sklearn速度复习-集成学习

#bagging
# 导入算法包以及数据集
from sklearn import neighbors
from sklearn import datasets
from sklearn.ensemble import BaggingClassifier
from sklearn import tree
from sklearn.model_selection import train_test_split
import numpy as np
import matplotlib.pyplot as plt

iris = datasets.load_iris()
x_data = iris.data[:,:2]
y_data = iris.target

x_train,x_test,y_train,y_test = train_test_split(x_data, y_data)

knn = neighbors.KNeighborsClassifier()
knn.fit(x_train, y_train)

def plot(model):
    x_min, x_max = x_data[:, 0].min() - 1, x_data[:, 0].max() + 1 # 获取数据值所在的范围
    y_min, y_max = x_data[:, 1].min() - 1, x_data[:, 1].max() + 1

    xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02), # 生成网格矩阵
                         np.arange(y_min, y_max, 0.02))

    z = model.predict(np.c_[xx.ravel(), yy.ravel()])# ravel与flatten类似，多维数据转一维。flatten不会改变原始数据，ravel会改变原始数据
    z = z.reshape(xx.shape)
    cs = plt.contourf(xx, yy, z)# 等高线图
    
plot(knn)# 画图
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data)# 样本散点图
plt.show()
knn.score(x_test, y_test)# 准确率

dtree = tree.DecisionTreeClassifier()
dtree.fit(x_train, y_train)

plot(dtree)# 画图
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data)# 样本散点图
plt.show()
dtree.score(x_test, y_test)# 准确率

bagging_knn = BaggingClassifier(knn, n_estimators=100)
bagging_knn.fit(x_train, y_train)# 输入数据建立模型
plot(bagging_knn)
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data)# 样本散点图
plt.show()
bagging_knn.score(x_test, y_test)

bagging_tree = BaggingClassifier(dtree, n_estimators=100)
bagging_tree.fit(x_train, y_train)# 输入数据建立模型
plot(bagging_tree)
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data)# 样本散点图
plt.show()
bagging_tree.score(x_test, y_test)

#RF
from sklearn import tree
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestClassifier
import numpy as np
import matplotlib.pyplot as plt

data = np.genfromtxt("LR-testSet2.txt", delimiter=",")# 载入数据
x_data = data[:,:-1]
y_data = data[:,-1]

plt.scatter(x_data[:,0],x_data[:,1],c=y_data)
plt.show()

x_train,x_test,y_train,y_test = train_test_split(x_data, y_data, test_size = 0.5)

def plot(model):
    x_min, x_max = x_data[:, 0].min() - 1, x_data[:, 0].max() + 1# 获取数据值所在的范围
    y_min, y_max = x_data[:, 1].min() - 1, x_data[:, 1].max() + 1

    xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02), # 生成网格矩阵
                         np.arange(y_min, y_max, 0.02))

    z = model.predict(np.c_[xx.ravel(), yy.ravel()])# ravel与flatten类似，多维数据转一维。flatten不会改变原始数据，ravel会改变原始数据
    z = z.reshape(xx.shape)
    cs = plt.contourf(xx, yy, z)# 等高线图
    plt.scatter(x_test[:, 0], x_test[:, 1], c=y_test)# 样本散点图
    plt.show()
    
dtree = tree.DecisionTreeClassifier()
dtree.fit(x_train, y_train)
plot(dtree)
dtree.score(x_test, y_test)

RF = RandomForestClassifier(n_estimators=50)
RF.fit(x_train, y_train)
plot(RF)
RF.score(x_test, y_test)

