#!/usr/bin/env python
# -*- coding: utf-8 -*-

import sklearn
import pandas as pd
import numpy as np

dane = pd.read_csv("mieszkania.csv")
print(dane.head())
print(dane.columns)

# check data for outliers
from matplotlib import pyplot as plt
plt.scatter(dane['SqrMeters'], dane['Expected'], color='g')
plt.show()
# remove all data points that have expected price <= 500.000 and living area <= 200 sqrt meters
plt.scatter(dane['Rooms'], dane['Expected'], color='g')
plt.show()
# remove all data points that represent flats with more than 8 rooms

flats = dane[(dane['Rooms'] < 10) & (dane['SqrMeters'] <= 200) & (dane['Expected'] <= 500000)]
print(flats.head(20))

y = flats['Expected']
X = flats.drop(['Id', 'Expected', 'Floor', 'Location',
               'Description', 'Unnamed: 7', 'Unnamed: 8', 'Unnamed: 9', 'Unnamed: 10', 'Unnamed: 11'], axis=1)
print(y.head())
print(X.head())


from sklearn.model_selection import train_test_split

train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.3, random_state=38, shuffle=True)

from sklearn.linear_model import LinearRegression
model = LinearRegression()
model.fit(X,y)


predicted = model.predict(test_X)
print("Predictions:", predicted[:5])

for p in zip(train_X.columns, model.coef_):
    print("Intercept for {}: {:.3}".format(p[0], p[1]))

from sklearn.metrics import mean_squared_error
rmse = np.sqrt(mean_squared_error(predicted, test_y))
print("RMSE:", rmse)

r2 = model.score(test_X, test_y)

print("R squared:", r2) # 0.54 comparing to 0.02 before cleaning the data