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

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


DEFAULT_PREDICTION = 'the:0.2 be:0.2 to:0.2 of:0.1 and:0.1 a:0.1 :0.1'

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



class Model():
    def __init__(self, alpha, train_file_name, test_file_name):
        
        file_expected = pd.read_csv(f'{train_file_name}/expected.tsv', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE, nrows=200000)
        file_in = pd.read_csv(f'{train_file_name}/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE, nrows=200000)
        file_in = file_in[[6, 7]]
        file_concat = pd.concat([file_in, file_expected], axis=1)
        file_concat['text'] = file_concat[6] + file_concat[0] + file_concat[7]
        
        self.file = file_concat[['text']]
        self.test_file_name = test_file_name
        self.alpha = alpha;
        self.model = defaultdict(lambda: defaultdict(lambda: 0))
    
    def train(self):
        rows = self.file.iterrows()
        rows_len = len(self.file)
        for index, (_, row) in enumerate(rows):
            if index % 1000 == 0:
                print(f'uczenie modelu: {index / rows_len}')
            words = word_tokenize(preprocess(str(row['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:
                    self.model[(word_1, word_3)][word_2] += 1
        model_len = len(self.model)
        for index, words_1_3 in enumerate(self.model):
            if index % 100000 == 0:
                print(f'normalizacja i wygładzanie: {index / model_len}')
            occurrences = sum(self.model[words_1_3].values())
            for word_2 in self.model[words_1_3]:
                self.model[words_1_3][word_2] += self.alpha
                self.model[words_1_3][word_2] /= float(occurrences + self.alpha + len(word_2))
    
    def predict_row(self, word_before, word_after):
        prediction = dict(Counter(dict(self.model[word_before, word_after])).most_common(6))
        result = []
        prob = 0.0
        for key, value in prediction.items():
            prob += value
            result.append(f'{key}:{value}')
        if prob == 0.0:
            return DEFAULT_PREDICTION
        result.append(f':{max(1 - prob, 0.01)}')
        return ' '.join(result)
    
    def predict(self):
        data = pd.read_csv(f'{self.test_file_name}/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE)
        with open(f'{self.test_file_name}/out.tsv', 'w', encoding='utf-8') as file_out:
            for _, row in data.iterrows():
                words_before, words_after = word_tokenize(preprocess(str(row[6]))), word_tokenize(preprocess(str(row[7])))
                if len(words_before) < 3 or len(words_after) < 3:
                    prediction = DEFAULT_PREDICTION
                else:
                    prediction = self.predict_row(words_before[-1], words_after[0])
                file_out.write(prediction + '\n')
        


alpha = float(sys.argv[1])
print(f'alfa: {alpha}')
model = Model(alpha, 'train', sys.argv[2])
model.train()
model.predict()