2023-10-17 17:30:25 +02:00
|
|
|
|
{
|
|
|
|
|
"cells": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"# Systemy informatyczne - 1. Organizacja pracy zespołowej"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"## Klonowanie dostępnych danych uczących"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-17 17:30:25 +02:00
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 1,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"name": "stderr",
|
|
|
|
|
"output_type": "stream",
|
|
|
|
|
"text": [
|
|
|
|
|
"fatal: destination path 'mieszkania5' already exists and is not an empty directory.\n"
|
|
|
|
|
]
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"!git clone git://gonito.net/mieszkania5"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"cell_type": "markdown",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"## Import danych treningowych, walidacyjnych i testowych"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 2,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"import numpy as np\n",
|
|
|
|
|
"import pandas as pd"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"cell_type": "markdown",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"### Dane treningowe"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 3,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"df_train = pd.read_csv(r'mieszkania5\\train\\train.tsv', sep='\\t', header=None)\n"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 4,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
|
|
|
|
"<div>\n",
|
|
|
|
|
"<style scoped>\n",
|
|
|
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
|
|
|
" vertical-align: middle;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe tbody tr th {\n",
|
|
|
|
|
" vertical-align: top;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe thead th {\n",
|
|
|
|
|
" text-align: right;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"</style>\n",
|
|
|
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
|
|
|
" <thead>\n",
|
|
|
|
|
" <tr style=\"text-align: right;\">\n",
|
|
|
|
|
" <th></th>\n",
|
|
|
|
|
" <th>0</th>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <th>1</th>\n",
|
|
|
|
|
" <th>2</th>\n",
|
|
|
|
|
" <th>3</th>\n",
|
|
|
|
|
" <th>4</th>\n",
|
|
|
|
|
" <th>5</th>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <th>6</th>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <th>7</th>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <th>8</th>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <th>9</th>\n",
|
|
|
|
|
" <th>...</th>\n",
|
|
|
|
|
" <th>16</th>\n",
|
|
|
|
|
" <th>17</th>\n",
|
|
|
|
|
" <th>18</th>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <th>19</th>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <th>20</th>\n",
|
|
|
|
|
" <th>21</th>\n",
|
|
|
|
|
" <th>22</th>\n",
|
|
|
|
|
" <th>23</th>\n",
|
|
|
|
|
" <th>24</th>\n",
|
|
|
|
|
" <th>25</th>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </thead>\n",
|
|
|
|
|
" <tbody>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>0</th>\n",
|
|
|
|
|
" <td>309000.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>do zamieszkania</td>\n",
|
|
|
|
|
" <td>390 zł</td>\n",
|
|
|
|
|
" <td>spółdzielcze własnościowe</td>\n",
|
|
|
|
|
" <td>7113</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/niezalezny-uklad-...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>2</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>43.44</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>gazowe</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>Polecamy na sprzedaż dwupokojowe mieszkanie p...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, meble, piwnica, g...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>1</th>\n",
|
|
|
|
|
" <td>314900.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>do wykończenia</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>7392</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/urokliwe-mieszkan...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>2</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>42.60</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>pierwotny</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>gazowe</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>Kameralne 2 pokojowe mieszkanie z aneksem kuc...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, drzwi / ...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2</th>\n",
|
|
|
|
|
" <td>249000.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>do remontu</td>\n",
|
|
|
|
|
" <td>300 zł</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>5621</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkanie-do-rem...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>2</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>44.30</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>miejskie</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>1960.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>2019-06-30</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>Oferta bezpośrednio od właściciela - bez pośr...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, domofon ...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>3</th>\n",
|
|
|
|
|
" <td>419000.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>do zamieszkania</td>\n",
|
|
|
|
|
" <td>490 zł</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>4761</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/w-szeregowcu-4-po...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>4</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>88</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>gazowe</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>Drodzy Państwo Zapraszam do zapoznania się z ...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>telewizja kablowa, internet, zmywarka, lodówka...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>4</th>\n",
|
|
|
|
|
" <td>499000.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>850 zł</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>6481</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/komfortowe-przest...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>3</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>77</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>Biuro Immohouse ma przyjemność proponować do ...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>balkon, piwnica, winda</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>...</th>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2542</th>\n",
|
|
|
|
|
" <td>507600.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>do wykończenia</td>\n",
|
|
|
|
|
" <td>1 zł</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>5400</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkanie-do-spr...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>4</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>94</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>gazowe</td>\n",
|
|
|
|
|
" <td>drewniane</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>1914.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>Do sprzedaży mieszkanie na drugim piętrze w s...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2543</th>\n",
|
|
|
|
|
" <td>342400.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>spółdzielcze własnościowe</td>\n",
|
|
|
|
|
" <td>6400</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkanie-53-50-...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>2</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>53.50</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>miejskie</td>\n",
|
|
|
|
|
" <td>drewniane</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>1999.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>| Świetnie zlokalizowane, przestronne, czyste...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, monitori...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2544</th>\n",
|
|
|
|
|
" <td>335000.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>280 zł</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>6063</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkanie-55-25-...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>3</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>55.25</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>1910.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>MIESZKANIE ŁAZARZ Przedmiotem sprzedaży jest ...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, monitori...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2545</th>\n",
|
|
|
|
|
" <td>260000.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>4194</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkanie-udzial...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>3</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>62</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>piece kaflowe</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>1930.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>2011-07-05</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>Polecam do sprzedaży mieszkanie w udziale kam...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>piwnica, oddzielna kuchnia, pom. użytkowe</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2546</th>\n",
|
|
|
|
|
" <td>1990000.0</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>do zamieszkania</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>5077</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkania-w-kami...</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>więcej niż 10</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>392</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>gazowe</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>Sprzedam 7 mieszkań w centrum Poznania przy u...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>lodówka, meble, piekarnik, kuchenka, pralka</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </tbody>\n",
|
|
|
|
|
"</table>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"<p>2547 rows × 26 columns</p>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"</div>"
|
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" 0 1 2 3 4 \\\n",
|
|
|
|
|
"0 309000.0 do zamieszkania 390 zł spółdzielcze własnościowe 7113 \n",
|
|
|
|
|
"1 314900.0 do wykończenia NaN pełna własność 7392 \n",
|
|
|
|
|
"2 249000.0 do remontu 300 zł pełna własność 5621 \n",
|
|
|
|
|
"3 419000.0 do zamieszkania 490 zł pełna własność 4761 \n",
|
|
|
|
|
"4 499000.0 NaN 850 zł NaN 6481 \n",
|
|
|
|
|
"... ... ... ... ... ... \n",
|
|
|
|
|
