textcleaning macht keinen spass

This commit is contained in:
jannis.grundmann 2017-09-18 16:08:11 +02:00
parent 092052dfe1
commit 20d9eed5b3
5 changed files with 21469 additions and 55 deletions

383
backup.py Normal file
View File

@ -0,0 +1,383 @@
# -*- coding: utf-8 -*-
############# misc
def printlog(string, level="INFO"):
"""log and prints"""
print(string)
if level=="INFO":
logging.info(string)
elif level=="DEBUG":
logging.debug(string)
elif level == "WARNING":
logging.warning(string)
printlog("Load functions")
def compose(*functions):
def compose2(f, g):
return lambda x: f(g(x))
return functools.reduce(compose2, functions, lambda x: x)
def get_calling_function():
"""finds the calling function in many decent cases.
https://stackoverflow.com/questions/39078467/python-how-to-get-the-calling-function-not-just-its-name
"""
fr = sys._getframe(1) # inspect.stack()[1][0]
co = fr.f_code
for get in (
lambda:fr.f_globals[co.co_name],
lambda:getattr(fr.f_locals['self'], co.co_name),
lambda:getattr(fr.f_locals['cls'], co.co_name),
lambda:fr.f_back.f_locals[co.co_name], # nested
lambda:fr.f_back.f_locals['func'], # decorators
lambda:fr.f_back.f_locals['meth'],
lambda:fr.f_back.f_locals['f'],
):
try:
func = get()
except (KeyError, AttributeError):
pass
else:
if func.__code__ == co:
return func
raise AttributeError("func not found")
def printRandomDoc(textacyCorpus):
import random
print()
printlog("len(textacyCorpus) = %i" % len(textacyCorpus))
randIndex = int((len(textacyCorpus) - 1) * random.random())
printlog("Index: {0} ; Text: {1} ; Metadata: {2}".format(randIndex, textacyCorpus[randIndex].text, textacyCorpus[randIndex].metadata))
print()
############# load xml
def generateMainTextfromTicketXML(path2xml, main_textfield='Description'):
"""
generates strings from XML
:param path2xml:
:param main_textfield:
:param cleaning_function:
:yields strings
"""
tree = ET.parse(path2xml, ET.XMLParser(encoding="utf-8"))
root = tree.getroot()
for ticket in root:
for field in ticket:
if field.tag == main_textfield:
yield field.text
def generateMetadatafromTicketXML(path2xml, leave_out=['Description']):
tree = ET.parse(path2xml, ET.XMLParser(encoding="utf-8"))
root = tree.getroot()
for ticket in root:
metadata = {}
for field in ticket:
if field.tag not in leave_out:
metadata[field.tag] = field.text
yield metadata
############# load csv
def csv_to_contentStream(path2csv: str, content_collumn_name: str):
"""
:param path2csv: string
:param content_collumn_name: string
:return: string-generator
"""
stream = textacy.fileio.read_csv(path2csv, delimiter=";") # ,encoding='utf8')
content_collumn = 0 # standardvalue
for i,lst in enumerate(stream):
if i == 0:
# look for desired column
for j,col in enumerate(lst):
if col == content_collumn_name:
content_collumn = j
else:
yield lst[content_collumn]
def csv_to_metaStream(path2csv: str, metalist: [str]):
"""
:param path2csv: string
:param metalist: list of strings
:return: dict-generator
"""
stream = textacy.fileio.read_csv(path2csv, delimiter=";") # ,encoding='utf8')
content_collumn = 0 # standardvalue
metaindices = []
metadata_temp = {}
for i,lst in enumerate(stream):
if i == 0:
for j,col in enumerate(lst): # geht bestimmt effizienter... egal, weil passiert nur einmal
for key in metalist:
if key == col:
metaindices.append(j)
metadata_temp = dict(zip(metalist,metaindices)) # zB {'Subject' : 1, 'categoryName' : 3, 'Solution' : 10}
else:
metadata = metadata_temp.copy()
for key,value in metadata.items():
metadata[key] = lst[value]
yield metadata
