fourgram 100k corpus

This commit is contained in:
s452662 2024-04-23 20:46:13 +02:00
parent 1450ea4378
commit 7743dd2472
3 changed files with 17812 additions and 17634 deletions

File diff suppressed because it is too large Load Diff

178
run.py Normal file
View File

@ -0,0 +1,178 @@
#!/usr/bin/env python
# coding: utf-8
# In[1]:
import lzma
def read_xz_file(file_path):
data = []
with lzma.open(file_path, 'rt', encoding='utf-8') as f:
for line in f:
line = line.lower().replace("-\\n", "").replace("\\n", " ").replace("\xad", "").replace("\\\\n", " ").replace("\\\\", " ").replace("\n", " ")
data.append(line)
return data
# In[2]:
def read_tsv_file(file_path):
data = []
with open(file_path, 'r', encoding='utf-8') as file:
for line in file:
line = line.strip().split('\t') # Rozdziel linie na elementy za pomocą tabulatora
data.append(line) # Dodaj elementy do listy danych
return data
# In[3]:
file_path = "train\\in.tsv.xz"
# In[4]:
data = read_xz_file(file_path)
# In[5]:
expected = read_tsv_file("train\\expected.tsv")
# In[6]:
corpus_before=[]
corpus_after=[]
for i in range(len(data)):
corpus_before.append(str(data[i].split("\t")[6]))
corpus_after.append(str(data[i].split("\t")[7]))
# In[7]:
for i in range(len(expected)):
expected[i] = str(expected[i]).lower()
# In[8]:
corpus = []
for i in range(len(expected)):
corpus.append(corpus_before[i] + " " + expected[i] + " " + corpus_after[i])
# In[9]:
from collections import defaultdict
from nltk import ngrams
from nltk.tokenize import word_tokenize
model = defaultdict(lambda: defaultdict(float))
dictionary = set()
for line in corpus[:100000]:
tokens = word_tokenize(line)
for word1, word2, word3, word4 in ngrams(tokens, n=4, pad_right=True, pad_left=True):
if word1 and word2 and word3 and word4:
model[(word2, word3, word4)][word1] += 1
model[(word1, word2, word3)][word4] += 1
dictionary.update([word1, word2, word3, word4])
# In[10]:
model2 = model.copy()
# In[ ]:
len(model)
# In[11]:
smoothing = 0.0001
for trio in model:
count_sum = sum(model[trio].values()) + smoothing * len(dictionary)
for token in model[trio]:
model[trio][token] = (model[trio][token] + smoothing) / count_sum
# In[12]:
from collections import Counter
default = "the:0.30000 of:0.20000 and:0.10000 to:0.10000 in:0.10000 a:0.10000 :0.10000"
data = read_xz_file("dev-0\\in.tsv.xz")
corpus_before=[]
corpus_after=[]
for i in range(len(data)):
corpus_before.append(str(data[i].split("\t")[6]))
corpus_after.append(str(data[i].split("\t")[7]))
with open("dev-0\\out.tsv", "w", encoding="utf-8") as output:
for text in corpus_before:
tokens = word_tokenize(text)
if len(tokens) < 4:
prediction = default
results = dict(model[(tokens[0], tokens[1], tokens[2])])
if not results:
prediction = default
prediction = ' '.join(
f"{term}:{round(prob, 5)}" for term, prob in Counter(results).most_common(6))
if prediction == "":
prediction = default
output.write(str(prediction.replace("\n", "").strip() + "\n"))
# In[13]:
from collections import Counter
default = "the:0.30000 of:0.20000 and:0.10000 to:0.10000 in:0.10000 a:0.10000 :0.10000"
data = read_xz_file("test-A\\in.tsv.xz")
corpus_before=[]
corpus_after=[]
for i in range(len(data)):
corpus_before.append(str(data[i].split("\t")[6]))
corpus_after.append(str(data[i].split("\t")[7]))
with open("test-A\\out.tsv", "w", encoding="utf-8") as output:
for text in corpus_before:
tokens = word_tokenize(text)
if len(tokens) < 4:
prediction = default
results = dict(model[(tokens[0], tokens[1], tokens[2])])
if not results:
prediction = default
prediction = ' '.join(
f"{term}:{round(prob, 5)}" for term, prob in Counter(results).most_common(6))
if prediction == "":
prediction = default
output.write(str(prediction.replace("\n", "").strip() + "\n"))
# In[ ]:

File diff suppressed because it is too large Load Diff