huangxiyun
/
dup_check
1
0
Креирај огранак 0
Код Дискусије 0 Захтеви за спајање 0 Издања 0 Вики Activity
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
1 Commit
1 Грана
92KB
Дрво: d9ffa090a9
Гране Ознаке
${ item.name }
Create branch ${ searchTerm }
from 'd9ffa090a9'
${ noResults }
dup_check/insert_history_data_total.py

284 lines
12KB
Датотека Blame Историја 

  1. # coding=utf-8

  2. 

  3. import re

  4. import mysql_pool

  5. from pymysql.converters import escape_string

  6. import cosin_similarity

  7. import pandas as pd

  8. import datetime

  9. import requests

  10. import os

  11. 

  12. wdys1 = {

  13.     "项目名称": "xmmc",

  14.     "现状问题": "xzwt",

  15.     "系统基础": "xtjc",

  16.     "项目目标": "xmmb",

  17.     "预期绩效": "yqjx",

  18.     "建设需求": "jsxq",

  19.     "数据需求": "sjxq",

  20.     "安全需求": "aqxq",

  21.     "业务领域": "ywly",

  22.     "核心业务": "hxyw",

  23.     "业务需求": "ywxq",

  24.     "业务协同": "ywxt",

  25.     "建设层级": "jscj",

  26.     "用户范围": "yhfw",

  27.     "目标群体": "mbqt",

  28.     "建设内容": "jsnr",

  29.     "功能模块": "gnmk",

  30.     "数据共享": "sjgx",

  31.     "智能要素": "znys",

  32.     "申报单位": "sbdw",

  33.     "所属地区": "ssdq",

  34.     "预算年度": "ysnd"

  35. }

  36. wdys2 = {

  37.     "xmmc": "项目名称",

  38.     "xzwt": "现状问题",

  39.     "xtjc": "系统基础",

  40.     "xmmb": "项目目标",

  41.     "yqjx": "预期绩效",

  42.     "jsxq": "建设需求",

  43.     "sjxq": "数据需求",

  44.     "aqxq": "安全需求",

  45.     "ywly": "业务领域",

  46.     "hxyw": "核心业务",

  47.     "ywxq": "业务需求",

  48.     "ywxt": "业务协同",

  49.     "jscj": "建设层级",

  50.     "yhfw": "用户范围",

  51.     "mbqt": "目标群体",

  52.     "jsnr": "建设内容",

  53.     "gnmk": "功能模块",

  54.     "sjgx": "数据共享",

  55.     "znys": "智能要素",

  56.     "sbdw": "申报单位",

  57.     "ssdq": "所属地区",

  58.     "ysnd": "预算年度"

  59. }

  60. gnmkys = {

  61.     "gnmc": "功能名称",

  62.     "gnms": "功能描述"

  63. }

  64. 

  65. 

  66. def getFlag():

  67.     data_dict = {}

  68.     df = pd.read_excel("0825-丽水系统查重维度.xlsx")

  69.     data = df.values

  70.     data = list(pd.Series(data[:, 1]).dropna())

  71.     for d in data:

  72.         try:

  73.             wd = re.search("(.*?)（.*?%）", d).group(1).strip()

  74.             wdc = wdys1.get(wd)

  75.             if wdc:

  76.                 qz = re.search(".*?（(.*?%)）", d).group(1)

  77.                 data_dict[wdc] = qz

  78.         except:

  79.             pass

  80.     return data_dict

  81. 

  82. 

