thesaurus fertiggestellt

This commit is contained in:
jannis.grundmann 2017-10-02 14:31:33 +02:00
parent 1a99d117ac
commit 3bfbebc894
2 changed files with 282 additions and 129 deletions

303
testo.py
View File

@ -8,7 +8,7 @@ print(datetime.now())
#path2csv = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/M42-Export/Tickets_med.csv" #path2csv = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/M42-Export/Tickets_med.csv"
path2csv = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/M42-Export/Tickets_small.csv" path2csv = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/M42-Export/Tickets_small.csv"
path2csv = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/M42-Export/de_tickets.csv" #path2csv = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/M42-Export/de_tickets.csv"
path_csv_split = path2csv.split("/") path_csv_split = path2csv.split("/")
print(path_csv_split[len(path_csv_split)-1]) print(path_csv_split[len(path_csv_split)-1])
@ -62,9 +62,17 @@ logging.basicConfig(filename=logile, level=logging.INFO)
#logging.basicConfig(filename=config.get("filepath","logfile"), level=logging.INFO) #logging.basicConfig(filename=config.get("filepath","logfile"), level=logging.INFO)
thesauruspath = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/openthesaurus.csv" #thesauruspath = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/openthesaurus.csv"
#thesauruspath = config.get("filepath","thesauruspath") #thesauruspath = config.get("filepath","thesauruspath")
THESAURUS = list(textacy.fileio.read_csv(thesauruspath, delimiter=";")) #THESAURUS = list(textacy.fileio.read_csv(thesauruspath, delimiter=";"))
# THESAURUS
lexicalentries = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/lexicalentries.xml"
synsets = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/synsets.xml"
path2words = '/home/jannis.grundmann/PycharmProjects/topicModelingTickets/deu_news_2015_1M-sentences.txt'
from langdetect import detect from langdetect import detect
@ -90,9 +98,9 @@ LEMMAS = list(textacy.fileio.read_file_lines(filepath="lemmatization-de.txt"))
VORNAMEN = list(textacy.fileio.read_file_lines("vornamen.txt")) VORNAMEN = list(textacy.fileio.read_file_lines("vornamen.txt"))
""" """
from nltk.corpus import stopwords
de_stop_words = list(map(textacy.preprocess.normalize_whitespace,textacy.fileio.read_file_lines("/home/jannis.grundmann/PycharmProjects/topicModelingTickets/de_stop_words.txt"))) de_stop_words = list(map(textacy.preprocess.normalize_whitespace,textacy.fileio.read_file_lines("/home/jannis.grundmann/PycharmProjects/topicModelingTickets/de_stop_words.txt")))
de_stop_words = de_stop_words + list(set(stopwords.words('english')))
#en_stop_words= set(list(__import__("spacy." + EN_PARSER.lang, globals(), locals(), ['object']).STOP_WORDS)) #en_stop_words= set(list(__import__("spacy." + EN_PARSER.lang, globals(), locals(), ['object']).STOP_WORDS))
LEMMAS = list(textacy.fileio.read_file_lines("/home/jannis.grundmann/PycharmProjects/topicModelingTickets/lemmas.txt")) LEMMAS = list(textacy.fileio.read_file_lines("/home/jannis.grundmann/PycharmProjects/topicModelingTickets/lemmas.txt"))
@ -430,8 +438,141 @@ def lemmatizeWord(word, l_dict=lemma_dict, w_dict=word_dict, n=3):
print(word) print(word)
return word return word
def build_thesaurus(path2lexicalentries, path2synsets):
lextree = ET.parse(path2lexicalentries, ET.XMLParser(encoding="utf-8"))
syntree = ET.parse(path2synsets, ET.XMLParser(encoding="utf-8"))
lexroot = lextree.getroot()
synroot = syntree.getroot()
thesaurus=[]
for r in synroot:
for element in r:
if element.tag == "Synset":
sysnet = []
attrib = element.attrib
id = attrib["id"]
for ro in lexroot:
for elem in ro:
if elem.tag == "LexicalEntry":
subs_dicts = [subentry.attrib for subentry in elem]
#<class 'list'>: [{'partOfSpeech': 'n', 'writtenForm': 'Kernspaltung'}, {'synset': 'de-1-n', 'id': 'w1_1-n'}]
dic = {k:v for x in subs_dicts for k,v in x.items()} # to one dict
if "synset" in dic.keys():
if dic["synset"] == id:
string = (dic["writtenForm"])
# replaceRockDots
string = re.sub(r'[ß]', "ss", string)
string = re.sub(r'[ö]', "oe", string)
string = re.sub(r'[ü]', "ue", string)
string = re.sub(r'[ä]', "ae", string)
# alle punkte raus
string = re.sub(r'[.]', "", string)
# alles in klammern raus
string = re.sub(r"\((.*)\)", " ", string)
# längeres leerzeichen normalisieren
string = textacy.preprocess.normalize_whitespace(string)
sysnet.append(string.lower().strip())
# nach anzhal der wörter in den strings sortieren
sysnet.sort(key=lambda x: len(x.split()))
if len(sysnet) != 0:
#todo warum sind manche leer?
thesaurus.append(sysnet)
return thesaurus
THESAURUS=[]
#THESAURUS=build_thesaurus(path2lexicalentries=lexicalentries,path2synsets=synsets) #todo anschalten
def getFirstSynonym(word, thesaurus=THESAURUS):
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 todo phrasen auch normalisieren
if word == syn:
return syn_block[0]
return str(word) # zur Not das ursrpüngliche Wort zurückgeben
########################## Spellchecking ##########################################
#http://norvig.com/spell-correct.html
#http://wortschatz.uni-leipzig.de/en/download
import re
from collections import Counter
def words(text): return re.findall(r'\w+', text.lower())
