diff --git a/Lab1_zad2.ipynb b/Lab1_zad2.ipynb
index ad185a9..dfa3eba 100644
--- a/Lab1_zad2.ipynb
+++ b/Lab1_zad2.ipynb
@@ -1 +1 @@
-{"cells":[{"cell_type":"code","execution_count":232,"metadata":{"executionInfo":{"elapsed":422,"status":"ok","timestamp":1696951840697,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"veKEtGweNaXi"},"outputs":[],"source":["import pandas as pd\n","import numpy as np\n","import joblib\n"]},{"cell_type":"code","execution_count":191,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":4,"status":"ok","timestamp":1696952151344,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"w7poi-MONhxI","outputId":"379c3cbe-96bc-4d7e-d27f-dd56d02a817b"},"outputs":[],"source":["df_train = pd.read_csv('train.tsv', sep='\\t', header=None)"]},{"cell_type":"code","execution_count":192,"metadata":{"executionInfo":{"elapsed":226,"status":"ok","timestamp":1696952356655,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"8vT9n8oCPIhS"},"outputs":[],"source":["pd.set_option('display.max_columns', 500)"]},{"cell_type":"code","execution_count":193,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":643},"executionInfo":{"elapsed":254,"status":"ok","timestamp":1696952363298,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"hbfWxhoOOeQH","outputId":"3a4608d9-8d37-47c3-b28e-d64be0c43e2d"},"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>10</th>\n","      <th>11</th>\n","      <th>12</th>\n","      <th>13</th>\n","      <th>14</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","      <th>25</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>309000.0</td>\n","      <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","      <td>2</td>\n","      <td>NaN</td>\n","      <td>43.44</td>\n","      <td>wtórny</td>\n","      <td>4.0</td>\n","      <td>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Niezależny Układ W Nowoczesnym Wydaniu</td>\n","      <td>1</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>Polecamy na sprzedaż dwupokojowe mieszkanie p...</td>\n","      <td>NaN</td>\n","      <td>telewizja kablowa, internet, meble, piwnica, g...</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>314900.0</td>\n","      <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","      <td>2</td>\n","      <td>NaN</td>\n","      <td>42.60</td>\n","      <td>pierwotny</td>\n","      <td>2.0</td>\n","      <td>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Urokliwe mieszkanie 2 pokojowe Strzeszyn</td>\n","      <td>1</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>Kameralne 2 pokojowe mieszkanie z aneksem kuc...</td>\n","      <td>NaN</td>\n","      <td>telewizja kablowa, internet, telefon, drzwi / ...</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>249000.0</td>\n","      <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","      <td>2</td>\n","      <td>NaN</td>\n","      <td>44.30</td>\n","      <td>wtórny</td>\n","      <td>4.0</td>\n","      <td>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Mieszkanie do remontu ul. Klonowa, blisko tramwaj</td>\n","      <td>2</td>\n","      <td>NaN</td>\n","      <td>miejskie</td>\n","      <td>plastikowe</td>\n","      <td>1960.0</td>\n","      <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","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>419000.0</td>\n","      <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","      <td>4</td>\n","      <td>NaN</td>\n","      <td>88</td>\n","      <td>wtórny</td>\n","      <td>3.0</td>\n","      <td>szeregowiec</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>W szeregowcu 4 pokoje z garażem</td>\n","      <td>1</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","      <td>NaN</td>\n","      <td>telewizja kablowa, internet, zmywarka, lodówka...</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>499000.0</td>\n","      <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","      <td>3</td>\n","      <td>NaN</td>\n","      <td>77</td>\n","      <td>wtórny</td>\n","      <td>16.0</td>\n","      <td>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Komfortowe,Przestronne,3Pokoje, Armii Krajowej!!!</td>\n","      <td>7</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>plastikowe</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Biuro Immohouse ma przyjemność proponować do ...</td>\n","      <td>NaN</td>\n","      <td>balkon, piwnica, winda</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["         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","                                                  5  6   7      8          9   \\\n","0  https://www.otodom.pl/oferta/niezalezny-uklad-...  2 NaN  43.44     wtórny   \n","1  https://www.otodom.pl/oferta/urokliwe-mieszkan...  2 NaN  42.60  pierwotny   \n","2  https://www.otodom.pl/oferta/mieszkanie-do-rem...  2 NaN  44.30     wtórny   \n","3  https://www.otodom.pl/oferta/w-szeregowcu-4-po...  4 NaN     88     wtórny   \n","4  https://www.otodom.pl/oferta/komfortowe-przest...  