交叉分析方法与实现

看一个部门的离职率的数据,简单分析一下,部门离职率与所做的工作的相关性:

因为数据太多,只能给出少量数据了,如果有想要数据的可以留言赠送

给定如下数据:

HR.csv:

satisfaction_level,last_evaluation,number_project,average_monthly_hours,time_spend_company,Work_accident,left,promotion_last_5years,department,salary
0.38,0.53,2,157,3,0,1,0,sales,low
0.8,0.86,5,262,6,0,1,0,sales,medium
0.11,0.88,7,272,4,0,1,0,sales,medium
0.72,0.87,5,223,5,0,1,0,sales,low
0.37,0.52,2,159,3,0,1,0,sales,low
0.41,0.5,2,153,3,0,1,0,sales,low
0.1,0.77,6,247,4,0,1,0,sales,low
0.92,0.85,5,259,5,0,1,0,sales,low
0.89,1,5,224,5,0,1,0,sales,low
0.42,0.53,2,142,3,0,1,0,sales,low
0.45,0.54,2,135,3,0,1,0,sales,low
0.11,0.81,6,305,4,0,1,0,sales,low
0.84,0.92,4,234,5,0,1,0,sales,low
0.41,0.55,2,148,3,0,1,0,sales,low
0.36,0.56,2,137,3,0,1,0,sales,low
0.38,0.54,2,143,3,0,1,0,sales,low
0.45,0.47,2,160,3,0,1,0,sales,low
0.78,0.99,4,255,6,0,1,0,sales,low
0.45,0.51,2,160,3,1,1,1,sales,low
0.76,0.89,5,262,5,0,1,0,sales,low
0.11,0.83,6,282,4,0,1,0,sales,low
0.38,0.55,2,147,3,0,1,0,sales,low
0.09,0.95,6,304,4,0,1,0,sales,low
0.46,0.57,2,139,3,0,1,0,sales,low
0.4,0.53,2,158,3,0,1,0,sales,low
0.89,0.92,5,242,5,0,1,0,sales,low
0.82,0.87,4,239,5,0,1,0,sales,low
0.4,0.49,2,135,3,0,1,0,sales,low
0.41,0.46,2,128,3,0,1,0,accounting,low
0.38,0.5,2,132,3,0,1,0,accounting,low
0.09,0.62,6,294,4,0,1,0,accounting,low
0.45,0.57,2,134,3,0,1,0,hr,low
0.4,0.51,2,145,3,0,1,0,hr,low
0.45,0.55,2,140,3,0,1,0,hr,low
0.84,0.87,4,246,6,0,1,0,hr,low
0.1,0.94,6,255,4,0,1,0,technical,low
0.38,0.46,2,137,3,0,1,0,technical,low
0.45,0.5,2,126,3,0,1,0,technical,low
0.11,0.89,6,306,4,0,1,0,technical,low
0.41,0.54,2,152,3,0,1,0,technical,low
0.87,0.88,5,269,5,0,1,0,technical,low
0.45,0.48,2,158,3,0,1,0,technical,low
0.4,0.46,2,127,3,0,1,0,technical,low
0.1,0.8,7,281,4,0,1,0,technical,low
0.09,0.89,6,276,4,0,1,0,technical,low
0.84,0.74,3,182,4,0,1,0,technical,low
0.4,0.55,2,147,3,0,1,0,support,low
0.57,0.7,3,273,6,0,1,0,support,low
0.4,0.54,2,148,3,0,1,0,support,low
0.43,0.47,2,147,3,0,1,0,support,low
0.13,0.78,6,152,2,0,1,0,support,low
0.44,0.55,2,135,3,0,1,0,support,low
0.38,0.55,2,134,3,0,1,0,support,low
0.39,0.54,2,132,3,0,1,0,support,low
0.1,0.92,7,307,4,0,1,0,support,low
0.37,0.46,2,140,3,0,1,0,support,low
0.11,0.94,7,255,4,0,1,0,support,low
0.1,0.81,6,309,4,0,1,0,technical,low
0.38,0.54,2,128,3,0,1,0,technical,low
0.85,1,4,225,5,0,1,0,technical,low
0.85,0.91,5,226,5,0,1,0,management,medium
0.11,0.93,7,308,4,0,1,0,IT,medium
0.1,0.95,6,244,5,0,1,0,IT,medium
0.36,0.56,2,132,3,0,1,0,IT,medium
0.11,0.94,6,286,4,0,1,0,IT,medium
0.81,0.7,6,161,4,0,1,0,IT,medium
0.43,0.54,2,153,3,0,1,0,product_mng,medium
0.9,0.98,4,264,6,0,1,0,product_mng,medium
0.76,0.86,5,223,5,1,1,0,product_mng,medium
0.43,0.5,2,135,3,0,1,0,product_mng,medium
0.74,0.99,2,277,3,0,1,0,IT,medium
0.09,0.77,5,275,4,0,1,0,product_mng,medium
0.45,0.49,2,149,3,0,1,0,product_mng,high
0.09,0.87,7,295,4,0,1,0,product_mng,low
0.11,0.97,6,277,4,0,1,0,product_mng,medium
0.11,0.79,7,306,4,0,1,0,product_mng,medium
0.1,0.83,6,295,4,0,1,0,product_mng,medium
0.4,0.54,2,137,3,0,1,0,marketing,medium
0.43,0.56,2,157,3,0,1,0,sales,low
0.39,0.56,2,142,3,0,1,0,accounting,low
0.45,0.54,2,140,3,0,1,0,support,low
0.38,0.49,2,151,3,0,1,0,technical,low
0.79,0.59,4,139,3,0,1,1,management,low
0.84,0.85,4,249,6,0,1,0,marketing,low
0.11,0.77,6,291,4,0,1,0,marketing,low
0.11,0.87,6,305,4,0,1,0,marketing,low
0.17,0.84,5,232,3,0,1,0,sales,low
0.44,0.45,2,132,3,0,1,0,sales,low
0.37,0.57,2,130,3,0,1,0,sales,low





简单 的代码实现过程:

import matplotlib.pyplot as plt
import seaborn as sns
import pandas as pd
import numpy as np
import scipy.stats as ss


from pandas import DataFrame,Series
#数据的路径
df = pd.read_csv("./skip_Data/HR.csv")
#我想要看各个部门的离职分布
#通过 indices 拿到分组后的索引,通过部门进行分组
df_index = df.groupby(by="department").indices
#拿到销售部门的离职值
sales_values = df['left'].iloc[df_index['sales']].values
technical_values = df['left'].iloc[df_index['technical']].values
#在python3中所有的keys加上一个list,然后才能转换为数组
dp_keys = list(df_index.keys())
#初始化一个矩阵
df_t_mat = np.zeros([len(dp_keys),len(dp_keys)])
for i in range(len(dp_keys)):
    for j in range(len(dp_keys)):
        p_value = ss.ttest_ind(df['left'].iloc[df_index[dp_keys[i]]].values,\
                  df['left'].iloc[df_index[dp_keys[j]]].values)[1]
        #对矩阵进行赋值
        if p_value<0.05:
            df_t_mat[i][j] = -1
        else :
            df_t_mat[i][j] = p_value
sns.heatmap(df_t_mat,xticklabels=dp_keys,yticklabels=dp_keys)
plt.savefig("1.jpg")
plt.show()

评论 1
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值