jupyter/数据处理.ipynb at master

512song/jupyter

0 Fork 0

Files

T

512song 321337fdda 20250703

2025-07-03 22:19:02 +08:00

51 KiB

Raw Permalink Blame History

基础知识

正则表达式分割文本

In [ ]:

import json
import openpyxl
import re

file_name = 'data/药食材性味归经.xlsx'
wb = openpyxl.load_workbook(file_name)
sheet = wb.active
#sheets = wb.sheetnames

list1 = []
dict1 = {}
mo =r'[。入归].+经$'
mo1 = r'[二]'
mo2 = r'[，、；]'
for n in range(2,sheet.max_row):
    name = sheet.cell(n,1).value
    content = re.findall(mo,sheet.cell(n,2).value)
    if len(content) > 0:
        l = len(content[0])
        gj = re.sub(mo1, '', content[0][1:l-1])        
        list_gj = re.split(mo2,gj)
        dict1[sheet.cell(n,1).value ] = list_gj
        #dict1['guijing'] = list_gj
        
filename = './data/药食材归经.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl,ensure_ascii=False) 

#print(list1)

In [ ]:

import re

s = '消化不良、胃下垂、急性胃炎、慢性胃炎、萎缩性胃炎、神经性呕吐、胆囊炎、胆石症、胆道蛔虫症、胸胁痛等'
ss = '健中和胃，消食止呕，理气疏郁，清热利胆。'
mo = '等$'
mo2 = r'[，、；。]'
s1 = re.sub(mo, '', s) 
list1 = re.split(mo2,s1)
if '' in list1:
    list1.remove('')
print(list1)

In [ ]:

import re
t = '5小时10分48秒'
m = re.match(r'(.*)小时(.*)分(.*)秒', t)
m.groups()

In [ ]:

import re
t = '10分48秒'
list1 = []
if '小时' in t and '分' in t:
    m = re.match(r'(.*)小时(.*)分(.*)秒', t)
    list1 = [m[1],m[2],m[3]]
elif '小时' in t:
    m = re.match(r'(.*)小时(.*)秒', t)
    list1 = [m[1],0,m[2]]
elif '分' in t:
    m = re.match(r'(.*)分(.*)秒', t)
    list1 = [0,m[1],m[2]]
print(list1)
#m.group()

In [ ]:

import re

s = '2022-09-28-《气郁组》-视频学习详情_155229'
m = re.findall(r'《(.+)》',s)
print(m)

日期计算

In [ ]:

import time

birth = '1989-01-25'
t_birth = time.strptime(birth,'%Y-%m-%d')
days = (time.time() -time.mktime(t_birth))//(365*24*60*60)
print(int(days))

字符串转换

In [3]:

import binascii

gbs = 'CDF5F0A9D1F300000000000000000000'
bs = binascii.a2b_hex(gbs)
print('bs', bs)
print('decode-bs:', bs.decode('gbk'))

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

bs b'\xcd\xf5\xf0\xa9\xd1\xf3\x00\x00\x00\x00\x00\x00\x00\x00\x00\x00'
decode-bs: 王皓洋����������
gbcode: b'\xcd\xf5\xf0\xa9\xd1\xf3'
gbs: cdf5f0a9d1f3

数据组合处理

In [ ]:

import itertools

list1 = ['气虚','阳虚','阴虚','痰湿','湿热','血瘀','气郁','特禀']
list2 = [0,1,2,3,4,5,6,7]

result=itertools.combinations(list1,7)
print(len(list(result)))

数字查询替换组合处理

In [ ]:

import re 
def replace_numbers(text):
    pattern = r'\d+'
    replacement = lambda x:'{{'+ f'img_{x.group()}'+'}}'
    modified_text = re.sub(pattern, replacement, text)
    return modified_text

# Example usage of the function
example_text = "In 2021, we had a total of 456 sales."
modified_text = replace_numbers(example_text)
print("Original Text:", example_text)
print("Modified Text:", modified_text)

