jupyter/体测单位/西藏.ipynb

人员信息导入

In [94]:

import openpyxl
import json


wb = openpyxl.load_workbook('data/xizang.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, 5).value)
        person.setdefault(code, {})
        dict1 = {}
        dict1['name'] = sheet.cell(n, 1).value
        if sheet.cell(n, 2).value ==0:
            sex = '男'
        else:
            sex = '女'
        dict1['sex'] = sex
        birth = str(sheet.cell(n, 3).value).split()[0]
        dict1['birth'] = birth
        
        if sheet.cell(n,5).value is not None:
            dict1['phone'] = str(sheet.cell(n, 4).value)        
        person[code] = dict1

filename = 'data/西藏人员.json'
with open(filename, 'w') as fl:
    json.dump(person, fl, ensure_ascii=False)
print('ok')

ok

问卷人员信息导入

In [ ]:

import openpyxl
import json
import datetime

wb = openpyxl.load_workbook('data/西藏健康体质检测人员名单.xlsx')
sheet = wb.active
# sheets = wb.sheetnames
person = {}

for n in range(2, sheet.max_row+1):
    if sheet.cell(n,7).value is not None and sheet.cell(n,4).value is not None:
        bh = int(sheet.cell(n, 7).value)
        person.setdefault(bh, {})
        dict1 = {}
        dict1['name'] = sheet.cell(n, 2).value
        dict1['code'] = sheet.cell(n, 1).value
        if sheet.cell(n, 3).value ==1:
            sex = '男'
        else:
            sex = '女'
        dict1['sex'] = sex
        birth = str(sheet.cell(n, 4).value).split()[0]
        
        if len(birth) == 2:
            dict1['age'] = int(birth)
        else:
            birth.replace('/','-')
            
            birth = birth.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, 5, 31)-datetime.date(nian,yue,ri)).days
            dict1['age'] = round(days/365)
        if sheet.cell(n,5).value is not None:
            dict1['phone'] = str(sheet.cell(n, 5).value)        
        person[bh] = dict1

filename = 'data/西藏手工问卷人员名单.json'
with open(filename, 'w') as fl:
    json.dump(person, fl, ensure_ascii=False)
print('ok')

导入脊柱问卷信息

In [ ]:

import openpyxl
import json


wb = openpyxl.load_workbook('data/西藏手工记录.xlsx')
sheet = wb['Sheet1']

dict1 = {}
data1 =list(sheet.values)
list_bh = data1[0][1:]
del data1[0]
for i in range(1,len(list_bh)+1):
    list2 = []
    dict1.setdefault(int(list_bh[i-1]),{})
    for item in data1:
        list2.append(item[i])
    dict1[int(list_bh[i-1])]['wenjuan'] = list2
print(dict1)
filename = 'data/西藏脊柱问卷原始信息.json'
with open(filename, 'w') as fl:
    json.dump(dict1, fl, ensure_ascii=False)
print('ok')

导入体测信息

In [ ]:

import openpyxl
import json


wb = openpyxl.load_workbook('data/西藏手工记录.xlsx')
sheet = wb['Sheet2']
filename = 'data/西藏脊柱问卷原始信息.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

data1 =list(sheet.values)

for item in data1:
    bh = str(item[0])
    dict1.setdefault(bh,{})
    xm = item[1]
    result = item[2]
    dict1[bh][xm] = result
filename = 'data/西藏脊柱问卷原始信息.json'
with open(filename, 'w') as fl:
    json.dump(dict1, fl, ensure_ascii=False)
print('ok')

