1 import pandas
 2 
 3 data=pandas.read_csv(
 4      "C:\\Users\\Jw\\Desktop\\python_work\\Python数据挖掘实战课程课件\\5.3\\data.csv")
 5 
 6 dummyColumns=["Gender", "ParentEncouragement"]
 7 
 8 for column in dummyColumns:
 9     data[column]=data[column].astype("category")
10     
11 
12 dummiesData=pandas.get_dummies(
13         data,
14         columns=dummyColumns,
15         prefix=dummyColumns,
16         prefix_sep="=",
17         drop_first=True)
18 
19 dummiesData.columns

fData=dummiesData[[
     ‘ParentIncome‘, ‘IQ‘, ‘Gender=Male‘,
    ‘ParentEncouragement=Not Encouraged‘]]
    
tData=dummiesData["CollegePlans"]

1 from sklearn.tree import DecisionTreeClassifier
2 
3 dtModel=DecisionTreeClassifier(max_leaf_nodes=8)   #该处为调优
4 
5 from sklearn.model_selection import cross_val_score
6 
7 cross_val_score(
8     dtModel,
9     fData,tData,cv=10)