"2542 507600.0 do wykończenia 1 zł pełna własność 5400 \n",
|
|
|
|
|
"2543 342400.0 NaN NaN spółdzielcze własnościowe 6400 \n",
|
|
|
|
|
"2544 335000.0 NaN 280 zł pełna własność 6063 \n",
|
|
|
|
|
"2545 260000.0 NaN NaN NaN 4194 \n",
|
|
|
|
|
"2546 1990000.0 do zamieszkania NaN NaN 5077 \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" 5 6 7 \\\n",
|
|
|
|
|
"0 https://www.otodom.pl/oferta/niezalezny-uklad-... 2 NaN \n",
|
|
|
|
|
"1 https://www.otodom.pl/oferta/urokliwe-mieszkan... 2 NaN \n",
|
|
|
|
|
"2 https://www.otodom.pl/oferta/mieszkanie-do-rem... 2 NaN \n",
|
|
|
|
|
"3 https://www.otodom.pl/oferta/w-szeregowcu-4-po... 4 NaN \n",
|
|
|
|
|
"4 https://www.otodom.pl/oferta/komfortowe-przest... 3 NaN \n",
|
|
|
|
|
"... ... ... .. \n",
|
|
|
|
|
"2542 https://www.otodom.pl/oferta/mieszkanie-do-spr... 4 NaN \n",
|
|
|
|
|
"2543 https://www.otodom.pl/oferta/mieszkanie-53-50-... 2 NaN \n",
|
|
|
|
|
"2544 https://www.otodom.pl/oferta/mieszkanie-55-25-... 3 NaN \n",
|
|
|
|
|
"2545 https://www.otodom.pl/oferta/mieszkanie-udzial... 3 NaN \n",
|
|
|
|
|
"2546 https://www.otodom.pl/oferta/mieszkania-w-kami... więcej niż 10 NaN \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" 8 9 ... 16 17 18 19 20 \\\n",
|
|
|
|
|
"0 43.44 wtórny ... NaN gazowe plastikowe NaN NaN \n",
|
|
|
|
|
"1 42.60 pierwotny ... NaN gazowe plastikowe NaN NaN \n",
|
|
|
|
|
"2 44.30 wtórny ... NaN miejskie plastikowe 1960.0 NaN \n",
|
|
|
|
|
"3 88 wtórny ... NaN gazowe plastikowe NaN NaN \n",
|
|
|
|
|
"4 77 wtórny ... NaN NaN plastikowe NaN NaN \n",
|
|
|
|
|
"... ... ... ... .. ... ... ... .. \n",
|
|
|
|
|
"2542 94 wtórny ... NaN gazowe drewniane 1914.0 NaN \n",
|
|
|
|
|
"2543 53.50 wtórny ... NaN miejskie drewniane 1999.0 NaN \n",
|
|
|
|
|
"2544 55.25 wtórny ... NaN NaN plastikowe 1910.0 NaN \n",
|
|
|
|
|
"2545 62 wtórny ... NaN piece kaflowe NaN 1930.0 NaN \n",
|
|
|
|
|
"2546 392 wtórny ... NaN gazowe NaN NaN NaN \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" 21 22 23 \\\n",
|
|
|
|
|
"0 NaN cegła Polecamy na sprzedaż dwupokojowe mieszkanie p... \n",
|
|
|
|
|
"1 NaN cegła Kameralne 2 pokojowe mieszkanie z aneksem kuc... \n",
|
|
|
|
|
"2 2019-06-30 cegła Oferta bezpośrednio od właściciela - bez pośr... \n",
|
|
|
|
|
"3 NaN cegła Drodzy Państwo Zapraszam do zapoznania się z ... \n",
|
|
|
|
|
"4 NaN NaN Biuro Immohouse ma przyjemność proponować do ... \n",
|
|
|
|
|
"... ... ... ... \n",
|
|
|
|
|
"2542 NaN cegła Do sprzedaży mieszkanie na drugim piętrze w s... \n",
|
|
|
|
|
"2543 NaN cegła | Świetnie zlokalizowane, przestronne, czyste... \n",
|
|
|
|
|
"2544 NaN cegła MIESZKANIE ŁAZARZ Przedmiotem sprzedaży jest ... \n",
|
|
|
|
|
"2545 2011-07-05 cegła Polecam do sprzedaży mieszkanie w udziale kam... \n",
|
|
|
|
|
"2546 NaN cegła Sprzedam 7 mieszkań w centrum Poznania przy u... \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" 24 25 \n",
|
|
|
|
|
"0 NaN telewizja kablowa, internet, meble, piwnica, g... \n",
|
|
|
|
|
"1 NaN telewizja kablowa, internet, telefon, drzwi / ... \n",
|
|
|
|
|
"2 NaN telewizja kablowa, internet, telefon, domofon ... \n",
|
|
|
|
|
"3 NaN telewizja kablowa, internet, zmywarka, lodówka... \n",
|
|
|
|
|
"4 NaN balkon, piwnica, winda \n",
|
|
|
|
|
"... .. ... \n",
|
|
|
|
|
"2542 NaN NaN \n",
|
|
|
|
|
"2543 NaN telewizja kablowa, internet, telefon, monitori... \n",
|
|
|
|
|
"2544 NaN telewizja kablowa, internet, telefon, monitori... \n",
|
|
|
|
|
"2545 NaN piwnica, oddzielna kuchnia, pom. użytkowe \n",
|
|
|
|
|
"2546 NaN lodówka, meble, piekarnik, kuchenka, pralka \n",
|
|
|
|
|
"\n",
|
|
|
|
|
"[2547 rows x 26 columns]"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 4,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_train"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Dane walidacyjne"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 5,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid = pd.read_csv(r'mieszkania5\\dev-0\\in.tsv', sep='\\t', header=None)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 6,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
|
|
|
|
"<div>\n",
|
|
|
|
|
"<style scoped>\n",
|
|
|
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
|
|
|
" vertical-align: middle;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe tbody tr th {\n",
|
|
|
|
|
" vertical-align: top;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe thead th {\n",
|
|
|
|
|
" text-align: right;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"</style>\n",
|
|
|
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
|
|
|
" <thead>\n",
|
|
|
|
|
" <tr style=\"text-align: right;\">\n",
|
|
|
|
|
" <th></th>\n",
|
|
|
|
|
" <th>0</th>\n",
|
|
|
|
|
" <th>1</th>\n",
|
|
|
|
|
" <th>2</th>\n",
|
|
|
|
|
" <th>3</th>\n",
|
|
|
|
|
" <th>4</th>\n",
|
|
|
|
|
" <th>5</th>\n",
|
|
|
|
|
" <th>6</th>\n",
|
|
|
|
|
" <th>7</th>\n",
|
|
|
|
|
" <th>8</th>\n",
|
|
|
|
|
" <th>9</th>\n",
|
|
|
|
|
" <th>...</th>\n",
|
|
|
|
|
" <th>15</th>\n",
|
|
|
|
|
" <th>16</th>\n",
|
|
|
|
|
" <th>17</th>\n",
|
|
|
|
|
" <th>18</th>\n",
|
|
|
|
|
" <th>19</th>\n",
|
|
|
|
|
" <th>20</th>\n",
|
|
|
|
|
" <th>21</th>\n",
|
|
|
|
|
" <th>22</th>\n",
|
|
|
|
|
" <th>23</th>\n",
|
|
|
|
|
" <th>24</th>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </thead>\n",
|
|
|
|
|
" <tbody>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>0</th>\n",
|
|
|
|
|
" <td>do zamieszkania</td>\n",
|
|
|
|
|
" <td>250 zł</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>6311</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/idealne-mieszkani...</td>\n",
|
|
|
|
|
" <td>3</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>59.10</td>\n",
|
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>4.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>miejskie</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>wielka płyta</td>\n",
|
|
|
|
|
" <td>Zamieszkaj od zaraz – idealna lokalizacja OFE...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, domofon ...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>1</th>\n",
|
|
|
|
|
" <td>do zamieszkania</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>7868</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/2-pokoje-38m2-po-...</td>\n",
|
|
|
|
|
" <td>2</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>38.00</td>\n",
|
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>12.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>inne</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>Na sprzedaż mieszkanie dwupokojowe na osiedlu...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>balkon</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2</th>\n",
|
|
|
|
|
" <td>do zamieszkania</td>\n",
|
|
|
|
|
" <td>650 zł</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>5717</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/3-pokoje-na-jezyc...</td>\n",
|
|
|
|
|
" <td>3</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>63.84</td>\n",
|
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>4.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>miejskie</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>1958.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>!! Oferta dostępna tylko u nas !! Polecam ofe...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, piwnica,...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>3</th>\n",
|
|
|
|
|
" <td>do zamieszkania</td>\n",
|
|
|
|
|
" <td>359 zł</td>\n",
|
|
|
|
|
" <td>spółdzielcze własnościowe</td>\n",
|
|
|
|
|
" <td>7380</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/uniwersytet-przyr...</td>\n",
|
|
|
|
|
" <td>4</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>50.00</td>\n",
|
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>10.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>miejskie</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>1975.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>2019-06-30</td>\n",
|
|
|
|
|
" <td>wielka płyta</td>\n",
|
|
|
|
|
" <td>Oferta bezpośrednio od właściciela - bez po...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, drzwi / ...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>4</th>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>7373</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkanie-blisko...</td>\n",
|
|
|
|
|
" <td>3</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>65.62</td>\n",
|
|
|
|
|
" <td>pierwotny</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>2020.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>2020-01-01</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>MIESZKANIE 3-POKOJOWE O POW.65,62M2 Mieszkani...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>garaż/miejsce parkingowe, taras, pom. użytkowe</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>...</th>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>457</th>\n",
|
|
|
|
|
" <td>do wykończenia</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>9007</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkanie-zajezd...</td>\n",
|
|
|
|
|
" <td>3</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>72.78</td>\n",
|
|
|
|
|
" <td>pierwotny</td>\n",
|
|
|
|
|
" <td>5.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>miejskie</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>2019.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>Zapraszam do zapoznania się z nową atrakcyjną...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, monitoring / ochr...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>458</th>\n",
|
|
|
|
|
" <td>do wykończenia</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>9202</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkanie-zajezd...</td>\n",
|
|
|
|
|
" <td>2</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>51.23</td>\n",
|
|
|
|
|
" <td>pierwotny</td>\n",
|
|
|
|
|
" <td>5.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>Zapraszam do zapoznania się z nową atrakcyjną...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>garaż/miejsce parkingowe, winda</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>459</th>\n",
|
|
|
|
|
" <td>do wykończenia</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>5723</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/nowe-mieszkanie-o...</td>\n",
|
|
|
|
|
" <td>3</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>54.16</td>\n",
|
|
|
|
|
" <td>pierwotny</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>kotłownia</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>2019.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>2019-12-31</td>\n",
|
|
|
|
|
" <td>silikat</td>\n",
|
|
|
|
|
