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

#%%
import pandas as pd
import csv
import os
import kenlm
from collections import Counter, defaultdict
from math import log10

#%%
def clean(text):
    text = str(text).lower().strip().replace("’", "'").replace('\\n', " ").replace("'t", " not").replace("'s", " is").replace("'ll", " will").replace("'m", " am").replace("'ve", " have").replace(",", "").replace("-", "").replace(".", "").replace("'", "".replace("”", "").replace(">", ""))
    return text

train_in = pd.read_csv("train/in.tsv.xz", sep='\t', header=None, encoding="UTF-8", on_bad_lines="skip", quoting=csv.QUOTE_NONE, nrows=300000)[[6, 7]]
train_expected = pd.read_csv("train/expected.tsv", sep='\t', header=None, encoding="UTF-8", on_bad_lines="skip", quoting=csv.QUOTE_NONE, nrows=300000)
data = pd.concat([train_in, train_expected], axis=1)
data = data[6] + data[0] + data[7]
data = data.apply(clean)

if not os.path.isfile('train_file.txt'):
    with open("train_file.txt", "w+") as f:
        for text in data:
            f.write(text + "\n")

#%%
#get_ipython().system('../kenlm/build/bin/lmplz -o 4 < train_file.txt > model.arpa --skip_symbols')
model = kenlm.Model("model.arpa")
#%%
import nltk
from nltk import word_tokenize
nltk.download('punkt')

most_common = defaultdict(lambda: 0)
for text in data:
    words = word_tokenize(text)
    if "d" in words:
        words.remove("d")
    for w in words:
        most_common[w] += 1
most_common = Counter(most_common).most_common(8000)

#%%
def predict(path, result_path):
    data = pd.read_csv(path, sep='\t', header=None, encoding="UTF-8", on_bad_lines="skip", quoting=csv.QUOTE_NONE)
    with open(result_path, "w+", encoding="UTF-8") as f:
        for i, row in data.iterrows():
            result = {}
            before = word_tokenize(clean(str(row[6])))[-3:]
            if(len(before) < 2):
                result = "a:0.2 the:0.2 to:0.2 of:0.1 and:0.1 of:0.1 :0.1"
            else:
                for w in most_common:
                    word = w[0]
                    prob = model.score(" ".join(before + [word]))
                    result[word] = prob
                predictions = dict(Counter(result).most_common(12))
                result = ""
                for word, prob in predictions.items():
                    result += f"{word}:{prob} "
            result  += f':{log10(0.99)}'
            f.write(result + "\n")
            print(result)


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