文本文件提取数据

In [ ]:

fn = 'file/人员名单.txt'

with open(fn, "r") as f:
    data = f.readlines()
for i in range(0,int(len(data)/5)):
    list1= []
    for n in range(0,5):
        s = data[5*i+n].replace('\n','')
        if n >0:
            list1.append(s.split('：')[1].replace(' ',''))
        else:
            list1.append(s)
   
    print(';'.join(list1))
    i+=1

医药体测

药膳归经明细文件生成

In [ ]:

import json

filename = 'data/药膳210927.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
filename = 'data/药食材归经.json'
with open(filename,'r') as fl:
    dict2 = json.load(fl)
k_zy = dict2.keys()
dict3 = {}
list1 = []
for item in dict1:
    print(item['name'])
    list1 = []
    #print(i,item['zy'])
    for m_zy in item['zy']:
        if m_zy in k_zy:
            dict4 = {}
            print(m_zy,dict2[m_zy])
            dict4[m_zy] = dict2[m_zy]
            list1.append(dict4)
    dict3[item['name']] = list1
filename = './data/药膳药食材.json'
with open(filename,'w') as fl:
    json.dump(dict3, fl,ensure_ascii=False)

药膳归经权重生成

In [ ]:

import json
import openpyxl
import os,sys,shutil

filename = './data/药膳药食材.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
list1 = []
for k, v in dict1.items():
    if len(v) > 0 :
        dict2 = {}
        #print(k,v)
        ys_name = k
        dict2.setdefault(ys_name,{})
        for item in v:
            for k1, v1 in item.items():
                for item1 in v1:
                    dict2[ys_name].setdefault(item1,0)
                    dict2[ys_name][item1] += 1
        list1.append(dict2)                    
    
dict_qz = {}
for item in list1:
    for k, v in item.items():
        qz = sorted(v.items(), key = lambda kv:(kv[1], kv[0]),reverse=True)
        dict_qz[k] = qz
#print(dict_qz)
qz_key = dict_qz.keys()
filename = 'data/药膳210927.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
#print(dict1)
wb = openpyxl.Workbook()
sheet = wb.active
sheet['A1'] = '药膳名称'
sheet['B1'] = '来源'
sheet['C1'] = '配方'
sheet['D1'] = '做法'
sheet['E1'] = '功效'
sheet['F1'] = '中药成分'
sheet['G1'] = '归经权重'

i =2
for item in dict1:
    sheet[f'A{i}'] = item['name']
    sheet[f'B{i}'] = item['source']
    sheet[f'C{i}'] = item['pf']
    sheet[f'D{i}'] = item['zf']
    sheet[f'E{i}'] = item['gx']
    sheet[f'F{i}'] = ','.join(item['zy'])
    if item['name'] in qz_key:
        s = ''
        for m_gj in dict_qz[item['name']]:
            s = s+ m_gj[0] +'('+str(m_gj[1])+')'
        sheet[f'G{i}'] = s
    else:
        sheet[f'G{i}'] = '暂无归经'
    i += 1

wb.save('data/test4.xlsx')

药膳文件处理

药膳文件预处理

In [ ]:

import re
import json

filename = 'data/286种药膳常用中药功能表.txt'
with open(filename, "r", encoding='utf-8') as f:  
    data = f.readlines()
dict1 = {}
for i in range(0,int(len(data)/7)) :    
    s = data[i*7].strip()
    bh = s.split('.')[0]
    name = s.split('.')[1].split('（')[0]
    #print(bh,name)
    id = str(i+1)
    dict1.setdefault(id,{})
    dict1[id]['name'] = name
    for n in range(1,7):
        ss = data[i*7+n].strip()
        p = re.compile(r'【(.*?)】')
        item = re.findall(p,ss)[0]
        content = ss.split('】')[1]
        dict1[id][item] = content
filename = 'data/286种药膳常用中药功能表.json'
with open(filename, 'w') as fl:
    json.dump(dict1, fl, ensure_ascii=False)
print('ok')

性味归经分解

In [ ]:

import re
import json

filename = 'data/286种药膳常用中药功能表.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
p = re.compile(r'[入归](.*?)经')
for k, v in dict1.items():
    if '性味归经' in v.keys():
        s = v['性味归经']
        item = re.search(p,s)
        if item is not None:
            ss = item.group()
            sss = re.sub(ss,'',s)
            
            p1 = r'[；:、，。：]+。'
            ssss = re.sub(p1,'。',sss)
            #print(k,ss,ssss)
            dict1[k]['归经'] = ss
            dict1[k]['性味'] = ssss
        else:
            dict1[k]['归经'] = s
       
filename = 'data/286种药膳常用中药功能表1.json'
with open(filename, 'w') as fl:
    json.dump(dict1, fl, ensure_ascii=False)
print('ok')

