jupyter/体测单位/北海炼化.ipynb

2022年体质检测

人员基本信息导入

In [ ]:

import openpyxl
import json

wb = openpyxl.load_workbook('data/北海石化监测花名册2022 .xlsx')
sheet = wb.active
# sheets = wb.sheetnames
person = {}
for n in range(2, sheet.max_row+1):
    if sheet.cell(n,2).value is None:
        break
    else:        
        code = int(sheet.cell(n, 4).value)
        person.setdefault(code, {})
        dict1 = {}
        dict1['name'] = sheet.cell(n, 6).value    
        xb = str(sheet.cell(n, 7).value)
        if xb == '1':
            sex = '男'
        elif xb =='2':
            sex = '女'
        dict1['sex'] = sex
        dict1['unit'] = sheet.cell(n, 3).value
        dict1['birth'] = str(sheet.cell(n,8).value).split(' ')[0]
        person[code] = dict1
filename = 'data/北海炼化人员_2022.json'
with open(filename, 'w') as fl:
    json.dump(person, fl, ensure_ascii=False)
print('ok')

获取人员测试成绩

In [ ]:

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
#SQL语句为：
# SELECT a.item_id,a.performance,a.score,a.date AS DATE1,a.avatar_id,b.unit,b.name FROM places_result AS a,_zgshhgxs AS b WHERE a.place_id=135 AND a.avatar_id=b.id AND a.avatar_id < 4999

re_ta = {}
dict1 = {}
list1 = []
#print("\n运动项目信息：")
filename = 'data/138_2210.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[4])
    m_item = str(result[0])    
    re_ta.setdefault(user,{})    
    re_ta[user]['name'] = str(result[6])
    re_ta[user]['unit'] = str(result[5])    
    item_name = item[m_item]['name']
    re_ta[user].setdefault(item_name,{})  
    score = int(result[1])/item[m_item]['divisor']    
    re_ta[user][item_name]['成绩'] = f'{score} {item[m_item]["unit"]}'
    re_ta[user][item_name]['得分'] =result[2]
filename = 'data/result_北海炼化2022.json'
with open(filename,'w') as fl:
    json.dump(re_ta, fl) 
print('ok')

导出测试成绩

In [ ]:

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/部门','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_北海炼化2022.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

filename = 'data/北海炼化人员_2022.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
    
list1 = []
for k, v in dict1.items():
    list2 = []
    list2.append(str(k).rjust(8,'0'))
    list2.append(v['name'])    
    list2.append(dict2[k]['sex'])
    list2.append(dict2[k]['unit'])    
    
    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/北海炼化体测情况表（截至20221101）.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)

统计报告人员信息表

In [ ]:

import json
import openpyxl
import os
import glob

filename = 'data/北海炼化人员_2022.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
m_path = '../file/221103'
fls = glob.glob(f'../file/221103/*.pdf')
list1 = []
for fn in fls:
    list2 = []
    code = os.path.basename(fn).split('.')[0]
    list2 = [code.rjust(5,"0"),dict1[code]['name'],dict1[code]['unit']]
    list1.append(list2)
title = ['编号','姓名','部门']    
filename = 'data/北海体测报告情况表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)

统计部门测试人员情况

In [ ]:

import json
import openpyxl

title = ['部门','部门人数','已测人数','未测人数']
filename = 'data/北海炼化人员_2022.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
filename = 'data/result_北海炼化2022.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)

dict3 = {}
for k, v in dict1.items():
    dict3.setdefault(v['unit'],{})
    dict3[v['unit']].setdefault('人数',0)
    dict3[v['unit']].setdefault('已测人数',0)
    dict3[v['unit']]['人数'] = dict3[v['unit']]['人数']+1
for k, v in dict2.items():
    if len(v.keys())>5:        
        dict3[v['unit']]['已测人数'] = dict3[v['unit']]['已测人数'] + 1
list1 = []

for k, v in dict3.items():
    list2 = []
    list2 = [k,v['人数'],v['已测人数'],v['人数']-v['已测人数']]
    
    list1.append(list2)
filename = 'data/北海炼化体测人数统计表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)
print('ok!')

