python使用sklearn實現(xiàn)決策樹的方法示例

# -*- coding: utf-8 -*-
"""
Created on Sun Dec 25 11:25:40 2016

@author: Administrator
"""

from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import tree
from sklearn import preprocessing
from sklearn.externals.six import StringIO
import pydotplus
from IPython.display import Image

# Read in the csv file and put features into list of dict and list of class label
allElectornicsData = open('AllElectronics.csv', 'r')
reader = csv.reader(allElectornicsData)
# headers = reader.next()  python2.7 supported  本質獲取csv 文件的第一行數(shù)據(jù)
#headers = reader.__next__()  python 3.5.2 
headers = next(reader)

print(headers)

featureList = []
labelList = []

for row in reader:
  labelList.append(row[len(row) - 1])
  rowDict = {}
  for i in range(1, len(row) - 1):
    rowDict[headers[i]] = row[i]
  featureList.append(rowDict)

print(featureList)
print(labelList)

# Vetorize features
vec = DictVectorizer()
dummyX = vec.fit_transform(featureList).toarray()

print("dummyX: " + str(dummyX))
print(vec.get_feature_names())
print("labelList: " + str(labelList))

# vectorize class labels
lb = preprocessing.LabelBinarizer()
dummyY = lb.fit_transform(labelList)
print("dummyY: ", str(dummyY))

# Using decision tree for classification    ===========【此處調用為算法核心】============
#clf = tree.DecisionTreeClassifier(criterion='entropy')
clf = tree.DecisionTreeClassifier(criterion='gini')
clf = clf.fit(dummyX, dummyY)
print("clf: ", str(clf))

# Visualize model
# dot -Tpdf iris.dot -o ouput.pdf
with open("allElectronicInformationGainOri.dot", 'w') as f:
  f = tree.export_graphviz(clf, feature_names = vec.get_feature_names(), out_file = f)


# predict
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))