" <td>Mieszkanie składa się z 3 pokoi, aneksu kuche...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, domofon ...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>460</th>\n",
|
|
|
|
|
" <td>do zamieszkania</td>\n",
|
|
|
|
|
" <td>1 102.05 zł</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>7758</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/apartament-w-atan...</td>\n",
|
|
|
|
|
" <td>3</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>90.10</td>\n",
|
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>5.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>kotłownia</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>2001.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>2018-04-13</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>Proponuję bardzo atrakcyjny, przestronny, w p...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, drzwi / okna antywłamaniowe...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>461</th>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>11822</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkanie-71-90-...</td>\n",
|
|
|
|
|
" <td>2</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>71.90</td>\n",
|
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>drewniane</td>\n",
|
|
|
|
|
" <td>2016.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>Link do oferty: -wielkopolskie-poznan-grunwal...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>balkon, garaż/miejsce parkingowe</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </tbody>\n",
|
|
|
|
|
"</table>\n",
|
|
|
|
|
"<p>462 rows × 25 columns</p>\n",
|
|
|
|
|
"</div>"
|
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
|
|
|
|
" 0 1 2 3 \\\n",
|
|
|
|
|
"0 do zamieszkania 250 zł pełna własność 6311 \n",
|
|
|
|
|
"1 do zamieszkania NaN pełna własność 7868 \n",
|
|
|
|
|
"2 do zamieszkania 650 zł pełna własność 5717 \n",
|
|
|
|
|
"3 do zamieszkania 359 zł spółdzielcze własnościowe 7380 \n",
|
|
|
|
|
"4 NaN NaN NaN 7373 \n",
|
|
|
|
|
".. ... ... ... ... \n",
|
|
|
|
|
"457 do wykończenia NaN pełna własność 9007 \n",
|
|
|
|
|
"458 do wykończenia NaN pełna własność 9202 \n",
|
|
|
|
|
"459 do wykończenia NaN pełna własność 5723 \n",
|
|
|
|
|
"460 do zamieszkania 1 102.05 zł pełna własność 7758 \n",
|
|
|
|
|
"461 NaN NaN NaN 11822 \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" 4 5 6 7 \\\n",
|
|
|
|
|
"0 https://www.otodom.pl/oferta/idealne-mieszkani... 3 NaN 59.10 \n",
|
|
|
|
|
"1 https://www.otodom.pl/oferta/2-pokoje-38m2-po-... 2 NaN 38.00 \n",
|
|
|
|
|
"2 https://www.otodom.pl/oferta/3-pokoje-na-jezyc... 3 NaN 63.84 \n",
|
|
|
|
|
"3 https://www.otodom.pl/oferta/uniwersytet-przyr... 4 NaN 50.00 \n",
|
|
|
|
|
"4 https://www.otodom.pl/oferta/mieszkanie-blisko... 3 NaN 65.62 \n",
|
|
|
|
|
".. ... .. .. ... \n",
|
|
|
|
|
"457 https://www.otodom.pl/oferta/mieszkanie-zajezd... 3 NaN 72.78 \n",
|
|
|
|
|
"458 https://www.otodom.pl/oferta/mieszkanie-zajezd... 2 NaN 51.23 \n",
|
|
|
|
|
"459 https://www.otodom.pl/oferta/nowe-mieszkanie-o... 3 NaN 54.16 \n",
|
|
|
|
|
"460 https://www.otodom.pl/oferta/apartament-w-atan... 3 NaN 90.10 \n",
|
|
|
|
|
"461 https://www.otodom.pl/oferta/mieszkanie-71-90-... 2 NaN 71.90 \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" 8 9 ... 15 16 17 18 19 20 \\\n",
|
|
|
|
|
"0 wtórny 4.0 ... NaN miejskie plastikowe NaN NaN NaN \n",
|
|
|
|
|
"1 wtórny 12.0 ... NaN inne plastikowe NaN NaN NaN \n",
|
|
|
|
|
"2 wtórny 4.0 ... NaN miejskie plastikowe 1958.0 NaN NaN \n",
|
|
|
|
|
"3 wtórny 10.0 ... NaN miejskie plastikowe 1975.0 NaN 2019-06-30 \n",
|
|
|
|
|
"4 pierwotny 3.0 ... NaN NaN NaN 2020.0 NaN 2020-01-01 \n",
|
|
|
|
|
".. ... ... ... .. ... ... ... .. ... \n",
|
|
|
|
|
"457 pierwotny 5.0 ... NaN miejskie plastikowe 2019.0 NaN NaN \n",
|
|
|
|
|
"458 pierwotny 5.0 ... NaN NaN NaN NaN NaN NaN \n",
|
|
|
|
|
"459 pierwotny 3.0 ... NaN kotłownia plastikowe 2019.0 NaN 2019-12-31 \n",
|
|
|
|
|
"460 wtórny 5.0 ... NaN kotłownia plastikowe 2001.0 NaN 2018-04-13 \n",
|
|
|
|
|
"461 wtórny 3.0 ... NaN NaN drewniane 2016.0 NaN NaN \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" 21 22 23 \\\n",
|
|
|
|
|
"0 wielka płyta Zamieszkaj od zaraz – idealna lokalizacja OFE... NaN \n",
|
|
|
|
|
"1 NaN Na sprzedaż mieszkanie dwupokojowe na osiedlu... NaN \n",
|
|
|
|
|
"2 cegła !! Oferta dostępna tylko u nas !! Polecam ofe... NaN \n",
|
|
|
|
|
"3 wielka płyta Oferta bezpośrednio od właściciela - bez po... NaN \n",
|
|
|
|
|
"4 NaN MIESZKANIE 3-POKOJOWE O POW.65,62M2 Mieszkani... NaN \n",
|
|
|
|
|
".. ... ... .. \n",
|
|
|
|
|
"457 cegła Zapraszam do zapoznania się z nową atrakcyjną... NaN \n",
|
|
|
|
|
"458 NaN Zapraszam do zapoznania się z nową atrakcyjną... NaN \n",
|
|
|
|
|
"459 silikat Mieszkanie składa się z 3 pokoi, aneksu kuche... NaN \n",
|
|
|
|
|
"460 cegła Proponuję bardzo atrakcyjny, przestronny, w p... NaN \n",
|
|
|
|
|
"461 cegła Link do oferty: -wielkopolskie-poznan-grunwal... NaN \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" 24 \n",
|
|
|
|
|
"0 telewizja kablowa, internet, telefon, domofon ... \n",
|
|
|
|
|
"1 balkon \n",
|
|
|
|
|
"2 telewizja kablowa, internet, telefon, piwnica,... \n",
|
|
|
|
|
"3 telewizja kablowa, internet, telefon, drzwi / ... \n",
|
|
|
|
|
"4 garaż/miejsce parkingowe, taras, pom. użytkowe \n",
|
|
|
|
|
".. ... \n",
|
|
|
|
|
"457 telewizja kablowa, internet, monitoring / ochr... \n",
|
|
|
|
|
"458 garaż/miejsce parkingowe, winda \n",
|
|
|
|
|
"459 telewizja kablowa, internet, telefon, domofon ... \n",
|
|
|
|
|
"460 telewizja kablowa, drzwi / okna antywłamaniowe... \n",
|
|
|
|
|
"461 balkon, garaż/miejsce parkingowe \n",
|
|
|
|
|
"\n",
|
|
|
|
|
"[462 rows x 25 columns]"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 6,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 7,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid_cena = pd.read_csv(r'mieszkania5\\dev-0\\expected.tsv', sep='\\t', header=None)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 8,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
|
|
|
|
"<div>\n",
|
|
|
|
|
"<style scoped>\n",
|
|
|
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
|
|
|
" vertical-align: middle;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe tbody tr th {\n",
|
|
|
|
|
" vertical-align: top;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe thead th {\n",
|
|
|
|
|
" text-align: right;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"</style>\n",
|
|
|
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
|
|
|
" <thead>\n",
|
|
|
|
|
" <tr style=\"text-align: right;\">\n",
|
|
|
|
|
" <th></th>\n",
|
|
|
|
|
" <th>0</th>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </thead>\n",
|
|
|
|
|
" <tbody>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>0</th>\n",
|
|
|
|
|
" <td>373000.00</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>1</th>\n",
|
|
|
|
|
" <td>299000.00</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2</th>\n",
|
|
|
|
|
" <td>365000.00</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>3</th>\n",
|
|
|
|
|
" <td>369000.00</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>4</th>\n",
|
|
|
|
|
" <td>483791.00</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>...</th>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>457</th>\n",
|
|
|
|
|
" <td>655544.02</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>458</th>\n",
|
|
|
|
|
" <td>471397.97</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>459</th>\n",
|
|
|
|
|
" <td>309958.00</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>460</th>\n",
|
|
|
|
|
" <td>699000.00</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>461</th>\n",
|
|
|
|
|
" <td>850000.00</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </tbody>\n",
|
|
|
|
|
"</table>\n",
|
|
|
|
|
"<p>462 rows × 1 columns</p>\n",
|
|
|
|
|
"</div>"
|
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
|
|
|
|
" 0\n",
|
|
|
|
|
"0 373000.00\n",
|
|
|
|
|
"1 299000.00\n",
|
|
|
|
|
"2 365000.00\n",
|
|
|
|
|
"3 369000.00\n",
|
|
|
|
|
"4 483791.00\n",
|
|
|
|
|
".. ...\n",
|
|
|
|
|
"457 655544.02\n",
|
|
|
|
|
"458 471397.97\n",
|
|
|
|
|
"459 309958.00\n",
|
|
|
|
|
"460 699000.00\n",
|
|
|
|
|
"461 850000.00\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"[462 rows x 1 columns]"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 8,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid_cena"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Dane testowe"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 9,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_test = pd.read_csv(r'mieszkania5\\test-A\\in.tsv', sep='\\t', header=None)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 10,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
|
|
|
|
"<div>\n",
|
|
|
|
|
"<style scoped>\n",
|
|
|
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
|
|
|
" vertical-align: middle;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe tbody tr th {\n",
|
|
|
|
|
" vertical-align: top;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe thead th {\n",
|
|
|
|
|
" text-align: right;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"</style>\n",
|
|
|
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
|
|
|
" <thead>\n",
|
|
|
|
|
" <tr style=\"text-align: right;\">\n",
|
|
|
|
|
" <th></th>\n",
|
|
|
|
|
" <th>0</th>\n",
|
|
|
|
|
" <th>1</th>\n",
|
|
|
|
|
" <th>2</th>\n",
|
|
|
|
|
" <th>3</th>\n",
|
|
|
|
|
" <th>4</th>\n",
|
|
|
|
|
" <th>5</th>\n",
|
|
|
|
|
" <th>6</th>\n",
|
|
|
|
|
" <th>7</th>\n",
|
|
|
|
|
" <th>8</th>\n",
|
|
|
|
|
" <th>9</th>\n",
|
|
|
|
|
" <th>...</th>\n",
|
|
|
|
|
" <th>15</th>\n",
|
|
|
|
|
" <th>16</th>\n",
|
|
|
|
|
" <th>17</th>\n",
|
|
|
|
|
" <th>18</th>\n",
|
|
|
|
|
" <th>19</th>\n",
|
|
|
|
|
" <th>20</th>\n",
|
|
|
|
|
" <th>21</th>\n",
|
|
|
|
|
" <th>22</th>\n",
|
|
|
|
|
" <th>23</th>\n",
|
|
|
|
|
" <th>24</th>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </thead>\n",
|
|
|
|
|
" <tbody>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>0</th>\n",
|
|
|
|
|
" <td>do wykończenia</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>6938</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/nowe-mieszkanie-z...</td>\n",
|
|
|
|
|
" <td>3</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>61.99</td>\n",
|
|
|
|
|
" <td>pierwotny</td>\n",
|
|
|
|
|
" <td>7.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>2020.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>Prezentujemy naszą najnowszą inwestycje zloka...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, drzwi / ...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>1</th>\n",
