import pandas as pd
import numpy as np
import gzip
from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import make_pipeline
from sklearn.metrics import accuracy_score


with gzip.open('train/train.tsv.gz', 'rb') as file:
    data = pd.read_csv(file, sep='\t', header=None, error_bad_lines=False)

# dane do trenowania
y_train = data[0]
x_train = data[1]

# dev
x_dev = pd.read_csv('dev-0/in.tsv',header = None, sep = '/t',engine = 'python')
x_dev = x_dev[0]

#test
x_test_A = pd.read_csv('test-A/in.tsv',header = None, sep = '/t',engine = 'python')
x_test_A = x_test_A[0]

# model 
model = make_pipeline(TfidfVectorizer(), MultinomialNB())
model.fit(x_train, y_train)

def predictions(zb, path_out, model):
    res = model.predict(zb)
    with open(path_out, 'wt') as file:
        for i in res:
            file.write(str(i) + '\n')

predictions(x_dev,'dev-0/out.tsv', model)
predictions(x_test_A,'test-A/out.tsv', model)