决策树：案例实战 -信用卡精准营销模型

决策树：案例实战 -信用卡精准营销模型

数据

（信用卡精准营销模型.xlsx）
特征变量：年龄，月收入，月消费，性别，月消费/月收入；
目标变量：响应；

工具

jupyter notebook

建模

（1）读取代码所在文件夹中的“信用卡精准营销模型.xlsx”；

import pandas as pd
df = pd.read_excel(r'信用卡精准营销模型.xlsx')
df.head()

2）提取特征变量和目标变量；

X = df.drop(columns = '响应')
y = df['响应']

（3）划分训练集和测试集数据（其中

test_size=0.2）；
from sklearn.model_selection import train_test_split
X_train,X_test,y_train,y_test = train_test_split(X,y,test_size=0.2, random_state=123)

4）建立决策树模型（使用默认参数）；

from sklearn.tree import DecisionTreeClassifier
model = DecisionTreeClassifier()
model.fit(X_train, y_train)

（5）预测数据结果（预测测试集结果），并通过DataFrame进行展示前5行数据；

y_pred = model.predict(X_test)
a = pd.DataFrame()
a['预测值'] = list(y_pred)
a['实际值'] = list(y_test)
a.head(5)

6）预测概率，并通过DataFrame进行展示前5行数据；

y_pred_proba = model.predict_proba(X_test)
b = pd.DataFrame(y_pred_proba,columns=['响应概率','不响应概率'])
b.head(5)

7）查看模型预测准确度；

from sklearn.metrics import accuracy_score
score = accuracy_score(y_pred,y_test)
score

（8）绘制模型ROC曲线；

from sklearn.metrics import roc_curve
fpr,tpr,thres = roc_curve(y_test,y_pred_proba[:,1])
a = pd.DataFrame()
a['阈值'] = list(thres)
a['假警报率'] = list(fpr)
a['命中率'] = list(tpr)
import matplotlib.pyplot as plt 
plt.plot(fpr, tpr)
plt.show()

（9）计算模型AUC值；

from sklearn.metrics import roc_auc_score
score = roc_auc_score(y_test,y_pred_proba[:,1])
score

（10）查看此时模型各个特征的特征重要性；

features = X.columns
importances = model.feature_importances_
importances_df = pd.DataFrame()
importances_df['特征名称'] = features
importances_df['特征重要性'] = importances
importances_df.sort_values("特征重要性",ascending = False)

决策树的可视化

使用Graphviz

from sklearn.tree import export_graphviz
import graphviz
import os
os.environ['PATH'] = os.pathsep + r'D:\Grapgviz\Graphviz\bin'
dot_data = export_graphviz(model, out_file=None, class_names = ['0','1'])
graph = graphviz.Source(dot_data)
graph.render("result")

—关于Graphviz的安装见后一篇博客—

参数调优

from sklearn.model_selection import GridSearchCV
parameters = {'max_depth': [1,3,5,7,9]}
model = DecisionTreeClassifier()
grid_search = GridSearchCV(model,parameters,scoring='roc_auc',cv=5)
grid_search.fit(X_train,y_train)
grid_search.best_params_

model = DecisionTreeClassifier(max_depth=7)
model.fit(X_train,y_train)
y_pred = model.predict(X_test)
from sklearn.metrics import accuracy_score
score = accuracy_score(y_pred,y_test)
score

y_pred_proba = model.predict_proba(X_test)
from sklearn.metrics import roc_auc_score
score_new = roc_auc_score(y_test.values,y_pred_proba[:,1])
score_new

print("调优前AUC值："+ str(score))
print("调优后AUC值："+ str(score_new))