topicModelingTickets/config.ini

95 lines
1.6 KiB
INI
Raw Normal View History

2017-10-16 14:01:38 +02:00
[thesaurus]
2017-10-18 17:37:20 +02:00
input=deWordNet.xml
pickle_file=thesaurus_dict.pkl
2017-10-16 14:01:38 +02:00
[spellchecking]
2017-10-18 17:37:20 +02:00
input=deu_news_2015_1M-sentences.txt
pickle_file=words_dict.pkl
2017-10-16 14:01:38 +02:00
[lemmatization]
2017-10-18 17:37:20 +02:00
input=lemmas.txt
pickle_file=lemma_dict.pkl
2017-10-16 14:01:38 +02:00
[nouns]
2017-10-18 17:37:20 +02:00
input1=nomen.txt
input2=nomen2.txt
pickle_file=nouns_list.pkl
2017-10-16 14:01:38 +02:00
[firstnames]
2017-10-18 17:37:20 +02:00
input=firstnames.txt
pickle_file=firstnames_list.pkl
2017-10-16 14:01:38 +02:00
[de_stopwords]
2017-10-18 17:37:20 +02:00
input1=de_stopwords_1.txt
input2=de_stopwords_2.txt
input3=de_stopwords_3.txt
pickle_file=de_stopwords_list.pkl
[en_stopwords]
pickle_file=en_stopwords_list.pkl
2017-10-16 14:01:38 +02:00
[logging]
2017-10-18 17:37:20 +02:00
level=INFO
filename=topicModelTickets.log
2017-10-16 14:01:38 +02:00
[de_corpus]
2017-10-30 12:56:52 +01:00
#input=M42-Export/Tickets_small.csv
input=M42-Export/de_tickets.csv
2017-10-16 14:01:38 +02:00
2017-10-18 17:37:20 +02:00
path=corpi/
2017-10-16 14:01:38 +02:00
[en_corpus]
2017-10-18 17:37:20 +02:00
input=M42-Export/en_tickets.csv
2017-10-16 14:01:38 +02:00
2017-10-18 17:37:20 +02:00
path=corpi/
2017-10-16 14:01:38 +02:00
[tickets]
2017-10-18 17:37:20 +02:00
content_collumn_name=Description
metaliste=TicketNumber,Subject,CreatedDate,categoryName,Impact,Urgency,BenutzerID,VerantwortlicherID,EigentuemerID,Solution
[preprocessing]
2017-10-30 12:56:52 +01:00
#ents2keep=WORK_OF_ART,ORG,PRODUCT,LOC
2017-10-18 17:37:20 +02:00
2017-10-30 12:56:52 +01:00
custom_words=geehrt,dr,not,frage,betreff,gerne,dame,herr,frau,hilfe,moeglichkeit,beste,freuen,voraus,problem,lauten,bedanken,voraus,hallo,gerne,freundlich,fragen,fehler,bitten,ehre,lieb,liebe,gruesse,helfen,versuchen,unbestimmt,woche,tadelos,klappen,mittlerweile,bekommen,erreichbar,gruss,auffahren,vorgang,hinweis,name,gruss,id,erfolg,folge,team,absender,versenden,vorname,strasse,prozess,portal,moeglichkeit,fremd,wende,rueckfrage,stehen,verfuegung,funktionieren,pruefen,hoffen,ok
2017-10-18 17:37:20 +02:00
[topicmodeling]
2017-09-11 13:24:20 +02:00
2017-10-18 17:37:20 +02:00
ngrams=(1,2)
2017-09-11 13:24:20 +02:00
2017-10-18 17:37:20 +02:00
min_df=0
max_df=1.0
no_below=20
no_above=0.5
2017-09-11 13:24:20 +02:00
2017-10-18 17:37:20 +02:00
topicModel=lda
2017-09-11 13:24:20 +02:00
2017-10-18 17:37:20 +02:00
top_topic_words=5
2017-09-11 13:24:20 +02:00
2017-10-18 17:37:20 +02:00
top_document_labels_per_topic=2