jupyter/体测单位/燕山石化.ipynb at 2e7d800503150917a768ec45e2623a9aa8cbb2b9

512song/jupyter

0 Fork 0

Files

T

512song 2e7d800503 20230516

2023-05-16 23:06:49 +08:00

32 KiB

Raw Blame History

导入人员信息

In [32]:

import openpyxl
import json


wb = openpyxl.load_workbook('data/燕山石化人员情况表.xlsx')
sheet = wb.active
# sheets = wb.sheetnames
person = {}

for n in range(2, sheet.max_row+1):
    if sheet.cell(n,1).value is not None:
        code = int(sheet.cell(n, 1).value)
        person.setdefault(code, {})
        dict1 = {}
        dict1['name'] = sheet.cell(n, 2).value
        if sheet.cell(n, 7).value ==1:
            sex = '男'
        else:
            sex = '女'
        dict1['sex'] = sheet.cell(n, 3).value
        birth = str(sheet.cell(n, 6).value).split()[0]
        dict1['birth'] = birth
        if sheet.cell(n,5).value is not None:
            dict1['phone'] = sheet.cell(n, 5).value
        if sheet.cell(n,7).value is not None:
            dict1['id_num'] = sheet.cell(n, 7).value
        if sheet.cell(n,8).value is not None:
            dict1['SAP'] = sheet.cell(n, 8).value
        if sheet.cell(n,9).value is not None:
            dict1['工作单位'] = sheet.cell(n, 9).value
        if sheet.cell(n,10).value is not None:
            dict1['车间'] = sheet.cell(n, 10).value
        else:
            dict1['车间'] =''
        if sheet.cell(n,11).value is not None:
            dict1['班组'] = sheet.cell(n, 11).value
        else:
            dict1['班组'] =''
        if sheet.cell(n,12).value is not None:
            dict1['工作性质'] = sheet.cell(n, 11).value
        person[code] = dict1
jianyuan = [6484,7110,6441,6541,6543,6549,6555,6600,2958,2981,3033,3231,3249,3287,3228,7741,7749,7794,7799,7806,7837,7863,7870,7880,7894,7895,7904,7936,7947,7953,7958,7968,7969,7974,8086,8114]

print(len(person))
for k in jianyuan:
    if k in person.keys():
        del person[k]
print(len(person))
bianwai =[449,6839]
for i in range(7139,7200):
    bianwai.append(i)
for k in bianwai:
    if k in person.keys():
        del person[k]
print(len(person))
filename = 'data/燕山石化人员名单.json'
with open(filename, 'w') as fl:
    json.dump(person, fl, ensure_ascii=False)
print('ok')

每日成绩导入

In [33]:

import json
import time
import csv

filename = '../item.json'
item = {}
unit = {}
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
for k,v in dict1.items():
    item[k] = v
re_ta = {}
dict1 = {}
list1 = []
filename = 'data/燕山石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 

filename = 'data/places_result_20230516.csv'
with open(filename,'r',newline='') as csv_file:
    fl = csv.reader(csv_file,delimiter=',')
    header = next(fl)    
    for line in fl:
        #line = re.sub('[\r\n\f ]{1,}', '', line)
        list1.append(line)
#print(list1)
for result in list1:
    user = str(result[2])
    if user in dict1.keys():        
        m_item = str(result[3])    
        re_ta.setdefault(user,{})    
        re_ta[user]['name'] = dict1[user]['name']
        re_ta[user]['sex'] = dict1[user]['sex'] 
        re_ta[user]['部门'] = dict1[user]['工作单位']
        item_name = item[m_item]['name']
        re_ta[user].setdefault(item_name,{})  
        score = int(result[4])/item[m_item]['divisor']    
        re_ta[user][item_name]['成绩'] = f'{score} {item[m_item]["unit"]}'
print(len(re_ta))
filename = 'data/result_燕山石化.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
for k in re_ta.keys():
    if k in dict2.keys():
        print(k,dict2[k]['name'],'已测试！')
for k, v in re_ta.items():
    if k not in dict2.keys():
        dict2[k] = v
    else:
        for k1,v1 in v.items():
            dict2[k][k1] = v1
filename = 'data/result_燕山石化（20230516）.json'
with open(filename,'w') as fl:
    json.dump(re_ta, fl, ensure_ascii=False) 
print(len(re_ta))
filename = 'data/result_燕山石化.json'
with open(filename,'w') as fl:
    json.dump(dict2, fl, ensure_ascii=False) 
print(len(dict2))

