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

import pandas as pd
import csv
import regex as re
from nltk import trigrams, word_tokenize
from collections import Counter, defaultdict

def clean_text(text):
    text = text.lower().replace('-\\n', '').replace('\\n', ' ')
    text = re.sub(r'\p{P}', '', text)

    return text


train_data = pd.read_csv('train/in.tsv.xz', sep='\t', error_bad_lines=False, warn_bad_lines=False, header=None, quoting=csv.QUOTE_NONE)
train_labels = pd.read_csv('train/expected.tsv', sep='\t', error_bad_lines=False, warn_bad_lines=False, header=None, quoting=csv.QUOTE_NONE)

train_data = train_data[[6, 7]]
train_data = pd.concat([train_data, train_labels], axis=1)

train_data['final'] = train_data[6] + train_data[0] + train_data[7]

model = defaultdict(lambda: defaultdict(lambda: 0))

for index, row in train_data.iterrows():
    text = clean_text(str(row['final']))
    words = word_tokenize(text)
    for w1, w2, w3 in trigrams(words, pad_right=True, pad_left=True):
        if w1 and w2 and w3:
            model[(w2, w3)][w1] += 1
    if index > 20000:
        break

for w2_w3 in model:
    total_count = float(sum(model[w2_w3].values()))
    for w1 in model[w2_w3]:
        model[w2_w3][w1] /= total_count

def predict_probs(word1, word2):
    raw_prediction = dict(model[word1, word2])
    prediction = dict(Counter(raw_prediction).most_common(12))
    
    total_prob = 0.0
    str_prediction = ''

    for word, prob in prediction.items():
        total_prob += prob
        str_prediction += f'{word}:{prob} '

    if total_prob == 0.0:
        return 'the:0.3 be:0.2 to:0.2 of:0.2 :0.1'

    remaining_prob = 1 - total_prob

    if remaining_prob < 0.0001:
        remaining_prob = 0.0001
        
    str_prediction += f':{remaining_prob}'
    
    return str_prediction


dev_data = pd.read_csv('dev-0/in.tsv.xz', sep='\t', error_bad_lines=False, warn_bad_lines=False, header=None, quoting=csv.QUOTE_NONE)
test_data = pd.read_csv('test-A/in.tsv.xz', sep='\t', error_bad_lines=False, warn_bad_lines=False, header=None, quoting=csv.QUOTE_NONE)

with open('dev-0/out.tsv', 'w') as file:
    for index, row in dev_data.iterrows():
        text = clean_text(str(row[7]))
        words = word_tokenize(text)
        if len(words) < 4:
            prediction = 'the:0.3 be:0.2 to:0.2 of:0.2 :0.1'
        else:
            prediction = predict_probs(words[0], words[1])
        file.write(prediction + '\n')

with open('test-A/out.tsv', 'w') as file:
    for index, row in test_data.iterrows():
        text = clean_text(str(row[7]))
        words = word_tokenize(text)
        if len(words) < 4:
            prediction = 'the:0.3 be:0.2 to:0.2 of:0.2 :0.1'
        else:
            prediction = predict_probs(words[0], words[1])
        file.write(prediction + '\n')