3 NaN     77     wtórny   \n","\n","     10           11  12  13  \\\n","0   4.0         blok NaN NaN   \n","1   2.0         blok NaN NaN   \n","2   4.0         blok NaN NaN   \n","3   3.0  szeregowiec NaN NaN   \n","4  16.0         blok NaN NaN   \n","\n","                                                  14 15  16        17  \\\n","0             Niezależny Układ W Nowoczesnym Wydaniu  1 NaN    gazowe   \n","1           Urokliwe mieszkanie 2 pokojowe Strzeszyn  1 NaN    gazowe   \n","2  Mieszkanie do remontu ul. Klonowa, blisko tramwaj  2 NaN  miejskie   \n","3                    W szeregowcu 4 pokoje z garażem  1 NaN    gazowe   \n","4  Komfortowe,Przestronne,3Pokoje, Armii Krajowej!!!  7 NaN       NaN   \n","\n","           18      19  20          21     22  \\\n","0  plastikowe     NaN NaN         NaN  cegła   \n","1  plastikowe     NaN NaN         NaN  cegła   \n","2  plastikowe  1960.0 NaN  2019-06-30  cegła   \n","3  plastikowe     NaN NaN         NaN  cegła   \n","4  plastikowe     NaN NaN         NaN    NaN   \n","\n","                                                  23  24  \\\n","0   Polecamy na sprzedaż dwupokojowe mieszkanie p... NaN   \n","1   Kameralne 2 pokojowe mieszkanie z aneksem kuc... NaN   \n","2   Oferta bezpośrednio od właściciela - bez pośr... NaN   \n","3   Drodzy Państwo Zapraszam do zapoznania się z ... NaN   \n","4   Biuro Immohouse ma przyjemność proponować do ... NaN   \n","\n","                                                  25  \n","0  telewizja kablowa, internet, meble, piwnica, g...  \n","1  telewizja kablowa, internet, telefon, drzwi / ...  \n","2  telewizja kablowa, internet, telefon, domofon ...  \n","3  telewizja kablowa, internet, zmywarka, lodówka...  \n","4                             balkon, piwnica, winda  "]},"execution_count":193,"metadata":{},"output_type":"execute_result"}],"source":["df_train.head()"]},{"cell_type":"markdown","metadata":{"id":"nt0TOLw5RAqS"},"source":["1,2,6, 8, 9 - to bedziemy w aplikacji używać\n"]},{"cell_type":"code","execution_count":194,"metadata":{},"outputs":[],"source":["df_train = df_train.iloc[:, [0, 1, 2, 6, 8, 9]]"]},{"cell_type":"code","execution_count":195,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":3,"status":"ok","timestamp":1696952402833,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"QdXwQzPsOza0","outputId":"d5d231f0-da54-432f-9bd6-454d4063eaff"},"outputs":[{"name":"stdout","output_type":"stream","text":["<class 'pandas.core.frame.DataFrame'>\n","RangeIndex: 2547 entries, 0 to 2546\n","Data columns (total 6 columns):\n"," #   Column  Non-Null Count  Dtype  \n","---  ------  --------------  -----  \n"," 0   0       2547 non-null   float64\n"," 1   1       1519 non-null   object \n"," 2   2       929 non-null    object \n"," 3   6       2547 non-null   object \n"," 4   8       2547 non-null   object \n"," 5   9       2547 non-null   object \n","dtypes: float64(1), object(5)\n","memory usage: 119.5+ KB\n"]}],"source":["df_train.info()"]},{"cell_type":"code","execution_count":196,"metadata":{},"outputs":[],"source":["df_train.rename(columns={0: \"cena m\", 1: \"stan\", 2: \"czynsz\", 6: \"l pokoi\", 8: \"metraż\", 9: \"rynek\"}, inplace=True)"]},{"cell_type":"code","execution_count":197,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["<class 'pandas.core.frame.DataFrame'>\n","RangeIndex: 2547 entries, 0 to 2546\n","Data columns (total 6 columns):\n"," #   Column   Non-Null Count  Dtype  \n","---  ------   --------------  -----  \n"," 0   cena m   2547 non-null   float64\n"," 1   stan     1519 non-null   object \n"," 2   czynsz   929 non-null    object \n"," 3   l pokoi  2547 non-null   object \n"," 4   metraż   2547 non-null   object \n"," 5   rynek    2547 non-null   object \n","dtypes: float64(1), object(5)\n","memory usage: 119.5+ KB\n"]}],"source":["df_train.info()"]},{"cell_type":"markdown","metadata":{},"source":["Usunięcie kolumn, w których jest dużo pustych wartości"]},{"cell_type":"code","execution_count":198,"metadata":{"executionInfo":{"elapsed":249,"status":"ok","timestamp":1696953612119,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"x6jB9brYRSTJ"},"outputs":[],"source":["df_train.drop(columns = ['czynsz'], axis=1, inplace=True)"]},{"cell_type":"code","execution_count":199,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":608},"executionInfo":{"elapsed":339,"status":"ok","timestamp":1696953613765,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"NIzvOY2BQqTK","outputId":"ceaa0534-470a-4296-f51c-97f1b9904190"},"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 m</th>\n","      <th>stan</th>\n","      <th>l pokoi</th>\n","      <th>metraż</th>\n","      <th>rynek</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>309000.0</td>\n","      <td>do zamieszkania</td>\n","      <td>2</td>\n","      <td>43.44</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>314900.0</td>\n","      <td>do wykończenia</td>\n","      <td>2</td>\n","      <td>42.60</td>\n","      <td>pierwotny</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>249000.0</td>\n","      <td>do remontu</td>\n","      <td>2</td>\n","      <td>44.30</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>419000.0</td>\n","      <td>do zamieszkania</td>\n","      <td>4</td>\n","      <td>88</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>499000.0</td>\n","      <td>NaN</td>\n","      <td>3</td>\n","      <td>77</td>\n","      <td>wtórny</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["     cena m             stan l pokoi