214
8151 赵春先 已测试！
999 张术申 已测试！
2709 刘巍 已测试！
214
7598

每日成绩导出

In [34]:

import json
import openpyxl

items = ['身高','体重','肺活量','握力','坐位体前屈','纵跳','俯卧撑','一分钟仰卧起坐','单脚站立','选择反应时','台阶指数']
title = ['编号','姓名','性别','单位','车间','班组','身高','体重','肺活量','握力','坐位体前屈','纵跳','俯卧撑','一分钟仰卧起坐','单脚站立','选择反应时','台阶指数']

filename = 'data/result_燕山石化（20230516）.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

filename = 'data/燕山石化人员名单.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
    
list1 = []
for k, v in dict1.items():
    list2 = []
    list2.append(str(k).rjust(5,'0'))
    list2.append(v['name'])    
    list2.append(dict2[k]['sex'])
    list2.append(dict2[k]['工作单位'])    
    list2.append(dict2[k]['车间'])
    list2.append(dict2[k]['班组'])
    for item in items:
        if item in v.keys():
            list2.append(v[item]['成绩'])            
        elif item =='name':
            list2.append(v[item])
        else:
            list2.append('') 
    list1.append(list2)
filename = 'data/燕山石化体测情况表(20230516).xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)

总成绩导出

In [198]:

import json
import openpyxl

items = ['身高','体重','肺活量','握力','坐位体前屈','纵跳','俯卧撑','一分钟仰卧起坐','单脚站立','选择反应时','台阶指数']
title = ['编号','姓名','性别','单位','车间','班组','身高','体重','肺活量','握力','坐位体前屈','纵跳','俯卧撑','一分钟仰卧起坐','单脚站立','选择反应时','台阶指数']

filename = 'data/result_燕山石化.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

filename = 'data/燕山石化人员名单.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
    
list1 = []
for k, v in dict1.items():
    list2 = []
    list2.append(str(k).rjust(5,'0'))
    list2.append(v['name'])    
    list2.append(dict2[k]['sex'])
    list2.append(dict2[k]['工作单位'])    
    list2.append(dict2[k]['车间'])
    list2.append(dict2[k]['班组'])
    for item in items:
        if item in v.keys():
            list2.append(v[item]['成绩'])            
        elif item =='name':
            list2.append(v[item])
        else:
            list2.append('') 
    list1.append(list2)
filename = 'data/燕山石化体测情况表(截至20230506).xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)

统计部门测试人数

In [35]:

import json
import openpyxl

filename = 'data/result_燕山石化（20230516）.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
dict2 = {}
for k, v in dict1.items():
    unit = v['部门']
    dict2.setdefault(unit,0)
    dict2[unit] = dict2[unit] + 1
print(dict2)
title =['单位','体测人数']
list1 = [] 
for k, v in dict2.items():
    list2 = []
    list2 = [k,v]
    list1.append(list2)
filename = 'data/燕山石化部门测试人数情况表(20230516).xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)

{'储运厂工会': 9, '热电厂工会': 65, '炼油厂工会': 48, '合成橡胶厂工会': 31, '检验计量中心工会': 34, '烯烃厂工会': 4, '化学品厂工会': 8, '合成树脂厂': 4, '生产运行保障中心': 1, '高科公司工会': 3, '有机化工厂工会': 3, '机关工会': 4}

每日未测试人员情况表

In [26]:

import json
import openpyxl


title = ['编号','姓名','性别','单位','车间','班组']
filename = 'data/result_燕山石化（20230417）.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

filename = 'data/燕山石化人员名单.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
list1 = []
for k, v in dict2.items():
    list2 = []
    if k not in dict1.keys():
        list2.append(str(k).rjust(5,'0'))
        list2.append(v['name'])    
        list2.append(dict2[k]['sex'])
        list2.append(dict2[k]['工作单位'])    
        list2.append(dict2[k]['车间'])
        list2.append(dict2[k]['班组'])
        list1.append(list2)
filename = 'data/燕山石化未体测人员名单(20230417).xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)

汇总未测试人员情况表

In [37]:

import json
import openpyxl


title = ['编号','姓名','性别','单位','车间','班组']
filename = 'data/result_燕山石化.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
# 筛选重名剔除名单
chongming = []
filename = 'data/燕山石化重名人员测试情况(20230515).xlsx'
wb = openpyxl.load_workbook(filename)
sheet = wb.active
for n in range(1, sheet.max_row+1,2):
    if sheet.cell(n,1).value is not None:
        code1 = int(sheet.cell(n, 1).value)
        code2 = int(sheet.cell(n+1, 1).value)
        bz1 = sheet.cell(n, 4).value
        bz2 = sheet.cell(n+1, 4).value
        if bz1 =='否' and bz2 =='否':
            chongming.append(max(code1,code2))
        else:
            chongming.append(code1)
            chongming.append(code2)

filename = 'data/燕山石化人员名单.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
list1 = []
for k, v in dict2.items():
    list2 = []
    if k not in dict1.keys() and int(k) not in chongming:
        list2.append(str(k).rjust(5,'0'))
        list2.append(v['name'])    
        list2.append(dict2[k]['sex'])
        list2.append(dict2[k]['工作单位'])    
        list2.append(dict2[k]['车间'])
        list2.append(dict2[k]['班组'])
        list1.append(list2)
filename = 'data/燕山石化未体测人员名单(截至20230516).xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
wb.save(filename)

