python 决策树

RID age income student credit_rating Class:buys_computer
1 youth high no fair no
2 youth high no excellent no
3 middle_aged high no fair no
4 senior medium no fair yes
5 senior low yes fair yes
6 senior low yes excellent no
7 middle_aged low yes excellent yes
8 youth medium no fair no
9 youth low yes fair yes
10 senior medium yes fair yes
11 youth medium yes excellent yes
12 middle_aged medium no excellent yes
13 middle_aged high yes fair yes
14 senior medium no excellent no

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

import csv
import numpy as np

all_csv_data = open(‘DT.csv‘, ‘rt‘)
reader = csv.reader(all_csv_data)
header = next(reader)

feature_list = []
label_list = []

for row in reader:
    label_list.append(row[len(row) - 1])
    row_dict = {}
    for i in range(1, len(row)-1):
        row_dict[header[i]] = row[i]
    feature_list.append(row_dict)
#print(feature_list)

vec = DictVectorizer()
dummyX = vec.fit_transform(feature_list).toarray()
print(dummyX)

lb = preprocessing.LabelBinarizer()
dummyY = lb.fit_transform(label_list)

clf = tree.DecisionTreeClassifier(criterion = ‘entropy‘)
clf = clf.fit(dummyX, dummyY)


with open("dt.dot", ‘w‘) as f:
    f = tree.export_graphviz(clf, feature_names=vec.get_feature_names(), out_file=f)

OneRowX = dummyX[0,:]
print("OneRowX:\n"+str(OneRowX))
#newRowX = OneRowX
#newRowX[0] = 1
#newRowX[1] = 0
#print("NewRowX:\n"+str(newRowX))

predY = clf.predict(dummyX)
print("predY :"+str(predY))
print("dummyX:"+str(np.array(dummyY).transpose()))