#adaboost
import numpy as np
import matplotlib.pyplot as plt
from sklearn import tree
from sklearn.ensemble import AdaBoostClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.datasets import make_gaussian_quantiles
from sklearn.metrics import classification_report
# 生成2维正态分布，生成的数据按分位数分为两类，500个样本,2个样本特征
x1, y1 = make_gaussian_quantiles(n_samples=500, n_features=2,n_classes=2)
# 生成2维正态分布，生成的数据按分位数分为两类，400个样本,2个样本特征均值都为3
x2, y2 = make_gaussian_quantiles(mean=(3, 3), n_samples=500, n_features=2, n_classes=2)
# 将两组数据合成一组数据
x_data = np.concatenate((x1, x2))
y_data = np.concatenate((y1, - y2 + 1))
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data)
plt.show()
# 决策树模型
model = tree.DecisionTreeClassifier(max_depth=3)
# 输入数据建立模型
model.fit(x_data, y_data)
# 获取数据值所在的范围
x_min, x_max = x_data[:, 0].min() - 1, x_data[:, 0].max() + 1
y_min, y_max = x_data[:, 1].min() - 1, x_data[:, 1].max() + 1
# 生成网格矩阵
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02),
                     np.arange(y_min, y_max, 0.02))
z = model.predict(np.c_[xx.ravel(), yy.ravel()])# ravel与flatten类似，多维数据转一维。flatten不会改变原始数据，ravel会改变原始数据
z = z.reshape(xx.shape)
# 等高线图
cs = plt.contourf(xx, yy, z)
# 样本散点图
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data)
plt.show()
# 模型准确率
model.score(x_data,y_data)
# AdaBoost模型
model = AdaBoostClassifier(DecisionTreeClassifier(max_depth=3),n_estimators=10)
# 训练模型
model.fit(x_data, y_data)
# 获取数据值所在的范围
x_min, x_max = x_data[:, 0].min() - 1, x_data[:, 0].max() + 1
y_min, y_max = x_data[:, 1].min() - 1, x_data[:, 1].max() + 1
# 生成网格矩阵
xx, yy = np.meshgrid(np.arange(x_min, x_max, 0.02),
                     np.arange(y_min, y_max, 0.02))
# 获取预测值
z = model.predict(np.c_[xx.ravel(), yy.ravel()])
z = z.reshape(xx.shape)
# 等高线图
cs = plt.contourf(xx, yy, z)
# 样本散点图
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data)
plt.show()
# 模型准确率
model.score(x_data,y_data)

#stacking
from sklearn import datasets  
from sklearn import model_selection  
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier  
from sklearn.tree import DecisionTreeClassifier
from mlxtend.classifier import StackingClassifier # pip install mlxtend
import numpy as np  
# 载入数据集
iris = datasets.load_iris()  
# 只要第1,2列的特征
x_data, y_data = iris.data[:, 1:3], iris.target  
# 定义三个不同的分类器
clf1 = KNeighborsClassifier(n_neighbors=1)  
clf2 = DecisionTreeClassifier() 
clf3 = LogisticRegression()  
# 定义一个次级分类器
lr = LogisticRegression()  
sclf = StackingClassifier(classifiers=[clf1, clf2, clf3],   
                          meta_classifier=lr)
for clf,label in zip([clf1, clf2, clf3, sclf],
                      ['KNN','Decision Tree','LogisticRegression','StackingClassifier']):  
    scores = model_selection.cross_val_score(clf, x_data, y_data, cv=3, scoring='accuracy')  
    print("Accuracy: %0.2f [%s]" % (scores.mean(), label)) 

#voting
from sklearn import datasets  
from sklearn import model_selection  
from sklearn.linear_model import LogisticRegression
from sklearn.neighbors import KNeighborsClassifier  
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import VotingClassifier
import numpy as np
# 载入数据集
iris = datasets.load_iris()  
# 只要第1,2列的特征
x_data, y_data = iris.data[:, 1:3], iris.target  
# 定义三个不同的分类器
clf1 = KNeighborsClassifier(n_neighbors=1)  
clf2 = DecisionTreeClassifier() 
clf3 = LogisticRegression()  
sclf = VotingClassifier([('knn',clf1),('dtree',clf2), ('lr',clf3)])   
for clf, label in zip([clf1, clf2, clf3, sclf],
                      ['KNN','Decision Tree','LogisticRegression','VotingClassifier']):  
    scores = model_selection.cross_val_score(clf, x_data, y_data, cv=3, scoring='accuracy')  
    print("Accuracy: %0.2f [%s]" % (scores.mean(), label))