In [ ]:

import re
import json

filename = 'data/286种药膳常用中药功能表.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
p = re.compile(r'[入归](.*?)经')
for k, v in dict1.items():
    if '性味归经' in v.keys():
        s = v['性味归经']
        item = re.search(p,s)
        #print(item)
        if item is not None:
            ss = item.group()
            sss = re.sub(ss,'',s)
            
            p1 = r'[；:、，。：]+。'
            ssss = re.sub(p1,'。',sss)
            print(k,ssss)

In [ ]:

体质数据处理

体质对应数据导入

In [ ]:

import json

filename = 'data/tijianbingzheng.txt'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
m_key = set()
for k, v in dict1.items():
    for item in v.keys():
        m_key.add(item)
print(dict1)

生成导入数据库语句

In [ ]:

import openpyxl
import json
from datetime import date

wb = openpyxl.load_workbook('data/镇海体测手工数据.xlsx')
sheet = wb.active
# sheets = wb.sheetnames
dict1 = {}
list1 = []
for n in range(1, sheet.max_row+1):
    id = int(sheet.cell(n, 1).value)
    item = int(sheet.cell(n, 2).value)
    perf = int(sheet.cell(n, 3).value)
    s = f'(345321,{id},{item},{perf},"2024-09-22","2024-09-22 18:00:00")'
    list1.append(s)
ss = ','.join(list1)
print(ss)

穴位数据导入

简单导出简介、内容

In [ ]:

import json
import re
dict1 = {}
filename = 'file/zhongyi/xuewei.json'
with open(filename,'r',encoding='utf-8') as fl:
    for line in fl:
        line1 = json.loads(re.sub(r'\xa0','',line))
        list1 = line1['tables']
        list2 = line1['contents']
        dict2 = dict(zip(list1, list2))
        #print(line1['title'],dict1)
        #print(dict1.keys())
        #print(line1)
        dict1.setdefault(line1['title'][0],{})
        dict1[line1['title'][0]]['简介'] = line1['jj'] 
        dict1[line1['title'][0]]['内容'] = dict2
filename = './file/穴位1.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl)

数据导入文件中

In [ ]:

import json
import re

dict1 = {}
filename = 'file/zhongyi/xuewei.json'
with open(filename,'r',encoding='utf-8') as fl:
    for line in fl:
        line1 = json.loads(re.sub(r'\xa0','',line))
        list1 = line1['tables']
        list2 = line1['contents']
        list3 = line1['jj']
        dict2 = dict(zip(list1, list2))
        dict1.setdefault(line1['title'][0],{})
        if len(list3) > 0:
            
            dict1[line1['title'][0]]['about'] = list3
        dict1[line1['title'][0]].setdefault('content',{})
        for k, v in dict2.items():
            dict1[line1['title'][0]]['content'][k] = v 
        #dict1[line1['title'][0]]['内容'] = dict2
filename = './file/穴位1.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl)

穴位数据导入数据库中

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
#dblist = myclient.list_database_names()
mydb = myclient['dayi']
mycol = mydb["xuewei"]
db_list = []
filename = 'file/zhongyi/xuewei.json'
with open(filename,'r',encoding='utf-8') as fl:
    for line in fl:
        dict1 = {}
        line1 = json.loads(re.sub(r'\xa0','',line))
        list1 = line1['tables']
        list2 = line1['contents']
        list3 = line1['jj']
        dict2 = dict(zip(list1, list2))
        dict1['name'] = line1['title'][0]
        if len(list3) > 0:
            dict1.setdefault('about',{})
            for s in list3:
                item = s.strip().split(':')
                dict1['about'][item[0].strip()] = item[1].strip()
        dict1.setdefault('content',{})
        for k, v in dict2.items():
            dict1['content'][k] = v 
        #dict1[line1['title'][0]]['内容'] = dict2
        db_list.append(dict1)
x = mycol.insert_many(db_list)
print('ok!')

中医症状数据导入数据库中

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
mydb = myclient['dayi']
mycol = mydb["zhongyizhengzhuang"]
db_list = []
filename = 'file/zhongyi/zhongyizhengzhuang.json'
with open(filename,'r',encoding='utf-8') as fl:
    for line in fl:
        dict1 = {}
        line1 = json.loads(re.sub(r'\xa0','',line))
        list1 = line1['tables']
        list2 = line1['contents']
        list3 = line1['jj']
        dict2 = dict(zip(list1, list2))
        dict1['name'] = line1['title'][0]
        if len(list3) > 0:
            dict1.setdefault('about',{})
            for i in range(0,int(len(list3)/2)):
                dict1['about'][list3[2*i]] = list3[2*i+1]
        dict1.setdefault('content',{})
        for k, v in dict2.items():
            dict1['content'][k] = v 
        #dict1[line1['title'][0]]['内容'] = dict2
        db_list.append(dict1)
x = mycol.insert_many(db_list)
print('ok!')

