jupyter/体测单位/体质检测数据处理.ipynb

体质检测数据处理

基础数据管理

体测项目标准导入

In [ ]:

import openpyxl
import json

tcbz ={
    'HeightWeigh':'身高体重',
    'StepExperiment':'台阶指数',
    'Lung':'肺活量',
    'Proneness':'坐位体前屈',
    'PowerfullGrip':'握力',
    'OneMinutePushUp':'一分钟仰卧起坐',
    'PushUp':'俯卧撑',
    'VerticalJump':'纵跳',
    'ReactionTime':'选择反应时',
    'FootStand':'单脚站立'
}
wb = openpyxl.load_workbook('data/体质检测标准.xlsx')
sheet = wb.active
# sheets = wb.sheetnames
dict1 = {}
dict3 = {}
for k, v in tcbz.items():
    dict3[v] = k
sheet = wb.active
data1 =list(sheet.values)
del data1[0]
for item in data1:
    sex = item[0][6:]
    if sex =='男':
        age_sex = 'M'+item[0][:5]
    else:
        age_sex = 'F'+item[0][:5]
    dict1.setdefault(age_sex,{})
    if item[1] in dict3.keys():
        xm = dict3[item[1]]
    dict1[age_sex].setdefault(xm,[])
    dict1[age_sex][xm].append(item[3]/item[4])
dict2 = {}
#print(dict1)
for k, v in dict1.items():
    i1 = int(k[1:3])
    i2 = int(k[-2:])
    m_sex = k[:1]
    for i in range(i1,i2+1):
        dict2[m_sex+str(i)] = k
dict3 = {}
dict3['person'] = dict2
dict3['criteria'] = dict1
filename = 'data/体质检测标准.json'
with open(filename, 'w') as fl:
    json.dump(dict3, fl, ensure_ascii=False)
print('ok')

身高标准导入

In [ ]:

import openpyxl
import json

tcbz ={
    'HeightWeigh':'身高体重',
    'StepExperiment':'台阶指数',
    'Lung':'肺活量',
    'Proneness':'坐位体前屈',
    'PowerfullGrip':'握力',
    'OneMinutePushUp':'一分钟仰卧起坐',
    'PushUp':'俯卧撑',
    'VerticalJump':'纵跳',
    'ReactionTime':'选择反应时',
    'FootStand':'单脚站立'
}
wb = openpyxl.load_workbook('data/体质检测标准_BMI.xlsx')
sheet = wb.active
# sheets = wb.sheetnames
dict1 = {}
dict3 = {}
for k, v in tcbz.items():
    dict3[v] = k
sheet = wb.active
data1 =list(sheet.values)
del data1[0]
for item in data1:
    min_age = int(item[1]/12)
    max_age = int((item[2]+1)/12) - 1
    sex = item[0]
    height = int(item[3])
    if sex ==0:
        age_sex = 'M'+str(min_age)+'~'+str(max_age)
    else:
        age_sex = 'F'+str(min_age)+'~'+str(max_age)
    dict1.setdefault(age_sex,{})
    
    dict1[age_sex].setdefault(height,[])
    dict1[age_sex][height].append(item[5]/1000)
dict2 = {}
#print(dict1)
for k, v in dict1.items():
    i1 = int(k[1:3])
    i2 = int(k[-2:])
    m_sex = k[:1]
    for i in range(i1,i2+1):
        dict2[m_sex+str(i)] = k
dict3 = {}
dict3['person'] = dict2
dict3['criteria'] = dict1
filename = 'data/体质检测标准_BMI.json'
with open(filename, 'w') as fl:
    json.dump(dict3, fl, ensure_ascii=False)
print('ok')

计算分数

In [ ]:

import json
import time
import csv

filename = 'data/体质检测标准.json'
item = {}
unit = {}
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
person = dict1['person']
criteria = dict1['criteria']
data = {'name':'张三','sex':'M','age':59,'item':'PowerfullGrip','result':51.0}
info = data['sex']+str(data['age'])
bz = person[info]
mx = criteria[bz][data['item']]
result = data['result']
score = -1
print(mx)
for bz1 in mx:
    if result < bz1:
        print(bz1)
        score = mx.index(bz1,0)
        break
    else:
        score = 5
#if score == -1:
 #   score = 5
print(score)

计算BMI分数

In [53]:

import json
import time
import csv

filename = 'data/体质检测标准_BMI.json'
item = {}
unit = {}
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
person = dict1['person']
criteria = dict1['criteria']
data = {'name':'张三','sex':'M','age':59,'item':'HeightWeight','result':'177.0,81.1'}
info = data['sex']+str(data['age'])

bz = person[info]
print(bz)
result = data['result']
print(result)
height = int(float(result.split(',')[0]))
weight = float(result.split(',')[1])
mx = criteria[bz][str(height)]
if weight < mx[0]:
    score = 1
elif weight < mx[1]:
    score = 3
elif weight < mx[2]:
    score = 5    
elif weight <= mx[3]:
    score = 3  
elif weight > mx[3]:
    score = 1
print(score)

M50~59
177.0,81.1
5

体质检测数据管理

数据导入Mycrm

导入系统人员信息

In [ ]:

import json
import time
import csv

list1 = []
filename = 'data/person_134.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)
dict1 = {}
for result in list1:
    code = str(result[4])
    if int(result[1]) == 0:
        sex = '男'
    else:
        sex = '女'
    
    m_item = str(result[3])    
    dict1.setdefault(code,{})    
    dict1[code]['name'] = result[0]
    dict1[code]['sex'] = sex
    dict1[code]['birth'] = result[2]
filename = 'data/天津石化人员清单.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl, ensure_ascii=False) 
print(len(dict1))    

导入测试项目item

In [ ]:

import json
import psycopg2
from psycopg2 import extras as ex

filename = '../item.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
data_list = []
for k, v in dict1.items():
    data_list.append((int(k),v['name'])) 
conn = psycopg2.connect(database="mycrm", user="postgres", password="songyi", host="localhost", port="5432")
cursor = conn.cursor()
sql = 'insert into tianjin_item (id,name) values %s'
ex.execute_values(cursor, sql, data_list, page_size=10000)
conn.commit()
cursor.close()
conn.close()
print('ok!')

