def testClass():
myDat, labels = tree.createDataSet()
myTree = tree.createTree(myDat, labels)
# persistenting the decision tree
tree.storeTree(myTree, 'myTree.train')
myTree2 = tree.grabTree('myTree.train')
testVec = [1, 0]
print "Test ",testVec," result: ", tree.classify(myTree2, labels, testVec)
testVec = [1, 1]
print "Test ",testVec," result: ", tree.classify(myTree2, labels, testVec)
def classifyTest():
import tree as t
import treePlotter as tp
dataSet, labels = t.createDataSet()
myTree = t.createTree(dataSet, labels.copy())
print(myTree)
print(labels)
print(classify(myTree, labels, [1, 0]))
print(classify(myTree, labels, [1, 1]))
tp.createPlot(myTree)
#!/usr/bin/python #encoding:utf-8 import tree from ScrolledText import example import plottree dataSet , labels = tree.createDataSet(); print tree.createTree(dataSet, labels) plottree.createPlot()
# -*- coding: utf-8 -*-
import tree
import copy
dataset, label = tree.createDataSet()
print(label)
# 这里仅仅用 labels=label是不行的，因为它们指向同一个内存
labels = copy.deepcopy(label)
myTree = tree.createTree(dataset, labels)
# print(myTree)
print(label)
testResult = tree.classify(myTree, label, [1, 1])
print(testResult)
tree.storeTree(myTree, "F:\NatureRecognition/tree.txt")
tt = tree.grabTree("F:\NatureRecognition/tree.txt")
print(tt)
import tree
# 计算数据集的香农熵
#myDat, labels = tree.createDataSet()
#print(myDat)
#print(tree.calcShannonEnt(myDat))
#myDat[0][-1] = 'maybe'
#print(myDat)
#print(tree.calcShannonEnt(myDat))
print("*****************************************************************")
# 在前面的简单样本数据上测试函数splitDataSet()
#print(tree.splitDataSet(myDat, 0, 1))
#print(tree.splitDataSet(myDat, 0, 0))
print("*****************************************************************")
#myDat, labels = tree.createDataSet()
#print(myDat)
#print(tree.chooseBestFeatureToSplit(myDat))
print("*****************************************************************")
# 变量myTree包含了很多代表树结构信息的嵌套字典。
# 从左边开始第一个关键字no surfacing是第一个划分数据集的特征名称，该关键字的值也是另一个数据字典。
# 第二个关键字是no surfacing特征划分的数据集，这些关键字的值是no surfacing节点的子节点
# 这些值可能是类标签，也可能是另一个数据字典。如果值是类标签，则该子节点是叶子节点；
# 如果值是另一个数据字典，则子节点是一个判断节点，这种格式结构不断重复就构成了整棵树，本节的例子中，这棵树包含了3个叶子节点以及2个判断节点
myDat, labels = tree.createDataSet()
myTree = tree.createTree(myDat, labels)
print(myTree)
#-*- coding:utf-8 -*- import tree mydat,label = tree.createDataSet() #mydat #tree.calcShannonEnt(mydat)#得到数据集的熵值 #reload(tree) #tree.splitDataSet(mydat,0,1)#得到第0个特征值为1的元素list #tree.splitDataSet(mydat,0,0) #tree.chooseBestFeatureToSplit(mydat)#得到最佳特征值索引 mytree = tree.createTree(mydat,label)#得到决策树信息 mytree
# -*- coding: utf-8 -*-
"""
Created on Wed May 23 09:56:25 2018
@author: 705family
"""
import os
os.chdir("C:/Users/705family/Desktop/decisiontree")
import tree
data, y = tree.createDataSet()
myTree = tree.createTree(data, y)
# In[] test Part 2
from sklearn.preprocessing import LabelEncoder
import pandas as pd
import numpy as np
data = pd.read_excel('西瓜数据集.xlsx')
data = data.iloc[:, 1:-1]
clf = LabelEncoder()
label = [[] for i in range(np.size(data, 1))]
for i in range(np.size(data, 1)):
data.iloc[:, i] = clf.fit_transform(data.iloc[:, i])
label[i][:] = list(clf.classes_)
y = data.iloc[:, -1]
data = np.array(data)
data = data.tolist()
def testEntr():
myDat, labels = tree.createDataSet()
print tree.calcShannonEnt(myDat)
