1.下載

2.安裝：雙擊

3.創建桌面快捷方式

安裝目錄\bin文件夾\：找到gvedit.exe文件右鍵 發送到桌面快捷方式，如下圖：

4.配置環境變量

將graphviz安裝目錄下的bin文件夾添加到Path環境變量中：

5.驗證是否安裝并配置成功

進入windows命令行界面，輸入dot -version，然后按回車，如果顯示graphviz的相關版本信息，則安裝配置成功。如圖：

6.python環境中安裝：(pycharm中)

File->Settings->Project:Python

然后輸入graphivz安裝

安裝需要等待一會。。。。

決策樹實戰代碼

# -*- coding:utf-8 -*-

from sklearn.feature_extraction import DictVectorizer

import csv

from sklearn import preprocessing

from sklearn import tree

from sklearn.externals.six import StringIO

#read the csv file

allElectronicsDate = open(r'D:\Python\date\AllElectronics.csv','rt')

reader = csv.reader(allElectronicsDate)

headers = next(reader)

# headers = reader.next()

print(headers)#打印輸出第一行標題

#['RID', 'age', 'income', 'student', 'credit_rating', 'Class_buys_computer']

featureList = [] #用來存儲特征值

labelList = [] #用來存儲類標簽

#獲取特征值并打印輸出

for row in reader:

labelList.append(row[len(row) - 1])#每一行最后的值，類標簽

rowDict = {}

for i in range(1,len(row) - 1):#每一行 遍歷除第一列和最后一列的值

rowDict[headers[i]] = row[i]

featureList.append(rowDict)

print(featureList)

#vectorize feature 使用sklearn自帶的方法將特征值離散化為數字標記

vec = DictVectorizer()

dummyX = vec.fit_transform(featureList).toarray()

print("dummyY:" + str(dummyX))

print(vec.get_feature_names())

# print("feature_name" + str(vec.get_feature_names()))

print("labelList:" + str(labelList))

#vectorize class labels #數字化類標簽

lb = preprocessing.LabelBinarizer()

dummyY = lb.fit_transform(labelList)

print("dummyY:" + str(dummyY))

#use the decision tree for classification

clf = tree.DecisionTreeClassifier(criterion='entropy')

clf = clf.fit(dummyX,dummyY) #構建決策樹

#打印構建決策樹采用的參數

print("clf:" + str(clf))

#visilize the model

with open("allElectronicInformationGainOri.dot",'w') as f:

f=tree.export_graphviz(clf,feature_names=vec.get_feature_names(),out_file=f)

#這時就生成了allElectronicInformationGainOri.dot文件

# dot -Tpdf in.dot -o out.pdf dot文件輸出為pdf文件

#驗證數據，取出一行數據，修改幾個屬性預測結果

oneRowX = dummyX[0,:]

print("oneRowX:" + str(oneRowX))

newRowX = oneRowX

newRowX[0] = 1

newRowX[2] = 0

print("newRowX:" + str(newRowX))

predictedY = clf.predict(newRowX)

print("predictedY:"+str(predictedY))

結果：

['RID', 'age', 'income', 'student', 'credit_rating', 'class_buys_computer']

[{'income': 'high', 'age': 'youth', 'student': 'no', 'credit_rating': 'fair'}, {'income': 'high', 'age': 'youth', 'student': 'no', 'credit_rating': 'excellent'}, {'income': 'high', 'age': 'middle_aged', 'student': 'no', 'credit_rating': 'fair'}, {'income': 'medium', 'age': 'senior', 'student': 'no', 'credit_rating': 'fair'}, {'income': 'low', 'age': 'senior', 'student': 'yes', 'credit_rating': 'fair'}, {'income': 'low', 'age': 'senior', 'student': 'yes', 'credit_rating': 'excellent'}, {'income': 'low', 'age': 'middle_aged', 'student': 'yes', 'credit_rating': 'excellent'}, {'income': 'medium', 'age': 'youth', 'student': 'no', 'credit_rating': 'fair'}, {'income': 'low', 'age': 'youth', 'student': 'yes', 'credit_rating': 'fair'}, {'income': 'medium', 'age': 'senior', 'student': 'yes', 'credit_rating': 'fair'}, {'income': 'medium', 'age': 'youth', 'student': 'yes', 'credit_rating': 'excellent'}, {'income': 'medium', 'age': 'middle_aged', 'student': 'no', 'credit_rating': 'excellent'}, {'income': 'high', 'age': 'middle_aged', 'student': 'yes', 'credit_rating': 'fair'}, {'income': 'medium', 'age': 'senior', 'student': 'no', 'credit_rating': 'excellent'}]

dummyY:[[ 0. 0. 1. 0. 1. 1. 0. 0. 1. 0.]

[ 0. 0. 1. 1. 0. 1. 0. 0. 1. 0.]

[ 1. 0. 0. 0. 1. 1. 0. 0. 1. 0.]

[ 0. 1. 0. 0. 1. 0. 0. 1. 1. 0.]

[ 0. 1. 0. 0. 1. 0. 1. 0. 0. 1.]

[ 0. 1. 0. 1. 0. 0. 1. 0. 0. 1.]

[ 1. 0. 0. 1. 0. 0. 1. 0. 0. 1.]

[ 0. 0. 1. 0. 1. 0. 0. 1. 1. 0.]

[ 0. 0. 1. 0. 1. 0. 1. 0. 0. 1.]

[ 0. 1. 0. 0. 1. 0. 0. 1. 0. 1.]

[ 0. 0. 1. 1. 0. 0. 0. 1. 0. 1.]

[ 1. 0. 0. 1. 0. 0. 0. 1. 1. 0.]

[ 1. 0. 0. 0. 1. 1. 0. 0. 0. 1.]

[ 0. 1. 0. 1. 0. 0. 0. 1. 1. 0.]]

['age=middle_aged', 'age=senior', 'age=youth', 'credit_rating=excellent', 'credit_rating=fair', 'income=high', 'income=low', 'income=medium', 'student=no', 'student=yes']

labelList:['no', 'no', 'yes', 'yes', 'yes', 'no', 'yes', 'no', 'yes', 'yes', 'yes', 'yes', 'yes', 'no']

dummyY:[[0]

[0]

[1]

[1]

[1]

[0]

[1]

[0]

[1]

[1]

[1]

[1]

[1]

[0]]

clf:DecisionTreeClassifier(class_weight=None, criterion='entropy', max_depth=None,

max_features=None, max_leaf_nodes=None, min_samples_leaf=1,

min_samples_split=2, min_weight_fraction_leaf=0.0,

random_state=None, splitter='best')

oneRowX:[ 0. 0. 1. 0. 1. 1. 0. 0. 1. 0.]

newRowX:[ 1. 0. 0. 0. 1. 1. 0. 0. 1. 0.]

predictedY:[1]

在項目路徑里面打開dot文件

將dot文件轉化為直觀的PDF文件(dos 里面輸入dot -Tpdf D:\Python\機器學習\allElectronicInformationGainOri.dot -o D:\Python\機器學習\out.pdf 然后回車)

dot -Tpdf D:\Python\機器學習\allElectronicInformationGainOri.dot -o D:\Python\機器學習\out.pdf