############################################ Preprocessing ##############################################
############# on str-gen
def processTokens(tokens, funclist, parser):
# in:tokenlist, funclist
# out: tokenlist
for f in funclist:
# idee: funclist sortieren,s.d. erst alle string-methoden ausgeführt werden, dann wird geparesed, dann wird auf tokens gearbeitet, dann evtl. auf dem ganzen Doc
if 'bool' in str(f.__annotations__):
tokens = list(filter(f, tokens))
elif 'str' in str(f.__annotations__):
tokens = list(map(f, tokens)) # purer text
doc = parser(" ".join(tokens)) # neu parsen
tokens = [tok for tok in doc] # nur tokens
elif 'spacy.tokens.doc.Doc' in str(f.__annotations__):
#todo wirkt gefrickelt
doc = parser(" ".join(tok.lower_ for tok in tokens)) # geparsed
tokens = f(doc)
doc = parser(" ".join(tokens)) # geparsed
tokens = [tok for tok in doc] # nur tokens
else:
warnings.warn("Unknown Annotation while preprocessing. Function: {0}".format(str(f)))
return tokens
def processTextstream(textstream, funclist, parser=DE_PARSER):
"""
:param textstream: string-gen
:param funclist: [func]
:param parser: spacy-parser
:return: string-gen
"""
# input:str-stream output:str-stream
pipe = parser.pipe(textstream)
for doc in pipe:
tokens = []
for tok in doc:
tokens.append(tok)
tokens = processTokens(tokens,funclist,parser)
yield " ".join([tok.lower_ for tok in tokens])
def processDictstream(dictstream, funcdict, parser=DE_PARSER):
"""
:param dictstream: dict-gen
:param funcdict:
clean_in_meta = {
"Solution":funclist,
...
}
:param parser: spacy-parser
:return: dict-gen
"""
for dic in dictstream:
result = {}
for key, value in dic.items():
if key in funcdict:
doc = parser(value)
tokens = [tok for tok in doc]
funclist = funcdict[key]
tokens = processTokens(tokens,funclist,parser)
result[key] = " ".join([tok.lower_ for tok in tokens])
else:
result[key] = value
yield result
############# return bool
def keepPOS(pos_list) -> bool:
ret = lambda tok : tok.pos_ in pos_list
ret.__annotations__ = get_calling_function().__annotations__
return ret
def removePOS(pos_list)-> bool:
ret = lambda tok : tok.pos_ not in pos_list
ret.__annotations__ = get_calling_function().__annotations__
return ret
def removeWords(words, keep=None)-> bool:
if hasattr(keep, '__iter__'):
for k in keep:
try:
words.remove(k)
except ValueError:
pass
ret = lambda tok : tok.lower_ not in words
ret.__annotations__ = get_calling_function().__annotations__
return ret
def keepENT(ent_list) -> bool:
ret = lambda tok : tok.ent_type_ in ent_list
ret.__annotations__ = get_calling_function().__annotations__
return ret
def removeENT(ent_list) -> bool:
ret = lambda tok: tok.ent_type_ not in ent_list
ret.__annotations__ = get_calling_function().__annotations__
return ret
def remove_words_containing_Numbers() -> bool:
ret = lambda tok: not bool(re.search('\d', tok.lower_))
ret.__annotations__ = get_calling_function().__annotations__
return ret
def remove_words_containing_specialCharacters() -> bool:
ret = lambda tok: not bool(re.search(r'[`\-=~!@#$%^&*()_+\[\]{};\'\\:"|<,./<>?]', tok.lower_))
ret.__annotations__ = get_calling_function().__annotations__
return ret
def remove_words_containing_topLVL() -> bool:
ret = lambda tok: not bool(re.search(r'\.[a-z]{2,3}(\.[a-z]{2,3})?', tok.lower_))
ret.__annotations__ = get_calling_function().__annotations__
return ret
def lemmatizeWord(word,filepath=LEMMAS):
"""http://www.lexiconista.com/datasets/lemmatization/"""
for line in list(textacy.fileio.read_file_lines(filepath=filepath)):
if word.lower() == line.split()[1].strip().lower():