疾病数据导入数据库中

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
mydb = myclient['dayi']
mycol = mydb["jibing"]
db_list = []
filename = 'file/zhongyi/jibing.json'
with open(filename,'r',encoding='utf-8') as fl:
    for line in fl:
        dict1 = {}
        line1 = json.loads(re.sub(r'\xa0','',line))
        list1 = line1['tables']
        list2 = line1['contents']
        list3 = line1['jj']
        dict2 = dict(zip(list1, list2))
        dict1['name'] = line1['title'][0]
        if len(list3) > 0:
            dict1.setdefault('about',{})
            for i in range(0,int(len(list3)/2)):
                dict1['about'][list3[2*i]] = list3[2*i+1]
        dict1.setdefault('content',{})
        for k, v in dict2.items():
            dict1['content'][k] = v 
        #dict1[line1['title'][0]]['内容'] = dict2
        db_list.append(dict1)
x = mycol.insert_many(db_list)
print('ok!')

术语数据导入数据库中

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
#dblist = myclient.list_database_names()
mydb = myclient['dayi']
mycol = mydb["shuyu"]
db_list = []
filename = 'file/zhongyi/shuyu.json'
with open(filename,'r',encoding='utf-8') as fl:
    for line in fl:
        dict1 = {}
        line1 = json.loads(re.sub(r'\xa0','',line))
        list1 = line1['tables']
        list2 = line1['contents']
        list3 = line1['jj']
        dict2 = dict(zip(list1, list2))
        dict1['name'] = line1['title'][0]
        if len(list3) > 0:
            dict1.setdefault('about',{})
            for s in list3:
                item = s.strip().split(':')
                dict1['about'][item[0]] = item[1]
        dict1.setdefault('content',{})
        for k, v in dict2.items():
            dict1['content'][k] = v 
        #dict1[line1['title'][0]]['内容'] = dict2
        db_list.append(dict1)
x = mycol.insert_many(db_list)
print('ok!')

西医症状数据导入数据库中

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
mydb = myclient['dayi']
mycol = mydb["xiyizhengzhuang"]
db_list = []
filename = 'file/zhongyi/xiyizhengzhuang.json'
with open(filename,'r',encoding='utf-8') as fl:
    for line in fl:
        dict1 = {}
        line1 = json.loads(re.sub(r'\xa0','',line))
        list1 = line1['tables']
        list2 = line1['contents']
        list3 = line1['jj']
        dict2 = dict(zip(list1, list2))
        dict1['name'] = line1['title'][0]
        if len(list3) > 0:
            dict1.setdefault('about',{})
            for i in range(0,int(len(list3)/2)):
                dict1['about'][list3[2*i]] = list3[2*i+1]
        dict1.setdefault('content',{})
        for k, v in dict2.items():
            dict1['content'][k] = v 
        #dict1[line1['title'][0]]['内容'] = dict2
        db_list.append(dict1)
x = mycol.insert_many(db_list)
print('ok!')

药剂数据导入数据库中

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
#dblist = myclient.list_database_names()
mydb = myclient['dayi']
mycol = mydb["yaoji"]
db_list = []
filename = 'file/zhongyi/yaoji.json'
with open(filename,'r',encoding='utf-8') as fl:
    for line in fl:
        dict1 = {}
        line1 = json.loads(re.sub(r'\xa0','',line))
        list1 = line1['tables']
        list2 = line1['contents']
        list3 = line1['jj']        
        dict2 = dict(zip(list1, list2))        
        if len(list3) > 0: 
            jj = {}
            for s in list3:
                item = s.strip().split(':')
                jj[item[0]] = item[1]        
        dict1['name'] = jj['名称']
        dict1['about'] = jj
        dict1.setdefault('content',{})
        for k, v in dict2.items():
            dict1['content'][k] = v 
        #dict1[line1['title'][0]]['内容'] = dict2
        db_list.append(dict1)
x = mycol.insert_many(db_list)
print('ok!')

