数据挖掘项目构建人才(用户)流失模型

# coding=utf-8
# @Time    : 2019/12/3 14:48
# @Author  : Z
# @Email   : S
# @File    : 2.6ML_SMOTO_talentFeatures.py

#数据挖掘项目构建人才(用户)流失模型

import pandas as pd

talent_data = pd.read_csv("./train.csv")
#1.不同类型数据的整理

# 数值型数据
num_cols = ["Age", "MonthlyIncome", "NumCompaniesWorked", "PercentSalaryHike", "PerformanceRating",
            "StandardHours", "TotalWorkingYears", "YearsAtCompany",
            "YearsInCurrentRole", "YearsSinceLastPromotion"]
# 类别型数据
cat_cols=["Gender","MaritalStatus","OverTime"]
# 有序型数据
ord_cols=["DistanceFromHome","Education","EnvironmentSatisfaction","JobInvolvement",
          "JobLevel","JobSatisfaction","RelationshipSatisfaction","StockOptionLevel",
          "TrainingTimesLastYear","WorkLifeBalance"]
#类别标签
target_col=["Attrition"]
total_data=num_cols+ord_cols+cat_cols
#将所有的特征数据和类别标签进行整合
use_data=talent_data[total_data+target_col]

#2.正负样本的比例
#正负样本的不均衡问题
neg_data = use_data[use_data["Attrition"] == 0] #未离职
pos_data = use_data[use_data["Attrition"] == 1] #离职
print("正负样本比例：", len(pos_data)/len(neg_data))
print("离职:",len(pos_data))
print("未离职:",len(neg_data))

#3.数据集的切分
# X=talent_data[total_data]
# y=talent_data["Attrition"]
# from sklearn.cross_validation import  train_test_split
# X_train,X_test,y_train,y_test=train_test_split(X,y,test_size=0.2,random_state=22