104 lines
3.7 KiB
Python
104 lines
3.7 KiB
Python
import lzma
|
|
import regex as re
|
|
import string
|
|
# text = lzma.open('train/in.tsv.xz').read()
|
|
trigrams = {}
|
|
bigrams = {}
|
|
pos = 0
|
|
index = 0
|
|
words = []
|
|
def read_file(file):
|
|
for line in file:
|
|
yield re.sub(' +|\t', ' ', line.replace("\\n"," ").replace("\n","").translate(str.maketrans('','', string.punctuation))).split(" ")
|
|
|
|
|
|
def get_words(file):
|
|
for words in read_file(file):
|
|
yield from words
|
|
|
|
def set_bigram_count(first_word, second_word, bigrams):
|
|
if f"{first_word}_{second_word}" not in bigrams:
|
|
bigrams[f"{first_word}_{second_word}"] = 1
|
|
else:
|
|
bigrams[f"{first_word}_{second_word}"] += 1
|
|
|
|
def set_trigram_count(first_word, second_word, third_word, trigrams):
|
|
if f"{first_word}_{second_word}_{third_word}" not in trigrams:
|
|
trigrams[f"{first_word}_{second_word}_{third_word}"] = 1
|
|
else:
|
|
trigrams[f"{first_word}_{second_word}_{third_word}"] += 1
|
|
|
|
with lzma.open('train/in.tsv.xz', mode='rt') as file:
|
|
wordNo = 1
|
|
first_word = ""
|
|
second_word = ""
|
|
third_word = ""
|
|
for i_, word in enumerate(get_words(file)):
|
|
if wordNo == 1:
|
|
first_word = word
|
|
if len(third_word) > 0:
|
|
set_bigram_count(third_word, first_word, bigrams)
|
|
if len(second_word) > 0:
|
|
set_trigram_count(second_word, third_word, first_word, trigrams)
|
|
|
|
elif wordNo == 2:
|
|
second_word = word
|
|
set_bigram_count(first_word, second_word, bigrams)
|
|
if len(third_word) > 0:
|
|
set_trigram_count(third_word, first_word, second_word, trigrams)
|
|
|
|
elif wordNo == 3:
|
|
third_word = word
|
|
set_bigram_count(second_word, third_word, bigrams)
|
|
set_trigram_count(first_word, second_word, third_word, trigrams)
|
|
wordNo = 0
|
|
|
|
wordNo += 1
|
|
if i_ == 100:
|
|
break
|
|
print(trigrams)
|
|
|
|
with lzma.open('train/in.tsv.xz', mode='rt') as file:
|
|
for line in file:
|
|
words += re.sub(' +|\t', ' ', line.replace("\\n"," ").replace("\n","").translate(str.maketrans('','', string.punctuation))).split(" ")
|
|
print(words)
|
|
break
|
|
|
|
# with lzma.open('train/in.tsv.xz', mode='rt') as file:
|
|
# for line in file:
|
|
# # print(line.replace("\\n"," ").replace("\n"," "))
|
|
# words += re.sub(' +|\t', ' ', line.replace("\\n"," ").replace("\n","").translate(str.maketrans('','', string.punctuation))).split(" ")
|
|
# print(words)
|
|
# last_two_words = []
|
|
# for i_, word in enumerate(words):
|
|
# if i_ + 2 < len(words):
|
|
# if f"{words[i_+1]}_{words[i_+2]}" not in bigrams:
|
|
# bigrams[f"{words[i_+1]}_{words[i_+2]}"] = 1
|
|
# else:
|
|
# bigrams[f"{words[i_+1]}_{words[i_+2]}"] += 1
|
|
|
|
# if f"{words[i_]}_{words[i_+1]}_{words[i_+2]}" not in trigrams:
|
|
# trigrams[f"{words[i_]}_{words[i_+1]}_{words[i_+2]}"] = 1
|
|
# else:
|
|
# trigrams[f"{words[i_]}_{words[i_+1]}_{words[i_+2]}"] += 1
|
|
# else:
|
|
# last_two_words = [words[-2]]+[words[-1]]
|
|
# print(last_two_words)
|
|
# words = []
|
|
# # print(words)
|
|
# # print(re.sub(' +|\t', ' ', line).replace("\\n", " ").replace("\n","").split(" "))
|
|
# # break
|
|
# if index == 2:
|
|
# break
|
|
# index += 1
|
|
|
|
# text = "one of the"
|
|
# print(bigrams["political_thirst"])
|
|
# print(trigrams["to_political_thirst"])
|
|
# for trigram in trigrams:
|
|
# if trigrams[trigram] > 1:
|
|
# print(trigram, trigrams[trigram])
|
|
# for bigram in bigrams:
|
|
# if bigrams[bigram] > 6:
|
|
# print(bigram, bigrams[bigram])
|