lp832ut/zpwiki
1
0
Fork 0
forked from KEMT/zpwiki
Code Issues Pull Requests Releases Wiki Activity

Smazat „pages/students/2016/jakub_maruniak/dp2021/annotation/data/text_to_sent.py“

Browse Source
This commit is contained in:
Jakub Maruniak 2020-05-22 19:17:52 +00:00
parent 2c24867494
commit 90f286cd2a
1 changed files with 0 additions and 24 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
pages/students/2016/jakub_maruniak/dp2021/annotation/data/text_to_sent.py
View File

@ -1,24 +0,0 @@
import csv
# load data
filename = 'dataminer.csv'
file = open(filename, 'rt', encoding='utf-8')
text = file.read()
# split text to sentences, with list of slovak abbreviations
from nltk.tokenize.punkt import PunktSentenceTokenizer, PunktParameters
punkt_param = PunktParameters()
punkt_param.abbrev_types = set(['rokov', 'sgt', 'storočia', 't.j', 'Kr', 'resp', 'poľ', 'tzv', 'pod', 'napr', 'prof', 'angl'])
sentence_splitter = PunktSentenceTokenizer(punkt_param)
sentences = sentence_splitter.tokenize(text)
# write data
with open("textfile.csv", mode='w', encoding='utf-8', newline='\n') as textfile:
for sentences in sentence_splitter.tokenize(text):
sentence1 = sentences.replace(";", "")
row_writer=csv.writer(textfile)
row_writer.writerow([sentence1])
print(sentence1)