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

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

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

    return text

class Model():
    def __init__(self, alpha):
        self.alpha = alpha
        self.probs = defaultdict(lambda: defaultdict(lambda: 0))
        self.vocab = set()

    def train(self, data):
        for index, row in data.iterrows():
            text = clean_text(str(row['text']))
            words = word_tokenize(text)
            for w1, w2, w3 in trigrams(words, pad_right=True, pad_left=True):
                if w1 and w2 and w3:
                    self.vocab.add(w1)
                    self.vocab.add(w2)
                    self.vocab.add(w3)
                    self.probs[(w1, w3)][w2] += 1
            # limit number of data rows used for training
            if index > 10000:
                break

        for w1_w3 in self.probs:
            total_count = float(sum(self.probs[w1_w3].values()))
            denominator = total_count + self.alpha * len(self.vocab)
            for w2 in self.probs[w1_w3]:
                nominator = self.probs[w1_w3][w2] + self.alpha
                self.probs[w1_w3][w2] = nominator / denominator

    def predict(self, w1, w3):
        raw_prediction = dict(self.probs[w1, w3])
        prediction = dict(Counter(raw_prediction).most_common(6))

        total_prob = 0.0
        str_prediction = ''

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

        remaining_prob = 1 - total_prob
            
        str_prediction += f':{remaining_prob}'
        
        return str_prediction


# check arguments
if len(sys.argv) != 2:
    print('Wrong number of arguments. Expected 1 - alpha smoothing parameter.')
    quit()
else:
    alpha = sys.argv[1]

# load training data
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['text'] = train_data[6] + train_data[0] + train_data[7]
train_data = train_data[['text']]

# init model with given aplha
model = Model(alpha)

# train model probs
model.train(train_data)

# make predictions
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():
        left_text = clean_text(str(row[6]))
        right_text = clean_text(str(row[7]))
        left_words = word_tokenize(left_text)
        right_words = word_tokenize(right_text)
        if len(left_words) < 2 or len(right_words) < 2:
            prediction = ':1.0'
        else:
            prediction = model.predict(left_words[len(left_words) - 1], right_words[0])
        file.write(prediction + '\n')

with open('test-A/out.tsv', 'w') as file:
    for index, row in test_data.iterrows():
        left_text = clean_text(str(row[6]))
        right_text = clean_text(str(row[7]))
        left_words = word_tokenize(left_text)
        right_words = word_tokenize(right_text)
        if len(left_words) < 2 or len(right_words) < 2:
            prediction = ':1.0'
        else:
            prediction = model.predict(left_words[len(left_words) - 1], right_words[0])
        file.write(prediction + '\n')