import pandas as pd
from pandas import DataFrame
from sklearn.linear_model import LinearRegression
from sklearn.metrics import mean_squared_error
import numpy as np

df = pd.read_csv("train/train.tsv", header=None, sep="\t", error_bad_lines=False, names=['price', 'mileage', 'year',
                                                                                         'brand', 'engineType',
                                                                                         'engineCapacity'])
dev0 = pd.read_csv("dev-0/in.tsv", header=None, sep="\t", error_bad_lines=False, names=['mileage', 'year',
                                                                                        'brand', 'engineType',
                                                                                        'engineCapacity'])
testA = pd.read_csv("test-A/in.tsv", header=None, sep="\t", error_bad_lines=False, names=['mileage', 'year',
                                                                                          'brand', 'engineType',
                                                                                          'engineCapacity'])
expected = pd.read_csv("dev-0/expected.tsv", header=None, sep="\t", error_bad_lines=False, names=['price'])

df = df[['price', 'year', 'mileage', 'engineCapacity']]

min_val = np.min(df)
max_val = np.max(df)
df = (df - min_val) / (max_val - min_val)

Y = df[['price']]
X = df[['year', 'mileage', 'engineCapacity']]

model = LinearRegression().fit(X, Y)

dev0 = (dev0[['year', 'mileage', 'engineCapacity']] - min_val) / (max_val - min_val)
testA = (testA[['year', 'mileage', 'engineCapacity']] - min_val) / (max_val - min_val)

predicted_dev0 = model.predict(dev0[['year', 'mileage', 'engineCapacity']])
predicted_testA = model.predict(testA[['year', 'mileage', 'engineCapacity']])

with open("dev-0/out.tsv", "w") as file:
    for pred in predicted_dev0:
        file.write(str(pred[0]) + "\n")

with open("test-A/out.tsv", "w") as file:
    for pred in predicted_testA:
        file.write(str(pred[0]) + "\n")


predicted_denormalized = []
for pred in predicted_dev0:
    denorm = pred[0] * (max_val[0] - min_val[0]) + min_val[0]
    predicted_denormalized.append(denorm)

predicted_denormalized = DataFrame(predicted_denormalized, columns=['pred'])
error = mean_squared_error(expected, predicted_denormalized)
for exp, pred in zip(expected.values, predicted_denormalized.values):
    print(exp, pred)

f = open("dev0_rmse.txt", "w")
f.write(str(error))
f.close()
print(error)