机器学习----决策树

信息熵增益计算决策树

sklearn实现信息熵增益决策树

from sklearn.feature_extraction import DictVectorizer
from sklearn import tree
from sklearn import preprocessing
import csv
import graphviz 

# 读入数据，数据是支付需要用csv读取
Dtree = open(r'AllElectronics.csv', 'r')
reader = csv.reader(Dtree)

# 获取第一行数据
headers = reader.__next__()

# 定义两个列表，特征表和标签表
featureList = []
labelList = []

# 每一行都建立起与头的对应字典
for row in reader:
    # 把label存入list
    labelList.append(row[-1])
    rowDict = {}
    for i in range(1, len(row)-1):
        #建立一个数据字典
        rowDict[headers[i]] = row[i]
    # 把数据字典存入list
    featureList.append(rowDict)

# 把特征数据转换成01表示
vec = DictVectorizer()
x_data = vec.fit_transform(featureList).toarray()

# 把标签转换成01表示
lb = preprocessing.LabelBinarizer()
y_data = lb.fit_transform(labelList)

# 创建决策树模型，criterion='entropy'表示用信息熵来计算
model = tree.DecisionTreeClassifier(criterion='entropy')
# 输入数据建立模型
model.fit(x_data, y_data)

# 测试
x_test = x_data[0]
print("x_test: " + str(x_test))
predict = model.predict(x_test.reshape(1,-1))
print("predict: " + str(predict))

# 导出决策树
dot_data = tree.export_graphviz(model, 
                                out_file = None, 
                                feature_names = vec.get_feature_names(),
                                class_names = lb.classes_,
                                filled = True,
                                rounded = True,
                                special_characters = True)
graph = graphviz.Source(dot_data)
graph.render('MyTree')

cart算法（gini系数决定决策树）

sklearn实现gini系数决策树（cart算法）

手动处理后的数据：

from sklearn import tree
import numpy as np

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

# 创建决策树模型，不传入任何参数默认就是调用的cart算法（利用gini系数来计算）
model = tree.DecisionTreeClassifier()
# 输入数据建立模型
model.fit(x_data, y_data)

# 导出决策树
import graphviz 

dot_data = tree.export_graphviz(model, 
                                out_file = None, 
                                feature_names = ['house_yes','house_no','single','married','divorced','income'],
                                class_names = ['no','yes'],
                                filled = True,
                                rounded = True,
                                special_characters = True)
graph = graphviz.Source(dot_data)
graph.render('Mycart')

导出的决策树（他第一个节点选择的是收入）：

决策树—线性二分类

数据：

import matplotlib.pyplot as plt
import numpy as np
from sklearn.metrics import classification_report
from sklearn import tree

# 载入数据
data = np.genfromtxt("LR-testSet.csv", delimiter=",")
x_data = data[:,:-1] #两列特征 
y_data = data[:,-1] # 一列标签
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data)

# 创建决策树模型（默认是cart算法）
model = tree.DecisionTreeClassifier()
# 输入数据建立模型
model.fit(x_data, y_data)

# 导出决策树
import graphviz 
dot_data = tree.export_graphviz(model, 
                                out_file = None, 
                                feature_names = ['x','y'],
                                class_names = ['label0','label1'],
                                filled = True,
                                rounded = True,
                                special_characters = True)
graph = graphviz.Source(dot_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(取值范围内的一些矩阵坐标点)
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:多维数据转一维.np.c_:横向拼接两个矩阵：[[1,2,3],[4,5,6]]-->[[1,4],[2,5],[3,6]]
z = z.reshape(xx.shape)

# 等高线图
plt.contourf(xx, yy, z)
# 样本散点图
plt.scatter(x_data[:, 0], x_data[:, 1], c=y_data)
plt.show()

结果：

决策树—非线性二分类

数据如下：

import matplotlib.pyplot as plt
import numpy as np
from sklearn.metrics import classification_report
from sklearn import tree
from sklearn.model_selection import train_test_split

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

#分割数据
x_train,x_test,y_train,y_test = train_test_split(x_data, y_data) 

# 创建决策树模型
# max_depth，树的深度
# min_samples_split 内部节点再划分所需最小样本数
model = tree.DecisionTreeClassifier(max_depth=7,min_samples_split=4)
# 输入数据建立模型
model.fit(x_train, y_train)


# 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()

结果：