统计测试项目不足人员

In [8]:

import json
import openpyxl

items = ['身高','体重','肺活量','握力','坐位体前屈','纵跳','俯卧撑','一分钟仰卧起坐','单脚站立','选择反应时','台阶指数']
title = ['编号','姓名','性别','单位','车间','班组','身高','体重','肺活量','握力','坐位体前屈','纵跳','俯卧撑','一分钟仰卧起坐','单脚站立','选择反应时','台阶指数']
filename = 'data/result_燕山石化-all.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

filename = 'data/燕山石化人员名单.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
dict3 = {}
for k, v in dict1.items():
    list1 = []
    for item in v.keys():
        if item in items:
            list1.append(item)
    dict3[k] = list1
list1 = []
for k, v in dict3.items():
    if len(v)<4 and '身高' in v and '体重' in v:
        list2 = []
        xm = ','.join(v)
        list2.append(k)
        list2.append(dict2[k]['name'])
        list2.append(dict2[k]['工作单位'])
        list2.append(xm)
        list1.append(list2)
print(list1)
filename = 'data/燕山石化测试项目不足人员（截止5月11日）.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
#sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)

[['4025', '马珺', '教育培训中心工会', '身高,体重,选择反应时'], ['7790', '吴志鹏', '生产运行保障中心', '身高,体重,握力'], ['8151', '赵春先', '合成树脂厂', '身高,体重,握力'], ['7682', '孙宏林', '有机化工厂工会', '肺活量,身高,体重'], ['2004', '刘鹏', '合成树脂厂', '身高,体重,握力'], ['3125', '李志斌', '化学品厂工会', '身高,体重,握力']]

汇总成绩导入

In [21]:

import json
import time
import csv

filename = '../item.json'
item = {}
unit = {}
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
for k,v in dict1.items():
    item[k] = v
re_ta = {}
dict1 = {}
list1 = []
filename = 'data/燕山石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 

filename = 'data/places_result_20230514.csv'
with open(filename,'r',newline='') as csv_file:
    fl = csv.reader(csv_file,delimiter=',')
    header = next(fl)    
    for line in fl:
        #line = re.sub('[\r\n\f ]{1,}', '', line)
        list1.append(line)
#print(list1)
for result in list1:
    user = str(result[2])
    if user in dict1.keys():        
        m_item = str(result[3])    
        re_ta.setdefault(user,{})    
        re_ta[user]['name'] = dict1[user]['name']
        re_ta[user]['sex'] = dict1[user]['sex'] 
        re_ta[user]['部门'] = dict1[user]['工作单位']
        item_name = item[m_item]['name']
        re_ta[user].setdefault(item_name,{})  
        score = int(result[4])/item[m_item]['divisor']    
        re_ta[user][item_name]['成绩'] = f'{score} {item[m_item]["unit"]}'
print(len(re_ta))

filename = 'data/result_燕山石化-all.json'
with open(filename,'w') as fl:
    json.dump(re_ta, fl, ensure_ascii=False) 
print(len(re_ta))

7117
7117

统计重复人员信息

In [132]:

import json
import time
import csv


list1 = []
list2 = set()
filename = 'data/燕山石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
filename = 'data/result_燕山石化-all.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl) 

for k,v in dict1.items():
    name = v['name']
    if name in list1:
        list2.add(name)
    list1.append(name)
list3 = []
for item in list2:
    for k,v in dict1.items():
        if v['name'] == item:
            list3.append([k,v['name'],v['sex'],v['birth']])
filename = 'data/燕山石化重名人员名单.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
#sheet.append(title)
for row in list3:
    sheet.append(row)
    
wb.save(filename)