导入2021年人员信息

In [ ]:

import json
import openpyxl

filename = 'data/北海炼化人员_2022.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

filename = 'data/all_result.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
dict3 = {}
dict3 = dict2['北海炼化']

for k, v in dict1.items():
    name = v['name']
    birth = v['birth']
    for k1, v1 in dict3.items():
        if v1['name'] == name and v1['birth'] == birth:
            dict1[k]['old_code'] = int(k1)
            dict1[k]['record'] = v1['record']
    
filename = 'data/北海炼化人员_2022.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl, ensure_ascii=False) 
print('ok')

核对2021体测人员

In [ ]:

import json
import openpyxl

filename = 'data/北海炼化人员_2022.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

list1 = []
for k,v in dict1.items():
    if 'old_code' in v.keys():
        list1.append(v['old_code'])
filename = 'data/all_result.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
dict3 = {}
dict3 = dict2['北海炼化']
for k, v in dict3.items():
    if int(k) not in list1:
        print(k,v['name'],v['birth'])

比照人员两年成绩

比照两年单项成绩

In [ ]:

import json
import openpyxl

filename = 'data/北海炼化人员_2022.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

list1 = dict1.keys()
items = ['台阶指数']
title = ['编号','姓名','部门','22年台阶指数','21年台阶指数']
filename = 'data/result_北海炼化2022.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
list4 = []
for k, v in dict2.items():
    if k in list1:
        list2 = [k,v['name'],v['unit']]
        list3 = []
        for item in items:
            # 获取2022年成绩
            if item in v.keys():                
                list2.append(v[item]['成绩'].split()[0])             
            else:
                list2.append('')
            # 获取2021年成绩
            if 'record' in dict1[k].keys() and item in dict1[k]['record'].keys():
                list3.append(dict1[k]['record'][item]['成绩'])             
            else:
                list3.append('')
        for cj in list3:
            if cj != '':
                list2.append(cj.split()[0])            
        
        list4.append(list2)
filename = 'data/b北海炼化成绩对照221026.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list4:
    sheet.append(row)
    
wb.save(filename)       

北海体检情况汇总

In [ ]:

import openpyxl
import json

wb = openpyxl.load_workbook('data/中国石化北海炼化有限责任公司2022年健康体检团体报告统计表.xlsx')
sheet = wb.active
# sheets = wb.sheetnames
dict1 = {}
for n in range(2, sheet.max_row+1):
    if sheet.cell(n,2).value is None:
        break
    else:        
        code = sheet.cell(n, 2).value
        dict1.setdefault(code, {})        
        dict1[code]['name'] = sheet.cell(n, 3).value    
        
        dict1[code]['sex'] = sheet.cell(n, 4).value 
        dict1[code]['age'] = sheet.cell(n, 5).value 
        dict1[code].setdefault('bz',[]) 
        dict1[code]['bz'].append(sheet.cell(n, 6).value) 
        
filename = 'data/北海炼化2022年健康体检团体报告.json'
with open(filename, 'w') as fl:
    json.dump(dict1, fl, ensure_ascii=False)
print('ok')
list1 = []
for k, v in dict1.items():
    list2 = []
    mbz = set(v['bz'])
    list2.append(k)
    list2.append(v['name'])
    list2.append(v['sex'])
    list2.append(v['age'])
    list2.append(','.join(mbz))
    list1.append(list2)
title = ['体检编号','姓名','性别','年龄','体检症状']
filename = 'data/中国石化北海炼化有限责任公司2022年健康体检团体报告汇总统计表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)  

北海体检情况汇总(文本文件)

In [ ]:

import openpyxl
import json
list2 = []
file_name = 'data/中国石化北海炼化有限责任公司2022年健康体检团体报告.txt'
with open(file_name,'r',encoding='utf-8') as fl:
    for l in fl:
        list1 = []
        list1 = l.strip('\n').split()
        del list1[0]
        list2.append(list1)
        
print(list2)    
title = ['体检编号','姓名','性别','年龄','体检症状']
filename = 'data/中国石化北海炼化有限责任公司2022年健康体检团体报告统计表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list2:
    sheet.append(row)
    
wb.save(filename)  

北海体检情况统计

In [ ]:

import openpyxl
import json
import itertools
import operator

filename = 'data/北海炼化2022年健康体检团体报告.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
bz = set()
for k, v in dict1.items():
    for i in v['bz']:
        bz.add(i)
print(len(bz))
dict2 = {}
dict3 = {}
i = 1
for n in [2,3,4]:
    iter1 = itertools.combinations(bz, n)
    list1 = list(iter1)
    print(len(list1))    
    
    list2 = []
    for item in list1:
        
        for k, v in dict1.items():            
            list3 = []
            if set(item).issubset(v['bz']):
                dict3[i] =item 
                list3 = [k,i]
                list2.append(list3)
        i = i+1
    dict2[n] = list2
dict2['bingzheng'] = dict3
filename = 'data/北海炼化2022年健康体检病症组合.json'
with open(filename,'w') as fl:
    json.dump(dict2, fl, ensure_ascii=False) 
print('ok')

北海体检情况分析

In [46]:

import openpyxl
import json
import itertools
import operator

filename = 'data/北海炼化2022年健康体检病症组合.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
bz = dict1['bingzheng']
bz1 = dict1['2']
list1 = []
for k, v in bz.items():
    list2 = []
    i = 1
    bzs = len(v)
    for v1 in dict1[str(bzs)]:
        if v1[1] == int(k):
            
            i+=1
    list2 =[bzs,','.join(v),i]
    list1.append(list2)
filename = 'data/中国石化北海炼化有限责任公司2022年病症统计表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
#sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)  

2023年体质检测

人员信息处理

人员信息汇总（批量人员）

In [98]:

import os,sys,shutil
import json
import glob
from pathlib import Path
import openpyxl

fi_path = 'data/北海炼化/'

fls = glob.glob(f'{fi_path}/*.xlsx')
i = 1
person = {}
for fl in fls:
    wb = openpyxl.load_workbook(fl)
    sheet = wb.active
    # sheets = wb.sheetnames
    

    for n in range(3,sheet.max_row+1):
        if sheet.cell(n,1).value is not None:
            code = str(i)
            person.setdefault(code, {})
            dict1 = {}
            dict1['name'] = sheet.cell(n, 2).value
            dict1['sex'] = sheet.cell(n,3 ).value
            dict1['婚姻'] = sheet.cell(n, 5).value
            dict1['phone'] = str(sheet.cell(n,6).value)
            dict1['id'] = sheet.cell(n,7 ).value
            dict1['总工龄'] = sheet.cell(n, 8).value
            dict1['损害工龄'] = sheet.cell(n, 9).value
            dict1['既往病史'] = sheet.cell(n,10 ).value
            dict1['有毒因素'] = sheet.cell(n, 11).value
            dict1['unit'] = sheet.cell(n, 12).value
            dict1['工种'] = sheet.cell(n, 13).value
            dict1['防护措施'] = sheet.cell(n,15 ).value              
            person[code] = dict1
            i+=1
          
filename = 'data/北海炼化2023.json'
with open(filename, 'w') as fl:
    json.dump(person, fl, ensure_ascii=False)
print('ok')

ok

检查身份证及手机号码唯一性

In [75]:

import json

filename = 'data/北海炼化2023.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
id= []
phone = [] 

for k, v in dict1.items():
    if v['phone'] not in phone:
        phone.append(v['phone'] )
    else:
        print(v['name'] ,v['phone'])
    if v['id'] not in id:
        id.append(v['id'] )
    else:
        print(v['id'] ,v['id'] )

董红军 18877976757
苗光浩 13927509537
440906199104060046 440906199104060046
黄仁进 13807799565

查找身份证号码

In [48]:

import json

filename = 'data/北海炼化2023.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
id= '440906199104060046'
for k, v in dict1.items():
    if v['id'] == id:
        print(id,v['name'])

440906199104060046 凌倩
440906199104060046 陈继杨

In [67]:

import json

filename = 'data/北海炼化2023.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
phone= ['13807799565','18877976757','13927509537']
for k, v in dict1.items():
    if v['phone'] in  phone:
        print(v['phone'],v['name'])

18877976757 刘前程
13927509537 黄洁强
18877976757 董红军
13927509537 苗光浩
13807799565 谢昌俊
13807799565 黄仁进

生成出生日期

In [101]:

import json

filename = 'data/北海炼化2023.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
for k, v in dict1.items():
    id = str(v['id']) 
    #print(id)
    birth = id[6:10] + '-' +id[10:12] + '-' +id[12:14]
    dict1[k]['birth'] = birth
    
    
filename = 'data/北海炼化2023.json'    
with open(filename, 'w') as fl:
    json.dump(dict1, fl, ensure_ascii=False)
print('ok')

ok

人员信息汇总（单个文件）

In [99]:

import json
import openpyxl

filename = 'data/北海炼化2023.json'
with open(filename,'r') as fl:
    person = json.load(fl)
i = len(person)+1
fl = 'data/北海炼化机关名单表(2023年汇总156人).xlsx'
wb = openpyxl.load_workbook(fl)
sheet = wb.active
# sheets = wb.sheetnames


