openthesaurus refactored.
This commit is contained in:
jannis
parent
bb9edcff25
commit
68d8115344
|
|
@ -1,3 +1,4 @@
|
|||
Kodewort;Schlüsselwort;Zugangscode;Passwort (Hauptform);Kennwort (Hauptform);Geheimcode;Losung;Codewort;Zugangswort;Losungswort;Parole
|
||||
Fission;Kernfission;Kernspaltung;Atomspaltung
|
||||
Wiederaufnahme;Fortführung
|
||||
davonfahren;abdüsen (ugs.);aufbrechen;abfliegen;abfahren;(von etwas) fortfahren;abreisen;wegfahren;wegfliegen
|
||||
|
|
@ -2182,7 +2183,6 @@ Spitzenklöppel (Handarbeit);Glockenklöppel;Klöppel
|
|||
gutartig;benigne (fachspr.)
|
||||
Beutelratte;Taschenratte
|
||||
rollen;kollern (ugs.);kullern;kugeln
|
||||
Kodewort;Schlüsselwort;Zugangscode;Kennwort (Hauptform);Geheimcode;Losung;Codewort;Zugangswort;Passwort (Hauptform);Losungswort;Parole
|
||||
packen;einpacken
|
||||
Ratschluss;Urteil;Wille;Entscheidung;Entschlossenheit;Beschluss;das letzte Wort (ugs.);Entschluss;Entscheid (schweiz.)
|
||||
dreckig machen;versiffen;beschmutzen;verschmutzen
|
||||
|
|
|
|||
|
Can't render this file because it is too large.
|
110
preprocessing.py
110
preprocessing.py
|
|
@ -20,12 +20,14 @@ csv.field_size_limit(sys.maxsize)
|
|||
|
||||
def printRandomDoc(textacyCorpus):
|
||||
print()
|
||||
|
||||
print("len(textacyCorpus) = %i" % len(textacyCorpus))
|
||||
randIndex = int((len(textacyCorpus) - 1) * random.random())
|
||||
print("Index: {0} ; Text: {1} ; Metadata: {2}".format(randIndex, textacyCorpus[randIndex].text, textacyCorpus[randIndex].metadata))
|
||||
|
||||
print()
|
||||
|
||||
|
||||
"""
|
||||
def getFirstSynonym(word, thesaurus_gen):
|
||||
|
||||
word = word.lower()
|
||||
|
|
@ -56,10 +58,9 @@ def getFirstSynonym(word, thesaurus_gen):
|
|||
return w
|
||||
|
||||
return word # zur Not die eingabe ausgeben
|
||||
"""
|
||||
|
||||
|
||||
def cleanText(string,custom_stopwords=None, custom_symbols=None, custom_words=None, customPreprocessing=None, lemmatize=False):
|
||||
import re
|
||||
def cleanText(string,custom_stopwords=None, custom_symbols=None, custom_words=None, customPreprocessing=None, lemmatize=False, normalize_synonyms=False):
|
||||
|
||||
# use preprocessing
|
||||
if customPreprocessing is not None:
|
||||
|
|
@ -156,17 +157,14 @@ def cleanText(string,custom_stopwords=None, custom_symbols=None, custom_words=No
|
|||
tokens.remove("\n")
|
||||
while "\n\n" in tokens:
|
||||
tokens.remove("\n\n")
|
||||
"""
|
||||
tokenz = []
|
||||
for tok in tokens:
|
||||
tokenz.append(str(getFirstSynonym(tok,THESAURUS_gen)))
|
||||
tokens = tokenz
|
||||
"""
|
||||
tokens = [str(getFirstSynonym(tok,THESAURUS_gen)) for tok in tokens]
|
||||
|
||||
#TODO abkürzungen auflösen (v.a. TU -> Technische Universität)
|
||||
|
||||
if normalize_synonyms:
|
||||
tokens = [str(getFirstSynonym(tok,THESAURUS_list)) for tok in tokens]
|
||||
|
||||
return " ".join(tokens)
|
||||
|
||||
|
||||
def generateTextfromXML(path2xml, clean=True, textfield='Beschreibung'):
|
||||
import xml.etree.ElementTree as ET
|
||||
|
||||
|
|
@ -196,7 +194,7 @@ def generateMetadatafromXML(path2xml, keys=["Loesung","Kategorie","Zusammenfassu
|
|||
|
||||
yield metadata
|
||||
|
||||
def generateFromXML(path2xml, clean=True, textfield='Beschreibung'):
|
||||
def generateFromXML(path2xml, textfield='Beschreibung', clean=False, normalize_Synonyms=False):
|
||||
import xml.etree.ElementTree as ET
|
||||
|
||||
tree = ET.parse(path2xml, ET.XMLParser(encoding="utf-8"))
|
||||
|
|
@ -208,17 +206,55 @@ def generateFromXML(path2xml, clean=True, textfield='Beschreibung'):
|
|||
for field in ticket:
|
||||
if field.tag == textfield:
|
||||
if clean:
|
||||
text = cleanText(field.text)
|
||||
text = cleanText(field.text,normalize_synonyms=normalize_Synonyms,lemmatize=False)
|
||||
else:
|
||||
text = field.text
|
||||
else:
|
||||
#todo hier auch cleanen?
