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

import pandas as pd
import csv
from collections import Counter, defaultdict
from nltk.tokenize import RegexpTokenizer
from nltk import trigrams
import regex as re
import lzma


class WordPred:

    def __init__(self):
        self.tokenizer = RegexpTokenizer(r"\w+")
        self.model = defaultdict(lambda: defaultdict(lambda: 0))       
        self.vocab = set()
        self.alpha = 0.001
        
    def read_file(self, file):
        for line in file:  
            text = line.split("\t") 
            yield re.sub(r"[^\w\d'\s]+", '', re.sub(' +', ' ', ' '.join([text[6], text[7]]).replace("\\n"," ").replace("\n","").lower()))
        
    def read_file_7(self, file):
        for line in file:  
            text = line.split("\t") 
            yield re.sub(r"[^\w\d'\s]+", '', re.sub(' +', ' ', text[7].replace("\\n"," ").replace("\n","").lower()))

    def read_train_data(self, file_path):
        with lzma.open(file_path, mode='rt') as file:
            for index, text in enumerate(self.read_file(file)):
                tokens = self.tokenizer.tokenize(text)
                for w1, w2, w3 in trigrams(tokens, pad_right=True, pad_left=True):
                    if w1 and w2 and w3:
                        self.model[(w2, w3)][w1] += 1
                        self.vocab.add(w1)
                        self.vocab.add(w2)
                        self.vocab.add(w3)
                if index == 300000:
                    break
            
            for word_pair in self.model:
                num_n_grams = float(sum(self.model[word_pair].values()))
                for word in self.model[word_pair]:
                    self.model[word_pair][word] = (self.model[word_pair][word] + self.alpha) / (num_n_grams + self.alpha*len(self.vocab))

    def generate_outputs(self, input_file, output_file):        
        with open(output_file, 'w') as outputf:
            with lzma.open(input_file, mode='rt') as file:
                for index, text in enumerate(self.read_file_7(file)):
                    tokens = self.tokenizer.tokenize(text)
                    if len(tokens) < 4:
                        prediction = 'the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1'
                    else:
                        prediction = wp.predict_probs(tokens[0], tokens[1])
                    outputf.write(prediction + '\n')

    def predict_probs(self, word1, word2):
        predictions = dict(self.model[word1, word2])
        most_common = dict(Counter(predictions).most_common(6))
        
        total_prob = 0.0
        str_prediction = ''

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

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

        if 1 - total_prob >= 0.01:
            str_prediction += f":{1-total_prob}"
        else:
            str_prediction += f":0.01"
        
        return str_prediction

wp = WordPred()
wp.read_train_data('train/in.tsv.xz')
wp.generate_outputs('dev-0/in.tsv.xz', 'dev-0/out.tsv')
wp.generate_outputs('test-A/in.tsv.xz', 'test-A/out.tsv')