forbidCodeErr()
from com.office.util.sqlUtil import save
from com.office.util import fileUtil
from com.office.template2 import DBNAME
from com.office.util.excelUtil import read
if __name__ == "__main__":
keywords = []
srcpathname = r"/Users/yangjie/Downloads/qq/prescription_use_method"
if srcpathname.endswith("xls") or srcpathname.endswith("xlsx"):
tableData = read(srcpathname, "Sheet1")
for row in tableData:
keywords.append(row[0])
else:
f1 = fileUtil.readFile(srcpathname)
keywords = f1.split("\r\n")
if len(keywords) < 2:
keywords = f1.split("\r")
if len(keywords) < 2:
keywords = f1.split("\n")
#上面的代码就是将原始数据转换城一个列表
data = []
save_sql = """insert into "main"."keys" ( "status", "keyword") values ( ?, ?);"""
import sqlite3
conn = sqlite3.connect(DBNAME)
conn.text_factory = str
count = 0
for keyword in keywords:
from com.office.stitch.db import DATABASE_PATHNAME
from com.office.util.excelUtil import read
from com.office.util.sqlUtil import save
from com.office.util import fileUtil
if __name__ == "__main__":
# import sqlite3
# conn = sqlite3.connect(DATABASE_PATHNAME)
# tableData = read(r"/Users/yangjie/Downloads/qq/ingredients_only.xls", "Sheet1");
# save_sql = """insert into "main"."keys" ( "status", "keyword") values ( ?, ?);"""
# data = []
# for row in tableData:
# keyword = row[0]
# data.append((0,keyword))
# if len(data) >=100:
# save(conn, save_sql, data)
# data=[]
# save(conn, save_sql, data)
import sqlite3
conn = sqlite3.connect(DATABASE_PATHNAME)
f1 = fileUtil.readFile("omim-id")
save_sql = """insert into "main"."keys" ( "status", "keyword") values ( ?, ?);"""
data = []
for row in f1.split("\r"):
keyword = row
data.append((0, keyword))
if len(data) >= 100:
save(conn, save_sql, data)
data = []
save(conn, save_sql, data)
from com.office.util.fileUtil import writeFile, readFile
sys.path.append('../')
import jieba.analyse
# file_name = "/Users/yangjie/Downloads/chrome/511.txt"
topK = 1000
withWeight = True
import codecs
# fp = codecs.open("/Users/yangjie/Downloads/qq/新建文本文档.txt", "r", 'gbk');
#
# alllines = fp.readlines();
# content = ""
# for line in alllines:
# content += line
content = readFile("tmp.txt")
content = content.replace(u"老公", "").replace(u"老婆", "")
writeFile("tmp2.txt", content)
tags = jieba.analyse.extract_tags(content, topK=topK, withWeight=withWeight)
result = ""
if withWeight is True:
for tag in tags:
if tag[0] in [u"杨大爷", u"孔敏佳"]:
continue
result += tag[0]
result += " "
result += str(int(tag[1] * 1000))
result += "\n"
print("tag: %s\t\t weight: %f" % (tag[0], tag[1]))
else:
from com.office.util.fileUtil import writeFile, readFile
sys.path.append('../')
import jieba.analyse
# file_name = "/Users/yangjie/Downloads/chrome/511.txt"
topK = 1000
withWeight = True
import codecs
# fp = codecs.open("/Users/yangjie/Downloads/qq/新建文本文档.txt", "r", 'gbk');
#
# alllines = fp.readlines();
# content = ""
# for line in alllines:
# content += line
content = readFile("/Users/yangjie/Downloads/qq/tmp.txt")
tags = jieba.analyse.extract_tags(content, topK=topK, withWeight=withWeight)
result = ""
if withWeight is True:
for tag in tags:
if tag[0] in [u"杨大爷", u"孔敏佳"]:
continue
result += tag[0]
result += " "
result += str(int(tag[1] * 1000))
result += "\n"
print("tag: %s\t\t weight: %f" % (tag[0], tag[1]))
else:
print(",".join(tags))
writeFile("ss.txt", result)