|
|
|
|
|
" <td>do zamieszkania</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>6078</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/3-pok-parter-nisk...</td>\n",
|
|
|
|
|
" <td>4</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>64.00</td>\n",
|
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>4.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>miejskie</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>1982.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>wielka płyta</td>\n",
|
|
|
|
|
" <td>Polecam na sprzedaż duże atrakcyjnie zlokaliz...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>domofon / wideofon, balkon</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2</th>\n",
|
|
|
|
|
" <td>do wykończenia</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>6150</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/hot-oferta-od-dew...</td>\n",
|
|
|
|
|
" <td>3</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>51.15</td>\n",
|
|
|
|
|
" <td>pierwotny</td>\n",
|
|
|
|
|
" <td>5.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>miejskie</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>2020.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>cegła</td>\n",
|
|
|
|
|
" <td>&gt...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, domofon ...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>3</th>\n",
|
|
|
|
|
" <td>do zamieszkania</td>\n",
|
|
|
|
|
" <td>350 zł</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>9373</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkanie-z-ogro...</td>\n",
|
|
|
|
|
" <td>2</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>45.77</td>\n",
|
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>7.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>!! OFERTA BEZPOŚREDNIA !! Na sprzedaż mieszkan...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, drzwi / ...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>4</th>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>7200</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/osiedle-nowych-ko...</td>\n",
|
|
|
|
|
" <td>2</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>44.36</td>\n",
|
|
|
|
|
" <td>pierwotny</td>\n",
|
|
|
|
|
" <td>13.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>2020-08-01</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>Inwestycja NOWYCH KOSMONAUTÓW powstaje u zbie...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, drzwi / ...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>...</th>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>413</th>\n",
|
|
|
|
|
" <td>do wykończenia</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>7150</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/zielony-marcelin-...</td>\n",
|
|
|
|
|
" <td>1</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>34.97</td>\n",
|
|
|
|
|
" <td>pierwotny</td>\n",
|
|
|
|
|
" <td>8.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>miejskie</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>Zielony Marcelin I etap mieszkanie nr 407, 1 ...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, drzwi / ...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>414</th>\n",
|
|
|
|
|
" <td>do wykończenia</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>6499</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/nowe-mieszkanie-p...</td>\n",
|
|
|
|
|
" <td>3</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>49.06</td>\n",
|
|
|
|
|
" <td>pierwotny</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>kotłownia</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>2018.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>2018-12-31</td>\n",
|
|
|
|
|
" <td>silikat</td>\n",
|
|
|
|
|
" <td>Mieszkanie składa się z 3 pokoi z aneksem kuc...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, domofon ...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>415</th>\n",
|
|
|
|
|
" <td>do wykończenia</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>9451</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkanie-76-71-...</td>\n",
|
|
|
|
|
" <td>3</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>76.71</td>\n",
|
|
|
|
|
" <td>pierwotny</td>\n",
|
|
|
|
|
" <td>5.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>2019.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>Zapraszam do zapoznania się z nową atrakcyjną...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>monitoring / ochrona, garaż/miejsce parkingowe...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>416</th>\n",
|
|
|
|
|
" <td>do wykończenia</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>9322</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/mieszkanie-zajezd...</td>\n",
|
|
|
|
|
" <td>3</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>72.63</td>\n",
|
|
|
|
|
" <td>pierwotny</td>\n",
|
|
|
|
|
" <td>5.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>Zapraszam do zapoznania się z nową atrakcyjną...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>garaż/miejsce parkingowe, winda</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>417</th>\n",
|
|
|
|
|
" <td>do wykończenia</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pełna własność</td>\n",
|
|
|
|
|
" <td>6500</td>\n",
|
|
|
|
|
" <td>https://www.otodom.pl/oferta/nowe-mieszkanie-w...</td>\n",
|
|
|
|
|
" <td>2</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>65.84</td>\n",
|
|
|
|
|
" <td>wtórny</td>\n",
|
|
|
|
|
" <td>10.0</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>miejskie</td>\n",
|
|
|
|
|
" <td>plastikowe</td>\n",
|
|
|
|
|
" <td>2012.0</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>pustak</td>\n",
|
|
|
|
|
" <td>Super mieszkanie 2-pokojowe 65,84m2. wykończo...</td>\n",
|
|
|
|
|
" <td>NaN</td>\n",
|
|
|
|
|
" <td>telewizja kablowa, internet, telefon, monitori...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </tbody>\n",
|
|
|
|
|
"</table>\n",
|
|
|
|
|
"<p>418 rows × 25 columns</p>\n",
|
|
|
|
|
"</div>"
|
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
|
|
|
|
" 0 1 2 3 \\\n",
|
|
|
|
|
"0 do wykończenia NaN pełna własność 6938 \n",
|
|
|
|
|
"1 do zamieszkania NaN pełna własność 6078 \n",
|
|
|
|
|
"2 do wykończenia NaN pełna własność 6150 \n",
|
|
|
|
|
"3 do zamieszkania 350 zł pełna własność 9373 \n",
|
|
|
|
|
"4 NaN NaN NaN 7200 \n",
|
|
|
|
|
".. ... ... ... ... \n",
|
|
|
|
|
"413 do wykończenia NaN NaN 7150 \n",
|
|
|
|
|
"414 do wykończenia NaN pełna własność 6499 \n",
|
|
|
|
|
"415 do wykończenia NaN pełna własność 9451 \n",
|
|
|
|
|
"416 do wykończenia NaN pełna własność 9322 \n",
|
|
|
|
|
"417 do wykończenia NaN pełna własność 6500 \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" 4 5 6 7 \\\n",
|
|
|
|
|
"0 https://www.otodom.pl/oferta/nowe-mieszkanie-z... 3 NaN 61.99 \n",
|
|
|
|
|
"1 https://www.otodom.pl/oferta/3-pok-parter-nisk... 4 NaN 64.00 \n",
|
|
|
|
|
"2 https://www.otodom.pl/oferta/hot-oferta-od-dew... 3 NaN 51.15 \n",
|
|
|
|
|
"3 https://www.otodom.pl/oferta/mieszkanie-z-ogro... 2 NaN 45.77 \n",
|
|
|
|
|
"4 https://www.otodom.pl/oferta/osiedle-nowych-ko... 2 NaN 44.36 \n",
|
|
|
|
|
".. ... .. .. ... \n",
|
|
|
|
|
"413 https://www.otodom.pl/oferta/zielony-marcelin-... 1 NaN 34.97 \n",
|
|
|
|
|
"414 https://www.otodom.pl/oferta/nowe-mieszkanie-p... 3 NaN 49.06 \n",
|
|
|
|
|
"415 https://www.otodom.pl/oferta/mieszkanie-76-71-... 3 NaN 76.71 \n",
|
|
|
|
|
"416 https://www.otodom.pl/oferta/mieszkanie-zajezd... 3 NaN 72.63 \n",
|
|
|
|
|
"417 https://www.otodom.pl/oferta/nowe-mieszkanie-w... 2 NaN 65.84 \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" 8 9 ... 15 16 17 18 19 20 \\\n",
|
|
|
|
|
"0 pierwotny 7.0 ... NaN NaN plastikowe 2020.0 NaN NaN \n",
|
|
|
|
|
"1 wtórny 4.0 ... NaN miejskie NaN 1982.0 NaN NaN \n",
|
|
|
|
|
"2 pierwotny 5.0 ... NaN miejskie plastikowe 2020.0 NaN NaN \n",
|
|
|
|
|
"3 wtórny 7.0 ... NaN NaN NaN NaN NaN NaN \n",
|
|
|
|
|
"4 pierwotny 13.0 ... NaN NaN plastikowe NaN NaN 2020-08-01 \n",
|
|
|
|
|
".. ... ... ... .. ... ... ... .. ... \n",
|
|
|
|
|
"413 pierwotny 8.0 ... NaN miejskie plastikowe NaN NaN NaN \n",
|
|
|
|
|
"414 pierwotny 3.0 ... NaN kotłownia plastikowe 2018.0 NaN 2018-12-31 \n",
|
|
|
|
|
"415 pierwotny 5.0 ... NaN NaN plastikowe 2019.0 NaN NaN \n",
|
|
|
|
|
"416 pierwotny 5.0 ... NaN NaN NaN NaN NaN NaN \n",
|
|
|
|
|
"417 wtórny 10.0 ... NaN miejskie plastikowe 2012.0 NaN NaN \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" 21 22 23 \\\n",
|
|
|
|
|
"0 NaN Prezentujemy naszą najnowszą inwestycje zloka... NaN \n",
|
|
|
|
|
"1 wielka płyta Polecam na sprzedaż duże atrakcyjnie zlokaliz... NaN \n",
|
|
|
|
|
"2 cegła >... NaN \n",
|
|
|
|
|
"3 NaN !! OFERTA BEZPOŚREDNIA !! Na sprzedaż mieszkan... NaN \n",
|
|
|
|
|
"4 NaN Inwestycja NOWYCH KOSMONAUTÓW powstaje u zbie... NaN \n",
|
|
|
|
|
".. ... ... .. \n",
|
|
|
|
|
"413 NaN Zielony Marcelin I etap mieszkanie nr 407, 1 ... NaN \n",
|
|
|
|
|
"414 silikat Mieszkanie składa się z 3 pokoi z aneksem kuc... NaN \n",
|
|
|
|
|
"415 NaN Zapraszam do zapoznania się z nową atrakcyjną... NaN \n",
|
|
|
|
|
"416 NaN Zapraszam do zapoznania się z nową atrakcyjną... NaN \n",
|
|
|
|
|
"417 pustak Super mieszkanie 2-pokojowe 65,84m2. wykończo... NaN \n",
|
|
|
|
|
"\n",
|
|
|
|
|
" 24 \n",
|
|
|
|
|
"0 telewizja kablowa, internet, telefon, drzwi / ... \n",
|
|
|
|
|
"1 domofon / wideofon, balkon \n",
|
|
|
|
|
"2 telewizja kablowa, internet, telefon, domofon ... \n",
|
|
|
|
|
"3 telewizja kablowa, internet, telefon, drzwi / ... \n",
|
|
|
|
|
"4 telewizja kablowa, internet, telefon, drzwi / ... \n",
|
|
|
|
|
".. ... \n",
|
|
|
|
|
"413 telewizja kablowa, internet, telefon, drzwi / ... \n",
|
|
|
|
|
"414 telewizja kablowa, internet, telefon, domofon ... \n",
|
|
|
|
|
"415 monitoring / ochrona, garaż/miejsce parkingowe... \n",
|
|
|
|
|
"416 garaż/miejsce parkingowe, winda \n",
|
|
|
|
|
"417 telewizja kablowa, internet, telefon, monitori... \n",
|
|
|
|
|
"\n",
|
|
|
|
|
