81 lines
2.4 KiB
Python
81 lines
2.4 KiB
Python
from nltk import trigrams, word_tokenize
|
|
import pandas as pd
|
|
import csv
|
|
import regex as re
|
|
from collections import Counter, defaultdict
|
|
|
|
|
|
train_set = pd.read_csv(
|
|
'train/in.tsv.xz',
|
|
sep='\t',
|
|
on_bad_lines='skip',
|
|
header=None,
|
|
uoting=csv.QUOTE_NONE,
|
|
nrows=50000)
|
|
|
|
|
|
train_labels = pd.read_csv(
|
|
'train/expected.tsv',
|
|
sep='\t',
|
|
on_bad_lines='skip',
|
|
header=None,
|
|
quoting=csv.QUOTE_NONE,
|
|
nrows=50000)
|
|
|
|
|
|
def data_preprocessing(text):
|
|
return re.sub(r'\p{P}', '', text.lower().replace('-\\n', '').replace('\\n', ' '))
|
|
|
|
|
|
def predict(before, after):
|
|
prediction = dict(Counter(dict(trigram[before, after])).most_common(5))
|
|
result = ''
|
|
prob = 0.0
|
|
for key, value in prediction.items():
|
|
prob += value
|
|
result += f'{key}:{value} '
|
|
if prob == 0.0:
|
|
return 'to:0.02 be:0.02 the:0.02 or:0.01 not:0.01 and:0.01 a:0.01 :0.9'
|
|
result += f':{max(1 - prob, 0.01)}'
|
|
return result
|
|
|
|
|
|
def make_prediction(file):
|
|
data = pd.read_csv(f'{file}/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
|
|
with open(f'{file}/out.tsv', 'w', encoding='utf-8') as file_out:
|
|
for _, row in data.iterrows():
|
|
before, after = word_tokenize(data_preprocessing(str(row[6]))), word_tokenize(data_preprocessing(str(row[7])))
|
|
if len(before) < 3 or len(after) < 3:
|
|
prediction = 'to:0.02 be:0.02 the:0.02 or:0.01 not:0.01 and:0.01 a:0.01 :0.9'
|
|
else:
|
|
prediction = predict(before[-1], after[0])
|
|
file_out.write(prediction + '\n')
|
|
|
|
|
|
train_set = train_set[[6, 7]]
|
|
train_set = pd.concat([train_set, train_labels], axis=1)
|
|
train_set['line'] = train_set[6] + train_set[0] + train_set[7]
|
|
|
|
|
|
trigram = defaultdict(lambda: defaultdict(lambda: 0))
|
|
|
|
rows = train_set.iterrows()
|
|
rows_len = len(train_set)
|
|
for index, (_, row) in enumerate(rows):
|
|
text = data_preprocessing(str(row['line']))
|
|
words = word_tokenize(text)
|
|
for word_1, word_2, word_3 in trigrams(words, pad_right=True, pad_left=True):
|
|
if word_1 and word_2 and word_3:
|
|
trigram[(word_1, word_3)][word_2] += 1
|
|
|
|
model_len = len(trigram)
|
|
for index, words_1_3 in enumerate(trigram):
|
|
count = sum(trigram[words_1_3].values())
|
|
for word_2 in trigram[words_1_3]:
|
|
trigram[words_1_3][word_2] += 0.25
|
|
trigram[words_1_3][word_2] /= float(count + 0.25 + len(word_2))
|
|
|
|
|
|
make_prediction('test-A')
|
|
make_prediction('dev-0')
|