s426206/challenging-america-word-gap-prediction
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Zrobione dodawanie bigramow i trigramow na tablicach.

Browse Source
This commit is contained in:
Jan Nowak 2022-03-26 01:21:57 +01:00
parent d5888a3d7a
commit 993eaaa168
1 changed files with 30 additions and 74 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

104
run.py
View File

@ -1,17 +1,14 @@
import lzma import lzma
import regex as re import regex as re
import string import string
import queue
# text = lzma.open('train/in.tsv.xz').read() # text = lzma.open('train/in.tsv.xz').read()
trigrams = {} trigrams = {}
bigrams = {} bigrams = {}
pos = 0
index = 0
words = []
def read_file(file): def read_file(file):
for line in file: for line in file:
yield re.sub(' +|\t', ' ', line.replace("\\n"," ").replace("\n","").translate(str.maketrans('','', string.punctuation))).split(" ") yield re.sub(' +|\t', ' ', line.replace("\\n"," ").replace("\n","").translate(str.maketrans('','', string.punctuation))).split(" ")
def get_words(file): def get_words(file):
for words in read_file(file): for words in read_file(file):
yield from words yield from words
@ -30,74 +27,33 @@ def set_trigram_count(first_word, second_word, third_word, trigrams):
with lzma.open('train/in.tsv.xz', mode='rt') as file: with lzma.open('train/in.tsv.xz', mode='rt') as file:
wordNo = 1 wordNo = 1
first_word = "" word_bi_last = ""
second_word = "" words = ["", "", ""]
third_word = "" for i_, word in enumerate(get_words(file)):
for i_, word in enumerate(get_words(file)): if len(word_bi_last) > 0:
if wordNo == 1: set_bigram_count(word_bi_last, word, bigrams)
first_word = word if i_ == 1:
if len(third_word) > 0: words[0]=word_bi_last
set_bigram_count(third_word, first_word, bigrams) words[1]=word
if len(second_word) > 0: elif i_ == 2:
set_trigram_count(second_word, third_word, first_word, trigrams) words[2]=word
set_trigram_count(words[0], words[1], words[2], trigrams)
elif wordNo == 2: elif i_ > 2:
second_word = word words[0]=words[1]
set_bigram_count(first_word, second_word, bigrams) words[1]=words[2]
if len(third_word) > 0: words[2]=word
set_trigram_count(third_word, first_word, second_word, trigrams) set_trigram_count(words[0], words[1], words[2], trigrams)
word_bi_last = word
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" if i_ == 10000:
# print(bigrams["political_thirst"]) break
# print(trigrams["to_political_thirst"])
# for trigram in trigrams: text = "one of the"
# if trigrams[trigram] > 1: print(bigrams["political_thirst"])
# print(trigram, trigrams[trigram]) print(trigrams["to_political_thirst"])
# for bigram in bigrams: for trigram in trigrams:
# if bigrams[bigram] > 6: if trigrams[trigram] > 1:
# print(bigram, bigrams[bigram]) print(trigram, trigrams[trigram])
for bigram in bigrams:
if bigrams[bigram] > 6:
print(bigram, bigrams[bigram])