"[418 rows x 25 columns]"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 10,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_test"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"## Wybranie interesujących nas kolumn (cena, ilość pokoi, metraż, rok budowy)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 11,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_train = df_train[[0, 6, 8, 19]]"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 12,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid[0] = df_valid_cena"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 13,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid = df_valid[[0, 5, 7, 18]]"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 14,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_test = df_test[[5, 7, 18]]"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"## Zamiana nazw kolumn"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 15,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_train = df_train.rename(columns = {0:\"cena\", 6:\"pokoje\", 8:\"metraz\", 19:\"rok\"})"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 16,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid = df_valid.rename(columns = {0:\"cena\", 5:\"pokoje\", 7:\"metraz\", 18:\"rok\"})"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 17,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_test = df_test.rename(columns = {5:\"pokoje\", 7:\"metraz\", 18:\"rok\"})"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"## Czyszczenie danych"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Czyszczenie danych treningowych"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 18,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_train = df_train.dropna()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 19,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_train = df_train.replace( \"więcej niż 10\", '11')"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 20,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_train = df_train[(df_train['rok'] >= 1800) & (df_train['rok'] <= 2023)]\n"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 21,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_train = df_train[df_train[\"metraz\"] != '6 909']\n"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 22,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_train[\"pokoje\"] = df_train[\"pokoje\"].astype(float)\n",
|
|
|
|
|
"df_train[\"metraz\"] = df_train[\"metraz\"].astype(float)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 23,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
|
|
|
|
"<div>\n",
|
|
|
|
|
"<style scoped>\n",
|
|
|
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
|
|
|
" vertical-align: middle;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe tbody tr th {\n",
|
|
|
|
|
" vertical-align: top;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe thead th {\n",
|
|
|
|
|
" text-align: right;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"</style>\n",
|
|
|
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
|
|
|
" <thead>\n",
|
|
|
|
|
" <tr style=\"text-align: right;\">\n",
|
|
|
|
|
" <th></th>\n",
|
|
|
|
|
" <th>cena</th>\n",
|
|
|
|
|
" <th>pokoje</th>\n",
|
|
|
|
|
" <th>metraz</th>\n",
|
|
|
|
|
" <th>rok</th>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </thead>\n",
|
|
|
|
|
" <tbody>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>count</th>\n",
|
|
|
|
|
" <td>1.763000e+03</td>\n",
|
|
|
|
|
" <td>1763.000000</td>\n",
|
|
|
|
|
" <td>1763.000000</td>\n",
|
|
|
|
|
" <td>1763.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>mean</th>\n",
|
|
|
|
|
" <td>4.262096e+05</td>\n",
|
|
|
|
|
" <td>2.609756</td>\n",
|
|
|
|
|
" <td>60.068327</td>\n",
|
|
|
|
|
" <td>1992.024957</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>std</th>\n",
|
|
|
|
|
" <td>2.478208e+05</td>\n",
|
|
|
|
|
" <td>1.038289</td>\n",
|
|
|
|
|
" <td>29.652713</td>\n",
|
|
|
|
|
" <td>37.968540</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>min</th>\n",
|
|
|
|
|
" <td>8.500000e+04</td>\n",
|
|
|
|
|
" <td>1.000000</td>\n",
|
|
|
|
|
" <td>19.000000</td>\n",
|
|
|
|
|
" <td>1840.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>25%</th>\n",
|
|
|
|
|
" <td>3.100000e+05</td>\n",
|
|
|
|
|
" <td>2.000000</td>\n",
|
|
|
|
|
" <td>43.000000</td>\n",
|
|
|
|
|
" <td>1976.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>50%</th>\n",
|
|
|
|
|
" <td>3.671000e+05</td>\n",
|
|
|
|
|
" <td>2.000000</td>\n",
|
|
|
|
|
" <td>52.300000</td>\n",
|
|
|
|
|
" <td>2010.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>75%</th>\n",
|
|
|
|
|
" <td>4.700000e+05</td>\n",
|
|
|
|
|
" <td>3.000000</td>\n",
|
|
|
|
|
" <td>68.000000</td>\n",
|
|
|
|
|
" <td>2019.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>max</th>\n",
|
|
|
|
|
" <td>6.000000e+06</td>\n",
|
|
|
|
|
" <td>11.000000</td>\n",
|
|
|
|
|
" <td>404.000000</td>\n",
|
|
|
|
|
" <td>2022.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </tbody>\n",
|
|
|
|
|
"</table>\n",
|
|
|
|
|
"</div>"
|
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
|
|
|
|
" cena pokoje metraz rok\n",
|
|
|
|
|
"count 1.763000e+03 1763.000000 1763.000000 1763.000000\n",
|
|
|
|
|
"mean 4.262096e+05 2.609756 60.068327 1992.024957\n",
|
|
|
|
|
"std 2.478208e+05 1.038289 29.652713 37.968540\n",
|
|
|
|
|
"min 8.500000e+04 1.000000 19.000000 1840.000000\n",
|
|
|
|
|
"25% 3.100000e+05 2.000000 43.000000 1976.000000\n",
|
|
|
|
|
"50% 3.671000e+05 2.000000 52.300000 2010.000000\n",
|
|
|
|
|
"75% 4.700000e+05 3.000000 68.000000 2019.000000\n",
|
|
|
|
|
"max 6.000000e+06 11.000000 404.000000 2022.000000"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 23,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_train.describe()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 24,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
|
|
|
|
"<div>\n",
|
|
|
|
|
"<style scoped>\n",
|
|
|
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
|
|
|
" vertical-align: middle;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe tbody tr th {\n",
|
|
|
|
|
" vertical-align: top;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe thead th {\n",
|
|
|
|
|
" text-align: right;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"</style>\n",
|
|
|
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
|
|
|
" <thead>\n",
|
|
|
|
|
" <tr style=\"text-align: right;\">\n",
|
|
|
|
|
" <th></th>\n",
|
|
|
|
|
" <th>cena</th>\n",
|
|
|
|
|
" <th>pokoje</th>\n",
|
|
|
|
|
" <th>metraz</th>\n",
|
|
|
|
|
" <th>rok</th>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </thead>\n",
|
|
|
|
|
" <tbody>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2</th>\n",
|
|
|
|
|
" <td>249000.0</td>\n",
|
|
|
|
|
" <td>2.0</td>\n",
|
|
|
|
|
" <td>44.30</td>\n",
|
|
|
|
|
" <td>1960.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>6</th>\n",
|
|
|
|
|
" <td>449000.0</td>\n",
|
|
|
|
|
" <td>4.0</td>\n",
|
|
|
|
|
" <td>92.00</td>\n",
|
|
|
|
|
" <td>1930.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>7</th>\n",
|
|
|
|
|
" <td>389000.0</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>63.60</td>\n",
|
|
|
|
|
" <td>1985.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>9</th>\n",
|
|
|
|
|
" <td>260000.0</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>44.20</td>\n",
|
|
|
|
|
" <td>1970.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>10</th>\n",
|
|
|
|
|
" <td>330682.0</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>48.99</td>\n",
|
|
|
|
|
" <td>2019.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>...</th>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2541</th>\n",
|
|
|
|
|
" <td>383680.0</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>70.40</td>\n",
|
|
|
|
|
" <td>2016.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2542</th>\n",
|
|
|
|
|
" <td>507600.0</td>\n",
|
|
|
|
|
" <td>4.0</td>\n",
|
|
|
|
|
" <td>94.00</td>\n",
|
|
|
|
|
" <td>1914.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2543</th>\n",
|
|
|
|
|
" <td>342400.0</td>\n",
|
|
|
|
|
" <td>2.0</td>\n",
|
|
|
|
|
" <td>53.50</td>\n",
|
|
|
|
|
" <td>1999.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2544</th>\n",
|
|
|
|
|
" <td>335000.0</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>55.25</td>\n",
|
|
|
|
|
" <td>1910.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2545</th>\n",
|
|
|
|
|
" <td>260000.0</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>62.00</td>\n",
|
|
|
|
|
" <td>1930.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </tbody>\n",
|
|
|
|
|
"</table>\n",
|
|
|
|
|
"<p>1763 rows × 4 columns</p>\n",
|
|
|
|
|
"</div>"
|
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
|
|
|
|
" cena pokoje metraz rok\n",
|
|
|
|
|
"2 249000.0 2.0 44.30 1960.0\n",
|
|
|
|
|
"6 449000.0 4.0 92.00 1930.0\n",
|
|
|
|
|
"7 389000.0 3.0 63.60 1985.0\n",
|
|
|
|
|
"9 260000.0 3.0 44.20 1970.0\n",
|
|
|
|
|
"10 330682.0 3.0 48.99 2019.0\n",
|
|
|
|
|
"... ... ... ... ...\n",
|
|
|
|
|
"2541 383680.0 3.0 70.40 2016.0\n",
|
|
|
|
|
"2542 507600.0 4.0 94.00 1914.0\n",
|
|
|
|
|
"2543 342400.0 2.0 53.50 1999.0\n",
|
|
|
|
|
"2544 335000.0 3.0 55.25 1910.0\n",
|
|
|
|
|
"2545 260000.0 3.0 62.00 1930.0\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"[1763 rows x 4 columns]"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 24,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_train"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Czyszczenie danych walidacyjnych"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 25,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
|
|
|
|
"<div>\n",
|
|
|
|
|
"<style scoped>\n",
|
|
|
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
|
|
|
" vertical-align: middle;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe tbody tr th {\n",
|
|
|
|
|
" vertical-align: top;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe thead th {\n",
|
|
|
|
|
" text-align: right;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"</style>\n",
|
|
|
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
|
|
|
" <thead>\n",
|
|
|
|
|
" <tr style=\"text-align: right;\">\n",
|
|
|
|
|
" <th></th>\n",
|
|
|
|
|
" <th>cena</th>\n",
|
|
|
|
|
" <th>pokoje</th>\n",
|
|
|
|
|
" <th>metraz</th>\n",
|
|
|
|
|
" <th>rok</th>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </thead>\n",
|
|
|
|
|
" <tbody>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>count</th>\n",
|
|
|
|
|
" <td>4.620000e+02</td>\n",
|
|
|
|
|
" <td>462.000000</td>\n",
|
|
|
|
|
" <td>462.000000</td>\n",
|
|
|
|
|
" <td>322.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>mean</th>\n",
|
|
|
|
|
" <td>4.108530e+05</td>\n",
|
|
|
|
|
" <td>2.528139</td>\n",
|
|
|
|
|
" <td>57.329113</td>\n",
|
|
|
|
|
" <td>1988.605590</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>std</th>\n",
|
|
|
|
|
" <td>2.049347e+05</td>\n",
|
|
|
|
|
" <td>0.953512</td>\n",
|
|
|
|
|
" <td>25.300686</td>\n",
|
|
|
|
|
" <td>113.363432</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>min</th>\n",
|
|
|
|
|
" <td>1.597610e+05</td>\n",
|
|
|
|
|
" <td>1.000000</td>\n",
|
|
|
|
|
" <td>1.000000</td>\n",
|
|
|
|
|
" <td>70.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>25%</th>\n",
