import gzip
import pandas as pd
import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.utils import shuffle
from sklearn.metrics import accuracy_score


def preprocess(x):
    x = pd.concat([x, x['engineType'].str.get_dummies().astype(bool)], axis=1)
    x = x.drop(['engineType', 'brand'], axis=1)
    return x


def makePrediction(path):
    x_pred = pd.read_table(path + '/in.tsv', error_bad_lines=False, header=None,
                           names=names[1:])
    x_pred = preprocess(x_pred)

    y_pred = model.predict(x_pred)
    y_pred.tofile(path + '/out.tsv', sep='\n')


names = ['price', 'mileage', 'year', 'brand', 'engineType', 'engineCap']

train = pd.read_table('train/train.tsv', error_bad_lines=False, header=None,
                      names=names)

y_train = train['price']
x_train = train.iloc[:, 1:]
x_train = preprocess(x_train)

model = LinearRegression()
model.fit(x_train, y_train)

makePrediction('dev-0')
makePrediction('test-A')