导出手工信息

In [ ]:

import json

filename = 'data/西藏手工问卷人员名单.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
filename = 'data/西藏脊柱问卷原始信息.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)

for k, v in dict1.items():
    s = ''
    if k in dict2.keys():
        if dict2[str(k)]['sex'] =='男':
            sex = "m"
        else:
            sex = "f"
        dict3 = {}
        list_mx = []
        name = dict2[str(k)]['name'] 
        list_mx.append(f'"name":"{name}"')
        list_mx.append(f'"Gender":"{sex}"')
        age = dict2[str(k)]['age']
        list_mx.append(f'"Age":{age}')
        dict3['surveyId'] = "zsyxz1"
        dict3['name'] = dict2[str(k)]['name'] 
        code =  dict2[str(k)]['code']
        for item in v.keys():
            if item == 'wenjuan':
                for i in range(0,21):
                    if v[item][i] ==1:
                        result = 'ture'
                    else:
                        result ='false'  
                    item_name = 'q'+str(i+1)
                    list_mx.append(f'"{item_name}":{result}')
                for i in range(23,25):
                    if v[item][i] ==1:
                        result = 'ture'
                    else:
                        result ='false'  
                    item_name = 'q'+str(i)
                    list_mx.append(f'"{item_name}":{result}')
                if sex == 'f':
                    item_name = 'q25a'
                    if v[item][21] ==1:
                        result = 'ture'
                    else:
                        result ='false'
                    list_mx.append(f'"{item_name}":{result}')
                else:
                    item_name = 'q22'
                    if v[item][22] ==1:
                        result = 'ture'
                    else:
                        result ='false'
                    list_mx.append(f'"{item_name}":{result}')
                    item_name = 'q25b'
                    if v[item][25] ==1:
                        result = 'ture'
                    else:
                        result ='false'
                    list_mx.append(f'"{item_name}":{result}')
            else:    
                item_name = item                
                list_mx.append(f'"{item_name}":{v[item]}')
        ss = ','.join(list_mx)
        ss ='{'+ss+'}'
        dict3['data'] = ss
        sj = '2023-06-01 20:00:00'
        s= s+f'("zsyxz1","{name}","{code}",\'{ss}\',"{sj}"),'
        print(s)

导入体测信息

In [66]:

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/西藏人员.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 

filename = 'data/places_result_20230704.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']         
        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_xizang.json'

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

165
165

报告更名

In [ ]:

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

fi_path = 'file/2023-06-06'
old = []
dict2 = {}

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

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

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')
    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')

数据分析

获取清理后数据

In [95]:

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/西藏人员.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_20230704.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]['birth'] = dict1[user]['birth'].replace('-','/')
        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]

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_xizang.json'
with open(filename,'w') as fl:
    json.dump(re_ta, fl) 
print('ok')
print(len(re_ta))

165
[]
165
ok
165

计算人员年龄

In [96]:

import json
import datetime

filename = 'data/result_xizang.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, 6, 10)-datetime.date(nian,yue,ri)).days
    v['age'] = int(days/365)
filename = 'data/result_xizang.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl) 
print('ok')    

ok

汇总人员信息及成绩

In [97]:

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']


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)            

with open(filename,'w') as fl:
    json.dump(dict1, fl) 
print('ok')

ok

计算测试等级

In [98]:

import 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')

with open(filename,'w') as fl:
    json.dump(dict1, fl) 
print('ok')

0~255分人数：115人,男性：67人,女性:48人
256~332分人数：42人,男性：27人,女性:15人
333~367分人数：8人,男性：4人,女性:4人
368~500分人数：0人,男性：0人,女性:0人
ok

根据年龄汇总人员信息及成绩

In [99]:

import json

nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,69]]

with open(filename,'r') as fl:
    dict1 = json.load(fl) 
for item in nld:
    di = item[0]
    gao = item[1]
    i = 0
    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}人,男性：{m}人')

20~24岁平均成绩：2.43分，人数：9人,男性：7人
25~29岁平均成绩：2.14分，人数：49人,男性：27人
30~34岁平均成绩：2.26分，人数：38人,男性：22人
35~39岁平均成绩：2.39分，人数：27人,男性：12人
40~44岁平均成绩：2.37分，人数：26人,男性：15人
45~49岁平均成绩：2.52分，人数：10人,男性：9人
50~54岁平均成绩：2.48分，人数：5人,男性：5人
55~69岁平均成绩：2.67分，人数：1人,男性：1人