return line.split()[0].strip().lower()
return word.lower() # falls nix gefunden wurde
def lemmatize() -> str:
ret = lambda tok: lemmatizeWord(tok.lower_)
ret.__annotations__ = get_calling_function().__annotations__
return ret
############# return strings
mentionFinder = re.compile(r"@[a-z0-9_]{1,15}", re.IGNORECASE)
emailFinder = re.compile(r"\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b", re.IGNORECASE)
urlFinder = re.compile(r"^(?:https?:\/\/)?(?:www\.)?[a-zA-Z0-9./]+$", re.IGNORECASE)
topLVLFinder = re.compile(r'\.[a-z]{2,3}(\.[a-z]{2,3})?', re.IGNORECASE)
specialFinder = re.compile(r'[`\-=~!@#$%^&*()_+\[\]{};\'\\:"|<,./>?]', re.IGNORECASE)
hardSFinder = re.compile(r'[ß]', re.IGNORECASE)
def replaceEmails(replace_with="EMAIL") -> str:
ret = lambda tok : emailFinder.sub(replace_with, tok.lower_)
ret.__annotations__ = get_calling_function().__annotations__
return ret
def replaceURLs(replace_with="URL") -> str:
ret = lambda tok: textacy.preprocess.replace_urls(tok.lower_,replace_with=replace_with)
#ret = lambda tok: urlFinder.sub(replace_with,tok.lower_)
ret.__annotations__ = get_calling_function().__annotations__
return ret
def replaceSpecialChars(replace_with=" ") -> str:
ret = lambda tok: specialFinder.sub(replace_with,tok.lower_)
ret.__annotations__ = get_calling_function().__annotations__
return ret
def replaceTwitterMentions(replace_with="TWITTER_MENTION") -> str:
ret = lambda tok : mentionFinder.sub(replace_with,tok.lower_)
ret.__annotations__ = get_calling_function().__annotations__
return ret
def replaceNumbers(replace_with="NUMBER") -> str:
ret = lambda tok: textacy.preprocess.replace_numbers(tok.lower_, replace_with=replace_with)
ret.__annotations__ = get_calling_function().__annotations__
return ret
def replacePhonenumbers(replace_with="PHONENUMBER") -> str:
ret = lambda tok: textacy.preprocess.replace_phone_numbers(tok.lower_, replace_with=replace_with)
ret.__annotations__ = get_calling_function().__annotations__
return ret
def replaceHardS(replace_with="ss") -> str:
ret = lambda tok: hardSFinder.sub(replace_with,tok.lower_)
ret.__annotations__ = get_calling_function().__annotations__
return ret
def fixUnicode() -> str:
ret = lambda tok: textacy.preprocess.fix_bad_unicode(tok.lower_, normalization=u'NFC')
ret.__annotations__ = get_calling_function().__annotations__
return ret
def resolveAbbreviations():
pass #todo
#todo wörter mit len < 2 entfernen( vorher abkürzungen (v.a. tu und fh) auflösen) und > 35 oder 50 ("Reiserücktrittskostenversicherung)
############# return docs
def keepUniqeTokens() -> spacy.tokens.Doc:
ret = lambda doc: (set([tok.lower_ for tok in doc]))
ret.__annotations__ = get_calling_function().__annotations__
return ret
def lower() -> spacy.tokens.Doc:
ret = lambda doc: ([tok.lower_ for tok in doc])
ret.__annotations__ = get_calling_function().__annotations__
return ret
################################################################################################################

58
spell.py Normal file
View File

@ -0,0 +1,58 @@
# -*- coding: utf-8 -*-
# https://github.com/norvig/pytudes/blob/master/spell.py
"""Spelling Corrector in Python 3; see http://norvig.com/spell-correct.html
Copyright (c) 2007-2016 Peter Norvig
MIT license: www.opensource.org/licenses/mit-license.php
"""
################ Spelling Corrector
import re
from collections import Counter
import spacy
import textacy
def words(text): return re.findall(r'\w+', text.lower())
WORDS = Counter(words(open('bigo.txt').read()))
x=0
def P(word, N=sum(WORDS.values())):
"Probability of `word`."