药膳数据导入数据库中

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
#dblist = myclient.list_database_names()
mydb = myclient['dayi']
mycol = mydb["yaoshan"]
db_list = []
filename = 'file/zhongyi/yaoshan.json'
with open(filename,'r',encoding='utf-8') as fl:
    for line in fl:
        dict1 = {}
        line1 = json.loads(re.sub(r'\xa0','',line))
        list1 = line1['tables']
        list2 = line1['contents']
        list3 = line1['jj']
        dict2 = dict(zip(list1, list2))
        dict1['name'] = line1['title'][0]
        if len(list3) > 0:
            dict1.setdefault('about',{})
            for s in list3:
                item = s.strip().split(':')
                dict1['about'][item[0]] = item[1]
        dict1.setdefault('content',{})
        for k, v in dict2.items():
            dict1['content'][k] = v 
        #dict1[line1['title'][0]]['内容'] = dict2
        db_list.append(dict1)
x = mycol.insert_many(db_list)
print('ok!')

中草药数据导入数据库中

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
mydb = myclient['dayi']
mycol = mydb["zhongcaoyao"]
db_list = []
filename = 'file/zhongyi/zhongcaoyao.json'
with open(filename,'r',encoding='utf-8') as fl:
    for line in fl:
        dict1 = {}
        line1 = json.loads(re.sub(r'\xa0','',line))
        list1 = line1['tables']
        list2 = line1['contents']
        list3 = line1['jj']
        dict2 = dict(zip(list1, list2))
        dict1['name'] = line1['title'][0]
        if len(list3) > 0:
            dict1.setdefault('about',{})
            for i in range(0,int(len(list3)/2)):
                dict1['about'][list3[2*i]] = list3[2*i+1]
        dict1.setdefault('content',{})
        for k, v in dict2.items():
            dict1['content'][k] = v 
        #dict1[line1['title'][0]]['内容'] = dict2
        db_list.append(dict1)
x = mycol.insert_many(db_list)
print('ok!')

穴位隶属整理

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
mydb = myclient['dayi']
mycol = mydb["xuewei"]
dict1 = {}
list1 = []
for x in mycol.find({},{ "_id": 0,"name":1,"about.隶属":1 }):
    if 'about' in x.keys():
        m_ls = x['about']['隶属']
        dict1.setdefault(m_ls,[])
        dict1[m_ls].append(x['name'])
'''
filename = './file/穴位隶属.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl)     
'''
for item in dict1.keys():
    print(item)

穴位功能、主治统计

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
mydb = myclient['dayi']
mycol = mydb["xuewei"]

dict1 = {}
mo = '等$'
mo2 = r'[，、；。]'

for x in mycol.find({},{ "_id": 0,"name":1,"about":1 }):
    dict1.setdefault(x['name'],{})
    if '主治' in x['about'].keys():
        #dict1[x['name']].setdefault('主治',[])
        s = x['about']['主治']
        s1 = re.sub(mo, '', s)
        list1 = re.split(mo2,s1)
        if '' in list1:
            list1.remove('')
        dict1[x['name']]['主治'] = list1
    if '功能' in x['about'].keys():
        #dict1[x['name']].setdefault('主治',[])
        s = x['about']['功能']
        s1 = re.sub(mo, '', s)
        list1 = re.split(mo2,s1)
        if '' in list1:
            list1.remove('')
        dict1[x['name']]['功能'] = list1
        

filename = './file/穴位主治功能统计.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl)

穴位数据导出Excel表

In [ ]:

import json
import openpyxl

filename = 'file/穴位.json'
with open(filename,'r') as fl:
    dict1 = json.load(fl)
filename = 'file/穴位简要情况表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet['A1'] = '穴位名称'
sheet['B1'] = '隶属'
sheet['C1'] = '位置'
sheet['D1'] = '主治'
sheet['E1'] = '功能'
sheet['F1'] = '操作'
sheet['G1'] = '主要配伍'
i = 2
for k, v in dict1.items():
    sheet[f'A{i}'] = k
    sheet[f'B{i}'] = v['简介'][0].split(':')[1]
    sheet[f'C{i}'] = v['简介'][1].split(':')[1]
    sheet[f'D{i}'] = v['简介'][2].split(':')[1]
    sheet[f'E{i}'] = v['简介'][3].split(':')[1]
    sheet[f'F{i}'] = v['简介'][4].split(':')[1]
    sheet[f'G{i}'] = v['简介'][5].split(':')[1]      
    i += 1
wb.save(filename)   
print('ok!')

