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

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

default_pred = 'to:0.02 be:0.02 the:0.02 or:0.01 not:0.01 and:0.01 a:0.01 :0.9'


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


class Model():
    def __init__(self, alpha, test_file_name):
        train_data = pd.read_csv('train/in.tsv.xz', sep='\t', on_bad_lines='skip', header=None, quoting=csv.QUOTE_NONE,
                                 nrows=20000)
        train_labels = pd.read_csv('train/expected.tsv', sep='\t', on_bad_lines='skip', header=None,
                                   quoting=csv.QUOTE_NONE, nrows=20000)
        train_data = train_data[[6, 7]]
        train_data = pd.concat([train_data, train_labels], axis=1)
        train_data['line'] = train_data[6] + train_data[0] + train_data[7]

        self.file = train_data[['line']]
        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):
            text = preprocess(str(row['line']))
            words = word_tokenize(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):
            count = 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(count + self.alpha + len(word_2))

    def predict(self, before, after):
        prediction = dict(Counter(dict(self.model[before, after])).most_common(5))
        result = []
        prob = 0.0
        for key, value in prediction.items():
            prob += value
            result.append(f'{key}:{value} ')
        if prob == 0.0:
            return default_pred
        result.append(f':{max(1 - prob, 0.01)}')
        return ''.join(result)

    def make_prediction(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():
                before, after = word_tokenize(preprocess(str(row[6]))), word_tokenize(preprocess(str(row[7])))
                if len(before) < 3 or len(after) < 3:
                    prediction = default_pred
                else:
                    prediction = self.predict(before[-1], after[0])
                file_out.write(prediction + '\n')


alpha = 0.1
model = Model(alpha, 'test-A')
model.train()
model.make_prediction()