重复人员测试情况

In [36]:

import json
import time
import csv


list1 = []
list2 = set()
filename = 'data/燕山石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
filename = 'data/result_燕山石化.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl) 


list3 = []

filename = 'data/燕山石化重名人员名单.xlsx'
wb = openpyxl.load_workbook(filename)
sheet = wb.active
# sheets = wb.sheetnames


for n in range(1, sheet.max_row+1):
    if sheet.cell(n,1).value is not None:
        code = int(sheet.cell(n, 1).value)
        name = dict1[str(code)]['name']
        unit = dict1[str(code)]['工作单位']
        if str(code) in dict2.keys():
            ce = '是'
        else:
            ce = '否'
        list3.append([code,name,unit,ce])
filename = 'data/燕山石化重名人员测试情况(20230516).xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
#sheet.append(title)
for row in list3:
    sheet.append(row)
    
wb.save(filename)

[0;31m---------------------------------------------------------------------------[0m
[0;31mKeyError[0m                                  Traceback (most recent call last)
Cell [0;32mIn[36], line 27[0m
[1;32m     25[0m [38;5;28;01mif[39;00m sheet[38;5;241m.[39mcell(n,[38;5;241m1[39m)[38;5;241m.[39mvalue [38;5;129;01mis[39;00m [38;5;129;01mnot[39;00m [38;5;28;01mNone[39;00m:
[1;32m     26[0m     code [38;5;241m=[39m [38;5;28mint[39m(sheet[38;5;241m.[39mcell(n, [38;5;241m1[39m)[38;5;241m.[39mvalue)
[0;32m---> 27[0m     name [38;5;241m=[39m [43mdict1[49m[43m[[49m[38;5;28;43mstr[39;49m[43m([49m[43mcode[49m[43m)[49m[43m][49m[[38;5;124m'[39m[38;5;124mname[39m[38;5;124m'[39m]
[1;32m     28[0m     unit [38;5;241m=[39m dict1[[38;5;28mstr[39m(code)][[38;5;124m'[39m[38;5;124m工作单位[39m[38;5;124m'[39m]
[1;32m     29[0m     [38;5;28;01mif[39;00m [38;5;28mstr[39m(code) [38;5;129;01min[39;00m dict2[38;5;241m.[39mkeys():

[0;31mKeyError[0m: '7160'

统计部门测试情况

In [193]:

import json
import openpyxl
filename = 'data/燕山石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
filename = 'data/result_燕山石化.json'
with open(filename,'r') as fl:
    dict3 = json.load(fl)
dict2 = {}
for k, v in dict1.items():
    unit = v['工作单位']
    dict2.setdefault(unit,0)
    dict2[unit] = dict2[unit] + 1
dict4 = {}
for k, v in dict3.items():
    unit = v['部门']
    dict4.setdefault(unit,0)
    dict4[unit] = dict4[unit] + 1
list1 = []
for k, v in dict2.items():
    list2 = []
    list2.append(k)
    list2.append(v)
    if k in dict4.keys():
        list2.append(dict4[k])
    else:
        list2.append(0)
    list1.append(list2)
print(list1)
filename = 'data/燕山石化部门测试情况（截止5月6日）.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
#sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)

[['机关工会', 446, 365], ['储运厂工会', 997, 780], ['高科公司工会', 311, 292], ['合成树脂厂', 464, 317], ['合成橡胶厂工会', 770, 310], ['化学品厂工会', 378, 296], ['检验计量中心工会', 635, 297], ['教育培训中心工会', 73, 72], ['炼油厂工会', 1043, 640], ['热电厂工会', 710, 121], ['物装中心工会', 182, 182], ['烯烃厂工会', 433, 287], ['消防中心工会', 221, 214], ['行政事务中心（离退中心）工会', 675, 503], ['有机化工厂工会', 454, 435], ['生产运行保障中心', 398, 367]]

In [217]:

#C2EDC1A2D1C7
gbs = 'C2EDC1A2D1C7'
import binascii
bs = binascii.a2b_hex(gbs)
print('bs', bs)
print('decode-bs:', bs.decode('gb2312'))

bs b'\xc2\xed\xc1\xa2\xd1\xc7'
decode-bs: 马立亚

In [219]:

s = '马立亚'
gbcode = s.encode('gb2312') # 先转成 bytes格式
print('gbcode:', gbcode)
gbs = "".join([hex(ch)[2:] for ch in gbcode])  #
print('gbs:', gbs)

gbcode: b'\xc2\xed\xc1\xa2\xd1\xc7'
gbs: c2edc1a2d1c7

In [ ]:

32 KiB Raw Blame History

导入人员信息

每日成绩导入

每日成绩导出

总成绩导出

统计部门测试人数

每日未测试人员情况表

汇总未测试人员情况表

统计测试项目不足人员

汇总成绩导入

统计重复人员信息

重复人员测试情况

统计部门测试情况

32 KiB

Raw Blame History