机器学习笔记(1) -- 决策树

csv的内容为：

运行的代码为：

from sklearn.feature_extraction import DictVectorizer
import csv
from sklearn import tree,preprocessing
from six import StringIO

allElectronicsData = open(r'/Users/zhangsanfeng/Documents/jupyterNotebook/AllElectronics.csv')
reader = csv.reader(allElectronicsData) 
headers = next(reader)  # 获取表头

print(headers)

featureList = []
labelList = []
for row in reader:
    labelList.append(row[len(row)-1])  # 取该行最后一个值
    rowDict = {}
    for i in range(1,len(row)-1):  # 从第二个值开始轮询该行，到倒数第二个值结束
        rowDict[headers[i]] = row[i]  # 用headers里面的值和该行的值组装成一个键值对
    featureList.append(rowDict)  # 将键值对拼接到列表里面

print(featureList)
print(labelList)

vec = DictVectorizer()
dummyX = vec.fit_transform(featureList).toarray()  # 将键值对中的值转换为坐标值
print("dummyX: " + str(dummyX))  # 打印转换后的结果
print(vec.get_feature_names())  # 打印每一项标识的含义
print("labelList: " + str(labelList))  # labelList尚未转换

lb = preprocessing.LabelBinarizer()
dummyY = lb.fit_transform(labelList)  # 转换labelList
print("dummyY: " + str(dummyY))

# 使用决策树进行分类
clf = tree.DecisionTreeClassifier(criterion='entropy')
clf = clf.fit(dummyX, dummyY)
print("clf: " + str(clf))

# 可视化模型，将结果写入到文件
with open("/Users/zhangsanfeng/Documents/jupyterNotebook/allElectronicInformationGainOri.dot", 'w') as f:
    f = tree.export_graphviz(clf, feature_names=vec.get_feature_names(), out_file=f)
oneRowX = dummyX[0, :]
print("oneRowX: " + str(oneRowX))


newRowX = oneRowX
newRowX[0] = 1
newRowX[2] = 0
newRowX = newRowX.reshape(1, -1)  # 这里需要将1维数组转换为2维数组，不然后面会报错

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

predictedY = clf.predict(newRowX)  # 验证测试结果
print("predictedY: " + str(predictedY))

输出结果为：

['RID', 'age', 'income', 'student', 'credit_rating', 'class_buys_computer']
[{'age': 'youth', 'income': 'high', 'student': 'no', 'credit_rating': 'fair'}, {'age': 'youth', 'income': 'high', 'student': 'no', 'credit_rating': 'excellent'}, {'age': 'middle_aged', 'income': 'high', 'student': 'no', 'credit_rating': 'fair'}, {'age': 'senior', 'income': 'medium', 'student': 'no', 'credit_rating': 'fair'}, {'age': 'senior', 'income': 'low', 'student': 'yes', 'credit_rating': 'fair'}, {'age': 'senior', 'income': 'low', 'student': 'yes', 'credit_rating': 'excellent'}, {'age': 'middle_aged', 'income': 'low', 'student': 'yes', 'credit_rating': 'excellent'}, {'age': 'youth', 'income': 'medium', 'student': 'no', 'credit_rating': 'fair'}, {'age': 'youth', 'income': 'low', 'student': 'yes', 'credit_rating': 'fair'}, {'age': 'senior', 'income': 'medium', 'student': 'yes', 'credit_rating': 'fair'}, {'age': 'youth', 'income': 'medium', 'student': 'yes', 'credit_rating': 'excellent'}, {'age': 'middle_aged', 'income': 'medium', 'student': 'no', 'credit_rating': 'excellent'}, {'age': 'middle_aged', 'income': 'high', 'student': 'yes', 'credit_rating': 'fair'}, {'age': 'senior', 'income': 'medium', 'student': 'no', 'credit_rating': 'excellent'}]
['no', 'no', 'yes', 'yes', 'yes', 'no', 'yes', 'no', 'yes', 'yes', 'yes', 'yes', 'yes', 'no']
dummyX: [[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(criterion='entropy')
oneRowX: [0. 0. 1. 0. 1. 1. 0. 0. 1. 0.]
newRowX: [[1. 0. 0. 0. 1. 1. 0. 0. 1. 0.]]
predictedY: [1]