from sklearn.feature_extraction.text import TfidfVectorizer
from sklearn.linear_model import LinearRegression
from sklearn.pipeline import make_pipeline
from sklearn import preprocessing
from sklearn import linear_model

import pandas as pd
import numpy as np

myT = pd.read_csv('train/train.tsv', sep='\t',
	names = ['price','mileage','year','brand','engineType','engineCapacity'])
datF = pd.DataFrame(myT, 
	columns = ['price','mileage','year','brand','engineType','engineCapacity'])
y = datF[['price']]
x = datF[['year','mileage','engineCapacity']]
reg = linear_model.LinearRegression()
reg.fit(x, y)
put = pd.read_csv('test-A/in.tsv', sep = '\t',
	names = ['mileage','year','brand','engineType','engineCapacity'])
datF = pd.DataFrame(put,
	columns = ['mileage','year','brand','engineType','engineCapacity'])
r = datF[['year','mileage','engineCapacity']]
y1 = reg.predict(r)
y1 = np.concatenate(y1)
tmp = np.array2string(y1, precision = 5, 
	separator = '\n', suppress_small = True)
tmp = tmp.lstrip('[').rstrip(']')
f = open("test-A/out.tsv", "a")
f.write(tmp)