return WORDS[word] / N
def correction(word):
"Most probable spelling correction for word."
return max(candidates(word), key=P)
def candidates(word):
"Generate possible spelling corrections for word."
return (known([word]) or known(edits1(word)) or known(edits2(word)) or [word])
def known(words):
"The subset of `words` that appear in the dictionary of WORDS."
return set(w for w in words if w in WORDS)
def edits1(word):
"All edits that are one edit away from `word`."
letters = 'abcdefghijklmnopqrstuvwxyz'
splits = [(word[:i], word[i:]) for i in range(len(word) + 1)]
deletes = [L + R[1:] for L, R in splits if R]
transposes = [L + R[1] + R[0] + R[2:] for L, R in splits if len(R) > 1]
replaces = [L + c + R[1:] for L, R in splits if R for c in letters]
inserts = [L + c + R for L, R in splits for c in letters]
return set(deletes + transposes + replaces + inserts)
def edits2(word):
"All edits that are two edits away from `word`."
return (e2 for e1 in edits1(word) for e2 in edits1(e1))

103
test.py
View File

@ -196,12 +196,14 @@ def processTokens(tokens, funclist, parser):
# in:tokenlist, funclist # in:tokenlist, funclist
# out: tokenlist # out: tokenlist
for f in funclist: for f in funclist:
# idee: funclist sortieren,s.d. erst alle string-methoden ausgeführt werden, dann wird geparesed, dann wird auf tokens gearbeitet, dann evtl. auf dem ganzen Doc
if 'bool' in str(f.__annotations__): if 'bool' in str(f.__annotations__):
tokens = list(filter(f, tokens)) tokens = list(filter(f, tokens))
elif 'str' in str(f.__annotations__): elif 'str' in str(f.__annotations__):
tokens = list(map(f, tokens)) # purer text tokens = list(map(f, tokens)) # purer text
doc = parser(" ".join(tokens)) # geparsed doc = parser(" ".join(tokens)) # neu parsen
tokens = [tok for tok in doc] # nur tokens tokens = [tok for tok in doc] # nur tokens
elif 'spacy.tokens.doc.Doc' in str(f.__annotations__): elif 'spacy.tokens.doc.Doc' in str(f.__annotations__):
@ -320,6 +322,14 @@ def remove_words_containing_specialCharacters() -> bool:
ret.__annotations__ = get_calling_function().__annotations__ ret.__annotations__ = get_calling_function().__annotations__
return ret return ret
def remove_words_containing_topLVL() -> bool:
ret = lambda tok: not bool(re.search(r'\.[a-z]{2,3}(\.[a-z]{2,3})?', tok.lower_))
ret.__annotations__ = get_calling_function().__annotations__
return ret
def lemmatizeWord(word,filepath=LEMMAS): def lemmatizeWord(word,filepath=LEMMAS):
"""http://www.lexiconista.com/datasets/lemmatization/""" """http://www.lexiconista.com/datasets/lemmatization/"""
for line in list(textacy.fileio.read_file_lines(filepath=filepath)): for line in list(textacy.fileio.read_file_lines(filepath=filepath)):
@ -334,58 +344,16 @@ def lemmatize() -> str:
return ret return ret
def normalizeSynonyms(default_return_first_Syn=False) -> str:
ret = lambda tok : getFirstSynonym(tok.lower_, default_return_first_Syn=default_return_first_Syn)
ret.__annotations__ = get_calling_function().__annotations__
return ret
def getFirstSynonym(word, thesaurus=THESAURUS, default_return_first_Syn=False):
if not isinstance(word, str):
return str(word)
word = word.lower()
# durch den thesaurrus iterieren
for syn_block in thesaurus: # syn_block ist eine liste mit Synonymen
for syn in syn_block:
syn = syn.lower()
if re.match(r'\A[\w-]+\Z', syn): # falls syn einzelwort ist
if word == syn:
return str(getHauptform(syn_block, word, default_return_first_Syn=default_return_first_Syn))
else: # falls es ein satz ist
if word in syn:
