sport-text-classification/run.py

import pandas as pd
from sklearn.naive_bayes import GaussianNB
from sklearn.feature_extraction.text import TfidfVectorizer


def read_train_data():
    print('Load train data')
    train_data = pd.read_csv("train/train.tsv", sep='\t', header=None)
    train_data = train_data[:10000]

    return train_data[1], train_data[0]

def read_pred_data():
    print('Load pred data')
    x_p = []
    with open("test-A/in.tsv", encoding='utf-8') as f:
        for line in f:
            x_p.append(line)
    return x_p

def vectorize(x,x_p):
    print('Vectorize')
    vectorizer = TfidfVectorizer()
    x = vectorizer.fit_transform(x)
    x_p = vectorizer.transform(x_p)
    return x, x_p

def calc_score(x, y, x_p):
    print('Calculate score')
    model = GaussianNB()
    model.fit(x.toarray(), y)
    return model.predict(x_p.toarray())

def get_result():
    x, y = read_train_data()
    x_p = read_pred_data()
    x, x_p = vectorize(x, x_p)
    return calc_score(x, y, x_p) 

pd.DataFrame(get_result()).to_csv("test-A/out.tsv", header=False, index=None)