其他
Kaggle竞赛:Python银行信用卡客户流失预测
The following article is from Python实用宝典 Author Ckend
2.数据集
https://www.kaggle.com/thomaskonstantin/bank-churn-data-exploration-and-churn-prediction/
3.代码与分析
pip install pandas
pip install plotly
pip install scikit-learn
pip install scikit-plot
# 最后模型预测需要用到,安装需要conda
# 如果只是想探索性分析数据,可以不导入 imblearn
conda install -c conda-forge imbalanced-learn
3.1 导入需要的模块
import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)
import matplotlib.pyplot as plt
import seaborn as sns
import plotly.express as ex
import plotly.graph_objs as go
import plotly.figure_factory as ff
from plotly.subplots import make_subplots
import plotly.offline as pyo
pyo.init_notebook_mode()
sns.set_style('darkgrid')
from sklearn.decomposition import PCA
from sklearn.model_selection import train_test_split,cross_val_score
from sklearn.ensemble import RandomForestClassifier,AdaBoostClassifier
from sklearn.svm import SVC
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.metrics import f1_score as f1
from sklearn.metrics import confusion_matrix
import scikitplot as skplt
plt.rc('figure',figsize=(18,9))
%pip install imbalanced-learn
from imblearn.over_sampling import SMOTE
遇到任何 No module named "XXX" 都可以尝试pip install一下。
3.2 加载数据
c_data = c_data[c_data.columns[:-2]]
c_data.head(3)
3.3 探索性数据分析
tr1=go.Box(x=c_data['Customer_Age'],name='Age Box Plot',boxmean=True)
tr2=go.Histogram(x=c_data['Customer_Age'],name='Age Histogram')
fig.add_trace(tr1,row=1,col=1)
fig.add_trace(tr2,row=2,col=1)
fig.update_layout(height=700, width=1200, title_text="Distribution of Customer Ages")
fig.show()
tr1=go.Box(x=c_data['Dependent_count'],name='Dependent count Box Plot',boxmean=True)
tr2=go.Histogram(x=c_data['Dependent_count'],name='Dependent count Histogram')
fig.add_trace(tr1,row=1,col=1)
fig.add_trace(tr2,row=2,col=1)
fig.update_layout(height=700, width=1200, title_text="Distribution of Dependent counts (close family size)")
fig.show()
可见大部分人的年收入处于60K美元以下。
tr1=go.Box(x=c_data['Months_on_book'],name='Months on book Box Plot',boxmean=True)
tr2=go.Histogram(x=c_data['Months_on_book'],name='Months on book Histogram')
fig.add_trace(tr1,row=1,col=1)
fig.add_trace(tr2,row=2,col=1)
fig.update_layout(height=700, width=1200, title_text="Distribution of months the customer is part of the bank")
fig.show()
tr1=go.Box(x=c_data['Total_Relationship_Count'],name='Total no. of products Box Plot',boxmean=True)
tr2=go.Histogram(x=c_data['Total_Relationship_Count'],name='Total no. of products Histogram')
fig.add_trace(tr1,row=1,col=1)
fig.add_trace(tr2,row=2,col=1)
fig.update_layout(height=700, width=1200, title_text="Distribution of Total no. of products held by the customer")
fig.show()
tr1=go.Box(x=c_data['Months_Inactive_12_mon'],name='number of months inactive Box Plot',boxmean=True)
tr2=go.Histogram(x=c_data['Months_Inactive_12_mon'],name='number of months inactive Histogram')
fig.add_trace(tr1,row=1,col=1)
fig.add_trace(tr2,row=2,col=1)
fig.update_layout(height=700, width=1200, title_text="Distribution of the number of months inactive in the last 12 months")
fig.show()
tr1=go.Box(x=c_data['Credit_Limit'],name='Credit_Limit Box Plot',boxmean=True)
tr2=go.Histogram(x=c_data['Credit_Limit'],name='Credit_Limit Histogram')
fig.add_trace(tr1,row=1,col=1)
fig.add_trace(tr2,row=2,col=1)
fig.update_layout(height=700, width=1200, title_text="Distribution of the Credit Limit")
fig.show()
tr1=go.Box(x=c_data['Total_Trans_Amt'],name='Total_Trans_Amt Box Plot',boxmean=True)
tr2=go.Histogram(x=c_data['Total_Trans_Amt'],name='Total_Trans_Amt Histogram')
fig.add_trace(tr1,row=1,col=1)
fig.add_trace(tr2,row=2,col=1)
fig.update_layout(height=700, width=1200, title_text="Distribution of the Total Transaction Amount (Last 12 months)")
fig.show()
3.4 数据预处理
c_data.Gender = c_data.Gender.replace({'F':1,'M':0})
c_data = pd.concat([c_data,pd.get_dummies(c_data['Education_Level']).drop(columns=['Unknown'])],axis=1)
