In [21]: import pandas as pd
import numpy as np
from scipy import stats
from matplotlib import pyplot as plt
my_data = pd.read_csv("C:\Python\Scripts\my_data\german_credit_data_dataset.csv
")#,dtype=str)
print(my_data.info())
<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000 entries, 0 to 999
Data columns (total 21 columns):
checking_account_status 1000 non-null object
duration 1000 non-null int64
credit_history 1000 non-null object
purpose 1000 non-null object
credit_amount 1000 non-null float64
savings 1000 non-null object
present_employment 1000 non-null object
installment_rate 1000 non-null float64
personal 1000 non-null object
other_debtors 1000 non-null object
present_residence 1000 non-null float64
property 1000 non-null object
age 1000 non-null float64
other_installment_plans 1000 non-null object
housing 1000 non-null object
existing_credits 1000 non-null float64
job 1000 non-null object
dependents 1000 non-null int64
telephone 1000 non-null object
foreign_worker 1000 non-null object
customer_type 1000 non-null int64
dtypes: float64(5), int64(3), object(13)
memory usage: 164.1+ KB
None

In [52]: from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeClassifier
feature_col=['checking_account_status','personal']
X=my_data[['customer_type','credit_amount']] #
for n,my_str in enumerate(feature_col):
my_dummy=pd.get_dummies(my_data[[my_str]],prefix=my_str)
X=pd.concat([X,my_dummy],axis=1)
XX_feature=['credit_amount','checking_account_status_A14','personal_A91',
'personal_A92','personal_A93','personal_A94']
XX=X[XX_feature]
Y=X['customer_type']
X_train,X_test,Y_train,Y_test=train_test_split(XX,Y,test_size=0.2,random_state=0)
my_tree=DecisionTreeClassifier(max_depth=3)
my_tree.fit(X_train,Y_train)
print('分类结果为： ',my_tree.predict(X_test),'\n')
print('平均准确率为： ',my_tree.score(X_test,Y_test))
分类结果为： [1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 2 2
1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1
1 1 1 1 1 1 2 1 1 1 1 1 1 1 1]
平均准确率为： 0.71

In [54]: pd.DataFrame({'feature':XX.columns,'importance':my_tree.feature_importances_})
Out[54]: feature importance
0 credit_amount 0.314532
1 checking_account_status_A14 0.671787
2 personal_A91 0.013680
3 personal_A92 0.000000
4 personal_A93 0.000000
5 personal_A94 0.000000

In [55]: from sklearn import tree
import matplotlib.pyplot as plt
plt.figure(figsize=(18,12))
tree.plot_tree(my_tree,fontsize=12,feature_names=XX.columns,class_names=['Good','Bad
'])
plt.savefig('my_tree')

?