WORDS={}
#WORDS = Counter(words(open(path2words).read())) #todo anschalten
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))
"""
DE_SPELLCHECKER = enchant.Dict("de_DE") DE_SPELLCHECKER = enchant.Dict("de_DE")
EN_SPELLCHECKER = enchant.Dict("en_US") EN_SPELLCHECKER = enchant.Dict("en_US")
@ -440,6 +581,18 @@ def autocorrectWord(word, spellchecker=DE_SPELLCHECKER):
return spellchecker.suggest(word)[0] if not spellchecker.check(word) else word return spellchecker.suggest(word)[0] if not spellchecker.check(word) else word
except: except:
return word return word
"""
def autocorrectWord(word):
try:
return correction(word)
except:
return word
##################################################################################################
############# stringcleaning ############# stringcleaning
@ -475,6 +628,9 @@ def stringcleaning(stringstream):
# lemmatize # lemmatize
string = " ".join([lemmatizeWord(word) for word in string.split()]) string = " ".join([lemmatizeWord(word) for word in string.split()])
# synonyme normalisieren #idee vor oder nach lemmatize?
#string = " ".join([getFirstSynonym(word) for word in string.split()])
# autocorrect # autocorrect
#string = " ".join([autocorrectWord(word) for word in string.split()]) #string = " ".join([autocorrectWord(word) for word in string.split()])
@ -534,10 +690,8 @@ def processContentstream(textstream, token_filterlist=None, parser=DE_PARSER):
tokens = filterTokens(tokens, token_filterlist) tokens = filterTokens(tokens, token_filterlist)
yield " ".join([tok.lower_ for tok in tokens])
#yield " ".join(list(set([tok.lower_ for tok in tokens])))
#yield " ".join([tok.lower_ for tok in tokens])
yield " ".join(list(set([tok.lower_ for tok in tokens])))
@ -602,8 +756,6 @@ custom_words=["geehrt","dame","herr","hilfe","problem","lauten","bedanken","vora
filter_tokens=[ filter_tokens=[
#removeENT(["PERSON"]), #removeENT(["PERSON"]),
#idee addressen enfernen #bisher mit cut_after("gruss") --> postal.parser #idee addressen enfernen #bisher mit cut_after("gruss") --> postal.parser
#idee rechtschreibkorrektur --> PyEnchant
#idee thesaurus --> WordNet
keepNouns(), keepNouns(),
@ -696,6 +848,11 @@ de_corpus.add_texts(
processDictstream(csv_to_metaStream(path2csv,metaliste),clean_in_meta) processDictstream(csv_to_metaStream(path2csv,metaliste),clean_in_meta)
) )
# leere docs aus corpus kicken
de_corpus.remove(lambda doc: len(doc)==0)
for i in range(10): for i in range(10):
printRandomDoc(de_corpus) printRandomDoc(de_corpus)
@ -706,6 +863,44 @@ end = time.time()
printlog("Time Elapsed Preprocessing:{0} min".format((end - start)/60)) printlog("Time Elapsed Preprocessing:{0} min".format((end - start)/60))
def printvecotorization(ngrams = 1,min_df = 1,max_df = 1.0,weighting ='tf',named_entities=True):
printlog(str("ngrams: {0}".format(ngrams)))
printlog(str("min_df: {0}".format(min_df)))
printlog(str("max_df: {0}".format(max_df)))
printlog(str("named_entities: {0}".format(named_entities)))
#printlog("vectorize corpus...")
vectorizer = Vectorizer(weighting=weighting, min_df=min_df, max_df=max_df)
terms_list = (doc.to_terms_list(ngrams=ngrams, named_entities=named_entities, as_strings=True) for doc in de_corpus)
doc_term_matrix = vectorizer.fit_transform(terms_list)
id2term = vectorizer.__getattribute__("id_to_term")
for t in terms_list:
print(t)
printlog("doc_term_matrix: {0}".format(doc_term_matrix))
printlog("id2term: {0}".format(id2term))
# todo gescheites tf(-idf) maß finden #idee: tf wird bei token-set immer = 1 sein
ngrams = 1
min_df = 1
max_df = 1.0
weighting = 'tf'
# weighting ='tfidf'
named_entities = False
#printvecotorization(ngrams=ngrams,min_df=min_df,max_df=max_df,weighting=weighting,named_entities=named_entities)
""" """
corpus_path = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/corpus/" corpus_path = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/corpus/"
corpus_name = "de_corpus" corpus_name = "de_corpus"
@ -809,7 +1004,7 @@ def topicModeling(ngrams,min_df,max_df,topicModel = 'lda',n_topics = len(LABELDI
"""
topicModeling(ngrams = 1, topicModeling(ngrams = 1,
min_df = 1, min_df = 1,
max_df = 1.0, max_df = 1.0,
@ -851,51 +1046,55 @@ topicModeling(ngrams = (1,2),
""" """
##################### LLDA Topic Modeling via JGibbsLabledLDA ############################################## ##################### LLDA Topic Modeling via JGibbsLabledLDA ##############################################
top_topic_words = 10
print("\n\n") print("\n\n")
start = time.time() start = time.time()
@ -933,7 +1132,7 @@ LLDA_filepath = "{0}models/tickets/tickets.gz".format(jgibbsLLDA_root)
#create file #create file
textacy.fileio.write_file_lines(generate_labled_lines(de_corpus), filepath=LLDA_filepath) textacy.fileio.write_file_lines(generate_labled_lines(de_corpus), filepath=LLDA_filepath)
#todfo ticket drucken
# wait for file to exist # wait for file to exist
while not os.path.exists(LLDA_filepath): while not os.path.exists(LLDA_filepath):
time.sleep(1) time.sleep(1)
@ -965,7 +1164,7 @@ end = time.time()
printlog("\n\n\nTime Elapsed Topic Modeling JGibbsLLDA:{0} min\n\n".format((end - start)/60)) printlog("\n\n\nTime Elapsed Topic Modeling JGibbsLLDA:{0} min\n\n".format((end - start)/60))
"""