return str(getHauptform(syn_block, word, default_return_first_Syn=default_return_first_Syn))
return str(word) # zur Not, das ursrpüngliche Wort zurückgeben
def getHauptform(syn_block, word, default_return_first_Syn=False):
for syn in syn_block:
syn = syn.lower()
if "hauptform" in syn and len(syn.split(" ")) <= 2:
# nicht ausgeben, falls es in Klammern steht#todo gibts macnmal?? klammern aus
for w in syn.split(" "):
if not re.match(r'\([^)]+\)', w):
return w
if default_return_first_Syn:
# falls keine hauptform enthalten ist, das erste Synonym zurückgeben, was kein satz ist und nicht in klammern steht
for w in syn_block:
if not re.match(r'\([^)]+\)', w):
return w
return word # zur Not, das ursrpüngliche Wort zurückgeben
############# return strings ############# return strings
mentionFinder = re.compile(r"@[a-z0-9_]{1,15}", re.IGNORECASE) mentionFinder = re.compile(r"@[a-z0-9_]{1,15}", re.IGNORECASE)
emailFinder = re.compile(r"\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b", re.IGNORECASE) emailFinder = re.compile(r"\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b", re.IGNORECASE)
urlFinder = re.compile(r"^(?:https?:\/\/)?(?:www\.)?[a-zA-Z0-9./]+$", re.IGNORECASE) urlFinder = re.compile(r"^(?:https?:\/\/)?(?:www\.)?[a-zA-Z0-9./]+$", re.IGNORECASE)
topLVLFinder = re.compile(r'\.[a-z]{2,3}(\.[a-z]{2,3})?', re.IGNORECASE)
specialFinder = re.compile(r'[`\-=~!@#$%^&*()_+\[\]{};\'\\:"|<,./>?]', re.IGNORECASE)
hardSFinder = re.compile(r'[ß]', re.IGNORECASE)
def replaceEmails(replace_with="EMAIL") -> str: def replaceEmails(replace_with="EMAIL") -> str:
ret = lambda tok : emailFinder.sub(replace_with, tok.lower_) ret = lambda tok : emailFinder.sub(replace_with, tok.lower_)
@ -400,6 +368,13 @@ def replaceURLs(replace_with="URL") -> str:
ret.__annotations__ = get_calling_function().__annotations__ ret.__annotations__ = get_calling_function().__annotations__
return ret return ret
def replaceSpecialChars(replace_with=" ") -> str:
ret = lambda tok: specialFinder.sub(replace_with,tok.lower_)
ret.__annotations__ = get_calling_function().__annotations__
return ret
def replaceTwitterMentions(replace_with="TWITTER_MENTION") -> str: def replaceTwitterMentions(replace_with="TWITTER_MENTION") -> str:
ret = lambda tok : mentionFinder.sub(replace_with,tok.lower_) ret = lambda tok : mentionFinder.sub(replace_with,tok.lower_)
@ -418,7 +393,11 @@ def replacePhonenumbers(replace_with="PHONENUMBER") -> str:
ret.__annotations__ = get_calling_function().__annotations__ ret.__annotations__ = get_calling_function().__annotations__
return ret return ret
def replaceHardS(replace_with="ss") -> str:
ret = lambda tok: hardSFinder.sub(replace_with,tok.lower_)
ret.__annotations__ = get_calling_function().__annotations__
return ret
def fixUnicode() -> str: def fixUnicode() -> str:
@ -428,11 +407,20 @@ def fixUnicode() -> str:
return ret return ret
def resolveAbbreviations(): def resolveAbbreviations():
pass #todo pass #todo
#todo wörter mit len < 2 entfernen( vorher abkürzungen (v.a. tu und fh) auflösen) und > 35 oder 50 ("Reiserücktrittskostenversicherung)
############# return docs #todo das stimmt nicht so ganz, da kommt kein doc raus, sondern n tokenset ############# return docs
def keepUniqeTokens() -> spacy.tokens.Doc: def keepUniqeTokens() -> spacy.tokens.Doc:
ret = lambda doc: (set([tok.lower_ for tok in doc])) ret = lambda doc: (set([tok.lower_ for tok in doc]))
@ -462,7 +450,6 @@ printlog("CSV: {0}".format(path2csv))
ticketcorpus = textacy.Corpus(DE_PARSER) ticketcorpus = textacy.Corpus(DE_PARSER)
#idee ß zu ss ändern? prinzipiell?