c_data = pd.concat([c_data,pd.get_dummies(c_data['Income_Category']).drop(columns=['Unknown'])],axis=1)
c_data = pd.concat([c_data,pd.get_dummies(c_data['Marital_Status']).drop(columns=['Unknown'])],axis=1)
c_data = pd.concat([c_data,pd.get_dummies(c_data['Card_Category']).drop(columns=['Platinum'])],axis=1)
c_data.drop(columns = ['Education_Level','Income_Category','Marital_Status','Card_Category','CLIENTNUM'],inplace=True)
显示热力图:
3.5 SMOTE模型采样
X, y = oversample.fit_resample(c_data[c_data.columns[1:]], c_data[c_data.columns[0]])
usampled_df = X.assign(Churn = y)
ohe_data =usampled_df[usampled_df.columns[15:-1]].copy()
usampled_df = usampled_df.drop(columns=usampled_df.columns[15:-1])
sns.heatmap(usampled_df.corr('pearson'),annot=True)
3.6 主成分分析
pca_model = PCA(n_components = N_COMPONENTS )
pc_matrix = pca_model.fit_transform(ohe_data)
evr = pca_model.explained_variance_ratio_
cumsum_evr = np.cumsum(evr)
ax = sns.lineplot(x=np.arange(0,len(cumsum_evr)),y=cumsum_evr,label='Explained Variance Ratio')
ax.set_title('Explained Variance Ratio Using {} Components'.format(N_COMPONENTS))
ax = sns.lineplot(x=np.arange(0,len(cumsum_evr)),y=evr,label='Explained Variance Of Component X')
ax.set_xticks([i for i in range(0,len(cumsum_evr))])
ax.set_xlabel('Component number #')
ax.set_ylabel('Explained Variance')
plt.show()
usampled_df_with_pcs
4.模型选择及测试
X = usampled_df_with_pcs[X_features]
y = usampled_df_with_pcs['Churn']
train_x,test_x,train_y,test_y = train_test_split(X,y,random_state=42)
4.1 交叉验证
ada_pipe = Pipeline(steps =[ ('scale',StandardScaler()), ("RF",AdaBoostClassifier(random_state=42,learning_rate=0.7)) ])
svm_pipe = Pipeline(steps =[ ('scale',StandardScaler()), ("RF",SVC(random_state=42,kernel='rbf')) ])
f1_cross_val_scores = cross_val_score(rf_pipe,train_x,train_y,cv=5,scoring='f1')
ada_f1_cross_val_scores=cross_val_score(ada_pipe,train_x,train_y,cv=5,scoring='f1')
svm_f1_cross_val_scores=cross_val_score(svm_pipe,train_x,train_y,cv=5,scoring='f1')
ax = sns.lineplot(x=range(0,len(f1_cross_val_scores)),y=f1_cross_val_scores)
ax.set_title('Random Forest Cross Val Scores')
ax.set_xticks([i for i in range(0,len(f1_cross_val_scores))])
ax.set_xlabel('Fold Number')
ax.set_ylabel('F1 Score')
plt.show()
plt.subplot(3,1,2)
ax = sns.lineplot(x=range(0,len(ada_f1_cross_val_scores)),y=ada_f1_cross_val_scores)
ax.set_title('Adaboost Cross Val Scores')
ax.set_xticks([i for i in range(0,len(ada_f1_cross_val_scores))])
ax.set_xlabel('Fold Number')
ax.set_ylabel('F1 Score')
plt.show()
plt.subplot(3,1,3)
ax = sns.lineplot(x=range(0,len(svm_f1_cross_val_scores)),y=svm_f1_cross_val_scores)
ax.set_title('SVM Cross Val Scores')
ax.set_xticks([i for i in range(0,len(svm_f1_cross_val_scores))])
ax.set_xlabel('Fold Number')
ax.set_ylabel('F1 Score')
plt.show()
看看三种模型都有什么不同的表现:
4.2 模型预测
rf_prediction = rf_pipe.predict(test_x)
ada_pipe.fit(train_x,train_y)
ada_prediction = ada_pipe.predict(test_x)
svm_pipe.fit(train_x,train_y)
svm_prediction = svm_pipe.predict(test_x)
print('F1 Score of Random Forest Model On Test Set - {}'.format(f1(rf_prediction,test_y)))
print('F1 Score of AdaBoost Model On Test Set - {}'.format(f1(ada_prediction,test_y)))
print('F1 Score of SVM Model On Test Set - {}'.format(f1(svm_prediction,test_y)))
4.3 对原始数据(采样前)进行模型预测
pc_matrix = pca_model.fit_transform(ohe_data)
original_df_with_pcs = pd.concat([c_data,pd.DataFrame(pc_matrix,columns=['PC-{}'.format(i) for i in range(0,N_COMPONENTS)])],axis=1)
unsampled_data_prediction_RF = rf_pipe.predict(original_df_with_pcs[X_features])
unsampled_data_prediction_ADA = ada_pipe.predict(original_df_with_pcs[X_features])
unsampled_data_prediction_SVM = svm_pipe.predict(original_df_with_pcs[X_features])
4.4 结果
ax.set_title('Prediction On Original Data With Random Forest Model Confusion Matrix')
ax.set_xticklabels(['Not Churn','Churn'],fontsize=18)
ax.set_yticklabels(['Predicted Not Churn','Predicted Churn'],fontsize=18)
plt.show()