metraż      rynek\n","0  309000.0  do zamieszkania       2  43.44     wtórny\n","1  314900.0   do wykończenia       2  42.60  pierwotny\n","2  249000.0       do remontu       2  44.30     wtórny\n","3  419000.0  do zamieszkania       4     88     wtórny\n","4  499000.0              NaN       3     77     wtórny"]},"execution_count":199,"metadata":{},"output_type":"execute_result"}],"source":["df_train.head()"]},{"cell_type":"markdown","metadata":{},"source":["Uzupełnianie braków w danych "]},{"cell_type":"code","execution_count":200,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":3,"status":"ok","timestamp":1696953649491,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"qNqxEsnNUZcH","outputId":"33ce3384-6b79-4795-c582-0d8fd8457943"},"outputs":[{"name":"stdout","output_type":"stream","text":["<class 'pandas.core.frame.DataFrame'>\n","RangeIndex: 2547 entries, 0 to 2546\n","Data columns (total 5 columns):\n"," #   Column   Non-Null Count  Dtype  \n","---  ------   --------------  -----  \n"," 0   cena m   2547 non-null   float64\n"," 1   stan     1519 non-null   object \n"," 2   l pokoi  2547 non-null   object \n"," 3   metraż   2547 non-null   object \n"," 4   rynek    2547 non-null   object \n","dtypes: float64(1), object(4)\n","memory usage: 99.6+ KB\n"]}],"source":["df_train.info()"]},{"cell_type":"code","execution_count":201,"metadata":{"executionInfo":{"elapsed":245,"status":"ok","timestamp":1696953995554,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"5BTDYi_xUdGF"},"outputs":[],"source":["df_train['stan'].fillna('brak info', inplace=True)"]},{"cell_type":"code","execution_count":202,"metadata":{},"outputs":[],"source":["df_train = df_train[df_train['metraż'] != \"6 909\"]"]},{"cell_type":"code","execution_count":203,"metadata":{},"outputs":[],"source":["df_train = df_train[df_train['l pokoi'] != \"więcej niż 10\"]"]},{"cell_type":"code","execution_count":204,"metadata":{},"outputs":[],"source":["df_train['l pokoi'] = pd.to_numeric(df_train['l pokoi'])"]},{"cell_type":"code","execution_count":205,"metadata":{},"outputs":[],"source":["df_train['metraż'] = pd.to_numeric(df_train['metraż'])"]},{"cell_type":"code","execution_count":206,"metadata":{},"outputs":[],"source":["X_train = df_train.drop(columns = [\"cena m\"])\n","y_train = df_train[\"cena m\"]"]},{"cell_type":"code","execution_count":207,"metadata":{"executionInfo":{"elapsed":240,"status":"ok","timestamp":1696955504933,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"LW2CpZn6V5sl"},"outputs":[],"source":["number_cols = X_train.select_dtypes(exclude=[object]).columns\n","object_cols = X_train.select_dtypes(include=[object]).columns"]},{"cell_type":"code","execution_count":208,"metadata":{"executionInfo":{"elapsed":6,"status":"ok","timestamp":1696954577003,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"DJOcANTvXMjl"},"outputs":[],"source":["from sklearn.compose import ColumnTransformer\n","from sklearn.preprocessing import OneHotEncoder\n","from sklearn.preprocessing import StandardScaler\n","from sklearn.pipeline import make_pipeline"]},{"cell_type":"code","execution_count":209,"metadata":{"executionInfo":{"elapsed":240,"status":"ok","timestamp":1696955508626,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"5nvY10OHXjEw"},"outputs":[],"source":["ct = ColumnTransformer([\n","        (number_cols, StandardScaler()),\n","        (object_cols, OneHotEncoder())\n","    ],remainder='passthrough')\n"]},{"cell_type":"code","execution_count":210,"metadata":{"executionInfo":{"elapsed":529,"status":"ok","timestamp":1696954626952,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"wcGvPEZzYDPZ"},"outputs":[],"source":["from sklearn.linear_model import Ridge"]},{"cell_type":"code","execution_count":211,"metadata":{"executionInfo":{"elapsed":343,"status":"ok","timestamp":1696955511401,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"4z3w4bzbYseK"},"outputs":[],"source":["scaler = StandardScaler()\n","encoder = OneHotEncoder()\n","# putting numeric columns to scaler and categorical to encoder\n","num_transformer = make_pipeline(scaler)\n","cat_transformer = make_pipeline(encoder)\n","\n","# getting together our scaler and encoder with preprocessor\n","preprocessor = ColumnTransformer(\n","      transformers=[('num', num_transformer, number_cols),\n","                    ('cat', cat_transformer, object_cols)])"]},{"cell_type":"code","execution_count":212,"metadata":{"executionInfo":{"elapsed":354,"status":"ok","timestamp":1696955513049,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"QXvbFrmXYLtR"},"outputs":[],"source":["clf = Ridge(alpha=1.0)"]},{"cell_type":"code","execution_count":213,"metadata":{"executionInfo":{"elapsed":428,"status":"ok","timestamp":1696955515987,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"pytR_osgX5Lb"},"outputs":[],"source":["model1 = make_pipeline(preprocessor, clf)"]},{"cell_type":"code","execution_count":214,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":608},"executionInfo":{"elapsed":233,"status":"ok","timestamp":1696955309653,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"vzR7OGK8Z-lD","outputId":"6aa1623d-b9fb-46ad-a200-f185708542ac"},"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>stan</th>\n","      <th>l