|
||||
metadata[field.tag] = field.text
|
||||
yield text, metadata
|
||||
|
||||
def getFirstSynonym(word, thesaurus_gen):
|
||||
|
||||
word = word.lower()
|
||||
|
||||
|
||||
# durch den thesaurrus iterieren
|
||||
for syn_block in thesaurus_gen: # 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 getHauptform(syn_block, word)
|
||||
else: # falls es ein satz ist
|
||||
if word in syn:
|
||||
return getHauptform(syn_block, word)
|
||||
return 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
|
||||
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
|
||||
|
||||
|
||||
####################'####################'####################'####################'####################'##############
|
||||
|
||||
|
||||
import de_core_news_md
|
||||
DATAPATH = "ticketSamples.xml"
|
||||
DATAPATH_thesaurus = "openthesaurus.csv"
|
||||
|
||||
|
|
@ -227,8 +263,11 @@ LANGUAGE = 'de'
|
|||
|
||||
####################'####################'####################'####################'####################'##############
|
||||
|
||||
PARSER = spacy.load(LANGUAGE)
|
||||
THESAURUS_gen = textacy.fileio.read_csv(DATAPATH_thesaurus, delimiter=";") # generator [[a,b,c,..],[a,b,c,..],...]
|
||||
PARSER = de_core_news_md.load()#spacy.load(LANGUAGE)
|
||||
|
||||
THESAURUS_list=list(textacy.fileio.read_csv(DATAPATH_thesaurus, delimiter=";")) ## !!!!!! list wichtig, da sonst nicht die gleichen Synonyme zurückgegeben werden, weil der generator während der laufzeit pickt
|
||||
|
||||
|
||||
|
||||
|
||||
## files to textacy-corpus
|
||||
|
|
@ -236,27 +275,40 @@ textacyCorpus = textacy.Corpus(PARSER)
|
|||
|
||||
print("add texts to textacy-corpus...")
|
||||
#textacyCorpus.add_texts(texts=generateTextfromXML(DATAPATH), metadatas=generateMetadatafromXML(DATAPATH))
|
||||
for txt, dic in generateFromXML(DATAPATH):
|
||||
for txt, dic in generateFromXML(DATAPATH,normalize_Synonyms=True,clean=True):
|
||||
textacyCorpus.add_text(txt,dic)
|
||||
|
||||
|
||||
|
||||
for doc in textacyCorpus:
|
||||
print(doc.text)
|
||||
|
||||
|
||||
print(textacyCorpus[2].text)
|
||||
#print(textacyCorpus[2].text)
|
||||
#printRandomDoc(textacyCorpus)
|
||||
#print(textacyCorpus[len(textacyCorpus)-1].text)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
print()
|
||||
print()
|
||||
|
||||
#################### 1
|
||||
|
||||
PARSER = de_core_news_md.load()#spacy.load(LANGUAGE)
|
||||
|
||||
## files to textacy-corpus
|
||||
textacyCorpus = textacy.Corpus(PARSER)
|
||||
|
||||
for txt, dic in generateFromXML(DATAPATH, normalize_Synonyms=False, clean=True):
|
||||
textacyCorpus.add_text(txt,dic)
|
||||
|
||||
|
||||
for doc in textacyCorpus:
|
||||
print(doc.text)
|
||||
|
||||
|
||||
|
||||
print()
|
||||
print()
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
90
test.py
90
test.py
|
|
@ -28,95 +28,59 @@ def generateFromXML(path2xml, clean=True, textfield='Beschreibung'):
|
|||
yield text, metadata
|
||||
|
||||
|
||||
def getFirstSynonym(word, thesaurus_gen):
|
||||
|
||||
word = word.lower()
|
||||
# TODO word cleaning https://stackoverflow.com/questions/3939361/remove-specific-characters-from-a-string-in-python
|
