机器学习：决策树推导及代码示例

 

 

特征提取代码

#导入字典特征提取库
from sklearn.feature_extraction import DictVectorizer
#输入字典数据
data=[{"city":"北京","temperature":100},
{"city":"上海","temperature":60},
{"city":"深圳","temperature":30}]
#实例化一个转化器类
tranfer = DictVectorizer(sparse=False)
#进行特征提取
data = tranfer.fit_transform(data)
#输出结果
print("特征名字为:\n",tranfer.get_feature_names())
print("返回结果为:\n",data)
"""-----------输出----------------
特征名字为:
 ['city=上海', 'city=北京', 'city=深圳', 'temperature']
返回结果为:
 [[  0.   1.   0. 100.]
 [  1.   0.   0.  60.]
 [  0.   0.   1.  30.]]
-----------------------------------"""
#输入字典数据
data=[{"city":"北京","temperature":100},
{"city":"上海","temperature":60},
{"city":"深圳","temperature":30}]
#实例化一个转化器
tranfer = DictVectorizer(sparse=True)
#进行特征提取
data = tranfer.fit_transform(data)
#输出结果
print("特征名字为:\n",tranfer.get_feature_names())
print("返回结果为:\n",data)
"""---------------------输出--------------------------
特征名字为:
 ['city=上海', 'city=北京', 'city=深圳', 'temperature']
返回结果为:
   (0, 1)	1.0
  (0, 3)	100.0
  (1, 0)	1.0
  (1, 3)	60.0
  (2, 2)	1.0
  (2, 3)	30.0
-------------------------------------------------------"""

决策树代码

""" 1.获取数据
 2.数据基本处理
-2.1 确定特征值、目标值
-2.2 缺失值处理
-2.3 数据集划分
3.特征工程（字典特征抽取）
4.机器学习（决策树）
5.模型评估"""

#读取文件库
import pandas as pd
import numpy as np
#数据集划分库
from sklearn.model_selection import train_test_split
#特征工程库
from sklearn.feature_extraction import DictVectorizer
#决策树库
from sklearn.tree import DecisionTreeClassifier
#可视化库
from sklearn.tree import export_graphviz
# 1.获取数据
data = pd.read_csv("DataSet.csv")
# 2.数据基本处理
# -2.1 确定特征值、目标值
x = data[["house","marital status","income"]]
y = data["default loan"]
#2.3 数据集划分
x_train,x_test,y_train,y_test = train_test_split(x,y,random_state=11,test_size=0.2)
#3.特征工程
x_train = x_train.to_dict(orient="records")
x_test = x_test.to_dict(orient="records")

transfer = DictVectorizer()
x_train = transfer.fit_transform(x_train)
x_test = transfer.fit_transform(x_test)
#4. 机器学习（决策树）
estimator = DecisionTreeClassifier()

estimator.fit(x_train,y_train)
#5. 模型评估
y_pre =estimator.predict(x_test)
estimator.score(x_test,y_test)
#决策树可视化
export_graphviz(estimator,out_file="tree1.dot",feature_names=transfer.get_feature_names())

data.csv

house	marital status	income	default loan
1	Single	125	0
0	Married	100	0
0	Single	70	0
1	Married	120	0
0	Divorced	95	1
0	Married	60	0
1	Divorced	220	0
0	Single	85	1
0	Married	75	0
0	single	90	1
1	Single	125	0
0	Married	100	0
0	Single	70	0
1	Married	120	0
0	Divorced	95	1
0	Married	60	0
1	Divorced	220	0
0	Single	85	1
0	Married	75	0
0	single	90	1
1	Single	125	0
0	Married	100	0
0	Single	70	0
1	Married	120	0
0	Divorced	95	1
0	Married	60	0
1	Divorced	220	0
0	Single	85	1
0	Married	75	0
0	single	90	1
1	Single	125	0
0	Married	100	0
0	Single	70	0
1	Married	120	0
0	Divorced	95	1
0	Married	60	0
1	Divorced	220	0
0	Single	85	1
0	Married	75	0
0	single	90	1
1	Single	125	0
0	Married	100	0
0	Single	70	0
1	Married	120	0
0	Divorced	95	1
0	Married	60	0
1	Divorced	220	0
0	Single	85	1
0	Married	75	0
0	single	90	1
1	Single	125	0
0	Married	100	0
0	Single	70	0
1	Married	120	0
0	Divorced	95	1
0	Married	60	0
1	Divorced	220	0
0	Single	85	1
0	Married	75	0
0	single	90	1
1	Single	125	0
0	Married	100	0
0	Single	70	0
1	Married	120	0
0	Divorced	95	1
0	Married	60	0
1	Divorced	220	0
0	Single	85	1
0	Married	75	0
0	single	90	1
1	Single	125	0
0	Married	100	0
0	Single	70	0
1	Married	120	0
0	Divorced	95	1
0	Married	60	0
1	Divorced	220	0
0	Single	85	1
0	Married	75	0
0	single	90	1

生成的决策树