import numpy as np
from sklearn.preprocessing import LabelEncoder
from sklearn.naive_bayes import MultinomialNB
from sklearn.pipeline import make_pipeline
from sklearn.feature_extraction.text import TfidfVectorizer

def Create_model(X_tsv, Y_tsv):

    with open(X_tsv) as f:
        X = f.readlines()

    with open(Y_tsv) as f:
        Y = f.readlines() 

    Y = LabelEncoder().fit_transform(Y)
    pipeline = make_pipeline(TfidfVectorizer(),MultinomialNB())

    return pipeline.fit(X, Y)


def predict(model, X_tsv, file_name):

    with open(X_tsv) as f:
        X = f.readlines()

    prediction = model.predict(X)
    np.savetxt(file_name, prediction, fmt='%d')


def main():
    
    model = Create_model("train/in.tsv", "train/expected.tsv")

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


if __name__ == '__main__':
    main()