sport-text-classification-ball/run.py

import pandas as pd
import numpy as np

from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import make_pipeline


data = pd.read_csv('train/train.tsv', sep='\t', header=None, error_bad_lines=False)


X = data[1]

with open('dev-0/in.tsv', 'r', encoding='utf8') as f:
    Xdev = f.readlines()
Xdev = pd.Series(Xdev)

with open('test-A/in.tsv', 'r', encoding='utf8') as f:
    Xtest = f.readlines()
Xtest = pd.Series(Xtest)



y = data[0].astype('str')

ydev = pd.read_csv('dev-0/expected.tsv', sep='\t', header=None)
ydev = ydev.squeeze()


model = make_pipeline(TfidfVectorizer(), MultinomialNB())

model.fit(X, y)


predictions_dev0 = model.predict(Xdev)
predictions_dev0 = pd.Series(predictions_dev0)
predictions_dev0 = predictions_dev0.astype('int')


with open('dev-0/out.tsv', 'wt') as f:
    for pred in predictions_dev0:
        f.write(str(pred)+'\n')


predictions_testA = model.predict(Xtest)
predictions_testA = pd.Series(predictions_testA)
predictions_testA = predictions_testA.astype('int')



with open('test-A/out.tsv', 'wt') as f:
    for pred in predictions_testA:
        f.write(str(pred)+'\n')