pokoi</th>\n","      <th>metraż</th>\n","      <th>rynek</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>do zamieszkania</td>\n","      <td>2</td>\n","      <td>43.44</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>do wykończenia</td>\n","      <td>2</td>\n","      <td>42.60</td>\n","      <td>pierwotny</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>do remontu</td>\n","      <td>2</td>\n","      <td>44.30</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>do zamieszkania</td>\n","      <td>4</td>\n","      <td>88.00</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>brak info</td>\n","      <td>3</td>\n","      <td>77.00</td>\n","      <td>wtórny</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["              stan  l pokoi  metraż      rynek\n","0  do zamieszkania        2   43.44     wtórny\n","1   do wykończenia        2   42.60  pierwotny\n","2       do remontu        2   44.30     wtórny\n","3  do zamieszkania        4   88.00     wtórny\n","4        brak info        3   77.00     wtórny"]},"execution_count":214,"metadata":{},"output_type":"execute_result"}],"source":["X_train.head()"]},{"cell_type":"code","execution_count":215,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":7,"status":"ok","timestamp":1696955419804,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"vcg92-RtbLSH","outputId":"457f8462-c2d8-4721-a19a-fb855998472c"},"outputs":[{"data":{"text/plain":["0       309000.0\n","1       314900.0\n","2       249000.0\n","3       419000.0\n","4       499000.0\n","          ...   \n","2541    383680.0\n","2542    507600.0\n","2543    342400.0\n","2544    335000.0\n","2545    260000.0\n","Name: cena m, Length: 2540, dtype: float64"]},"execution_count":215,"metadata":{},"output_type":"execute_result"}],"source":["y_train"]},{"cell_type":"markdown","metadata":{"id":"GY_ZQICKc__t"},"source":["## Model Ridge - regresja liniowa"]},{"cell_type":"code","execution_count":216,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":191},"executionInfo":{"elapsed":236,"status":"ok","timestamp":1696955526976,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"cFvgBYD5YYz7","outputId":"008e021f-cb56-4458-99e8-ca95df32e68d"},"outputs":[{"data":{"text/html":["<style>#sk-container-id-7 {color: black;}#sk-container-id-7 pre{padding: 0;}#sk-container-id-7 div.sk-toggleable {background-color: white;}#sk-container-id-7 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-7 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-7 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-7 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-7 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 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-7 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-7 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-7 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 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-7 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-7 div.sk-item {position: relative;z-index: 1;}#sk-container-id-7 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-7 div.sk-item::before, #sk-container-id-7 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-7 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-7 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-7 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-7 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-7 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-7 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-7 div.sk-label-container {text-align: center;}#sk-container-id-7 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-7 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-7\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;columntransformer&#x27;,\n","                 ColumnTransformer(transformers=[(&#x27;num&#x27;,\n","                                                  Pipeline(steps=[(&#x27;standardscaler&#x27;,\n","                                                                   StandardScaler())]),\n","                                                  Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)),\n","                                                 (&#x27;cat&#x27;,\n","                                                  Pipeline(steps=[(&#x27;onehotencoder&#x27;,\n","                                                                   OneHotEncoder())]),\n","                                                  Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;))])),\n","                (&#x27;ridge&#x27;, Ridge())])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-43\" type=\"checkbox\" ><label for=\"sk-estimator-id-43\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;columntransformer&#x27;,\n","                 ColumnTransformer(transformers=[(&#x27;num&#x27;,\n","                                                  Pipeline(steps=[(&#x27;standardscaler&#x27;,\n","                                                                   StandardScaler())]),\n","                                                  Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)),\n","                                                 (&#x27;cat&#x27;,\n","                                                  