topicModelingTickets/testra.py

110 lines
2.6 KiB
Python

# -*- coding: utf-8 -*-
import time
start = time.time()
import corenlp as corenlp
import os
import re
import spacy
import textacy
import nltk
from textblob_de import TextBlobDE
from textblob_de import PatternParser
#from polyglot.text import Text
import hunspell
from postal.parser import parse_address
print(parse_address(str(textacy.fileio.read_file("teststring.txt"))))
"""
regex_specialChars = r'[`\-=~!#@,.$%^&*()_+\[\]{};\'\\:"|</>?]'
def stringcleaning(stringstream, funclist):
for string in stringstream:
for f in funclist:
string = f(string)
yield string
def seperate_words_on_regex(regex=regex_specialChars):
return lambda string: " ".join(re.compile(regex).split(string))
words = [
"uniaccount",
"nr54065467",
"nr54065467",
"455a33c5,"
"tvt?=",
"tanja.saborowski@tu-dortmund.de",
"-",
"m-sw1-vl4053.itmc.tu-dortmund.de",
"------problem--------"
]
topLVLFinder = re.compile(r'\.[a-z]{2,3}(\.[a-z]{2,3})?', re.IGNORECASE)
specialFinder = re.compile(r'[`\-=~!@#$%^&*()_+\[\]{};\'\\:"|<,./>?]', re.IGNORECASE)
for s in stringcleaning((w for w in words),[seperate_words_on_regex()]):
print(s.strip())
#print(stringcleaning(w,string_comp))
#print(bool(re.search(r'\.[a-z]{2,3}(\.[a-z]{2,3})?',w)))
#print(bool(re.search(r'[`\-=~!@#$%^&*()_+\[\]{};\'\\:"|<,./>?]',w)))
#result = specialFinder.sub(" ", w)
#print(re.sub(r'[`\-=~!@#$%^&*()_+\[\]{};\'\\:"|<,./>?]'," ",w))
#print(re.sub(r'\.[a-z]{2,3}(\.[a-z]{2,3})?', " ", w))
"""
"""
de_stop_words= set(
list(__import__("spacy." + DE_PARSER.lang, globals(), locals(), ['object']).STOP_WORDS) +
list(textacy.fileio.read_file_lines("stopwords-de.txt"))
)
LEMMAS = list(textacy.fileio.read_file_lines(filepath="lemmatization-de.txt"))
VORNAMEN = list(textacy.fileio.read_file_lines("vornamen.txt"))
#blob = Text(str(textacy.fileio.read_file("teststring.txt")))#,parser=PatternParser(pprint=True, lemmata=True))
#print(blob.entities)
de_stop_words = list(map(replaceRockDots(),de_stop_words))
LEMMAS = list(map(replaceRockDots(),LEMMAS))
VORNAMEN = list(map(replaceRockDots(),VORNAMEN))
de_stop_words = list(map(textacy.preprocess.normalize_whitespace,de_stop_words))
LEMMAS = list(map(textacy.preprocess.normalize_whitespace,LEMMAS))
VORNAMEN = list(map(textacy.preprocess.normalize_whitespace,VORNAMEN))
textacy.fileio.write_file_lines(LEMMAS,"lemmas.txt")
textacy.fileio.write_file_lines(VORNAMEN,"firstnames.txt")
textacy.fileio.write_file_lines(de_stop_words,"de_stop_words.txt")
"""
end = time.time()
print("\n\n\nTime Elapsed Topic:{0}\n\n".format(end - start))