challenging-america-word-gap-prediction/run2.ipynb

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

ENCODING = "utf-8"

def clean_text(text):
    res = str(text).lower().strip()
    return res

def get_csv(fname):
    return pd.read_csv(
        fname,
        sep="\t",
        on_bad_lines='skip',
        header=None,
        quoting=QUOTE_NONE,
        encoding=ENCODING
    )

def train_model(data, model):
    for _, row in data.iterrows():
        words = nltk.word_tokenize(clean_text(row[607]))
        for w1, w2 in nltk.bigrams(words, pad_left=True, pad_right=True):
            if w1 and w2:
                model[w2][w1] += 1
    for w2 in model:
        total_count = float(sum(model[w2].values()))
        for w1 in model[w2]:
            model[w2][w1] /= total_count

def predict_data(read_path, save_path, model):
    data = get_csv(read_path)

    with open(save_path, "w", encoding=ENCODING) as f:
        for _, row in data.iterrows():
            words = nltk.word_tokenize(clean_text(row[7]))
            if len(words) < 3:
                prediction = "the:0.3 be:0.2 to:0.2 of:0.1 and:0.1 :0.1"
            else:
                prediction = predict(words[0], model)
            f.write(prediction + "\n")

def predict(word, model):
    predictions = dict(model[word])
    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:0.3 be:0.2 to:0.2 of:0.1 and:0.1 :0.1"

    rem_prob = 1 - total_prob
    if rem_prob < 0.01:
        rem_prob = 0.01

    str_prediction += f":{rem_prob}"

    return str_prediction

data = get_csv("train/in.tsv.xz")

train_words = get_csv("train/expected.tsv")
train_data = data[[6, 7]]
train_data = pd.concat([train_data, train_words], axis=1)

train_data[607] = train_data[6] + train_data[0] + train_data[7]

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

train_model(train_data, model)

predict_data("dev-0/in.tsv.xz", "dev-0/out.tsv", model)
predict_data("test-A/in.tsv.xz", "test-A/out.tsv", model)