Pipeline(steps=[(&#x27;onehotencoder&#x27;,\n","                                                                   OneHotEncoder())]),\n","                                                  Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;))])),\n","                (&#x27;ridge&#x27;, Ridge())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-44\" type=\"checkbox\" ><label for=\"sk-estimator-id-44\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">columntransformer: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(transformers=[(&#x27;num&#x27;,\n","                                 Pipeline(steps=[(&#x27;standardscaler&#x27;,\n","                                                  StandardScaler())]),\n","                                 Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)),\n","                                (&#x27;cat&#x27;,\n","                                 Pipeline(steps=[(&#x27;onehotencoder&#x27;,\n","                                                  OneHotEncoder())]),\n","                                 Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;))])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-45\" type=\"checkbox\" ><label for=\"sk-estimator-id-45\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">num</label><div class=\"sk-toggleable__content\"><pre>Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-46\" type=\"checkbox\" ><label for=\"sk-estimator-id-46\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-47\" type=\"checkbox\" ><label for=\"sk-estimator-id-47\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">cat</label><div class=\"sk-toggleable__content\"><pre>Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-48\" type=\"checkbox\" ><label for=\"sk-estimator-id-48\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder()</pre></div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-49\" type=\"checkbox\" ><label for=\"sk-estimator-id-49\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Ridge</label><div class=\"sk-toggleable__content\"><pre>Ridge()</pre></div></div></div></div></div></div></div>"],"text/plain":["Pipeline(steps=[('columntransformer',\n","                 ColumnTransformer(transformers=[('num',\n","                                                  Pipeline(steps=[('standardscaler',\n","                                                                   StandardScaler())]),\n","                                                  Index(['l pokoi', 'metraż'], dtype='object')),\n","                                                 ('cat',\n","                                                  Pipeline(steps=[('onehotencoder',\n","                                                                   OneHotEncoder())]),\n","                                                  Index(['stan', 'rynek'], dtype='object'))])),\n","                ('ridge', Ridge())])"]},"execution_count":216,"metadata":{},"output_type":"execute_result"}],"source":["model1.fit(X_train, y_train)"]},{"cell_type":"code","execution_count":217,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":451,"status":"ok","timestamp":1696955647207,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"M7X8ScQobnwG","outputId":"a30f27eb-2e34-4a91-fae0-a9ab53505322"},"outputs":[],"source":["df_test = pd.read_csv('in.tsv', sep='\\t', header=None)"]},{"cell_type":"code","execution_count":218,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":573},"executionInfo":{"elapsed":5,"status":"ok","timestamp":1696955652118,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"x3qN4TMKcDfL","outputId":"ed2fa477-65e6-494e-9423-de6894c47ef8"},"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>10</th>\n","      <th>11</th>\n","      <th>12</th>\n","      <th>13</th>\n","      <th>14</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>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>idealne mieszkanie do zamieszkania od zaraz</td>\n","      <td>2</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>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>2 pokoje / 38m2 / po remoncie / Winogrady</td>\n","      <td>4</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>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>3 pokoje na Jeżycach blisko Rusałki</td>\n","      <td>4</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>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Uniwersytet Przyrodniczy - 4 pokoje - ROI 8-10%</td>\n","      <td>10</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>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Mieszkanie blisko centrum w kameralnej okolicy.</td>\n","      <td>1</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","  </tbody>\n","</table>\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","                                                  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","          8     9     10  11  12  \\\n","0     wtórny   4.0  blok NaN NaN   \n","1     wtórny  12.0  blok NaN NaN   \n","2     wtórny   4.0  blok NaN NaN   \n","3     wtórny  10.0  blok NaN NaN   \n","4  pierwotny   3.0   NaN NaN NaN   \n","\n","                                                13  14  15        16  \\\n","0      idealne mieszkanie do zamieszkania od zaraz   2 NaN  miejskie   \n","1        2 pokoje / 38m2 / po remoncie / Winogrady   4 NaN      inne   \n","2              3 pokoje na Jeżycach blisko Rusałki   4 NaN  miejskie   \n","3  Uniwersytet Przyrodniczy - 4 pokoje - ROI 8-10%  10 NaN  miejskie   \n","4  Mieszkanie blisko centrum w kameralnej okolicy.   