131 lines
4.6 KiB
Python
131 lines
4.6 KiB
Python
import spacy
|
||
import copy
|
||
import pandas as pd
|
||
import rapidfuzz
|
||
from rapidfuzz.fuzz import partial_ratio
|
||
import time
|
||
from rapidfuzz.utils import default_process
|
||
import sys
|
||
|
||
spacy.require_gpu()
|
||
|
||
spacy_nlp_en = spacy.load('en_core_web_sm')
|
||
spacy_nlp_pl = spacy.load("pl_core_news_sm")
|
||
|
||
|
||
def read_arguments():
|
||
try:
|
||
corpus_path, glossary_path = sys.argv
|
||
return corpus_path, glossary_path
|
||
except:
|
||
print("ERROR: Wrong argument amount.")
|
||
sys.exit(1)
|
||
|
||
|
||
|
||
glossary = pd.read_csv('mt-summit-corpora/glossary.tsv', sep='\t', header=None, names=['source', 'result'])
|
||
|
||
source_lemmatized = []
|
||
for word in glossary['source']:
|
||
temp = []
|
||
for token in spacy_nlp_en(word):
|
||
temp.append(token.lemma_)
|
||
source_lemmatized.append(' '.join(temp).replace(' - ', '-').replace(' ’', '’').replace(' / ', '/').replace(' ( ', '(').replace(' ) ', ')'))
|
||
|
||
result_lemmatized = []
|
||
for word in glossary['result']:
|
||
temp = []
|
||
for token in spacy_nlp_pl(word):
|
||
temp.append(token.lemma_)
|
||
result_lemmatized.append(' '.join(temp).replace(' - ', '-').replace(' ’', '’').replace(' / ', '/').replace(' ( ', '(').replace(' ) ', ')'))
|
||
|
||
glossary['source_lem'] = source_lemmatized
|
||
glossary['result_lem'] = result_lemmatized
|
||
glossary = glossary[['source', 'source_lem', 'result', 'result_lem']]
|
||
glossary.to_csv('kompendium_lem.tsv', sep='\t')
|
||
|
||
corpus_path = 'mt-summit-corpora/train/'
|
||
|
||
skip_chars = ''',./!?'''
|
||
|
||
with open(corpus_path + 'in.tsv', 'r') as file:
|
||
file_lemmatized = []
|
||
for line in file:
|
||
if len(file_lemmatized) % 10000 == 0:
|
||
print(len(file_lemmatized), end='\r')
|
||
temp = []
|
||
for token in spacy_nlp_en(line):
|
||
temp.append(token.lemma_)
|
||
file_lemmatized.append(' '.join([x for x in temp if x not in skip_chars]).replace(' - ', '-').replace(' ’', '’').replace(' / ', '/').replace(' ( ', '(').replace(' ) ', ')'))
|
||
|
||
with open(corpus_path + 'expected.tsv', 'r') as file:
|
||
file_pl_lemmatized = []
|
||
for line in file:
|
||
if len(file_pl_lemmatized) % 10000 == 0:
|
||
print(len(file_lemmatized), end='\r')
|
||
temp = []
|
||
for token in spacy_nlp_pl(line):
|
||
temp.append(token.lemma_)
|
||
file_pl_lemmatized.append(' '.join([x for x in temp if x not in skip_chars]).replace(' - ', '-').replace(' ’', '’').replace(' / ', '/').replace(' ( ', '(').replace(' ) ', ')'))
|
||
|
||
THRESHOLD = 88
|
||
|
||
def is_injectable(sentence_pl, sequence):
|
||
sen = sentence_pl.split()
|
||
window_size = len(sequence.split())
|
||
maxx = 0
|
||
for i in range(len(sen) - window_size):
|
||
current = rapidfuzz.fuzz.partial_ratio(' '.join(sen[i:i + window_size]), sequence)
|
||
if current > maxx:
|
||
maxx = current
|
||
return maxx
|
||
|
||
def inject(sentence, sequence):
|
||
sen = sentence.split()
|
||
window_size = len(sequence.split())
|
||
maxx = 0
|
||
maxxi = 0
|
||
for i in range(len(sen) - window_size):
|
||
current = rapidfuzz.fuzz.partial_ratio(' '.join(sen[i:i + window_size]), sequence)
|
||
if current > maxx:
|
||
maxx = current
|
||
maxxi = i
|
||
return ' '.join(sen[:maxxi + window_size]) + ' ' \
|
||
+ glossary.loc[lambda df: df['source_lem'] == sequence]['result'].astype(str).values.flatten() \
|
||
+ ' ' + ' '.join(sen[maxxi + window_size:])
|
||
|
||
glossary = pd.read_csv('../kompendium_lem_cleaned.tsv', sep='\t', header=0, index_col=0)
|
||
glossary['source_lem'] = [default_process(x) for x in glossary['source_lem']]
|
||
|
||
start_time = time.time_ns()
|
||
en = []
|
||
translation_line_counts = []
|
||
for line, line_pl in zip(file_lemmatized, file_pl_lemmatized):
|
||
if len(translation_line_counts) % 50000 == 0:
|
||
print(str(len(translation_line_counts)) + '/' + str(len(file_lemmatized), end='\r'))
|
||
line = default_process(line)
|
||
line_pl = default_process(line_pl)
|
||
matchez = rapidfuzz.process.extract(query=line, choices=glossary['source_lem'], limit=5, score_cutoff=THRESHOLD, scorer=partial_ratio)
|
||
translation_line_counts.append(len(matchez))
|
||
for match in matchez:
|
||
# if is_injectable(line_pl, match[0]):
|
||
en.append(inject(line, match[0])[0])
|
||
|
||
|
||
stop = time.time_ns()
|
||
timex = (stop - start_time) / 1000000000
|
||
print(timex)
|
||
|
||
tlcs = copy.deepcopy(translation_line_counts)
|
||
|
||
translations = pd.read_csv(corpus_path + 'expected.tsv', sep='\t', header=None, names=['text'])
|
||
with open(corpus_path + 'extected.tsv.injected.crossvalidated.pl', 'w') as file_pl:
|
||
for line, translation_line_ct in zip(translations, tlcs):
|
||
for i in range(translation_line_ct):
|
||
file_pl.write(line)
|
||
|
||
|
||
with open(corpus_path + 'in.tsv.injected.crossvalidated.en', 'w') as file_en:
|
||
for e in en:
|
||
file_en.write(e + '\n')
|