#basic imports
import pandas
from sklearn.linear_model import LinearRegression

#basic paths
openTrain = './train/train.tsv'
openDev = './dev-0/in.tsv'
openTest = './test-A/in.tsv'

#read from files
with open('./names') as f_names:
    names = f_names.read().rstrip('\n').split('\t')
read0 = pandas.read_table(openTrain, sep='\t', names=names)
read1 = pandas.read_table(openDev, sep='\t', names=['mileage', 'year', 'brand', 'engineType', 'engineCapacity'])

#basic normalization & filtering
trainSet = pandas.get_dummies(read0, columns=['engineType'])
categories1 = trainSet.select_dtypes(include=object).columns.values
for c in categories1:
    trainSet[c] = trainSet[c].astype('category').cat.codes
trainSet = trainSet.loc[(trainSet['price'] > 10000)] #to avoid suspicious observations
#for some reason this value gives the smallest RMSE according to geval, while smaller or bigger
#price gives RMSE >34k

#Model training
X = trainSet.loc[:, trainSet.columns != 'price']
solution = LinearRegression().fit(X, trainSet['price'])

devSet = pandas.get_dummies(read1, columns=['engineType'])
categories2 = devSet.select_dtypes(include=object).columns.values
for c in categories2:
    devSet[c] = devSet[c].astype('category').cat.codes

predict = solution.predict(devSet)
predict.tofile("./dev-0/out.tsv", sep='\n')
testSet = pandas.get_dummies(read1, columns=['engineType'])

categories3 = testSet.select_dtypes(include=object).columns.values
for c in categories3:
    testSet[c] = testSet[c].astype('category').cat.codes

predict = solution.predict(devSet)
predict.tofile("./test-A/out.tsv", sep='\n')

#Outcome: 33956 for prices >10000