1 NaN       NaN   \n","\n","           17      18  19          20            21  \\\n","0  plastikowe     NaN NaN         NaN  wielka płyta   \n","1  plastikowe     NaN NaN         NaN           NaN   \n","2  plastikowe  1958.0 NaN         NaN         cegła   \n","3  plastikowe  1975.0 NaN  2019-06-30  wielka płyta   \n","4         NaN  2020.0 NaN  2020-01-01           NaN   \n","\n","                                                  22  23  \\\n","0   Zamieszkaj od zaraz – idealna lokalizacja OFE... NaN   \n","1   Na sprzedaż mieszkanie dwupokojowe na osiedlu... NaN   \n","2   !! Oferta dostępna tylko u nas !! Polecam ofe... NaN   \n","3   Oferta  bezpośrednio od właściciela  - bez po... NaN   \n","4   MIESZKANIE 3-POKOJOWE O POW.65,62M2 Mieszkani... 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  "]},"execution_count":218,"metadata":{},"output_type":"execute_result"}],"source":["df_test.head()"]},{"cell_type":"code","execution_count":219,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":244,"status":"ok","timestamp":1696955801209,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"UybULQjXcMbT","outputId":"1bd9cb56-50cf-4040-f797-0d54e0293ef5"},"outputs":[],"source":["y_test = pd.read_csv('expected.tsv', sep='\\t', header=None)"]},{"cell_type":"code","execution_count":220,"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>stan</th>\n","      <th>l pokoi</th>\n","      <th>metraż</th>\n","      <th>rynek</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>do zamieszkania</td>\n","      <td>2</td>\n","      <td>43.44</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>do wykończenia</td>\n","      <td>2</td>\n","      <td>42.60</td>\n","      <td>pierwotny</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>do remontu</td>\n","      <td>2</td>\n","      <td>44.30</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>do zamieszkania</td>\n","      <td>4</td>\n","      <td>88.00</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>brak info</td>\n","      <td>3</td>\n","      <td>77.00</td>\n","      <td>wtórny</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>do wykończenia</td>\n","      <td>3</td>\n","      <td>70.40</td>\n","      <td>pierwotny</td>\n","    </tr>\n","    <tr>\n","      <th>2542</th>\n","      <td>do wykończenia</td>\n","      <td>4</td>\n","      <td>94.00</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>2543</th>\n","      <td>brak info</td>\n","      <td>2</td>\n","      <td>53.50</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>2544</th>\n","      <td>brak info</td>\n","      <td>3</td>\n","      <td>55.25</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>2545</th>\n","      <td>brak info</td>\n","      <td>3</td>\n","      <td>62.00</td>\n","      <td>wtórny</td>\n","    </tr>\n","  </tbody>\n","</table>\n","<p>2540 rows × 4 columns</p>\n","</div>"],"text/plain":["                 stan  l pokoi  metraż      rynek\n","0     do zamieszkania        2   43.44     wtórny\n","1      do wykończenia        2   42.60  pierwotny\n","2          do remontu        2   44.30     wtórny\n","3     do zamieszkania        4   88.00     wtórny\n","4           brak info        3   77.00     wtórny\n","...               ...      ...     ...        ...\n","2541   do wykończenia        3   70.40  pierwotny\n","2542   do wykończenia        4   94.00     wtórny\n","2543        brak info        2   53.50     wtórny\n","2544        brak info        3   55.25     wtórny\n","2545        brak info        3   62.00     wtórny\n","\n","[2540 rows x 4 columns]"]},"execution_count":220,"metadata":{},"output_type":"execute_result"}],"source":["X_train"]},{"cell_type":"code","execution_count":221,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":8,"status":"ok","timestamp":1696955946495,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"WMsGxdMwdMM8","outputId":"d2a8f0ac-4051-465e-d43c-e1fb7b9a3034"},"outputs":[],"source":["df_test.rename(columns={0: \"stan\", 1: \"czynsz\", 5: \"l pokoi\", 7: \"metraż\", 8: \"rynek\"}, inplace=True)"]},{"cell_type":"code","execution_count":222,"metadata":{"executionInfo":{"elapsed":226,"status":"ok","timestamp":1696956067214,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"TNHLwq_5daGO"},"outputs":[{"data":{"text/plain":["Index([   'stan',  'czynsz',         2,         3,         4, 'l pokoi',\n","               6,  'metraż',   'rynek',         9,        10,        11,\n","              12,        13,        14,        15,        16,        17,\n","              18,        19,        20,        21,        22,        23,\n","              24],\n","      dtype='object')"]},"execution_count":222,"metadata":{},"output_type":"execute_result"}],"source":["df_test.columns"]},{"cell_type":"code","execution_count":223,"metadata":{},"outputs":[],"source":["df_test = df_test[['stan', 'l pokoi', 'metraż',  