From 1b88f510c6d637e662de9a3c6b348c10e1a41c77 Mon Sep 17 00:00:00 2001 From: 512song Date: Tue, 16 Nov 2021 21:40:07 +0800 Subject: [PATCH] 20211116 --- 体质检测管理.ipynb | 3 +- 数据处理.ipynb | 206 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 208 insertions(+), 1 deletion(-) create mode 100644 数据处理.ipynb diff --git a/体质检测管理.ipynb b/体质检测管理.ipynb index e665731..497b4f4 100644 --- a/体质检测管理.ipynb +++ b/体质检测管理.ipynb @@ -797,7 +797,8 @@ "cell_type": "markdown", "id": "3711130b-59e3-4844-ac31-234ba77cd46c", "metadata": { - "tags": [] + "tags": [], + "toc-hr-collapsed": true }, "source": [ "## 脊柱症状统计" diff --git a/数据处理.ipynb b/数据处理.ipynb new file mode 100644 index 0000000..3546759 --- /dev/null +++ b/数据处理.ipynb @@ -0,0 +1,206 @@ +{ + "cells": [ + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 正则表达式分割文本" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import json\n", + "import openpyxl\n", + "import re\n", + "\n", + "file_name = 'data/药食材性味归经.xlsx'\n", + "wb = openpyxl.load_workbook(file_name)\n", + "sheet = wb.active\n", + "#sheets = wb.sheetnames\n", + "\n", + "list1 = []\n", + "dict1 = {}\n", + "mo =r'[。入归].+经$'\n", + "mo1 = r'[二]'\n", + "mo2 = r'[，、；]'\n", + "for n in range(2,sheet.max_row):\n", + " name = sheet.cell(n,1).value\n", + " content = re.findall(mo,sheet.cell(n,2).value)\n", + " if len(content) > 0:\n", + " l = len(content[0])\n", + " gj = re.sub(mo1, '', content[0][1:l-1]) \n", + " list_gj = re.split(mo2,gj)\n", + " dict1[sheet.cell(n,1).value ] = list_gj\n", + " #dict1['guijing'] = list_gj\n", + " \n", + "filename = './data/药食材归经.json'\n", + "with open(filename,'w') as fl:\n", + " json.dump(dict1, fl,ensure_ascii=False) \n", + "\n", + "#print(list1)" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 药膳归经明细文件生成" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": { + "tags": [] + }, + "outputs": [], + "source": [ + "import json\n", + "\n", + "filename = 'data/药膳210927.json'\n", + "with open(filename,'r') as fl:\n", + " dict1 = json.load(fl)\n", + "filename = 'data/药食材归经.json'\n", + "with open(filename,'r') as fl:\n", + " dict2 = json.load(fl)\n", + "k_zy = dict2.keys()\n", + "dict3 = {}\n", + "list1 = []\n", + "for item in dict1:\n", + " print(item['name'])\n", + " list1 = []\n", + " #print(i,item['zy'])\n", + " for m_zy in item['zy']:\n", + " if m_zy in k_zy:\n", + " dict4 = {}\n", + " print(m_zy,dict2[m_zy])\n", + " dict4[m_zy] = dict2[m_zy]\n", + " list1.append(dict4)\n", + " dict3[item['name']] = list1\n", + "filename = './data/药膳药食材.json'\n", + "with open(filename,'w') as fl:\n", + " json.dump(dict3, fl,ensure_ascii=False) \n", + " \n" + ] + }, + { + "cell_type": "markdown", + "metadata": {}, + "source": [ + "## 药膳归经权重生成" + ] + }, + { + "cell_type": "code", + "execution_count": 60, + "metadata": { + "execution": { + "iopub.execute_input": "2021-11-16T13:34:52.373277Z", + "iopub.status.busy": "2021-11-16T13:34:52.372041Z", + "iopub.status.idle": "2021-11-16T13:34:52.529747Z", + "shell.execute_reply": "2021-11-16T13:34:52.527803Z", + "shell.execute_reply.started": "2021-11-16T13:34:52.373167Z" + }, + "tags": [] + }, + "outputs": [], + "source": [ + "import json\n", + "import openpyxl\n", + "import os,sys,shutil\n", + "\n", + "filename = './data/药膳药食材.json'\n", + "with open(filename,'r') as fl:\n", + " dict1 = json.load(fl)\n", + "list1 = []\n", + "for k, v in dict1.items():\n", + " if len(v) > 0 :\n", + " dict2 = {}\n", + " #print(k,v)\n", + " ys_name = k\n", + " dict2.setdefault(ys_name,{})\n", + " for item in v:\n", + " for k1, v1 in item.items():\n", + " for item1 in v1:\n", + " dict2[ys_name].setdefault(item1,0)\n", + " dict2[ys_name][item1] += 1\n", + " list1.append(dict2) \n", + " \n", + "dict_qz = {}\n", + "for item in list1:\n", + " for k, v in item.items():\n", + " qz = sorted(v.items(), key = lambda kv:(kv[1], kv[0]),reverse=True)\n", + " dict_qz[k] = qz\n", + "#print(dict_qz)\n", + "qz_key = dict_qz.keys()\n", + "filename = 'data/药膳210927.json'\n", + "with open(filename,'r') as fl:\n", + " dict1 = json.load(fl)\n", + "#print(dict1)\n", + "wb = openpyxl.Workbook()\n", + "sheet = wb.active\n", + "sheet['A1'] = '药膳名称'\n", + "sheet['B1'] = '来源'\n", + "sheet['C1'] = '配方'\n", + "sheet['D1'] = '做法'\n", + "sheet['E1'] = '功效'\n", + "sheet['F1'] = '中药成分'\n", + "sheet['G1'] = '归经权重'\n", + "\n", + "i =2\n", + "for item in dict1:\n", + " sheet[f'A{i}'] = item['name']\n", + " sheet[f'B{i}'] = item['source']\n", + " sheet[f'C{i}'] = item['pf']\n", + " sheet[f'D{i}'] = item['zf']\n", + " sheet[f'E{i}'] = item['gx']\n", + " sheet[f'F{i}'] = ','.join(item['zy'])\n", + " if item['name'] in qz_key:\n", + " s = ''\n", + " for m_gj in dict_qz[item['name']]:\n", + " s = s+ m_gj[0] +'('+str(m_gj[1])+')'\n", + " sheet[f'G{i}'] = s\n", + " else:\n", + " sheet[f'G{i}'] = '暂无归经'\n", + " i += 1\n", + "\n", + "wb.save('data/test4.xlsx') \n", + "\n" + ] + }, + { + "cell_type": "code", + "execution_count": null, + "metadata": {}, + "outputs": [], + "source": [] + } + ], + "metadata": { + "kernelspec": { + "display_name": "Python 3", + "language": "python", + "name": "python3" + }, + "language_info": { + "codemirror_mode": { + "name": "ipython", + "version": 3 + }, + "file_extension": ".py", + "mimetype": "text/x-python", + "name": "python", + "nbconvert_exporter": "python", + "pygments_lexer": "ipython3", + "version": "3.8.10" + } + }, + "nbformat": 4, + "nbformat_minor": 4 +}