术语数据处理

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
mydb = myclient['dayi']
mycol = mydb["shuyu"]
dict1 = {}
list1 = []
for x in mycol.find({},{ "_id": 0,"name":1,"about":1 }):
    if '类别' in x['about'].keys():
        m_lb = x['about']['类别'].replace(' ','')
    else:
        m_lb = '无类别'
    dict1.setdefault(re.sub('\xa0+','',m_lb),[])
    dict1[m_lb].append(x['name'])
filename = './file/术语类别.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl)

疾病数据处理

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
mydb = myclient['dayi']
mycol = mydb["jibing"]
dict1 = {}
list1 = []
for x in mycol.find({},{ "_id": 0,"name":1,"about":1 }):
    if '疾病分类' in x['about'].keys():
        m_lb = x['about']['疾病分类'].replace(' ','')
    else:
        m_lb = '无类别'
    dict1.setdefault(re.sub('\xa0+','',m_lb),[])
    dict1[m_lb].append(x['name'])
filename = './file/疾病类别.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl)

中草药数据处理

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
mydb = myclient['dayi']
mycol = mydb["zhongcaoyao"]

dict1 = {}
mo = '等$'
mo2 = r'[，、；。]'

for x in mycol.find({},{ "_id": 0,"name":1,"about":1 }):
    dict1.setdefault(x['name'],{})
    if '别名' in x['about'].keys():
        #dict1[x['name']].setdefault('主治',[])
        s = x['about']['别名']
        s1 = re.sub(mo, '', s)
        list1 = re.split(mo2,s1)
        if '' in list1:
            list1.remove('')
        dict1[x['name']]['别名'] = list1
    if '功能' in x['about'].keys():
        #dict1[x['name']].setdefault('主治',[])
        s = x['about']['功能']
        s1 = re.sub(mo, '', s)
        list1 = re.split(mo2,s1)
        if '' in list1:
            list1.remove('')
        dict1[x['name']]['功能'] = list1
    if '主治' in x['about'].keys():
        #dict1[x['name']].setdefault('主治',[])
        dict1[x['name']]['主治'] = s = x['about']['主治']
        

filename = './file/中草药主治功能统计.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl)

药剂数据处理

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
mydb = myclient['dayi']
mycol = mydb["yaoji"]

dict1 = {}
mo = '等$'
mo2 = r'[，、；。]'

for x in mycol.find({},{ "_id": 0,"name":1,"about":1 }):
    dict1.setdefault(x['name'],{})
    if '功用' in x['about'].keys():
        #dict1[x['name']].setdefault('主治',[])
        s = x['about']['功用']
        s1 = re.sub(mo, '', s)
        list1 = re.split(mo2,s1)
        if '' in list1:
            list1.remove('')
        dict1[x['name']]['功用'] = list1
    if '主治' in x['about'].keys():
        #dict1[x['name']].setdefault('主治',[])
        dict1[x['name']]['主治'] = s = x['about']['主治']
        

filename = './file/药剂主治功用统计.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl)

药膳数据处理

In [ ]:

import json
import re
import pymongo

myclient = pymongo.MongoClient('mongodb://10.147.17.6:27017/')
mydb = myclient['dayi']
mycol = mydb["yaoshan"]

dict1 = {}
mo = '等$'
mo2 = r'[，、；。]'

for x in mycol.find({},{ "_id": 0,"name":1,"about":1 }):
    dict1.setdefault(x['name'],{})
    if '功效' in x['about'].keys():
        #dict1[x['name']].setdefault('主治',[])
        s = x['about']['功效']
        s1 = re.sub(mo, '', s)
        list1 = re.split(mo2,s1)
        if '' in list1:
            list1.remove('')
        dict1[x['name']]['功效'] = list1
    if '相关疾病' in x['about'].keys():
        #dict1[x['name']].setdefault('主治',[])
        s = x['about']['相关疾病']
        s1 = re.sub(mo, '', s)
        list1 = re.split(mo2,s1)
        if '' in list1:
            list1.remove('')
        dict1[x['name']]['相关疾病'] = list1    
        

filename = './file/药膳功能统计.json'
with open(filename,'w') as fl:
    json.dump(dict1, fl)

