challenging-america-word-gap-prediction/model.py

from nltk.tokenize import word_tokenize
from nltk import trigrams
import string
from collections import defaultdict, Counter
import pandas as pd
import csv


trigrams_list = []
model = defaultdict(lambda: defaultdict(lambda: 0))


def preprocess(text):
    _text = str(text)
    _text = _text.lower().replace("-\\n", "").replace('\\n', ' ').strip()
    for character in _text:
        if character not in string.ascii_lowercase + ' ':
            _text = _text.replace(character, '')
    words = word_tokenize(_text)
    if len(words):
        return words
    return ['']


def predict(word_before, word_after):
    prob_list = dict(Counter(model[(word_before, word_after)]).most_common(5)).items()
    predictions = []
    prob_sum = 0.0
    for key, value in prob_list:
        prob_sum += value
        predictions.append(f'{key}:{value}')
    if prob_sum == 0.0:
        return 'the:0:2 be:0.2 to:0.2 of:0.15 and:0.15 :0.1'
    elif prob_sum < 1.0:
        predictions.append(f':{max(1 - prob_sum, 0.01)}')
    return ' '.join(predictions)


file_in = pd.read_csv('train/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE, nrows=200000)
file_expected = pd.read_csv('train/expected.tsv', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE, nrows=200000)

for index, (line_in, expected) in enumerate(zip(file_in.iterrows(), file_expected.iterrows())):
    if index % 1000 == 0:
        print('zbieranie trigramów', index)
    before = line_in[1][6]
    after = line_in[1][7]
    expected = expected[1][0]
    before, expected, after = preprocess(before), preprocess(expected), preprocess(after)
    words = before + expected + after
    trigrams_list += trigrams(words, pad_right=True, pad_left=True)
    length = len(trigrams_list)

trigrams_len = len(trigrams_list)

for index, trigram in enumerate(trigrams_list):
    if index % 100000 == 0:
        print(f'uczenie modelu: {index / trigrams_len}')
    if trigram[0] and trigram[1] and trigram[2]:
        model[(trigram[0], trigram[2])][trigram[1]] += 1


model_len = len(model)

for index, words_1_3 in enumerate(model):
    if index % 100000 == 0:
        print(f'normalizacja: {index / model_len}')
    count = sum(model[words_1_3].values())
    for word_2 in model[words_1_3]:
        model[words_1_3][word_2] /= float(count)

file_in = pd.read_csv('test-A/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
with open('test-A/out.tsv', 'w', encoding='utf-8') as file_out:
    print('zapisywanie test-A')
    for line_in in file_in.iterrows():
        before = line_in[1][6]
        after = line_in[1][7]
        word_before_in, word_after_in = preprocess(before)[-1], preprocess(after)[0]
        file_out.write(predict(word_before_in, word_after_in) + '\n')


file_in = pd.read_csv('dev-0/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
with open('dev-0/out.tsv', 'w', encoding='utf-8') as file_out:
    print('zapisywanie dev-0')
    for line_in in file_in.iterrows():
        before = line_in[1][6]
        after = line_in[1][7]
        word_before_in, word_after_in = preprocess(before)[-1], preprocess(after)[0]
        file_out.write(predict(word_before_in, word_after_in) + '\n')

print('koniec')