'rynek']] "]},{"cell_type":"code","execution_count":224,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":6,"status":"ok","timestamp":1696956090162,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"tbcOpXendvZv","outputId":"93eddcd2-b741-4aa6-b185-59c96dc2e833"},"outputs":[{"name":"stdout","output_type":"stream","text":["<class 'pandas.core.frame.DataFrame'>\n","RangeIndex: 462 entries, 0 to 461\n","Data columns (total 4 columns):\n"," #   Column   Non-Null Count  Dtype  \n","---  ------   --------------  -----  \n"," 0   stan     275 non-null    object \n"," 1   l pokoi  462 non-null    int64  \n"," 2   metraż   462 non-null    float64\n"," 3   rynek    462 non-null    object \n","dtypes: float64(1), int64(1), object(2)\n","memory usage: 14.6+ KB\n"]}],"source":["df_test.info()"]},{"cell_type":"code","execution_count":225,"metadata":{"executionInfo":{"elapsed":323,"status":"ok","timestamp":1696956241887,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"j5IFS4YQdKPW"},"outputs":[],"source":["df_test['stan'].fillna('brak info', inplace=True)"]},{"cell_type":"code","execution_count":226,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["<class 'pandas.core.frame.DataFrame'>\n","RangeIndex: 462 entries, 0 to 461\n","Data columns (total 4 columns):\n"," #   Column   Non-Null Count  Dtype  \n","---  ------   --------------  -----  \n"," 0   stan     462 non-null    object \n"," 1   l pokoi  462 non-null    int64  \n"," 2   metraż   462 non-null    float64\n"," 3   rynek    462 non-null    object \n","dtypes: float64(1), int64(1), object(2)\n","memory usage: 14.6+ KB\n"]}],"source":["df_test.info()"]},{"cell_type":"code","execution_count":227,"metadata":{},"outputs":[{"data":{"text/plain":["0      59.10\n","1      38.00\n","2      63.84\n","3      50.00\n","4      65.62\n","       ...  \n","457    72.78\n","458    51.23\n","459    54.16\n","460    90.10\n","461    71.90\n","Name: metraż, Length: 462, dtype: float64"]},"execution_count":227,"metadata":{},"output_type":"execute_result"}],"source":["df_test['metraż']"]},{"cell_type":"code","execution_count":228,"metadata":{},"outputs":[],"source":["df_test.reset_index(drop=True, inplace=True)"]},{"cell_type":"code","execution_count":229,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["<class 'pandas.core.frame.DataFrame'>\n","RangeIndex: 462 entries, 0 to 461\n","Data columns (total 4 columns):\n"," #   Column   Non-Null Count  Dtype  \n","---  ------   --------------  -----  \n"," 0   stan     462 non-null    object \n"," 1   l pokoi  462 non-null    int64  \n"," 2   metraż   462 non-null    float64\n"," 3   rynek    462 non-null    object \n","dtypes: float64(1), int64(1), object(2)\n","memory usage: 14.6+ KB\n"]}],"source":["df_test.info()"]},{"cell_type":"code","execution_count":230,"metadata":{},"outputs":[{"data":{"text/html":["<style>#sk-container-id-8 {color: black;}#sk-container-id-8 pre{padding: 0;}#sk-container-id-8 div.sk-toggleable {background-color: white;}#sk-container-id-8 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-8 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-8 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-8 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-8 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-8 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-8 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-8 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-8 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 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-8 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-8 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-8 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-8 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 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-8 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-8 div.sk-item {position: relative;z-index: 1;}#sk-container-id-8 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-8 div.sk-item::before, #sk-container-id-8 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-8 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-8 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-8 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-8 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-8 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-8 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-8 div.sk-label-container {text-align: center;}#sk-container-id-8 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-8 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-8\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;columntransformer&#x27;,\n","                 ColumnTransformer(transformers=[(&#x27;num&#x27;,\n","                                                  Pipeline(steps=[(&#x27;standardscaler&#x27;,\n","                                                                   StandardScaler())]),\n","                                                  Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)),\n","                                                 (&#x27;cat&#x27;,\n","                                                  Pipeline(steps=[(&#x27;onehotencoder&#x27;,\n","                                                                   