||||
|
||||
|
||||
# durch den thesaurrus iterieren
|
||||
for syn_block in thesaurus_gen: # syn_block ist eine liste mit Synonymen
|
||||
|
||||
# durch den synonymblock iterieren
|
||||
for syn in syn_block:
|
||||
syn = syn.lower().split(" ") if not re.match(r'\A[\w-]+\Z', syn) else syn # aus synonym mach liste (um evtl. sätze zu identifieziren)
|
||||
|
||||
# falls das wort in dem synonym enthalten ist (also == einem Wort in der liste ist)
|
||||
if word in syn:
|
||||
|
||||
# Hauptform suchen
|
||||
if "Hauptform" in syn:
|
||||
# nicht ausgeben, falls es in Klammern steht
|
||||
for w in syn:
|
||||
if not re.match(r'\([^)]+\)', w) and w is not None:
|
||||
return w
|
||||
|
||||
# falls keine hauptform enthalten ist, das erste Synonym zurückgeben, was kein satz ist und nicht in klammern steht
|
||||
if len(syn) == 1:
|
||||
w = syn[0]
|
||||
if not re.match(r'\([^)]+\)', w) and w is not None:
|
||||
return w
|
||||
|
||||
return word # zur Not die eingabe ausgeben
|
||||
|
||||
|
||||
|
||||
def getFirstSynonym(word, thesaurus_gen):
|
||||
|
||||
word = word.lower()
|
||||
# TODO word cleaning https://stackoverflow.com/questions/3939361/remove-specific-characters-from-a-string-in-python
|
||||
|
||||
|
||||
# durch den thesaurrus iterieren
|
||||
for syn_block in thesaurus_gen: # 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:
|
||||
getHauptform(syn_block)
|
||||
return getHauptform(syn_block,word)
|
||||
else: # falls es ein satz ist
|
||||
if word in syn:
|
||||
return getHauptform(syn_block,word)
|
||||
return word #zur Not, das ursrpüngliche Wort zurückgeben
|
||||
|
||||
|
||||
|
||||
|
||||
def getHauptform(syn_block):
|
||||
for s in syn_block:
|
||||
if "Hauptform" in s:
|
||||
def getHauptform(syn_block,word,default_return_first_Syn=False):
|
||||
|
||||
for syn in syn_block:
|
||||
syn = syn.lower()
|
||||
|
||||
if "hauptform" in syn:
|
||||
# nicht ausgeben, falls es in Klammern steht
|
||||
for w in s:
|
||||
if not re.match(r'\([^)]+\)', w) and w is not None:
|
||||
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
|
||||
if len(s) == 1:
|
||||
w = s[0]
|
||||
if not re.match(r'\([^)]+\)', w) and w is not None:
|
||||
for w in syn_block:
|
||||
if not re.match(r'\([^)]+\)', w):
|
||||
return w
|
||||
return word # zur Not, das ursrpüngliche Wort zurückgeben
|
||||
|
||||
THESAURUS_gen = list(textacy.fileio.read_csv(DATAPATH_thesaurus, delimiter=";")) # generator [[a,b,c,..],[a,b,c,..],...]
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
strings = ["passwort",""]
|
||||
THESAURUS_gen = textacy.fileio.read_csv(DATAPATH_thesaurus, delimiter=";") # generator [[a,b,c,..],[a,b,c,..],...]
|
||||
strings = ["anmachen","Kernspaltung"]
|
||||
#strings = ["Kernspaltung","Kennwort"]
|
||||
|
||||
for s in strings:
|
||||
print(getFirstSynonym(s,THESAURUS_gen))
|
||||
|
||||
strings = ["Kennwort"]
|
||||
#THESAURUS_gen = textacy.fileio.read_csv(DATAPATH_thesaurus, delimiter=";") # generator [[a,b,c,..],[a,b,c,..],...]
|
||||
|
||||
for s in strings:
|
||||
print(getFirstSynonym(s, THESAURUS_gen))
|
||||
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue