topicModelingTickets/test.py

90 lines
2.4 KiB
Python
Raw Normal View History

2017-08-29 15:01:17 +02:00
# -*- coding: utf-8 -*-
import re
import spacy
import textacy
2017-08-30 12:56:59 +02:00
import xml.etree.ElementTree as ET
2017-08-29 15:01:17 +02:00
DATAPATH_thesaurus = "openthesaurus.csv"
2017-08-30 12:56:59 +02:00
def generateFromXML(path2xml, clean=True, textfield='Beschreibung'):
import xml.etree.ElementTree as ET
tree = ET.parse(path2xml, ET.XMLParser(encoding="utf-8"))
root = tree.getroot()
for ticket in root:
metadata = {}
text = "ERROR"
for field in ticket:
if field.tag == textfield:
if clean:
text = (field.text)
else:
text = field.text
else:
metadata[field.tag] = field.text
yield text, metadata
2017-08-29 15:01:17 +02:00
def getFirstSynonym(word, thesaurus_gen):
2017-08-30 12:56:59 +02:00
word = word.lower()
2017-08-29 15:01:17 +02:00
2017-08-30 12:56:59 +02:00
# durch den thesaurrus iterieren
for syn_block in thesaurus_gen: # syn_block ist eine liste mit Synonymen
2017-08-29 15:01:17 +02:00
2017-08-30 12:56:59 +02:00
for syn in syn_block:
2017-08-31 10:38:29 +02:00
syn = syn.lower()
2017-08-30 12:56:59 +02:00
if re.match(r'\A[\w-]+\Z', syn): #falls syn einzelwort ist
if word == syn:
2017-08-31 10:38:29 +02:00
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
2017-08-30 12:56:59 +02:00
2017-08-31 10:38:29 +02:00
def getHauptform(syn_block,word,default_return_first_Syn=False):
2017-08-30 12:56:59 +02:00
2017-08-31 10:38:29 +02:00
for syn in syn_block:
syn = syn.lower()
2017-08-30 12:56:59 +02:00
2017-08-31 10:38:29 +02:00
if "hauptform" in syn:
# nicht ausgeben, falls es in Klammern steht
for w in syn.split(" "):
if not re.match(r'\([^)]+\)', w):
return w
2017-08-30 12:56:59 +02:00
2017-08-31 10:38:29 +02:00
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
2017-08-30 12:56:59 +02:00
2017-08-31 10:38:29 +02:00
THESAURUS_gen = list(textacy.fileio.read_csv(DATAPATH_thesaurus, delimiter=";")) # generator [[a,b,c,..],[a,b,c,..],...]
2017-08-30 12:56:59 +02:00
2017-08-31 10:38:29 +02:00
strings = ["anmachen","Kernspaltung"]
#strings = ["Kernspaltung","Kennwort"]
2017-08-30 12:56:59 +02:00
2017-08-31 10:38:29 +02:00
for s in strings:
print(getFirstSynonym(s,THESAURUS_gen))
2017-08-30 12:56:59 +02:00
2017-08-31 10:38:29 +02:00
strings = ["Kennwort"]
#THESAURUS_gen = textacy.fileio.read_csv(DATAPATH_thesaurus, delimiter=";") # generator [[a,b,c,..],[a,b,c,..],...]
2017-08-30 12:56:59 +02:00
for s in strings:
2017-08-31 10:38:29 +02:00
print(getFirstSynonym(s, THESAURUS_gen))
2017-08-30 12:56:59 +02:00
2017-08-29 15:01:17 +02:00