""" """
vllt kategorien in unterkategorien aufteilen vllt kategorien in unterkategorien aufteilen
@ -503,20 +490,26 @@ clean_in_meta = {
printlog("Start Preprocessing") printlog("Start Preprocessing")
clean_in_content=[ clean_in_content=[
replaceHardS(),
replaceSpecialChars(),
removePOS(["SPACE","PUNCT","NUM"]), remove_words_containing_topLVL(),
remove_words_containing_Numbers(), remove_words_containing_Numbers(),
remove_words_containing_specialCharacters(), remove_words_containing_specialCharacters(),
#removePOS(["SPACE","PUNCT","NUM"]),
#removeENT("PERSON"),
#keepPOS(["NOUN"]),
#replaceURLs(), #replaceURLs(),
#replaceEmails(), #replaceEmails(),
#fixUnicode(), #fixUnicode(),
#lemmatize(), lemmatize(),
#removeWords(de_stop_words + config.get("preprocessing","custom_words").split(",")), removeWords(de_stop_words + config.get("preprocessing","custom_words").split(",")),
#removeENT("PERSON"),
#keepPOS(["NOUN"]),
#keepUniqeTokens(), #keepUniqeTokens(),
#keepENT(config.get("preprocessing","ents2keep")) #keepENT(config.get("preprocessing","ents2keep"))

419
testo.py Normal file
View File

@ -0,0 +1,419 @@
# -*- coding: utf-8 -*-
import time
start = time.time()
import logging
import csv
import functools
import os.path
import re
import subprocess
import time
import xml.etree.ElementTree as ET
import sys
import spacy
import textacy
from scipy import *
from textacy import Vectorizer
import warnings
import configparser as ConfigParser
import sys
csv.field_size_limit(sys.maxsize)
# Load the configuration file
config_ini = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/config.ini"
config = ConfigParser.ConfigParser()
with open(config_ini) as f:
config.read_file(f)
# config logging
logging.basicConfig(filename=config.get("filepath","logfile"), level=logging.INFO)
thesauruspath = config.get("filepath","thesauruspath")
THESAURUS = list(textacy.fileio.read_csv(thesauruspath, delimiter=";"))
DE_PARSER = spacy.load("de") #todo spacherkennung idee: verschiedene Corpi für verschiedene Sprachen
de_stop_words=list(__import__("spacy." + DE_PARSER.lang, globals(), locals(), ['object']).STOP_WORDS)
LEMMAS=config.get("filepath","lemmas")
VORNAMEN = list(textacy.fileio.read_file_lines("vornamen.txt"))
regex_specialChars = r'[`\-=~!#@,.$%^&*()_+\[\]{};\'\\:"|</>?]'
regex_topLvl = r'\.[a-z]{2,3}(\.[a-z]{2,3})?'
