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

import pandas as pd
from matplotlib import pyplot as plt
from sklearn import linear_model

def wczytaj_dane():
    data = pd.read_csv("J:/PycharmProjects/Python2018/labs06/mieszkania.csv")
    return pd.DataFrame(data)

def most_common_room_number(dane):
    dane2 = dane['Rooms'].value_counts().head(1)
    pokoje = int(dane2.index[0])
    return pokoje

def cheapest_flats(dane, n):
    result = dane.sort_values('Expected').head(n)
    return result

def find_borough(desc):
    dzielnice = ['Stare Miasto',
                 'Wilda',
                 'Jeżyce',
                 'Rataje',
                 'Piątkowo',
                 'Winogrady',
                 'Miłostowo',
                 'Dębiec']
    for i in range(0,len(dzielnice)):
        if dzielnice[i] in desc:
            result = dzielnice[i]
            break
        else:
            result = 'Inne'
    return result

def add_borough(dane):
    dane['Borough'] = dane['Location'].apply(find_borough)
    return dane

def write_plot(dane, filename):
    dane['Borough'].value_counts().plot(kind='barh')
    plt.savefig('J:/PycharmProjects/Python2018/labs06/'+filename)
    return 0

def mean_price(dane, room_number):
    dane2 = dane[dane.Rooms == room_number]
    srednia = round(dane2.Expected.mean(),2)
    return srednia

def find_13(dane):
    dane2 = dane[dane.Floor == 13]
    lista_dzielnic = dane2['Borough'].unique()
    return lista_dzielnic

def find_best_flats(dane):
    dane2 = dane[(dane['Borough']=='Winogrady') & (dane['Rooms']==3) & (dane['Floor']==1)]
    return dane2

def reg_lin(dane, metraz, pokoje):
    reg = linear_model.LinearRegression()
    reg.fit(dane[['SqrMeters', 'Rooms']], dane['Expected'])
    result = reg.predict(pd.DataFrame([(metraz, pokoje)], columns=['var1', 'var2']))
    return result

"""
dane = wczytaj_dane()
print(most_common_room_number(dane))
print(cheapest_flats(dane, 2))
print(find_borough('Winogrady i Jeżyce'))
add_borough(dane)
write_plot(dane, 'wykres')
print(mean_price(dane, 3))
print(find_13(dane))
print(find_best_flats(dane).shape[0])
print(reg_lin(dane, 60, 3))
"""

def main():
    dane = wczytaj_dane()
    print(dane[:5])

    print("Najpopularniejsza liczba pokoi w mieszkaniu to: {}"
          .format(most_common_room_number(dane)))

    print("{} to najłądniejsza dzielnica w Poznaniu."
          .format(find_borough("Grunwald i Jeżyce")))

    print("Średnia cena mieszkania 3-pokojowego, to: {}"
          .format(mean_price(dane, 3)))

if __name__ == "__main__":
    main()