Python練手,樣本
import pandas as pd def getEmpDataFrame(num): '''創建一份可復用的數據,有一定的隨機性和真實性''' #員工編號 emp = [''] * num lenNum = len(str(num)) for i in range(num): emp[i] = str(i+1).zfill(lenNum) #性別:男多女少 sex = [1] * int(round(num*0.7)) + [0] * (num - int(round(num*0.7))) #年齡:年齡是平均分布的,相對來說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 #職級:越高級越罕有 與其他因素無關 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 #入職年長:跟職級和年齡有關 #通常4年升1級 #年齡-最低年齡=可能最大的入職年長 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 #學歷:年齡小的平均學歷相對高些,職級高的學歷相對高些 edu = [0] * num for i in range(num): if lvl[i] == 5 or lvl[i] == 4 : if age[i] < 40 : edu[i] = 4 #年輕高級是博士 else: edu[i] = 3 #年老高級是碩士 else: if age[i] < 40 : edu[i] = 2 #年輕低級是大學 else: edu[i] = 1 #年老低級是大專 #工資:規則計算 加上一點隨機變化 在加上一點入職時長的倍數鼓勵 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) #離職風險:高低 #年輕大學生容易離職 #低學歷大年齡且入職時間短容易被淘汰 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))