  83. def gong_neng_mo_kuai(xmmc, mysql, dl, data, er_title):

  84.     # 将excel文件中的所有第三维度内容进行拼接

  85.     str_dict = {}

  86.     for et in er_title:

  87.         for d in data:

  88.             if d[1] == et:

  89.                 if str_dict.get(et):

  90.                     str_dict[et] = str_dict.get(et) + d[3]

  91.                 else:

  92.                     str_dict[et] = d[3]

  93.     for k, v in str_dict.items():

  94.         mysql.sql_change_msg("""insert into user_history_module_data_total(xmmc,gnmc,gnms) value("%s", "%s", "%s")""" % (

  95.             escape_string(xmmc), escape_string(k), escape_string(v)))

  96.         #

  97.         # similarity = cosin_similarity.CosineSimilarity(v, v)

  98.         # similarity, keywords_x, keywords_y = similarity.main()

  99.         # mysql.sql_change_msg("""insert into user_history_module_keywords (xmmc,gnmc,gnms) value("%s" ,"%s", "%s")""" % (

  100.         #     xmmc, escape_string(k), str(keywords_y)[dup_file_test:-dup_file_test]))

  101. 

  102. 

  103. def project_check(data_list):

  104.     mysql = mysql_pool.ConnMysql()

  105.     # 读取维度和权重

  106.     # get_data_dict = getFlag()

  107.     # 遍历excel存储路径

  108.     for dl in data_list:

  109.         # path = "0825-丽水系统查重维度1.xlsx"

  110.         # 读取路径下的excel

  111.         print(dl)

  112.         df = pd.read_excel(dl[1])

  113.         xmmc = df.keys()

  114.         # print(type(xmmc[dup_file_test]))

  115.         xmmc=xmmc[1]

  116.         # print(type(xmmc))

  117.         # xmmc1=''

  118. 

  119.         if "可研报告"or "可研性报告"or "可行性研究报告" in xmmc:

  120.             xmmc=xmmc.replace('可研报告','')

  121.             xmmc=xmmc.replace('可研性报告','')

  122.             xmmc=xmmc.replace('可行性研究报告','')

  123.         # print(xmmc)

  124.         data = df.values

  125.         # 将excel文件中的所有维度内容进行拼接

  126.         join_str = ""

  127.         str_dict = {}

  128.         title = ""

  129.         er_title = set()

  130.         # for d in data:

  131.         #     # print(d)

  132.         #     if pd.notnull(d[0]):

  133.         #         title = d[0]

  134.         #         if title == "功能模块":

  135.         #             er_title.add(d[dup_file_test])

  136.         #         join_str = ""

  137.         #         for i in d[dup_file_test:]:

  138.         #             if pd.notnull(i):

  139.         #                 join_str += i

  140.         #         str_dict[wdys1.get(title)] = join_str

  141.         #     else:

  142.         #         if title == "功能模块":

  143.         #             er_title.add(d[dup_file_test])

  144.         #         for i in d[dup_file_test:]:

  145.         #             if pd.notnull(i):

  146.         #                 join_str += i

  147.         #         str_dict[wdys1.get(title)] = str_dict.get(wdys1.get(title)) + join_str

  148.         # print(str_dict)

  149.         gnmk_str = []

  150.         # print(data)

  151.         for d in data:

  152.             if pd.notnull(d[0]):

  153.                 title = d[0]

  154.                 if title == "功能模块":

  155.                     er_title.add(d[1])

  156.                 join_str = ""

  157.                 for i in d[1:]:

  158.                     # print(type(i))

  159.                     # i=str(i)

  160.                     if pd.notnull(i):

  161.                         join_str += str(i)

  162.                         if title == "功能模块":

  163.                             # for j in d[3:]:

  164.                             if i == '功能描述':

  165.                                 continue

  166.                             else:

  167.                                 gnmk_str.append(i)

  168.                 str_dict[wdys1.get(title)] = join_str

  169.                 # print(str_dict.get(wdys1.get(title)))

  170.             else:

  171.                 if title == "功能模块":

  172.                     er_title.add(d[1])

  173.                 for i in d[3:]:

  174.                     if pd.notnull(i):

  175.                         join_str += str(i)

  176.                         if title == "功能模块":

  177.                             gnmk_str.append(i)

  178.                 str_dict[wdys1.get(title)] = str_dict.get(wdys1.get(title)) + join_str

  179.                 # gnmk="".join(gnmk_str)