北海炼化体检数据提取

In [ ]:

import json
import openpyxl
import os,sys,shutil

file_name = 'file/中石化北海炼化2020年团体体检报告.xlsx'
wb = openpyxl.load_workbook(file_name)
sheet = wb.active
dict1 = {}
for n in range(1,sheet.max_row+1):
    bh = sheet.cell(n,2).value
    name = sheet.cell(n,3).value
    xb = sheet.cell(n,4).value
    nl = sheet.cell(n,5).value
    bz = sheet.cell(n,7).value
    dict1.setdefault(bh,{})
    dict1[bh]['姓名'] = name
    dict1[bh]['性别'] = xb
    dict1[bh]['年龄'] = nl
    dict1[bh].setdefault('病症',[])
    dict1[bh]['病症'].append(bz.strip())
wb.close()
#print(dict1)
    
        
filename = 'file/中石化北海炼化2020年体检人员情况表.xlsx'
wb = openpyxl.Workbook()
sheet = wb.active
sheet['A1'] = '体检编号'
sheet['B1'] = '姓名'
sheet['C1'] = '性别'
sheet['D1'] = '年龄'
sheet['E1'] = '异常名称'

i =2
for k, v in dict1.items():
    sheet[f'A{i}'] = k
    sheet[f'B{i}'] = v['姓名']
    sheet[f'C{i}'] = v['性别']
    sheet[f'D{i}'] = v['年龄']
    sheet[f'E{i}'] = ','.join(v['病症'])    
    i += 1
wb.save(filename)

excel数据读取

In [ ]:

import openpyxl
import json

filename = 'data/长岭全成绩.xlsx'
wb = openpyxl.load_workbook(filename)
sheet = wb.active
data1 =list(sheet.values)
del data1[0]
print(data1)
#for data in data1:
#    print(data)

图表生成

高考一分一段表生成

In [ ]:

from pyecharts.globals import CurrentConfig, NotebookType
CurrentConfig.NOTEBOOK_TYPE = NotebookType.JUPYTER_LAB
from pyecharts import options as opts
from pyecharts.charts import Bar,Line
import pyecharts.options as opts
from pyecharts.faker import Faker
import json

list_x = []
list_y = []
filename = 'data/17-21年一分一段表.json'
with open(filename,'r') as fl:
    m_xx = json.load(fl)
dict1 =m_xx['2020']['z']
for i in sorted(dict1,reverse=True): #降序
    list_x.append(i)
    list_y.append(dict1[i]['num_person'])
    #print(i,dict1[i]['num_person'])
bar = (
    Bar()
    .add_xaxis(list_x)
    .add_yaxis("2020年一分一段表", list_y, category_gap=0, color=Faker.rand_color())
    .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
    .set_global_opts(title_opts=opts.TitleOpts(title="Bar-直方图"))
    .render("bar_histogram2020.html")
#    .set_global_opts(title_opts=opts.TitleOpts(title="运动步幅及步频", subtitle="户外运动"),)
)
#bar.load_javascript()

In [ ]:

bar.render_notebook()

In [ ]:

from pyecharts.globals import CurrentConfig, NotebookType
CurrentConfig.NOTEBOOK_TYPE = NotebookType.JUPYTER_LAB
from pyecharts import options as opts
from pyecharts.charts import Bar,Line
import pyecharts.options as opts
from pyecharts.faker import Faker
import json

x_2021 = []
y_2021 = []
x_2020 = []
y_2020 = []
filename = 'data/17-21年一分一段表.json'
with open(filename,'r') as fl:
    m_xx = json.load(fl)
dict1 =m_xx['2021']['z']
for i in sorted(dict1,reverse=True): #降序
    x_2021.append(i)
    y_2021.append(dict1[i]['num_person'])
dict1 =m_xx['2020']['z']
for i in sorted(dict1,reverse=True): #降序
    x_2021.append(i)
    y_2021.append(dict1[i]['num_person'])
    #print(i,dict1[i]['num_person'])
bar = (
    Bar()
    .add_xaxis(list_x)
    .add_yaxis("人数", list_y, category_gap=0, color=Faker.rand_color())
    .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
    .set_global_opts(title_opts=opts.TitleOpts(title="Bar-直方图"))
    .render("bar_histogram.html")

