【阿旭机器学习实战】【32】预测银行客户是否会开设定期存款账户--逻辑回归

import pandas as pd
import numpy as np
from sklearn import preprocessing
import matplotlib.pyplot as plt 
plt.rc("font", size=14)
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
import seaborn as sns
sns.set(style="white")
sns.set(style="whitegrid", color_codes=True)

data = pd.read_csv('banking.csv', header=0)
data = data.dropna()
print(data.shape)
print(list(data.columns))

(41188, 21)
['age', 'job', 'marital', 'education', 'default', 'housing', 'loan', 'contact', 'month', 'day_of_week', 'duration', 'campaign', 'pdays', 'previous', 'poutcome', 'emp_var_rate', 'cons_price_idx', 'cons_conf_idx', 'euribor3m', 'nr_employed', 'y']

data.head()

data['education'].unique()

array(['basic.4y', 'unknown', 'university.degree', 'high.school',
       'basic.9y', 'professional.course', 'basic.6y', 'illiterate'],
      dtype=object)

# 将教育类型basic.9y，basic.6y，basic.4y 均变为Basic
data['education']=np.where(data['education'] =='basic.9y', 'Basic', data['education'])
data['education']=np.where(data['education'] =='basic.6y', 'Basic', data['education'])
data['education']=np.where(data['education'] =='basic.4y', 'Basic', data['education'])

data['education'].unique()

array(['Basic', 'unknown', 'university.degree', 'high.school',
       'professional.course', 'illiterate'], dtype=object)

data['y'].value_counts()

0    36548
1     4640
Name: y, dtype: int64

# 查看数据标签比例
sns.countplot(x='y', data = data, palette='hls')
plt.show()
plt.savefig('count_plot')

count_no_sub = len(data[data['y']==0])
count_sub = len(data[data['y']==1])
pct_of_no_sub = count_no_sub/(count_no_sub+count_sub)
print('未开户的百分比:  %.2f%%' % (pct_of_no_sub*100))
pct_of_sub = count_sub/(count_no_sub+count_sub)
print('开户的百分比:  %.2f%%' % (pct_of_sub*100))

未开户的百分比:  88.73%
开户的百分比:  11.27%

data.groupby('y').mean()

data.groupby('job').mean()

data.groupby('marital').mean()

data.groupby('education').mean()

%matplotlib inline
table=pd.crosstab(data.job,data.y)
table.div(table.sum(1).astype(float), axis=0).plot(kind='bar', stacked=True)
plt.title('Stacked Bar Chart of Job title vs Purchase')
plt.xlabel('Job')
plt.ylabel('Proportion of Purchase')
plt.savefig('purchase_vs_job')

table=pd.crosstab(data.marital,data.y)
table.div(table.sum(1).astype(float), axis=0).plot(kind='bar', stacked=True)
plt.title('Stacked Bar Chart of Marital Status vs Purchase')
plt.xlabel('Marital Status')
plt.ylabel('Proportion of Customers')
plt.savefig('mariral_vs_pur_stack')

table=pd.crosstab(data.education,data.y)
table.div(table.sum(1).astype(float), axis=0).plot(kind='bar', stacked=True)
plt.title('Stacked Bar Chart of Education vs Purchase')
plt.xlabel('Education')
plt.ylabel('Proportion of Customers')
plt.savefig('edu_vs_pur_stack')

table=pd.crosstab(data.day_of_week,data.y)#.plot(kind='bar')
table.div(table.sum(1).astype(float), axis=0).plot(kind='bar', stacked=True)
plt.title('Stacked Bar Chart of Day of Week vs Purchase')
plt.xlabel('Day of Week')
plt.ylabel('Proportion of Purchase')
plt.savefig('dow_vs_purchase')

cat_vars=['job','marital','education','default','housing','loan','contact','month','day_of_week','poutcome']
# 对以上特征参数进行独热编码
for var in cat_vars:
    cat_list = pd.get_dummies(data[var], prefix=var)
    data=data.join(cat_list)