  180.                 # str_dict['gnmk']=gnmk

  181.         gnmk = "".join(gnmk_str)

  182.         str_dict['gnmk'] = gnmk

  183.         # print(str_dict)

  184.         # print(str_dict.get("xzwt")if str_dict.get("xzwt") else None)

  185.         # print(str_dict.get('gnmk')if str_dict.get('gnmk')else None)

  186.         mysql.sql_change_msg(

  187.             """insert into user_history_data_total (xmmc, xzwt, xtjc, xmmb, yqjx, jsxq, sjxq, aqxq, ywly, hxyw, ywxq, ywxt, jscj, yhfw, mbqt, jsnr, gnmk, sjgx, znys,sbdw,ssdq,ysnd) value ("%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s","%s","%s","%s")"""

  188.             % (escape_string(xmmc),

  189.                escape_string(str_dict.get("xzwt")) if str_dict.get("xzwt") else None,

  190.                escape_string(str_dict.get("xtjc")) if str_dict.get("xtjc") else None,

  191.                escape_string(str_dict.get("xmmb")) if str_dict.get("xmmb") else None,

  192.                escape_string(str_dict.get("yqjx")) if str_dict.get("yqjx") else None,

  193.                escape_string(str_dict.get("jsxq")) if str_dict.get("jsxq") else None,

  194.                escape_string(str_dict.get("sjxq")) if str_dict.get("sjxq") else None,

  195.                escape_string(str_dict.get("aqxq")) if str_dict.get("aqxq") else None,

  196.                escape_string(str_dict.get("ywly")) if str_dict.get("ywly") else None,

  197.                escape_string(str_dict.get("hxyw")) if str_dict.get("hxyw") else None,

  198.                escape_string(str_dict.get("ywxq")) if str_dict.get("ywxq") else None,

  199.                escape_string(str_dict.get("ywxt")) if str_dict.get("ywxt") else None,

  200.                escape_string(str_dict.get("jscj")) if str_dict.get("jscj") else None,

  201.                escape_string(str_dict.get("yhfw")) if str_dict.get("yhfw") else None,

  202.                escape_string(str_dict.get("mbqt")) if str_dict.get("mbqt") else None,

  203.                escape_string(str_dict.get("jsnr")) if str_dict.get("jsnr") else None,

  204.                escape_string(str_dict.get("gnmk")) if str_dict.get("gnmk") else None,

  205.                escape_string(str_dict.get("sjgx")) if str_dict.get("sjgx") else None,

  206.                escape_string(str_dict.get("znys")) if str_dict.get("znys") else None,

  207.                escape_string(str_dict.get("sbdw")) if str_dict.get("sbdw") else None,

  208.                escape_string(str_dict.get("ssdq")) if str_dict.get("ssdq") else None,

  209.                escape_string(str_dict.get("ysnd")) if str_dict.get("ysnd") else None

  210.                ))

  211.         # project_gjc = {}

  212.         # for w in wdys2.keys():

  213.         #     content_x = str_dict.get(w)

  214.         #     content_y = str_dict.get(w)

  215.         #     if content_x and content_y:

  216.         #         # 循环遍历每一个维度

  217.         #         similarity = cosin_similarity.CosineSimilarity(content_x, content_y)

  218.         #         # 相似度  关键词

  219.         #         similarity, keywords_x, keywords_y = similarity.main()

  220.         #         project_gjc[w] = keywords_y

  221.         # mysql.sql_change_msg(

  222.         #     """insert into user_history_keywords (xmmc, xzwt, xtjc, xmmb, yqjx, jsxq, sjxq, aqxq, ywly, hxyw, ywxq, ywxt, jscj, yhfw, mbqt, jsnr, gnmk, sjgx, znys) value ("%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s", "%s")"""

  223.         #     % (xmmc, str(project_gjc.get("xzwt"))[dup_file_test:-dup_file_test] if project_gjc.get("xzwt") else None,

  224.         #        str(project_gjc.get("xtjc"))[dup_file_test:-dup_file_test] if project_gjc.get("xtjc") else None,

  225.         #        str(project_gjc.get("xmmb"))[dup_file_test:-dup_file_test] if project_gjc.get("xmmb") else None,

  226.         #        str(project_gjc.get("yqjx"))[dup_file_test:-dup_file_test] if project_gjc.get("yqjx") else None,

  227.         #        str(project_gjc.get("jsxq"))[dup_file_test:-dup_file_test] if project_gjc.get("jsxq") else None,

  228.         #        str(project_gjc.get("sjxq"))[dup_file_test:-dup_file_test] if project_gjc.get("sjxq") else None,

  229.         #        str(project_gjc.get("aqxq"))[dup_file_test:-dup_file_test] if project_gjc.get("aqxq") else None,

  230.         #        str(project_gjc.get("ywly"))[dup_file_test:-dup_file_test] if project_gjc.get("ywly") else None,

  231.         #        str(project_gjc.get("hxyw"))[dup_file_test:-dup_file_test] if project_gjc.get("hxyw") else None,

  232.         #        str(project_gjc.get("ywxq"))[dup_file_test:-dup_file_test] if project_gjc.get("ywxq") else None,

  233.         #        str(project_gjc.get("ywxt"))[dup_file_test:-dup_file_test] if project_gjc.get("ywxt") else None,

  234.         #        str(project_gjc.get("jscj"))[dup_file_test:-dup_file_test] if project_gjc.get("jscj") else None,

  235.         #        str(project_gjc.get("yhfw"))[dup_file_test:-dup_file_test] if project_gjc.get("yhfw") else None,

  236.         #        str(project_gjc.get("mbqt"))[dup_file_test:-dup_file_test] if project_gjc.get("mbqt") else None,

  237.         #        str(project_gjc.get("jsnr"))[dup_file_test:-dup_file_test] if project_gjc.get("jsnr") else None,

  238.         #        str(project_gjc.get("gnmk"))[dup_file_test:-dup_file_test] if project_gjc.get("gnmk") else None,

  239.         #        str(project_gjc.get("sjgx"))[dup_file_test:-dup_file_test] if project_gjc.get("sjgx") else None,

  240.         #        str(project_gjc.get("znys"))[dup_file_test:-dup_file_test] if project_gjc.get("znys") else None))

  241. 

  242.         gong_neng_mo_kuai(xmmc, mysql, dl, data, er_title)

  243. 

  244. 

  245. if __name__ == "__main__":

  246.     path = r"D:\dup_file_test"

  247.     data_list = os.listdir(path)

  248.     print(len(data_list))

  249.     for file in data_list:

  250.         # print(path+'\\'+file)

  251.         data_list = [(0, path + '\\' + file, "")]

  252.         project_check(data_list)

  253.         print("已存入************************************* %s" % file)

  254. 

  255. """

  256. 建设目标，业务功能

  257. 

  258. gnmk_str = []

  259. for d in data:

  260.     if pd.notnull(d[0]):

  261.         title = d[0]

  262.         if title == "功能模块":

  263.             er_title.add(d[dup_file_test])

  264.         join_str = ""

  265.         for i in d[dup_file_test:]:

  266.             if pd.notnull(i):

  267.                 join_str += i

  268.                 if title == "功能模块":

  269.                     gnmk_str.append(i)

  270.         str_dict[wdys1.get(title)] = join_str

  271.     else:

  272.         if title == "功能模块":

  273.             er_title.add(d[dup_file_test])

  274.         for i in d[dup_file_test:]:

  275.             if pd.notnull(i):

  276.                 join_str += i

  277.                 if title == "功能模块":

  278.                     gnmk_str.append(i)

  279.         str_dict[wdys1.get(title)] = str_dict.get(wdys1.get(title)) + join_str

  280. gnmk = "".join(gnmk_str)

  281. 

  282. 

  283. """