108
testra.py
View File

@ -7,6 +7,7 @@ import textacy
start = time.time() start = time.time()
import enchant
from datetime import datetime from datetime import datetime
@ -15,12 +16,8 @@ import xml.etree.ElementTree as ET
print(datetime.now()) print(datetime.now())
nomen=[]
#PARSER=spacy.load("de") #PARSER=spacy.load("de")
#todo: thesaurus....yay...
""" """
def normalizeSynonyms(default_return_first_Syn=False, parser=PARSER): def normalizeSynonyms(default_return_first_Syn=False, parser=PARSER):
@ -67,7 +64,6 @@ def getHauptform(syn_block, word, default_return_first_Syn=False):
### extract from deWordNet.xml ### extract from deWordNet.xml
#https://github.com/hdaSprachtechnologie/odenet #https://github.com/hdaSprachtechnologie/odenet
#idee synsets bilden
""" """
@ -98,90 +94,46 @@ for r in root:
""" """
lexicalentries = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/lexicalentries.xml"
synsets = "/home/jannis.grundmann/PycharmProjects/topicModelingTickets/synsets.xml"
lextree = ET.parse(lexicalentries, ET.XMLParser(encoding="utf-8"))
syntree = ET.parse(synsets, ET.XMLParser(encoding="utf-8"))
lexroot = lextree.getroot()
synroot = syntree.getroot()
for r in synroot:
for element in r:
if element.tag == "Synset":
sysnet = []
attrib = element.attrib
id = attrib["id"]
for ro in lexroot:
for elem in ro:
if elem.tag == "LexicalEntry":
subs_dicts = [subentry.attrib for subentry in elem]
#<class 'list'>: [{'partOfSpeech': 'n', 'writtenForm': 'Kernspaltung'}, {'synset': 'de-1-n', 'id': 'w1_1-n'}]
dic = {k:v for x in subs_dicts for k,v in x.items()} # to one dict
if "synset" in dic.keys():
if dic["synset"] == id:
if id == "de-1004-n":
x = 0
string = (dic["writtenForm"])
# replaceRockDots
string = re.sub(r'[ß]', "ss", string)
string = re.sub(r'[ö]', "oe", string)
string = re.sub(r'[ü]', "ue", string)
string = re.sub(r'[ä]', "ae", string)
# alle punkte raus
string = re.sub(r'[.]', "", string)
# alles in klammern raus
stringlist = string.split()
strings=[]
for w in stringlist:
if not bool(re.match(r'/\(([^)]+)\)/', w)): #todo funzt nich wie's soll
strings.append(w)
string = " ".join(strings)
#re.sub(r'/\(([^)]+)\)/', " ", string)
sysnet.append(string.lower().strip())
print(id,sysnet)
import re
from collections import Counter
def words(text): return re.findall(r'\w+', text.lower())
WORDS = Counter(words(open('/home/jannis.grundmann/PycharmProjects/topicModelingTickets/deu_news_2015_1M-sentences.txt').read()))
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))
@ -367,3 +319,5 @@ textacy.fileio.write_file_lines(de_stop_words,"german_stopwords.txt")
end = time.time() end = time.time()
print("\n\n\nTime Elapsed Topic:{0}\n\n".format(end - start)) print("\n\n\nTime Elapsed Topic:{0}\n\n".format(end - start))