|
|
|
|
|
" <td>2.984000e+05</td>\n",
|
|
|
|
|
" <td>2.000000</td>\n",
|
|
|
|
|
" <td>42.000000</td>\n",
|
|
|
|
|
" <td>1980.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>50%</th>\n",
|
|
|
|
|
" <td>3.520765e+05</td>\n",
|
|
|
|
|
" <td>2.000000</td>\n",
|
|
|
|
|
" <td>50.510000</td>\n",
|
|
|
|
|
" <td>2013.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>75%</th>\n",
|
|
|
|
|
" <td>4.687800e+05</td>\n",
|
|
|
|
|
" <td>3.000000</td>\n",
|
|
|
|
|
" <td>66.315000</td>\n",
|
|
|
|
|
" <td>2019.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>max</th>\n",
|
|
|
|
|
" <td>2.318580e+06</td>\n",
|
|
|
|
|
" <td>6.000000</td>\n",
|
|
|
|
|
" <td>234.200000</td>\n",
|
|
|
|
|
" <td>2021.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </tbody>\n",
|
|
|
|
|
"</table>\n",
|
|
|
|
|
"</div>"
|
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
|
|
|
|
" cena pokoje metraz rok\n",
|
|
|
|
|
"count 4.620000e+02 462.000000 462.000000 322.000000\n",
|
|
|
|
|
"mean 4.108530e+05 2.528139 57.329113 1988.605590\n",
|
|
|
|
|
"std 2.049347e+05 0.953512 25.300686 113.363432\n",
|
|
|
|
|
"min 1.597610e+05 1.000000 1.000000 70.000000\n",
|
|
|
|
|
"25% 2.984000e+05 2.000000 42.000000 1980.000000\n",
|
|
|
|
|
"50% 3.520765e+05 2.000000 50.510000 2013.000000\n",
|
|
|
|
|
"75% 4.687800e+05 3.000000 66.315000 2019.000000\n",
|
|
|
|
|
"max 2.318580e+06 6.000000 234.200000 2021.000000"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 25,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid.describe()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 26,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid = df_valid.dropna()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 27,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid = df_valid[df_valid['metraz'] > 10]"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 28,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid = df_valid[(df_valid['rok'] >= 1800) & (df_valid['rok'] <= 2023)]\n"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 29,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid = df_valid.replace( \"więcej niż 10\", '11')"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 30,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid[\"pokoje\"] = df_valid[\"pokoje\"].astype(float)\n",
|
|
|
|
|
"df_valid[\"metraz\"] = df_valid[\"metraz\"].astype(float)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 31,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
|
|
|
|
"<div>\n",
|
|
|
|
|
"<style scoped>\n",
|
|
|
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
|
|
|
" vertical-align: middle;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe tbody tr th {\n",
|
|
|
|
|
" vertical-align: top;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe thead th {\n",
|
|
|
|
|
" text-align: right;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"</style>\n",
|
|
|
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
|
|
|
" <thead>\n",
|
|
|
|
|
" <tr style=\"text-align: right;\">\n",
|
|
|
|
|
" <th></th>\n",
|
|
|
|
|
" <th>cena</th>\n",
|
|
|
|
|
" <th>pokoje</th>\n",
|
|
|
|
|
" <th>metraz</th>\n",
|
|
|
|
|
" <th>rok</th>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </thead>\n",
|
|
|
|
|
" <tbody>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>2</th>\n",
|
|
|
|
|
" <td>365000.00</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>63.84</td>\n",
|
|
|
|
|
" <td>1958.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>3</th>\n",
|
|
|
|
|
" <td>369000.00</td>\n",
|
|
|
|
|
" <td>4.0</td>\n",
|
|
|
|
|
" <td>50.00</td>\n",
|
|
|
|
|
" <td>1975.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>4</th>\n",
|
|
|
|
|
" <td>483791.00</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>65.62</td>\n",
|
|
|
|
|
" <td>2020.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>5</th>\n",
|
|
|
|
|
" <td>430000.00</td>\n",
|
|
|
|
|
" <td>5.0</td>\n",
|
|
|
|
|
" <td>96.00</td>\n",
|
|
|
|
|
" <td>2019.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>9</th>\n",
|
|
|
|
|
" <td>325000.00</td>\n",
|
|
|
|
|
" <td>2.0</td>\n",
|
|
|
|
|
" <td>49.00</td>\n",
|
|
|
|
|
" <td>2001.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>...</th>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>455</th>\n",
|
|
|
|
|
" <td>641395.58</td>\n",
|
|
|
|
|
" <td>2.0</td>\n",
|
|
|
|
|
" <td>72.78</td>\n",
|
|
|
|
|
" <td>2019.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>457</th>\n",
|
|
|
|
|
" <td>655544.02</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>72.78</td>\n",
|
|
|
|
|
" <td>2019.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>459</th>\n",
|
|
|
|
|
" <td>309958.00</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>54.16</td>\n",
|
|
|
|
|
" <td>2019.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>460</th>\n",
|
|
|
|
|
" <td>699000.00</td>\n",
|
|
|
|
|
" <td>3.0</td>\n",
|
|
|
|
|
" <td>90.10</td>\n",
|
|
|
|
|
" <td>2001.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>461</th>\n",
|
|
|
|
|
" <td>850000.00</td>\n",
|
|
|
|
|
" <td>2.0</td>\n",
|
|
|
|
|
" <td>71.90</td>\n",
|
|
|
|
|
" <td>2016.0</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </tbody>\n",
|
|
|
|
|
"</table>\n",
|
|
|
|
|
"<p>320 rows × 4 columns</p>\n",
|
|
|
|
|
"</div>"
|
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
|
|
|
|
" cena pokoje metraz rok\n",
|
|
|
|
|
"2 365000.00 3.0 63.84 1958.0\n",
|
|
|
|
|
"3 369000.00 4.0 50.00 1975.0\n",
|
|
|
|
|
"4 483791.00 3.0 65.62 2020.0\n",
|
|
|
|
|
"5 430000.00 5.0 96.00 2019.0\n",
|
|
|
|
|
"9 325000.00 2.0 49.00 2001.0\n",
|
|
|
|
|
".. ... ... ... ...\n",
|
|
|
|
|
"455 641395.58 2.0 72.78 2019.0\n",
|
|
|
|
|
"457 655544.02 3.0 72.78 2019.0\n",
|
|
|
|
|
"459 309958.00 3.0 54.16 2019.0\n",
|
|
|
|
|
"460 699000.00 3.0 90.10 2001.0\n",
|
|
|
|
|
"461 850000.00 2.0 71.90 2016.0\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"[320 rows x 4 columns]"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 31,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_valid"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Czyszczenie danych testowych"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 32,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"df_test['rok'].fillna(df_test['rok'].mean(), inplace=True)"
|
2023-10-17 17:45:35 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 33,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"df_test = df_test.dropna()"
|
2023-10-17 17:45:35 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"execution_count": 34,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"source": [
|
|
|
|
|
"df_test = df_test.replace( \"więcej niż 10\", '11')"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
|
|
|
|
"execution_count": 35,
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"source": [
|
|
|
|
|
"df_test[\"pokoje\"] = df_test[\"pokoje\"].astype(float)\n",
|
|
|
|
|
"df_test[\"metraz\"] = df_test[\"metraz\"].astype(float)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 36,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
|
|
|
|
"<div>\n",
|
|
|
|
|
"<style scoped>\n",
|
|
|
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
|
|
|
" vertical-align: middle;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe tbody tr th {\n",
|
|
|
|
|
" vertical-align: top;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe thead th {\n",
|
|
|
|
|
" text-align: right;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"</style>\n",
|
|
|
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
|
|
|
" <thead>\n",
|
|
|
|
|
" <tr style=\"text-align: right;\">\n",
|
|
|
|
|
" <th></th>\n",
|
|
|
|
|
" <th>cena</th>\n",
|
|
|
|
|
" <th>pokoje</th>\n",
|
|
|
|
|
" <th>metraz</th>\n",
|
|
|
|
|
" <th>rok</th>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </thead>\n",
|
|
|
|
|
" <tbody>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>count</th>\n",
|
|
|
|
|
" <td>1.763000e+03</td>\n",
|
|
|
|
|
" <td>1763.000000</td>\n",
|
|
|
|
|
" <td>1763.000000</td>\n",
|
|
|
|
|
" <td>1763.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>mean</th>\n",
|
|
|
|
|
" <td>4.262096e+05</td>\n",
|
|
|
|
|
" <td>2.609756</td>\n",
|
|
|
|
|
" <td>60.068327</td>\n",
|
|
|
|
|
" <td>1992.024957</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>std</th>\n",
|
|
|
|
|
" <td>2.478208e+05</td>\n",
|
|
|
|
|
" <td>1.038289</td>\n",
|
|
|
|
|
" <td>29.652713</td>\n",
|
|
|
|
|
" <td>37.968540</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>min</th>\n",
|
|
|
|
|
" <td>8.500000e+04</td>\n",
|
|
|
|
|
" <td>1.000000</td>\n",
|
|
|
|
|
" <td>19.000000</td>\n",
|
|
|
|
|
" <td>1840.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>25%</th>\n",
|
|
|
|
|
" <td>3.100000e+05</td>\n",
|
|
|
|
|
" <td>2.000000</td>\n",
|
|
|
|
|
" <td>43.000000</td>\n",
|
|
|
|
|
" <td>1976.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>50%</th>\n",
|
|
|
|
|
" <td>3.671000e+05</td>\n",
|
|
|
|
|
" <td>2.000000</td>\n",
|
|
|
|
|
" <td>52.300000</td>\n",
|
|
|
|
|
" <td>2010.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>75%</th>\n",
|
|
|
|
|
" <td>4.700000e+05</td>\n",
|
|
|
|
|
" <td>3.000000</td>\n",
|
|
|
|
|
" <td>68.000000</td>\n",
|
|
|
|
|
" <td>2019.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>max</th>\n",
|
|
|
|
|
" <td>6.000000e+06</td>\n",
|
|
|
|
|
" <td>11.000000</td>\n",
|
|
|
|
|
" <td>404.000000</td>\n",
|
|
|
|
|
" <td>2022.000000</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </tbody>\n",
|
|
|
|
|
"</table>\n",
|
|
|
|
|
"</div>"
|
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
|
|
|
|
" cena pokoje metraz rok\n",
|
|
|
|
|
"count 1.763000e+03 1763.000000 1763.000000 1763.000000\n",
|
|
|
|
|
"mean 4.262096e+05 2.609756 60.068327 1992.024957\n",
|
|
|
|
|
"std 2.478208e+05 1.038289 29.652713 37.968540\n",
|
|
|
|
|
"min 8.500000e+04 1.000000 19.000000 1840.000000\n",
|
|
|
|
|
"25% 3.100000e+05 2.000000 43.000000 1976.000000\n",
|
|
|
|
|
"50% 3.671000e+05 2.000000 52.300000 2010.000000\n",
|
|
|
|
|
"75% 4.700000e+05 3.000000 68.000000 2019.000000\n",
|
|
|
|
|
"max 6.000000e+06 11.000000 404.000000 2022.000000"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 36,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"df_train.describe()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"## Model regresji liniowej"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 37,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"from sklearn.linear_model import LinearRegression"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Podział danych"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 38,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"X_train = df_train[[\"pokoje\", \"metraz\", \"rok\"]]\n",
|
|
|
|
|
"y_train = df_train[[\"cena\"]]"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 39,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"X_val = df_valid[[\"pokoje\", \"metraz\", \"rok\"]]\n",
|
|
|
|
|
"y_val = df_valid[[\"cena\"]]"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 40,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"X_test = df_test[[\"pokoje\", \"metraz\", \"rok\"]]"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Uczenie modelu"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 41,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"model = LinearRegression()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 42,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"<style>#sk-container-id-1 {color: black;}#sk-container-id-1 pre{padding: 0;}#sk-container-id-1 div.sk-toggleable {background-color: white;}#sk-container-id-1 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-1 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-1 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-1 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-1 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-1 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-1 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-1 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-1 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-1 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-1 div.sk-item {position: relative;z-index: 1;}#sk-container-id-1 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-1 div.sk-item::before, #sk-container-id-1 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-1 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-1 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-1 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-1 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-1 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-1 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-1 div.sk-label-container {text-align: center;}#sk-container-id-1 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-1 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-r
|
2023-10-17 17:45:35 +02:00
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"LinearRegression()"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 42,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"model.fit(X_train, y_train)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Walidacja modelu"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 43,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2023-10-24 17:58:23 +02:00
|
|
|
|
"from sklearn.metrics import mean_squared_error, r2_score, mean_absolute_error"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 44,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"y_train_pred = model.predict(X_train)"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 45,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"0.6264197107092035"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 45,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"r2_score(y_true=y_train, y_pred=y_train_pred)"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 46,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"22930468691.882328"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 46,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"mean_squared_error(y_true=y_train, y_pred=y_train_pred)"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 47,
|
2023-10-24 17:58:23 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"74283.11238859448"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 47,
|
2023-10-24 17:58:23 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"mean_absolute_error(y_true=y_train, y_pred=y_train_pred)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 48,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"y_val_pred = model.predict(X_val)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 49,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"0.5872189061243203"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 49,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"r2_score(y_true=y_val, y_pred=y_val_pred)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 50,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"12603444942.321444"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 50,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"mean_squared_error(y_true=y_val, y_pred=y_val_pred)"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 17:58:23 +02:00
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 51,
|
2023-10-24 17:58:23 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/plain": [
|
|
|
|
|
"68895.89161086899"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 51,
|
2023-10-24 17:58:23 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"mean_absolute_error(y_true=y_val, y_pred=y_val_pred)"
|
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-17 17:45:35 +02:00
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Predykcja cen mieszkań"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 52,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"y_test_pred = model.predict(X_test)"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 53,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/html": [
|
|
|
|
|
"<div>\n",
|
|
|
|
|
"<style scoped>\n",
|
|
|
|
|
" .dataframe tbody tr th:only-of-type {\n",
|
|
|
|
|
" vertical-align: middle;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe tbody tr th {\n",
|
|
|
|
|
" vertical-align: top;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"\n",
|
|
|
|
|
" .dataframe thead th {\n",
|
|
|
|
|
" text-align: right;\n",
|
|
|
|
|
" }\n",
|
|
|
|
|
"</style>\n",
|
|
|
|
|
"<table border=\"1\" class=\"dataframe\">\n",
|
|
|
|
|
" <thead>\n",
|
|
|
|
|
" <tr style=\"text-align: right;\">\n",
|
|
|
|
|
" <th></th>\n",
|
|
|
|
|
" <th>cena</th>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </thead>\n",
|
|
|
|
|
" <tbody>\n",
|
|
|
|
|
" <tr>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <th>0</th>\n",
|
|
|
|
|
" <td>445999.679659</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <th>1</th>\n",
|
|
|
|
|
" <td>391984.112513</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <th>2</th>\n",
|
|
|
|
|
" <td>361680.683534</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <th>3</th>\n",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
" <td>341889.696262</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <th>4</th>\n",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
" <td>330922.003962</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>...</th>\n",
|
|
|
|
|
" <td>...</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
" <th>413</th>\n",
|
|
|
|
|
" <td>299103.486333</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
" <th>414</th>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>343927.359472</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
" <th>415</th>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>559751.151754</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
" <th>416</th>\n",
|
|
|
|
|
" <td>509598.699344</td>\n",
|
|
|
|
|
" </tr>\n",
|
|
|
|
|
" <tr>\n",
|
|
|
|
|
" <th>417</th>\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" <td>511183.577622</td>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
" </tr>\n",
|
|
|
|
|
" </tbody>\n",
|
|
|
|
|
"</table>\n",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"<p>418 rows × 1 columns</p>\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"</div>"
|
|
|
|
|
],
|
|
|
|
|
"text/plain": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
" cena\n",
|
|
|
|
|
"0 445999.679659\n",
|
|
|
|
|
"1 391984.112513\n",
|
|
|
|
|
"2 361680.683534\n",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"3 341889.696262\n",
|
|
|
|
|
"4 330922.003962\n",
|
2023-10-17 17:45:35 +02:00
|
|
|
|
".. ...\n",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"413 299103.486333\n",
|
|
|
|
|
"414 343927.359472\n",
|
|
|
|
|
"415 559751.151754\n",
|
|
|
|
|
"416 509598.699344\n",
|
|
|
|
|
"417 511183.577622\n",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"\n",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"[418 rows x 1 columns]"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 53,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"y_test_pred_df = pd.DataFrame(y_test_pred, columns=['cena'])\n",
|
|
|
|
|
"y_test_pred_df"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"cell_type": "markdown",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"## Wizualizacja regresji liniowej"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 54,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"import matplotlib.pyplot as plt"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"cell_type": "markdown",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"### Cena nieruchomości ze względna na liczbę pokoi dla danych treningowych"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 55,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"image/png": "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
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"text/plain": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"<Figure size 640x480 with 1 Axes>"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {},
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"output_type": "display_data"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"coef = np.polyfit(X_train['pokoje'], y_train['cena'], 1)\n",
|
|
|
|
|
"poly1d_fn = np.poly1d(coef)\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"plt.plot(X_train['pokoje'], y_train['cena'], 'o', X_train['pokoje'], poly1d_fn(X_train['pokoje']), '--k')\n",
|
|
|
|
|
"plt.show()"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"cell_type": "markdown",
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"### Cena nieruchomości ze względna na rok wybudowania dla danych treningowych"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 56,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"image/png": "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
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"text/plain": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"<Figure size 640x480 with 1 Axes>"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {},
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"output_type": "display_data"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"coef = np.polyfit(X_train['rok'], y_train['cena'], 1)\n",