导入一级部门

In [ ]:

import json
import psycopg2
from psycopg2 import extras as ex

conn = psycopg2.connect(database="mycrm", user="postgres", password="songyi", host="localhost", port="5432")
cursor = conn.cursor()
filename = 'data/天津石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
unit = set()
for k, v in dict1.items():
    #if 'sub_unit' not in v.keys():
    #    print(k,v['name'])
    unit.add(v['unit'])
print(unit)    
i = 1
dict2 = {}
for item in unit:
    dict2[item] = i
    i+=1
data_list = []
for k,  v in dict2.items():
    data_list.append((v,k)) 
    
sql = 'insert into tianjin_unit (id,name) values %s'
ex.execute_values(cursor, sql, data_list, page_size=10000)
conn.commit()
cursor.close()
conn.close()
print('ok!')

导入二级部门

In [ ]:

import json
import psycopg2
from psycopg2 import extras as ex

conn = psycopg2.connect(database="mycrm", user="postgres", password="songyi", host="localhost", port="5432")
cursor = conn.cursor()
filename = 'data/天津石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
unit = set()
for k, v in dict1.items():
    #if 'sub_unit' not in v.keys():
    #    print(k,v['name'])
    unit.add(v['unit'])
print(unit)    
i = 1
dict2 = {}
for item in unit:
    dict2[item] = i
    i+=1
data_list = []
dict3 = {}
for k,  v in dict1.items():
    dict3.setdefault(v['unit'],set())
    dict3[v['unit']].add(v['sub_unit'])
i = 1    
for k, v in dict3.items():
    unit_id = dict2[k]
    for item in v:
        data_list.append((i,item,unit_id))
        i+=1
sql = 'insert into tianjin_sub_unit (id,name,unit_id) values %s'
ex.execute_values(cursor, sql, data_list, page_size=10000)
conn.commit()
cursor.close()
conn.close()
print('ok!')

导入人员信息

In [ ]:

import json
import psycopg2
from psycopg2 import extras as ex

conn = psycopg2.connect(database="mycrm", user="postgres", password="songyi", host="localhost", port="5432")
cursor = conn.cursor()
filename = 'data/天津石化人员清单.json'
with open(filename,'r') as fl:
    person = json.load(fl)
    
filename = 'data/天津石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
unit = set()
for k, v in dict1.items():
    #if 'sub_unit' not in v.keys():
    #    print(k,v['name'])
    unit.add(v['unit'])
print(unit)    
i = 1
dict2 = {}
for item in unit:
    dict2[item] = i
    i+=1
data_list = []
dict3 = {}
dict4 = {}
for k,  v in dict1.items():
    dict3.setdefault(v['unit'],set())
    dict3[v['unit']].add(v['sub_unit'])    
i = 1    
for k, v in dict3.items():
    unit_id = dict2[k]
    for item in v:
        data_list.append((i,item,unit_id))
        i+=1
for item in data_list:
    sub_id = item[0]
    dict4[sub_id] = {'name':item[1],'unit':item[2]}
dict5 = {}
for k, v in dict1.items():
    id_unit = dict2[v['unit']]
    sub_name = v['sub_unit']
    id_sub = 0
    for k1, v1 in dict4.items():
        if v1['name'] == sub_name and v1['unit'] == id_unit:
            id_sub = int(k1)
    if id_sub >0:
        dict5[k] = {'unit':id_unit,'sub_unit':id_sub}
    else:
        print(k,'not fund')
data_list = []
for k, v in dict5.items():
    id = int(k)
    name = person[k]['name']
    sex = person[k]['sex']
    birth = person[k]['birth']
    phone = ''
    note = ''
    unit = v['sub_unit']
    data_list.append((id,name,sex,birth,unit))
sql = 'insert into tianjin_person (id,name,sex,birth,unit_id) values %s'
ex.execute_values(cursor, sql, data_list, page_size=10000)
conn.commit()
cursor.close()
conn.close()
print('ok!')   
    

导入测试成绩及得分

In [50]:

import json
import psycopg2
from psycopg2 import extras as ex

filename = '../item.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
dict2 = {}
for k, v in dict1.items():
    dict2[v['name']] = int(k)
conn = psycopg2.connect(database="mycrm", user="postgres", password="songyi", host="localhost", port="5432")
cursor = conn.cursor()
data_list = []
filename = 'data/result_天津.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl) 
for k, v in dict1.items():
    for item in v.keys():
        if item in dict2.keys():
            item_id = dict2[item]
            if v[item]['得分'] == '\\N':
                score = None
            else:
                score = int(v[item]['得分'])
                
            data_list.append((v[item]['成绩'],score,int(k),item_id))
         
sql = 'insert into tianjin_records (performance,score,avatar_id_id,item_id_id) values %s'
ex.execute_values(cursor, sql, data_list, page_size=10000)
conn.commit()
cursor.close()
conn.close()
print('ok!')           
    

ok!

In [ ]:

import json

filename = 'data/天津石化人员名单.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
for k, v in dict1.items():
    if 'num_id' not in v.keys():
        print(k,v['name'])

In [ ]: