jupyter/体测单位/石家庄石化.ipynb at master

512song/jupyter

0 Fork 0

Files

T

512song 23ce121293 20230905

2023-09-05 16:28:09 +08:00

33 KiB

Raw Permalink Blame History

导入人员信息

In [ ]:

import openpyxl
import json


wb = openpyxl.load_workbook('data/student_20140922(石家庄监测花名册2023年).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, 4).value)
        person.setdefault(code, {})
        dict1 = {}
        dict1['name'] = sheet.cell(n, 6).value
        if sheet.cell(n, 7).value ==1:
            sex = '男'
        else:
            sex = '女'
        dict1['sex'] = sex
        dict1['unit'] = sheet.cell(n, 3).value
        dict1['birth'] = sheet.cell(n, 8).value
        person[code] = dict1
filename = 'data/石家庄2023.json'
with open(filename, 'w') as fl:
    json.dump(person, fl, ensure_ascii=False,default=str)
print('ok')

每日成绩导入

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
re_ta = {}
dict1 = {}
list1 = []
filename = 'data/石家庄2023.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 

filename = 'data/places_result_20230427-sjz.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]['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"]}'
print(len(re_ta))
filename = 'data/result_石家庄（20230427）.json'
with open(filename,'w') as fl:
    json.dump(re_ta, fl) 
print('ok')

每日成绩导出

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','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_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

filename = 'data/石家庄2023.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]['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/石家庄石化体测情况表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)

总成绩导入

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
re_ta = {}
dict1 = {}
list1 = []
filename = 'data/石家庄2023.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 

filename = 'data/places_result_20230505-sjz.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]['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"]}'
print(len(re_ta))
filename = 'data/result_石家庄.json'
with open(filename,'w') as fl:
    json.dump(re_ta, fl) 
print('ok')

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','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_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

filename = 'data/石家庄2023.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]['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/石家庄石化体测情况表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
    
wb.save(filename)

统计部门测试情况

In [ ]:

import json
import openpyxl

filename = 'data/result_石家庄.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/石家庄测试名单部门情况(20230426).xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet.append(title)
for row in list1:
    sheet.append(row)
wb.save(filename)

统计未测试人员名单

In [ ]:

import json
import openpyxl

filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
list1 = []
filename = 'data/石家庄2023.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
for k, v in dict2.items():
    if k not in dict1.keys():
        list1.append([k,v['name'],v['unit']])
filename = 'data/石家庄未测试名单(截至20230426).xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
title =['测试编号','姓名','单位']
sheet.append(title)
for row in list1:
    sheet.append(row)
wb.save(filename)

生成查询文件

In [ ]:

import json
filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
dict2 = {}
for k, v in dict1.items():
    dict2[k] = v['name']
filename = 'data/shijiazhuang.json'
with open(filename, 'w') as fl:
    json.dump(dict2, fl, ensure_ascii=False)
print('ok')

报告按部门分类更名

In [ ]:

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

fi_path = 'file/2023-04-30'
old = []
dict2 = {}

filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

for k, v in dict1.items():
    m_name = v['name']
    m_depart = v['unit']    
    dict2[int(k)] = [m_name,m_depart]

fls = glob.glob(f'{fi_path}/*.pdf')

for fn in fls:
    old.append(os.path.basename(fn).split('.')[0])

for n in old:    
    o_name = f'{fi_path}/{n}.pdf'
    new_path = Path(fi_path,'new',dict1[n]['unit'])
    new_path.mkdir(parents = True, exist_ok = True)
    n_name = Path(new_path,f'{str(n).rjust(5,"0")}-{dict2[int(n)][0]}.pdf')
    if not os.path.exists(n_name):
        shutil.copyfile(o_name,n_name)
        print(n_name)
    
print('ok')

生成电子文件明细表

In [5]:

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

fi_path = 'file/2023-04-30'
old = []
dict2 = {}
list1 = []

filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

for k, v in dict1.items():    
    m_name = v['name']
    m_depart = v['unit']    
    dict2[int(k)] = [m_name,m_depart]
    list1.append([k.rjust(5,"0"),m_depart,m_name])
filename = 'data/石家庄测试报告明细表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active

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

数据分析

获取清理后报告数据

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
filename = 'data/石家庄2023.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

re_ta = {}
list1 = []
#print("\n运动项目信息：")
filename = 'data/places_result_sjz.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]['unit'] = dict1[user]['unit']
        re_ta[user]['sex'] = dict1[user]['sex']
        re_ta[user]['birth'] = dict1[user]['birth']
        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][item_name]['得分'] =result[5]
filename = 'data/result_石家庄.json'
print(len(re_ta))
liwai = []
for k, v in re_ta.items():
    if (len(v)<8 and '身高' in v and '体重' in v) or (len(v)<7 and '身高' not in v and '体重' not in v) :
        liwai.append(k)
print(liwai)
for k in liwai:
    del re_ta[k]
print(len(re_ta))
filename = 'data/result_石家庄.json'
with open(filename,'w') as fl:
    json.dump(re_ta, fl) 
print('ok')

核对报告

In [ ]:

import json
import time
import csv
import os,sys,shutil
import glob

filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

m_path = 'file/2023-04-30'
old = []
fls = glob.glob(f'{m_path}/*.pdf')
for fn in fls:
    #old = os.path.basename(fn).split('.')[0].rjust(8,'0') 
    old.append(os.path.basename(fn).split('.')[0])
for k, v in dict1.items():
    if k not in old and '身高' not in v.keys():
        print(k,v,'\n')

计算人员年龄

In [ ]:

import json
import datetime

filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
for k, v in dict1.items():
    birth = v['birth'].split()[0].split('-')
    
    nian = int(birth[0].strip())
    yue = int(birth[1].strip())
    ri = int(birth[2].strip())
    #print(k,nian,yue,ri)
    days = (datetime.date(2023, 4, 23)-datetime.date(nian,yue,ri)).days
    v['age'] = round(days/365)
filename = 'data/result_石家庄.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl) 
print('ok')

汇总人员信息及成绩

In [ ]:

import json


items = ['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_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
for k,v in dict1.items():
    score = 0
    i = 0
    for k1,v1 in v.items():  
        if k1 in items:
            score = score + int(v1['得分'])
            i+=1
    dict1[k]['score'] = round(score/i,2)            
filename = 'data/result_石家庄.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl) 
print('ok')

计算测试等级

In [6]:

import json

filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
dict2 = {}
dict2['不合格'] = [0,255]
dict2['合格'] = [256,332]
dict2['良好'] = [333,367]
dict2['优秀'] = [368,500]

for k1, v1 in dict2.items():
    di = v1[0]
    gao = v1[1]
    i = 0    
    m = 0
    f = 0
    for k,v in dict1.items():
        if int(v['score']*100) in range(di,gao+1):
            dict1[k]['level'] = k1
            i+=1
            if v['sex'] == '男':
                m = m +1
            else:
                f = f+1
    print(f'{di}~{gao}分人数：{i}人,男性：{m}人,女性:{f}人')
filename = 'data/result_石家庄.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl) 
print('ok')

0~255分人数：779人,男性：678人,女性:101人
256~332分人数：1009人,男性：786人,女性:223人
333~367分人数：316人,男性：189人,女性:127人
368~500分人数：129人,男性：57人,女性:72人
ok

根据年龄汇总人员信息及成绩

In [ ]:

import json

nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,59],[60,69]]
filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
for item in nld:
    di = item[0]
    gao = item[1]
    i = 1
    score = 0
    m = 0
    f = 0
    for k,v in dict1.items():
        if v['age'] in range(di,gao+1):
            score = score+v['score']
            i+=1
            if v['sex'] == '男':
                m = m +1
            
    print(f'{di}~{gao}岁平均成绩：{round(score/i,2)}分，人数：{i-1}人,男性：{m}人')

In [ ]:

import json

nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,59],[60,69]]
filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
for item in nld:
    di = item[0]
    gao = item[1]
    i = 1
    score = 0
    m = 0
    f = 0
    for k,v in dict1.items():
        if v['age'] in range(di,gao+1) and v['sex'] == '男':
            score = score+v['score']
            i+=1
            
            
    print(f'{di}~{gao}岁平均成绩：{round(score/i,2)}分，人数：{i-1}人')

In [ ]:

import json
nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,59],[60,69]]
filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
for item in nld:
    di = item[0]
    gao = item[1]
    i = 1
    score = 0
    m = 0
    f = 0
    for k,v in dict1.items():
        if v['age'] in range(di,gao+1) and v['sex'] == '女':
            score = score+v['score']
            i+=1
            
            
    print(f'{di}~{gao}岁平均成绩：{round(score/i,2)}分，人数：{i-1}人')

生成平均成绩直方图

In [ ]:

import pygal
from pygal.style import Style

custom_style = Style(
    colors=('#9BC850', '#ffeb44', '#ff00ff'))

filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
pjf = []
for k, v in dict1.items():    
    pjf.append(v['score'])
pjf.sort()
bar_chart = pygal.Bar(style=custom_style)
bar_chart.add('平均分',pjf)  # Add some values
bar_chart.render_to_file('bar_chart.svg')

计算平均成绩

In [ ]:

import json

nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,59],[60,69]]
filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
i = 1
m = 0
f = 0
score = 0
t_score = 0
for k,v in dict1.items():
    if v['sex'] == '男':
        m = m +1
        score = score+v['score']
print(f'平均成绩：{round(score/m,4)}分，男性：{m}人')
t_score = t_score + score
score = 0
for k,v in dict1.items():
    if v['sex'] == '女':
        f = f +1
        score = score+v['score']
print(f'平均成绩：{round(score/f,4)}分，女性：{f}人')
t_score = t_score + score
print(f'平均成绩：{round(t_score/2233,4)}分，女性：2233人')

计算测试等级

In [ ]:

import json

filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
dict2 = {}
dict2['不合格'] = [0,255]
dict2['合格'] = [256,332]
dict2['良好'] = [333,367]
dict2['优秀'] = [368,500]

for k1, v1 in dict2.items():
    di = v1[0]
    gao = v1[1]
    i = 0    
    m = 0
    f = 0
    for k,v in dict1.items():
        if int(v['score']*100) in range(di,gao+1):
            dict1[k]['level'] = k1
            i+=1
            if v['sex'] == '男':
                m = m +1
            else:
                f = f+1
    print(f'{di}~{gao}分人数：{i}人,男性：{m}人,女性:{f}人')
filename = 'data/result_石家庄.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl) 
print('ok')

计算各年龄段测试等级(男）

In [ ]:

nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,59],[60,69]]
filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
dict2 = {}
dict2['不合格'] = [0,255]
dict2['合格'] = [256,332]
dict2['良好'] = [333,367]
dict2['优秀'] = [368,500]
dict3 = {}
for item in nld:
    di = item[0]
    gao = item[1]
    age = f'{di}-{gao}'
    dict3.setdefault(age,{})
    i = 0    
    m = 0
    f = 0
    for k,v in dict1.items():
        if v['age'] in range(di,gao+1):            
            dict3[age].setdefault(v['level'],0)
            if v['sex'] == '女':
                dict3[age][v['level']] = dict3[age][v['level']]+1
            
for k, v in dict3.items():
    print(k,v)

按照部门计算平均成绩

In [ ]:

with open(filename,'r') as fl:
    dict1 = json.load(fl) 
depart = []
for k, v in dict1.items():
    if v['unit'] not in depart:
        depart.append(v['unit'])

for item in depart:
    score = 0
    n = 0
    for k, v in dict1.items():
        if item == v['unit']:
            score = score + v['score']
            n = n +1 
    print(item,round(score/n,2),n)

计算各项目成绩

In [ ]:

filename = 'data/result_石家庄.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
items = ['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']
for item in items:
    score = 0
    n = 0
    for k, v in dict1.items():
        if item in v.keys():
            n = n + 1
            score =score + int(v[item]['得分'])
    print(item,round(score/n,2))

In [ ]:

filename = 'data/tiangongyuan.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
print(dict1)

In [ ]:

33 KiB Raw Permalink Blame History

导入人员信息

每日成绩导入

每日成绩导出

总成绩导入

统计部门测试情况

统计未测试人员名单

生成查询文件

报告按部门分类更名

生成电子文件明细表

数据分析

获取清理后报告数据

核对报告

计算人员年龄

汇总人员信息及成绩

计算测试等级

根据年龄汇总人员信息及成绩

生成平均成绩直方图

计算平均成绩

计算测试等级

计算各年龄段测试等级(男）

按照部门计算平均成绩

计算各项目成绩

33 KiB

Raw Permalink Blame History