mentionFinder = re.compile(r"@[a-z0-9_]{1,15}", re.IGNORECASE)
emailFinder = re.compile(r"\b[A-Z0-9._%+-]+@[A-Z0-9.-]+\.[A-Z]{2,}\b", re.IGNORECASE)
urlFinder = re.compile(r"^(?:https?:\/\/)?(?:www\.)?[a-zA-Z0-9./]+$", re.IGNORECASE)
topLVLFinder = re.compile(r'\.[a-z]{2,3}(\.[a-z]{2,3})?', re.IGNORECASE)
specialFinder = re.compile(r'[`\-=~!@#$%^&*()_+\[\]{};\'\\:"|<,./>?]', re.IGNORECASE)
hardSFinder = re.compile(r'[ß]', re.IGNORECASE)
def printlog(string, level="INFO"):
"""log and prints"""
print(string)
if level=="INFO":
logging.info(string)
elif level=="DEBUG":
logging.debug(string)
elif level == "WARNING":
logging.warning(string)
printlog("Load functions")
def compose(*functions):
def compose2(f, g):
return lambda x: f(g(x))
return functools.reduce(compose2, functions, lambda x: x)
def get_calling_function():
"""finds the calling function in many decent cases.
https://stackoverflow.com/questions/39078467/python-how-to-get-the-calling-function-not-just-its-name
"""
fr = sys._getframe(1) # inspect.stack()[1][0]
co = fr.f_code
for get in (
lambda:fr.f_globals[co.co_name],
lambda:getattr(fr.f_locals['self'], co.co_name),
lambda:getattr(fr.f_locals['cls'], co.co_name),
lambda:fr.f_back.f_locals[co.co_name], # nested
lambda:fr.f_back.f_locals['func'], # decorators
lambda:fr.f_back.f_locals['meth'],
lambda:fr.f_back.f_locals['f'],
):
try:
func = get()
except (KeyError, AttributeError):
pass
else:
if func.__code__ == co:
return func
raise AttributeError("func not found")
def printRandomDoc(textacyCorpus):
import random
print()
printlog("len(textacyCorpus) = %i" % len(textacyCorpus))
randIndex = int((len(textacyCorpus) - 1) * random.random())
printlog("Index: {0} ; Text: {1} ; Metadata: {2}".format(randIndex, textacyCorpus[randIndex].text, textacyCorpus[randIndex].metadata))
print()
def csv_to_contentStream(path2csv: str, content_collumn_name: str):
"""
:param path2csv: string
:param content_collumn_name: string
:return: string-generator
"""
stream = textacy.fileio.read_csv(path2csv, delimiter=";") # ,encoding='utf8')
content_collumn = 0 # standardvalue
for i,lst in enumerate(stream):
if i == 0:
# look for desired column
for j,col in enumerate(lst):
if col == content_collumn_name:
content_collumn = j
else:
yield lst[content_collumn]
############# return bool
def keepPOS(pos_list):
return lambda tok : tok.pos_ in pos_list
def removePOS(pos_list):
return lambda tok : tok.pos_ not in pos_list
def removeWords(words, keep=None):
if hasattr(keep, '__iter__'):
for k in keep:
try:
words.remove(k)
except ValueError:
pass
return lambda tok : tok.lower_ not in words
def keepENT(ent_list):
return lambda tok : tok.ent_type_ in ent_list
def removeENT(ent_list):
return lambda tok: tok.ent_type_ not in ent_list
def remove_words_containing_Numbers():
return lambda tok: not bool(re.search('\d', tok.lower_))
def remove_words_containing_specialCharacters():
return lambda tok: not bool(re.search(regex_specialChars, tok.lower_))
def remove_long_words():
return lambda tok: not len(tok.lower_) < 2
def remove_short_words():
return lambda tok: not len(tok.lower_) > 35
def remove_first_names():
return lambda tok: tok.lower_ not in [name.lower() for name in VORNAMEN]
############# strings
def stringcleaning(stringstream, funclist):
for string in stringstream:
for f in funclist:
string = f(string)
yield string
def remove_words_containing_topLVL():
return lambda string: " ".join([w.lower() for w in string.split() if not re.search(regex_topLvl, w) ])
