_child_weight=2, subsample=0.8,
                     colsample_bytree=0.8, objective='binary:logistic')
clf2 = RandomForestClassifier(n_estimators=50, max_depth=1, min_samples_split=4,
                              min_samples_leaf=63,oob_score=True)
clf3 = SVC(C=0.1, probability=True)

# 软投票
eclf = VotingClassifier(estimators=[('xgb', clf1), ('rf', clf2), ('svc', clf3)], voting='soft', weights=[2, 1, 1])
clf1.fit(x_train, y_train)

for clf, label in zip([clf1, clf2, clf3, eclf], ['XGBBoosting', 'Random Forest', 'SVM', 'Ensemble']):
    scores = cross_val_score(clf, x, y, cv=5, scoring='accuracy')
    print("Accuracy: %0.2f (+/- %0.2f) [%s]" % (scores.mean(), scores.std(), label))

#分类的Stacking\Blending融合
'''
5-Fold Stacking
'''
from sklearn.ensemble import RandomForestClassifier
from sklearn.ensemble import ExtraTreesClassifier,GradientBoostingClassifier
import pandas as pd
#创建训练的数据集
data_0=iris.data
data=data_0[:100,:]
target_0=iris.target
target=target_0[:100]
#模型融合中使用到的单个单模型
clfs=[LogisticRegression(solver='lbfgs'),
      RandomForestClassifier(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=0.3, random_state=2020)

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_splits = 5
skf = StratifiedKFold(n_splits)
skf = skf.split(X, y)

for j, clf in enumerate(clfs):
    #依次训练各个单模型
    dataset_blend_test_j = np.zeros((X_predict.shape[0], 5))
    for i, (train, test) in enumerate(skf):
        #5-Fold交叉训练，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。
        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(solver='lbfgs')
clf.fit(dataset_blend_train, y)
y_submission = clf.predict_proba(dataset_blend_test)[:, 1]

print("Val auc Score of Stacking: %f" % (roc_auc_score(y_predict, y_submission)))

#分类的Stacking融合(利用mlxtend)
import warnings
warnings.filterwarnings('ignore')
import itertools
import numpy as np
import seaborn as sns
import matplotlib.pyplot as plt
import matplotlib.gridspec as gridspec
from sklearn import datasets
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB 
from sklearn.ensemble import RandomForestClassifier
from mlxtend.classifier import StackingClassifier
from sklearn.model_selection import cross_val_score
from mlxtend.plotting import plot_learning_curves
from mlxtend.plotting import plot_decision_regions

iris = datasets.load_iris()
X, y = iris.data[:, 1:3], iris.target

clf1 = KNeighborsClassifier(n_neighbors=1)
clf2 = RandomForestClassifier(random_state=1)
clf3 = GaussianNB()
lr = LogisticRegression()
sclf = StackingClassifier(classifiers=[clf1, clf2, clf3], 
                          meta_classifier=lr)
label = ['KNN', 'Random Forest', 'Naive Bayes', 'Stacking Classifier']
clf_list=[clf1,clf2,clf3,sclf]
fig=plt.figure(figsize=(10,8))
gs=gridspec.GridSpec(2,2)
grid=itertools.product([0,1],repeat=2)

clf_cv_mean=[]
clf_cv_std=[]
for clf, label, grd in zip(clf_list, label, grid):
        
    scores = cross_val_score(clf, X, y, cv=3, scoring='accuracy')
    print("Accuracy: %.2f (+/- %.2f) [%s]" %(scores.mean(), scores.std(), label))
    clf_cv_mean.append(scores.mean())
    clf_cv_std.append(scores.std())
        
    clf.fit(X, y)
    ax = plt.subplot(gs[grd[0], grd[1]])
    fig = plot_decision_regions(X=X, y=y, clf=clf)
    plt.title(label)

plt.show()

关于Blending
比stacking简单
使用数据少，可能会过拟合
其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。在第一层，在这70%的数据上训练多个模型，然后去预测那30%数据的label，同时也预测test集的label。在第二层，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，然后用test集第一层预测的label做特征，用第二层训练的模型做进一步预测