生成雷达图

In [ ]:

from pyecharts.globals import CurrentConfig, NotebookType
import pyecharts.options as opts
CurrentConfig.NOTEBOOK_TYPE = NotebookType.JUPYTER_LAB
from pyecharts.charts import Radar


v1 = [[90, 100, 80, 76, 88, 95]]
v2 = [[5000, 14000, 28000, 31000, 42000, 21000]]

bar =(
    Radar(init_opts=opts.InitOpts())
    .add_schema(
        schema=[
            opts.RadarIndicatorItem(name="销售（sales）", max_=100),
            opts.RadarIndicatorItem(name="管理（Administration）", max_=100),
            opts.RadarIndicatorItem(name="信息技术（Information Technology）", max_=100),
            opts.RadarIndicatorItem(name="客服（Customer Support）", max_=100),
            opts.RadarIndicatorItem(name="研发（Development）", max_=100),
            opts.RadarIndicatorItem(name="市场（Marketing）", max_=100),
        ],
        splitarea_opt=opts.SplitAreaOpts(
            is_show=True, areastyle_opts=opts.AreaStyleOpts(opacity=1)
        ),
        textstyle_opts=opts.TextStyleOpts(color="#aaa"),
    )
    .add(
        series_name="预算分配（Allocated Budget）",
        data=v1,
        linestyle_opts=opts.LineStyleOpts(color="#CD0000"),
    )
    
    .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
    .set_global_opts(
        title_opts=opts.TitleOpts(title="基础雷达图"), legend_opts=opts.LegendOpts()
    )
    #.render("basic_radar_chart.html")
    
)
bar.load_javascript()

In [ ]:

bar.render_notebook()

In [ ]:

from pyecharts.globals import CurrentConfig, NotebookType
import pyecharts.options as opts
CurrentConfig.NOTEBOOK_TYPE = NotebookType.JUPYTER_LAB
from pyecharts.charts import Radar
from pyecharts.render import make_snapshot
from snapshot_phantomjs import snapshot


v1 = [[90, 100, 80, 76, 88, 95]]
v2 = [[5000, 14000, 28000, 31000, 42000, 21000]]

bar =(
    Radar(init_opts=opts.InitOpts())
    .add_schema(
        schema=[
            opts.RadarIndicatorItem(name="销售（sales）", max_=100),
            opts.RadarIndicatorItem(name="管理（Administration）", max_=100),
            opts.RadarIndicatorItem(name="信息技术（Information Technology）", max_=100),
            opts.RadarIndicatorItem(name="客服（Customer Support）", max_=100),
            opts.RadarIndicatorItem(name="研发（Development）", max_=100),
            opts.RadarIndicatorItem(name="市场（Marketing）", max_=100),
        ],
        splitarea_opt=opts.SplitAreaOpts(
            is_show=True, areastyle_opts=opts.AreaStyleOpts(opacity=1)
        ),
        textstyle_opts=opts.TextStyleOpts(color="#aaa"),
    )
    .add(
        series_name="预算分配（Allocated Budget）",
        data=v1,
        linestyle_opts=opts.LineStyleOpts(color="#CD0000"),
    )
    
    .set_series_opts(label_opts=opts.LabelOpts(is_show=False))
    .set_global_opts(
        title_opts=opts.TitleOpts(title="基础雷达图"), legend_opts=opts.LegendOpts()
    )
    #.render("basic_radar_chart.html")
    
)
make_snapshot(snapshot, bar.render(), "bar0.png")

In [ ]:

import pygal 

radar_chart = pygal.Radar()
radar_chart.title = 'V8 benchmark results'
radar_chart.x_labels = ['Richards', 'DeltaBlue', 'Crypto', 'RayTrace', 'EarleyBoyer', 'RegExp', 'Splay', 'NavierStokes']
radar_chart.add('Chrome', [6395, 8212, 7520, 7218, 12464, 1660, 2123, 8607])

radar_chart.render_to_png('chart.png')

In [ ]:

51 KiB Raw Permalink Blame History

基础知识

正则表达式分割文本

日期计算

字符串转换

数据组合处理

数字查询替换组合处理

文本文件提取数据

医药体测

药膳归经明细文件生成

药膳归经权重生成

药膳文件处理

药膳文件预处理

性味归经分解

体质数据处理

体质对应数据导入

生成导入数据库语句

穴位数据导入

简单导出简介、内容

数据导入文件中

穴位数据导入数据库中

中医症状数据导入数据库中

疾病数据导入数据库中

术语数据导入数据库中

西医症状数据导入数据库中

药剂数据导入数据库中

药膳数据导入数据库中

中草药数据导入数据库中

穴位隶属整理

穴位功能、主治统计

穴位数据导出Excel表

术语数据处理

疾病数据处理

中草药数据处理

药剂数据处理

药膳数据处理

北海炼化体检数据提取

excel数据读取

图表生成

高考一分一段表生成

生成雷达图

51 KiB

Raw Permalink Blame History