Neaya~

笔记、记录、总结

决策树

发表于 更新于 分类于 评论数：
本文字数： 5.2k 阅读时长 ≈ 5 分钟

决策树、分类

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 yes
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 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
"""
# @Time    :  2020/8/3
# @Author  :  Jimou Chen
"""
from sklearn.feature_extraction import DictVectorizer  # 把字符数据转化成0和1
from sklearn import tree  # 导入决策树
from sklearn import preprocessing
import csv

# 读入数据
f = open(r'AllElectronics.csv', 'r')
reader = csv.reader(f)

# 获取csv文件第一行数据，即特征
header = reader.__next__()
# print(header)

# 定义特征和标签列表
feature_list = []
label_list = []

# 获取1-6列有效数据
for row in reader:
    # print(row)
    # 把label存入list
    label_list.append(row[-1])
    row_dict = {}
    # 第0列数据是序号，没有用的，所以不要，最后一列也不取
    for i in range(1, len(row) - 1):
        row_dict[header[i]] = row[i]
    # 得到有效的特征数据
    feature_list.append(row_dict)

print('feature_list :\n', feature_list)

# 把数据转化成01,先实例化一个对象
vec = DictVectorizer()
x_data = vec.fit_transform(feature_list).toarray()
print('x_data : \n', x_data)

# 打印特征名称
print(vec.get_feature_names())
# 打印标签列表
print(label_list)

# 把标签也转换为01
label = preprocessing.LabelBinarizer()
y_data = label.fit_transform(label_list)
print('y_data : \n', y_data)

# 创建决策树模型,分类器是属性为entropy的分类器
tree_model = tree.DecisionTreeClassifier(criterion='entropy')
# 输入数据建立模型
tree_model.fit(x_data, y_data)

# 先拿个训练数据来测试一下
x_test = x_data[0]
print('x_test:', x_test)
# print(x_test.reshape(1, -1))
# reshape(1, -1)是把x_test从一维变成二维，predict里面要求传二维数据
prediction = tree_model.predict(x_test.reshape(1, -1))
print('预测结果是：', prediction)

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
feature_list :
 [{'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'}]
x_data : 
 [[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']
['no', 'no', 'yes', 'yes', 'yes', 'no', 'yes', 'no', 'yes', 'yes', 'yes', 'yes', 'yes', 'no']
y_data : 
 [[0]
 [0]
 [1]
 [1]
 [1]
 [0]
 [1]
 [0]
 [1]
 [1]
 [1]
 [1]
 [1]
 [0]]
x_test: [0. 0. 1. 0. 1. 1. 0. 0. 1. 0.]
预测结果是： [0]

  • reshape(1, -1)是把x_test从一维变成二维，predict里面要求传二维数据
Welcome to reward