for n in range(3,sheet.max_row+1):
    if sheet.cell(n,1).value is not None:
        code = str(i)
        person.setdefault(code, {})
        dict1 = {}
        dict1['name'] = sheet.cell(n, 2).value
        dict1['sex'] = sheet.cell(n,3 ).value        
        dict1['phone'] = sheet.cell(n,6).value
        dict1['id'] = sheet.cell(n,5 ).value        
        dict1['婚姻'] = sheet.cell(n, 11).value
        dict1['unit'] = sheet.cell(n, 8).value         
        person[code] = dict1
        i+=1
filename = 'data/北海炼化2023.json'    
with open(filename, 'w') as fl:
    json.dump(person, fl, ensure_ascii=False)
print('ok')

ok

In [100]:

import json
import openpyxl

filename = 'data/北海炼化2023.json'
with open(filename,'r') as fl:
    person = json.load(fl)
i = len(person)+1
fl = 'data/北海炼化上岗体检人员名单 （2023年）.xlsx'
wb = openpyxl.load_workbook(fl)
sheet = wb.active
# sheets = wb.sheetnames


for n in range(5,sheet.max_row+1):
    if sheet.cell(n,1).value is not None:
        code = str(i)
        person.setdefault(code, {})
        dict1 = {}
        dict1['name'] = sheet.cell(n, 2).value
        dict1['sex'] = sheet.cell(n,3 ).value        
        dict1['phone'] = str(sheet.cell(n,7).value)
        dict1['id'] = sheet.cell(n,6 ).value
        
        dict1['有毒因素'] = sheet.cell(n, 11).value
        dict1['unit'] = '新上岗'
        dict1['工种'] = sheet.cell(n, 8).value
        dict1['防护措施'] = sheet.cell(n,13 ).value         
        person[code] = dict1
        i+=1
filename = 'data/北海炼化2023.json'    
with open(filename, 'w') as fl:
    json.dump(person, fl, ensure_ascii=False)
print('ok')

ok

人员信息汇总导出

In [102]:

import json
import openpyxl

filename = 'data/北海炼化2023.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
list1 = []
for k, v in dict1.items():
    list2 = []
    list2 = [str(k).rjust(4,'0'),v['name'],v['sex'],v['unit'],v['birth'],v['phone']]
    list1.append(list2)
filename = 'data/北海炼化人员信息（2023年）.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active

for row in list1:
    sheet.append(row)
    
wb.save(filename)

生成人员信息

In [104]:

import openpyxl
import json


wb = openpyxl.load_workbook('data/北海炼化人员信息（2023年）.xlsx')
sheet = wb.active
# sheets = wb.sheetnames
person = {}

for n in range(2, sheet.max_row+1):
    code = int(sheet.cell(n, 1).value)
    person.setdefault(code, {})
    dict1 = {}
    dict1['name'] = sheet.cell(n, 2).value
    dict1['sex'] = sheet.cell(n, 3).value
    dict1['unit'] = sheet.cell(n, 4).value
    dict1['birth'] = sheet.cell(n,5).value
    if sheet.cell(n,6).value is not None:
        dict1['phone'] = sheet.cell(n,6).value    
    person[code] = dict1
filename = 'data/北海炼化2023年.json'
with open(filename, 'w') as fl:
    json.dump(person, fl, ensure_ascii=False)
print('ok')

ok

生成读卡系统文件

In [9]:

import json

filename = 'data/北海炼化2023年.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
list1 = []
for k, v in dict1.items():
    dict2 = {}
    #if dict1['sex'] =='男':
    #    sex = 1
    
    dict2 = {'id':k,'name':v['name'],'gender':v['sex'],'birth':v['birth'],'unit':v['unit']}
    list1.append(dict2)
json_data = json.dumps(list1,ensure_ascii=False, indent=4)  

# 将 json 数据写入文件
with open("data/data_北海炼化.json", "w",encoding = 'utf-8') as file:
    file.write(json_data)   
print('ok')

ok

获取人员测试成绩

In [11]:

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/北海炼化2023年.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 

filename = 'data/places_result_20231108.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]['unit'] = dict1[user]['unit']
        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"]}'
        re_ta[user]['rq'] = str(result[6]) 
print(len(re_ta))
filename = 'data/result_北海炼化2023.json'

with open(filename,'w') as fl:
    json.dump(re_ta, fl, ensure_ascii=False) 
print(len(re_ta))

347
347

统计所有部门未体测人员明细表

In [14]:

import json
import openpyxl

filename = 'data/result_北海炼化2023.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

filename = 'data/北海炼化2023年.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)

list1 = []

i = 1
for k, v in dict2.items():
    
    if k not in dict1.keys():
        list2 = [i,k,v['name'],v['unit']]
        i+=1
        list1.append(list2)
filename = f'data/北海炼化未测试人员名单.xlsx'
title = ['序号','员工编号','姓名','部门']
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)    
wb.save(filename)

In [ ]: