from sklearn.linear_model import LinearRegression
import pandas as pd
import numpy as np


def get_model():
    df = pd.read_csv('./train/train.tsv', sep='\t',
                 names=["price", "mileage", "year", "brand", "engine_type", "engine_capacity"])
    X = df.loc[:, df.columns != 'price']
    y = df['price']

    X = X.drop(["brand"], axis=1)
    X = pd.get_dummies(X,  columns= ["engine_type"], drop_first=True)
    regr = LinearRegression()
    return regr.fit(X, y)


def predict_and_write(path, model):
    with open(f'{path}out.tsv', 'w') as out:
        df_dev = pd.read_csv(f'{path}in.tsv', sep='\t',
                            names=["mileage", "year", "brand", "engine_type", "engine_capacity"])
        df_dev = df_dev.drop(["brand"], axis=1)
        df_dev = pd.get_dummies(df_dev, columns= ["engine_type"], drop_first=True)
        predictions = model.predict(df_dev).astype(int)
        for prediction in predictions:
            out.write(f"{prediction}\n")

def main():
    model = get_model()
    predict_and_write('./dev-0/', model)
    predict_and_write('./test-A/', model)

if __name__ == '__main__':
    main()