|
|
|
|
|
"poly1d_fn = np.poly1d(coef)\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"plt.plot(X_train['rok'], y_train['cena'], 'o', X_train['rok'], poly1d_fn(X_train['rok']), '--k')\n",
|
|
|
|
|
"plt.show()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Cena nieruchomości ze względna na metraż dla danych treningowych"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 57,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAhYAAAGsCAYAAACB/u5dAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8pXeV/AAAACXBIWXMAAA9hAAAPYQGoP6dpAABGMUlEQVR4nO3de1zUVf4/8NdwG0BgEBEBRcS7hJpXJPOSoqGmQlvburWa+tU0dTXbtqxtzdqifq3dy1pLWdfM1r5C3i95t/CGmhJeES8pFwW5wwAz5/cH35kcZgZm4DP31/Px4PHI+ZyZOacRP6/5fM55H5kQQoCIiIhIAm627gARERE5DwYLIiIikgyDBREREUmGwYKIiIgkw2BBREREkmGwICIiIskwWBAREZFkGCyIiIhIMgwWREREJBkGCyIiIpKMzYLFwYMHMXHiRISHh0MmkyEtLc3s1xBC4J///Ce6d+8OuVyO9u3b480335S+s0RERGQSD1u9cUVFBfr27YsZM2bg0UcfbdZrLFy4ELt27cI///lP9O7dG0VFRSgqKpK4p0RERGQqmT1sQiaTyZCamorExETtY0qlEq+88gq++eYbFBcXIyYmBu+88w5GjhwJADh37hz69OmDzMxM9OjRwzYdJyIiIh12O8di/vz5SE9Px/r163HmzBk8/vjjSEhIwKVLlwAAmzdvRufOnbFlyxZERUWhU6dO+J//+R9esSAiIrIhuwwW169fx+rVq7FhwwYMGzYMXbp0wV/+8hc8+OCDWL16NQDgypUruHbtGjZs2IA1a9YgJSUFGRkZeOyxx2zceyIiItdlszkWjTl79ixUKhW6d++u87hSqUSbNm0AAGq1GkqlEmvWrNG2++qrrzBgwABcuHCBt0eIiIhswC6DRXl5Odzd3ZGRkQF3d3edY35+fgCAsLAweHh46ISPXr16Aai/4sFgQUREZH12GSz69esHlUqFgoICDBs2zGCboUOHoq6uDtnZ2ejSpQsA4OLFiwCAyMhIq/WViIiIfmOzVSHl5eW4fPkygPog8d577+Ghhx5CUFAQOnbsiKeeego//vgjli9fjn79+uH27dvYs2cP+vTpgwkTJkCtVmPQoEHw8/PDBx98ALVajXnz5iEgIAC7du2yxZCIiIhcns2Cxf79+/HQQw/pPT5t2jSkpKSgtrYW//jHP7BmzRrcvHkTwcHBGDJkCJYtW4bevXsDAG7duoUFCxZg165daNWqFcaNG4fly5cjKCjI2sMhIiIi2EkdCyIiInIOdrnclIiIiBwTgwURERFJxuqrQtRqNW7dugV/f3/IZDJrvz0RERE1gxACZWVlCA8Ph5ub8esSVg8Wt27dQkREhLXfloiIiCRw48YNdOjQwehxqwcLf39/APUdCwgIsPbbExERUTOUlpYiIiJCex43xurBQnP7IyAggMGCiIjIwTQ1jYGTN4mIiEgyDBZEREQkGQYLIiIikgyDBREREUmGwYKIiIgkw2BBREREkmGwICIiIskwWBAREZFkrF4gi4iInI9KLXAspwgFZdUI8ffG4KgguLtxPyhXZHawuHnzJl588UVs374dlZWV6Nq1K1avXo2BAwdaon9ERGTndmTmYtnmLOSWVGsfC1N4Y+nEaCTEhNmwZ2QLZt0KuXv3LoYOHQpPT09s374dWVlZWL58OVq3bm2p/hERkR3bkZmLuWtP6oQKAMgrqcbctSexIzPXRj0jWzHrisU777yDiIgIrF69WvtYVFSU5J0iIiL7p1ILLNucBWHgmAAgA7BscxbGRIfytogLMeuKxaZNmzBw4EA8/vjjCAkJQb9+/bBy5cpGn6NUKlFaWqrzQ0REju9YTpHelYp7CQC5JdU4llNkvU6RzZkVLK5cuYIVK1agW7du2LlzJ+bOnYs///nP+Pe//230OcnJyVAoFNqfiIiIFneaiIhsr6DMeKhoTjtyDjIhhKGrWAZ5eXlh4MCB+Omnn7SP/fnPf8bx48eRnp5u8DlKpRJKpVL7Z81+7iUlJdw2nYjIgaVnF2LKyiNNtvtm1hDEdWljhR6RJZWWlkKhUDR5/jbrikVYWBiio6N1HuvVqxeuX79u9DlyuRwBAQE6P0RE5PgGRwUhTOENY7MnZKhfHTI4Ksia3SIbMytYDB06FBcuXNB57OLFi4iMjJS0U0REZP/c3WRYOrH+y2bDcKH589KJ0Zy46WLMChbPPfccjhw5grfeeguXL1/GunXr8K9//Qvz5s2zVP+IiMiOJcSEYcVT/RGq8NZ5PFThjRVP9WcdCxdk1hwLANiyZQuWLFmCS5cuISoqCosXL8asWbNMfr6p92iIiMhxsPKm8zP1/G12sGgpBgsiIiLHY5HJm0RERESNYbAgIiIiyTBYEBERkWQYLIiIiEgyDBZEREQkGQYLIiIikgyDBREREUmGwYKIiIgkw2BBREREkmGwICIiIskwWBAREZFkGCyIiIhIMgwWREREJBkGCyIiIpIMgwURERFJhsGCiIiIJMNgQURERJJhsCAiIiLJMFgQERGRZBgsiIiISDIMFkRERCQZBgsiIiKSDIMFERERSYbBgoiIiCTDYEFERESSYbAgIiIiyTBYEBERkWQYLIiIiEgyDBZEREQkGQYLIiIikgyDBREREUmGwYKIiIgkw2BBREREkmGwICIiIskwWBAREZFkGCyIiIhIMgwWREREJBkGCyIiIpIMgwURERFJhsGCiIiIJMNgQURERJJhsCAiIiLJMFgQERGRZBgsiIiISDIMFkRERCQZBgsiIiKSjFnB4rXXXoNMJtP56dmzp6X6RkRERA7Gw9wn3Hffffjhhx9+ewEPs1+CiIiInJTZqcDDwwOhoaGW6AsRERE5OLPnWFy6dAnh4eHo3LkznnzySVy/fr3R9kqlEqWlpTo/RERE5JzMChaxsbFISUnBjh07sGLFCuTk5GDYsGEoKysz+pzk5GQoFArtT0RERIs7TURERPZJJoQQzX1ycXExIiMj8d5772HmzJkG2yiVSiiVSu2fS0tLERERgZKSEgQEBDT3rYmIiMiKSktLoVAomjx/t2jmZWBgILp3747Lly8bbSOXyyGXy1vyNkREROQgWlTHory8HNnZ2QgLC5OqP0REROTAzAoWf/nLX3DgwAFcvXoVP/30E5KSkuDu7o4pU6ZYqn9ERETkQMy6FfLrr79iypQpKCwsRNu2bfHggw/iyJEjaNu2raX6R0RERA7ErGCxfv16S/WDiIiInAD3CiEiIiLJMFgQERGRZBgsiIiISDIMFkRERCQZBgsiIiKSDIMFERERSYbBgoiIiCTDYEFERESSYbAgIiIiyTBYEBERkWQYLIiIiEgyDBZEREQkGQYLIiIikgyDBREREUmGwYKIiIgkw2BBREREkmGwICIiIskwWBAREZFkGCyIiIhIMgwWREREJBkGCyIiIpIMgwURERFJhsGCiIiIJMNgQURERJJhsCAiIiLJMFgQERGRZBgsiIiISDIMFkRERCQZBgsiIiKSDIMFERERSYbBgoiIiCTDYEFERESSYbAgIiIiyTBYEBERkWQYLIiIiEgyDBZEREQkGQYLIiIikgyDBREREUmGwYKIiIgkw2BBREREkmGwICIiIskwWBAREZFkGCyIiIhIMgwWREREJBkGCyIiIpIMgwURERFJpkXB4u2334ZMJsOiRYsk6g4RERE5smYHi+PHj+OLL75Anz59pOwPERERObBmBYvy8nI8+eSTWLlyJVq3bi11n4iIiMhBNStYzJs3DxMmTEB8fHyTbZVKJUpLS3V+iIiIyDl5mPuE9evX4+TJkzh+/LhJ7ZOTk7Fs2TKzO0ZERESOx6wrFjdu3MDChQvx9ddfw9vb26TnLFmyBCUlJdqfGzduNKujREREZP9kQghhauO0tDQkJSXB3d1d+5hKpYJMJoObmxuUSqXOMUNKS0uhUChQUlKCgICA5veciIiIrMbU87dZt0JGjx6Ns2fP6jw2ffp09OzZEy+++GKToYKIiIicm1nBwt/fHzExMTqPtWrVCm3atNF7nIiIiFwPK28SERGRZMxeFdLQ/v37Jeg
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"text/plain": [
|
|
|
|
|
"<Figure size 640x480 with 1 Axes>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"coef = np.polyfit(X_train['metraz'], y_train['cena'], 1)\n",
|
|
|
|
|
"poly1d_fn = np.poly1d(coef)\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"plt.plot(X_train['metraz'], y_train['cena'], 'o', X_train['metraz'], poly1d_fn(X_train['metraz']), '--k')\n",
|
|
|
|
|
"plt.show()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Cena nieruchomości ze względna na liczbę pokoi dla danych testowych"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 58,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"image/png": "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
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"text/plain": [
|
|
|
|
|
"<Figure size 640x480 with 1 Axes>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"coef = np.polyfit(X_train['metraz'], y_train['cena'], 1)\n",
|
|
|
|
|
"poly1d_fn = np.poly1d(coef)\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"plt.plot(X_test['pokoje'], y_test_pred_df['cena'], 'yo', X_train['pokoje'], poly1d_fn(X_train['pokoje']), '--k')\n",
|
|
|
|
|
"plt.show()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Cena nieruchomości ze względna na rok wybudowania dla danych testowych"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 59,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"image/png": "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
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"text/plain": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"<Figure size 640x480 with 1 Axes>"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {},
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
|
|
|
|
"coef = np.polyfit(X_train['metraz'], y_train['cena'], 1)\n",
|
|
|
|
|
"poly1d_fn = np.poly1d(coef)\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"plt.plot(X_test['rok'], y_test_pred_df['cena'], 'yo', X_train['rok'], poly1d_fn(X_train['rok']), '--k')\n",
|
|
|
|
|
"plt.show()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Cena nieruchomości ze względna na metraż dla danych testowych"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 60,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
2023-10-17 17:30:25 +02:00
|
|
|
|
{
|
|
|
|
|
"data": {
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"image/png": "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
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"text/plain": [
|
|
|
|
|
"<Figure size 640x480 with 1 Axes>"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "display_data"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"coef = np.polyfit(X_train['metraz'], y_train['cena'], 1)\n",
|
|
|
|
|
"poly1d_fn = np.poly1d(coef)\n",
|
|
|
|
|
"\n",
|
|
|
|
|
"plt.plot(X_test['metraz'], y_test_pred_df['cena'], 'yo', X_train['metraz'], poly1d_fn(X_train['metraz']), '--k')\n",
|
|
|
|
|
"plt.show()"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"## Funkcja predykcji ceny mieszkania"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 61,
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"def cena_mieszkania(pokoje, metraz, rok):\n",
|
|
|
|
|
" mieszkanie = pd.DataFrame([[pokoje, metraz, rok]], columns=['pokoje', 'metraz', 'rok'])\n",
|
|
|
|
|
" cena = model.predict(mieszkanie).item()\n",
|
|
|
|
|
" return np.round(cena, 2)"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 62,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [
|
|
|
|
|
{
|
|
|
|
|
"data": {
|
|
|
|
|
"text/plain": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"184531.94"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 62,
|
2023-10-17 17:30:25 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"output_type": "execute_result"
|
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"source": [
|
2023-10-17 17:45:35 +02:00
|
|
|
|
"cena_mieszkania(pokoje=2, metraz=25, rok=2000)"
|
2023-10-17 17:30:25 +02:00
|
|
|
|
]
|
2023-10-17 18:50:02 +02:00
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 63,
|
2023-10-17 18:50:02 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"# Zapisanie modelu do pliku\n",
|
|
|
|
|
"import pickle\n",
|
|
|
|
|
"filename = 'mieszkania_model'\n",
|
|
|
|
|
"pickle.dump(model, open(filename, 'wb'))\n"
|
|
|
|
|
]
|
2023-10-24 17:58:23 +02:00
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"## Zapisywanie wyników"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Zapisywanie wyników zbioru walidacyjnego"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 64,
|
2023-10-24 17:58:23 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
|
|
|
|
"y_val_pred = pd.DataFrame(y_val_pred)"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 65,
|
2023-10-24 17:58:23 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"y_val_pred.to_csv(r'dev-0\\out.tsv', sep='\\t', header=None, index=None)"
|
2023-10-24 17:58:23 +02:00
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "markdown",
|
|
|
|
|
"metadata": {},
|
|
|
|
|
"source": [
|
|
|
|
|
"### Zapisywanie wyników zbioru testowego"
|
|
|
|
|
]
|
|
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
"cell_type": "code",
|
2023-10-24 18:48:16 +02:00
|
|
|
|
"execution_count": 66,
|
2023-10-24 17:58:23 +02:00
|
|
|
|
"metadata": {},
|
|
|
|
|
"outputs": [],
|
|
|
|
|
"source": [
|
2023-10-24 18:04:12 +02:00
|
|
|
|
"y_test_pred_df.to_csv(r'test-A\\out.tsv', sep='\\t', header=None, index=None)"
|
2023-10-24 17:58:23 +02:00
|
|
|
|
]
|
2023-10-17 17:30:25 +02:00
|
|
|
|
}
|
|
|
|
|
],
|
|
|
|
|
"metadata": {
|
|
|
|
|
"kernelspec": {
|
|
|
|
|
"display_name": "Python 3",
|
|
|
|
|
"language": "python",
|
|
|
|
|
"name": "python3"
|
|
|
|
|
},
|
|
|
|
|
"language_info": {
|
|
|
|
|
"codemirror_mode": {
|
|
|
|
|
"name": "ipython",
|
|
|
|
|
"version": 3
|
|
|
|
|
},
|
|
|
|
|
"file_extension": ".py",
|
|
|
|
|
"mimetype": "text/x-python",
|
|
|
|
|
"name": "python",
|
|
|
|
|
"nbconvert_exporter": "python",
|
|
|
|
|
"pygments_lexer": "ipython3",
|
|
|
|
|
"version": "3.10.11"
|
|
|
|
|
}
|
|
|
|
|
},
|
|
|
|
|
"nbformat": 4,
|
|
|
|
|
"nbformat_minor": 2
|
|
|
|
|
}
|