def replaceSpecialChars(replace_with=" "):
return lambda string: re.sub(regex_specialChars, replace_with, string.lower())
def replaceNumbers(replace_with="NUMBER"):
return lambda string : textacy.preprocess.replace_numbers(string.lower(), replace_with=replace_with)
def replacePhonenumbers(replace_with="PHONENUMBER"):
return lambda string: textacy.preprocess.replace_phone_numbers(string.lower(), replace_with=replace_with)
def replaceHardS(replace_with="ss"):
return lambda string: re.sub(r'[ß]',replace_with,string.lower())
def fixUnicode():
return lambda string: textacy.preprocess.fix_bad_unicode(string.lower(), normalization=u'NFC')
def lemmatizeWord(word,filepath=LEMMAS):
"""http://www.lexiconista.com/datasets/lemmatization/"""
for line in list(textacy.fileio.read_file_lines(filepath=filepath)):
if word.lower() == line.split()[1].strip().lower():
return line.split()[0].strip().lower()
return word.lower() # falls nix gefunden wurde
def lemmatize():
#todo https://alpha.spacy.io/docs/usage/adding-languages#lemmatizer
return lambda tok: lemmatizeWord(tok.lower_)
def processTextstream(textstream, string_funclist, tok_funclist,parser=DE_PARSER):
"""
:param textstream: string-gen
:param funclist: [func]
:param parser: spacy-parser
:return: string-gen
"""
pipe = parser.pipe(stringcleaning(textstream,string_funclist))
for doc in pipe:
tokens = [tok for tok in doc]
tokens = processTokens(tokens,tok_funclist,parser)
yield " ".join([tok.lower_ for tok in tokens])
def processTokens(tokens, funclist, parser):
# in:tokenlist, funclist
# out: tokenlist
for f in funclist:
tokens = list(filter(f, tokens))
return tokens
string_comp=[
replaceHardS(),
remove_words_containing_topLVL(),
replaceSpecialChars(),
]
tok_comp=[
removeENT(["PERSON"]),
remove_words_containing_Numbers(),
#keepPOS(["NOUN"]),
removePOS(["PUNCT","SPACE","NUM"]),
removeWords(de_stop_words),
remove_long_words(),
remove_short_words(),
remove_first_names()
]
"""
pipe=[
##String
fixUnicode(),
replaceHardS(),
resolveAbbrivations(),
remove_words_containing_topLVL(),
replaceSpecialChars(" "), (mit Leerzeichen erstzen, dadruch werden Terme wie 8203;verfügung getrennt
remove_words_containing_Numbers(),
##spacyParse
removeENT("PERSON"),
keepPOS(["NOUN"]),
#ODER
lemmatize(),
removeWords(de_stop_words + config.get("preprocessing","custom_words").split(",")),
# evtl.
spellCorrection(),
keepUniqeTokens(),
]
"""
path2csv = "M42-Export/Tickets_med.csv"
ticketcorpus = textacy.Corpus(DE_PARSER)
## add files to textacy-corpus,
printlog("add texts to textacy-corpus")
ticketcorpus.add_texts(
processTextstream(csv_to_contentStream(path2csv,"Description"), string_funclist=string_comp,tok_funclist=tok_comp)
)
for i in range(10):
printRandomDoc(ticketcorpus)
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 w in words:
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))
"""
spracherkennung
alles nach grüße ist irrelevant außer PS:
vllt kategorien in unterkategorien aufteilen
allg:
utf-korregieren,
emails, urls, nummern raus
vllt sogar alles, was ebend jenes enthält (oder auf .toplvldomain bzw. sonderzeichen enthält oder alles was ein @ enthält
sinnvoller wörter von müll trennen: 8203;verfügung -> bei sonderzeichen wörter trennen
abkürzungen raus: m.a, o.ä.
wörter korrigieren
sinnlose bsp: nr54065467 455a33c5 tvt?= ------problem--------
"""

20561
vornamen.txt Normal file

File diff suppressed because it is too large Load Diff