根据年龄汇总人员信息及成绩（男）

In [100]:

import json

nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,80]]

with open(filename,'r') as fl:
    dict1 = json.load(fl) 
for item in nld:
    di = item[0]
    gao = item[1]
    i = 0
    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
    if i >0:
            print(f'{di}~{gao}岁平均成绩：{round(score/i,2)}分，人数：{i}人')
    else:
        print(f'{di}~{gao}岁平均成绩：0分，人数：0人') 

20~24岁平均成绩：2.45分，人数：7人
25~29岁平均成绩：2.0分，人数：27人
30~34岁平均成绩：2.39分，人数：22人
35~39岁平均成绩：2.36分，人数：12人
40~44岁平均成绩：2.53分，人数：15人
45~49岁平均成绩：2.54分，人数：9人
50~54岁平均成绩：2.48分，人数：5人
55~80岁平均成绩：2.67分，人数：1人

根据年龄汇总人员信息及成绩（女）

In [74]:

import json

nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,80]]
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
for item in nld:
    di = item[0]
    gao = item[1]
    i = 0
    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
    if i >0:
            print(f'{di}~{gao}岁平均成绩：{round(score/i,2)}分，人数：{i}人')
    else:
        print(f'{di}~{gao}岁平均成绩：0分，人数：0人') 

20~24岁平均成绩：2.33分，人数：2人
25~29岁平均成绩：2.32分，人数：22人
30~34岁平均成绩：2.07分，人数：16人
35~39岁平均成绩：2.41分，人数：15人
40~44岁平均成绩：2.15分，人数：11人
45~49岁平均成绩：2.33分，人数：1人
50~54岁平均成绩：0分，人数：0人
55~80岁平均成绩：0分，人数：0人

计算平均成绩

In [104]:

import json

nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,80]]
#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/165,4)}分，总体：165人')

平均成绩：2.3266分，男性：98人
平均成绩：2.2533分，女性：67人
平均成绩：2.2968分，总体：165人

计算各年龄段测试等级(女）

In [91]:

nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,80]]

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)

20-24 {'合格': 1, '不合格': 1}
25-29 {'良好': 2, '不合格': 15, '合格': 5}
30-34 {'合格': 3, '不合格': 12, '良好': 1}
35-39 {'合格': 4, '良好': 1, '不合格': 10}
40-44 {'不合格': 9, '良好': 0, '合格': 2}
45-49 {'不合格': 1, '合格': 0, '良好': 0}
50-54 {'合格': 0, '良好': 0, '不合格': 0}
55-80 {'合格': 0}

计算各年龄段测试等级(男）

In [102]:

nld = [[20,24],[25,29],[30,34],[35,39],[40,44],[45,49],[50,54],[55,80]]

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'] == '男':
                dict3[age][v['level']] = dict3[age][v['level']]+1
            
for k, v in dict3.items():
    print(k,v)

20-24 {'合格': 3, '不合格': 4}
25-29 {'良好': 0, '不合格': 24, '合格': 3}
30-34 {'合格': 7, '不合格': 15, '良好': 0}
35-39 {'合格': 5, '良好': 0, '不合格': 7}
40-44 {'不合格': 9, '良好': 1, '合格': 5}
45-49 {'不合格': 5, '合格': 2, '良好': 2}
50-54 {'合格': 1, '良好': 1, '不合格': 3}
55-80 {'合格': 1}

计算各项目成绩

In [103]:

with open(filename,'r') as fl:
    dict1 = json.load(fl) 
items = ['体重','肺活量','握力','坐位体前屈','单脚站立','选择反应时']
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),n)

体重 3.46 164
肺活量 2.22 164
握力 1.19 164
坐位体前屈 1.9 163
单脚站立 2.19 165
选择反应时 2.8 165

In [ ]: