sklearn实现多种机器学习中的集成算法。包括Adaboost，随机森林，梯度提升回归等算法-蒲公英云

sklearn实现多种机器学习中的集成算法。包括Adaboost，随机森林，梯度提升回归等算法

求各位进来的老铁帮个忙。。帮我把最后自己写的那个提升算法完善一下。。测试集该怎么测试准确率？？？求大佬补充

from sklearn.datasets import load_iris
# 用决策树作为基础模型
from sklearn.tree import DecisionTreeClassifier
from sklearn.model_selection import train_test_split
from sklearn.ensemble import GradientBoostingClassifier
from sklearn.ensemble import AdaBoostClassifier
from sklearn.ensemble import RandomForestClassifier
import pandas as pd
# bagging模型
def RandomForestBagging(X, y):
    '''
    随机森林
    :param X:
    :param y:
    :return:
    '''
    x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
    rd = RandomForestClassifier(
        n_estimators=100,
        criterion="gini",
        max_depth=4,
    )
    rd.fit(x_train, y_train)
    print("随机森林的测试集上的准确率:", rd.score(x_test, y_test))
    print("随机森林的训练集上的准确率:", rd.score(x_train, y_train))
# boosting模型汇总
def GardientBoosting(X, y):
    '''
    梯度提升算法
    :return:
    '''
    x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
    gbrt = GradientBoostingClassifier(max_depth=2, n_estimators=3, learning_rate=1.0)
    gbrt.fit(x_train, y_train)
    print("梯度提升回归树的测试集上准确率:", gbrt.score(x_test, y_test))
    print("梯度提升回归树的训练集上准确率:", gbrt.score(x_train, y_train))
def AdaBoosting(X, y):
    '''
    自适应提升算法
    :param X:
    :param y:
    :return:
    '''
    x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
    ada = AdaBoostClassifier(
        base_estimator=DecisionTreeClassifier(max_depth=1),
        n_estimators=100,
        learning_rate=0.5,
        algorithm='SAMME.R',
        random_state=0
    )
    ada.fit(x_train, y_train)
    print("自适应提升算法的测试集上准确率:", ada.score(x_test, y_test))
    print("自适应提升算法的训练集上准确率:", ada.score(x_train, y_train))
# stacking模型汇总
def selfsuanfa(x_train, y_train):
    from sklearn.svm import SVC
    from sklearn.naive_bayes import GaussianNB
    from sklearn.ensemble import RandomForestClassifier, GradientBoostingClassifier
    from sklearn.linear_model import LogisticRegression
    from sklearn.neighbors import KNeighborsClassifier
    from sklearn.neural_network import MLPClassifier
    SEED = 1
    nb = GaussianNB()
    svc = SVC(C=100, probability=True)
    knn = KNeighborsClassifier(n_neighbors=3)
    lr = LogisticRegression(C=100, random_state=SEED)
    nn = MLPClassifier((80, 10), early_stopping=False, random_state=SEED)
    gb = GradientBoostingClassifier(n_estimators=100, random_state=SEED)
    rf = RandomForestClassifier(n_estimators=10, max_features=3, random_state=SEED)
    # 第一层定义好了
    nb.fit(x_train, y_train)
    data1 = nb.predict(x_train).reshape(-1, 1)
    svc.fit(x_train, y_train)
    data2 = svc.predict(x_train).reshape(-1, 1)
    knn.fit(x_train, y_train)
    data3 = knn.predict(x_train).reshape(-1, 1)
    data_level1 = pd.DataFrame(data1, columns=['nb'])
    data_level1['svc'] = data2
    data_level1['knn'] = data3
    data_level1['real'] = y_train
    # print(data_level1)
    # 第二层
    X1 = data_level1[['nb', 'svc', 'knn']]
    y1 = data_level1['real']
    x_train1 = X1
    y_train1 = y1
    nn.fit(x_train1, y_train1)
    data11 = nn.predict(x_train1).reshape(-1, 1)
    data_level2 = pd.DataFrame(data11, columns=['nn'])
    gb.fit(x_train1, y_train1)
    data22 = gb.predict(x_train1).reshape(-1, 1)
    data_level2['gb'] = data22
    lr.fit(x_train1, y_train1)
    data33 = lr.predict(x_train1).reshape(-1, 1)
    data_level2['lr'] = data33
    data_level2['real2'] = y_train1
    # print(data_level2)
    # 第三层
    X2 = data_level2[['nn', 'gb', 'lr']]
    y2 = data_level2[['real2']]
    x_train2 = X2
    y_train2 = y2
    rf.fit(x_train2, y_train2)
    print("最强集成算法的测试集上准确率:", rf.score(x_train2, y_train2))
if __name__ == '__main__':
    iris = load_iris()
    X = iris.data
    y = iris.target
    # model1(X, y)
    RandomForestBagging(X, y)  # 随机森林算法
    GardientBoosting(X, y)  # 梯度提升算法
    AdaBoosting(X, y)   # 自适应提升算法
    x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
    # 训练集上的准确率
    selfsuanfa(x_train, y_train)   # 就这个算法，求老铁补充一下