# 删除cat_vars原始类型特征列
data_final=data.drop(cat_vars, axis=1)
data_final.columns.values

array(['age', 'duration', 'campaign', 'pdays', 'previous', 'emp_var_rate',
       'cons_price_idx', 'cons_conf_idx', 'euribor3m', 'nr_employed', 'y',
       'job_admin.', 'job_blue-collar', 'job_entrepreneur',
       'job_housemaid', 'job_management', 'job_retired',
       'job_self-employed', 'job_services', 'job_student',
       'job_technician', 'job_unemployed', 'job_unknown',
       'marital_divorced', 'marital_married', 'marital_single',
       'marital_unknown', 'education_Basic', 'education_high.school',
       'education_illiterate', 'education_professional.course',
       'education_university.degree', 'education_unknown', 'default_no',
       'default_unknown', 'default_yes', 'housing_no', 'housing_unknown',
       'housing_yes', 'loan_no', 'loan_unknown', 'loan_yes',
       'contact_cellular', 'contact_telephone', 'month_apr', 'month_aug',
       'month_dec', 'month_jul', 'month_jun', 'month_mar', 'month_may',
       'month_nov', 'month_oct', 'month_sep', 'day_of_week_fri',
       'day_of_week_mon', 'day_of_week_thu', 'day_of_week_tue',
       'day_of_week_wed', 'poutcome_failure', 'poutcome_nonexistent',
       'poutcome_success'], dtype=object)

通过从次要类（已经开户的用户）创建合成样本而不是创建副本来工作。
随机选择一个k-最近邻居并使用它来创建一个类似但随机调整的新观察结果。

X = data_final.loc[:, data_final.columns != 'y']
y = data_final.loc[:, data_final.columns == 'y'].values.ravel()
from imblearn.over_sampling import SMOTE
os = SMOTE(random_state=0)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
columns = X_train.columns
os_data_X,os_data_y=os.fit_resample(X_train, y_train)
os_data_X = pd.DataFrame(data=os_data_X,columns=columns )
os_data_y= pd.DataFrame(data=os_data_y,columns=['y'])
# we can Check the numbers of our data
print("过采样以后的数据量: ",len(os_data_X))
print("未开户的用户数量: ",len(os_data_y[os_data_y['y']==0]))
print("开户的用户数量: ",len(os_data_y[os_data_y['y']==1]))
print("未开户的用户数量的百分比: ",len(os_data_y[os_data_y['y']==0])/len(os_data_X))
print("开户的用户数量的百分比: ",len(os_data_y[os_data_y['y']==1])/len(os_data_X))

过采样以后的数据量:  51134
未开户的用户数量:  25567
开户的用户数量:  25567
未开户的用户数量的百分比:  0.5
开户的用户数量的百分比:  0.5

from sklearn.linear_model import LogisticRegression
from sklearn import metrics
#X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=0)
logreg = LogisticRegression()
logreg.fit(os_data_X, os_data_y.values.reshape(-1))

y_pred = logreg.predict(X_test)
print('在测试数据集上面的预测准确率: {:.2f}'.format(logreg.score(X_test, y_test)))

在测试数据集上面的预测准确率: 0.90

from sklearn.metrics import classification_report
print(classification_report(y_test, y_pred))

precision    recall  f1-score   support
           0       0.95      0.93      0.94     10981
           1       0.52      0.63      0.57      1376
    accuracy                           0.90     12357
   macro avg       0.74      0.78      0.76     12357
weighted avg       0.90      0.90      0.90     12357

from sklearn.metrics import roc_auc_score
from sklearn.metrics import roc_curve
logit_roc_auc = roc_auc_score(y_test, logreg.predict(X_test))
fpr, tpr, thresholds = roc_curve(y_test, logreg.predict_proba(X_test)[:,1])
plt.figure()
plt.plot(fpr, tpr, label='Logistic Regression (area = %0.2f)' % logit_roc_auc)
plt.plot([0, 1], [0, 1],'r--')
plt.xlim([0.0, 1.0])
plt.ylim([0.0, 1.05])
plt.xlabel('False Positive Rate')
plt.ylabel('True Positive Rate')
plt.title('Receiver operating characteristic')
plt.legend(loc="lower right")
plt.savefig('Log_ROC')
plt.show()