Python练手，样本
import pandas as pd def getEmpDataFrame(num): '''创建一份可复用的数据，有一定的随机性和真实性''' #员工编号 emp = [''] * num lenNum = len(str(num)) for i in range(num): emp[i] = str(i+1).zfill(lenNum) #性别：男多女少 sex = [1] * int(round(num*0.7)) + [0] * (num - int(round(num*0.7))) #年龄：年龄是平均分布的，相对来说男同事比女同事要大些 age = [0] * num for i in range(num): if sex[i] == 1 : age[i] = 28 + i % 33 if sex[i] == 0 : age[i] = 22 + i % 33 #职级：越高级越罕有 与其他因素无关 lvl = [0] * num for i in range(num): if lvl[i] ==0 and (i+1) % 33 == 0 : lvl[i] = 5 continue if lvl[i] ==0 and (i+1) % 23 == 0 : lvl[i] = 4 continue if lvl[i] ==0 and (i+1) % 13 == 0 : lvl[i] = 3 continue if lvl[i] ==0 and (i+1) % 3 == 0 : lvl[i] = 2 continue lvl[i] = 1 #入职年长：跟职级和年龄有关 #通常4年升1级 #年龄-最低年龄=可能最大的入职年长 yrs = [0] * num for i in range(num): if sex[i] == 1 : if lvl[i] * 4 >= age[i] - 28 : yrs[i] = age[i] - 28 else: yrs[i] = lvl[i] * 4 if sex[i] == 0 : if lvl[i] * 4 >= age[i] - 22 : yrs[i] = age[i] - 22 else: yrs[i] = lvl[i] * 4 #学历：年龄小的平均学历相对高些，职级高的学历相对高些 edu = [0] * num for i in range(num): if lvl[i] == 5 or lvl[i] == 4 : if age[i] < 40 : edu[i] = 4 #年轻高级是博士 else: edu[i] = 3 #年老高级是硕士 else: if age[i] < 40 : edu[i] = 2 #年轻低级是大学 else: edu[i] = 1 #年老低级是大专 #工资：规则计算 加上一点随机变化 在加上一点入职时长的倍数鼓励 sal = [0.] * num for i in range(num): sal[i] = round( ( 3000 + yrs[i] * 200 + edu[i] * 1000 + ( lvl[i] - 1 ) * 3000 + sex[i] * 1000 + i % 7 * 300 ) * ( 1 + yrs[i] / 100 ) ,3) #离职风险：高低 #年轻大学生容易离职 #低学历大年龄且入职时间短容易被淘汰 ris = [0] * num for i in range(num): if yrs[i] < 2 and age[i] < 35 and edu[i] == 2: ris[i] = 1 if edu[i] == 1 and age[i] > 50 and yrs[i] < 5: ris[i] = 1 df = pd.DataFrame({"sex":sex, "age":age, "lvl":lvl, "yrs":yrs, "edu":edu, "sal":sal, "ris":ris}, index = emp) return df # print(getEmpDataFrame(60))