OneHotEncoder())]),\n","                                                  Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;))])),\n","                (&#x27;ridge&#x27;, Ridge())])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-50\" type=\"checkbox\" ><label for=\"sk-estimator-id-50\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;columntransformer&#x27;,\n","                 ColumnTransformer(transformers=[(&#x27;num&#x27;,\n","                                                  Pipeline(steps=[(&#x27;standardscaler&#x27;,\n","                                                                   StandardScaler())]),\n","                                                  Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)),\n","                                                 (&#x27;cat&#x27;,\n","                                                  Pipeline(steps=[(&#x27;onehotencoder&#x27;,\n","                                                                   OneHotEncoder())]),\n","                                                  Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;))])),\n","                (&#x27;ridge&#x27;, Ridge())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-51\" type=\"checkbox\" ><label for=\"sk-estimator-id-51\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">columntransformer: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(transformers=[(&#x27;num&#x27;,\n","                                 Pipeline(steps=[(&#x27;standardscaler&#x27;,\n","                                                  StandardScaler())]),\n","                                 Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)),\n","                                (&#x27;cat&#x27;,\n","                                 Pipeline(steps=[(&#x27;onehotencoder&#x27;,\n","                                                  OneHotEncoder())]),\n","                                 Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;))])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-52\" type=\"checkbox\" ><label for=\"sk-estimator-id-52\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">num</label><div class=\"sk-toggleable__content\"><pre>Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-53\" type=\"checkbox\" ><label for=\"sk-estimator-id-53\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-54\" type=\"checkbox\" ><label for=\"sk-estimator-id-54\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">cat</label><div class=\"sk-toggleable__content\"><pre>Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-55\" type=\"checkbox\" ><label for=\"sk-estimator-id-55\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder()</pre></div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-56\" type=\"checkbox\" ><label for=\"sk-estimator-id-56\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Ridge</label><div class=\"sk-toggleable__content\"><pre>Ridge()</pre></div></div></div></div></div></div></div>"],"text/plain":["Pipeline(steps=[('columntransformer',\n","                 ColumnTransformer(transformers=[('num',\n","                                                  Pipeline(steps=[('standardscaler',\n","                                                                   StandardScaler())]),\n","                                                  Index(['l pokoi', 'metraż'], dtype='object')),\n","                                                 ('cat',\n","                                                  Pipeline(steps=[('onehotencoder',\n","                                                                   OneHotEncoder())]),\n","                                                  Index(['stan', 'rynek'], dtype='object'))])),\n","                ('ridge', Ridge())])"]},"execution_count":230,"metadata":{},"output_type":"execute_result"}],"source":["model1"]},{"cell_type":"markdown","metadata":{},"source":["Przykład - przewidywanie cen na danych testowych"]},{"cell_type":"code","execution_count":231,"metadata":{},"outputs":[{"data":{"text/plain":["array([ 407917.66889452,  285306.27863261,  444184.94702291,\n","        299459.05926666,  459271.83408962,  614055.95902743,\n","        311243.98561031,  361244.58944658,  329238.65906305,\n","        369470.84812889,  285350.13919824,  329238.65906305,\n","        420020.53940636,  399085.99304054,  368717.32379097,\n","        339834.65864991,  335512.74515277,  304524.88092914,\n","        367036.20209137,  286773.80808993,  354525.20168926,\n","        282085.35025252,  386303.76202814,  477660.29347794,\n","        407152.53644455,  490742.17175818,  529758.94244497,\n","        335044.40697838,  399501.21194489,  431641.29394143,\n","        331214.22563058,  334772.89329194,  404282.20491201,\n","        369968.98599038,  392538.22357404,  354476.13872373,\n","        531690.53563375,  428309.25045513,  298510.41733766,\n","        551966.54555785,  332974.0302655 ,  474293.99377424,\n","        247049.65613431,  383931.85143325,  546789.20856336,\n","        438766.28443053,  275556.44383868,  325403.7381088 ,\n","        319934.12593671,  277654.95413295,  294800.60980049,\n","        285306.27863261,  283776.01373268,  282811.35937324,\n","        511210.54963994,  327121.56879228,  335039.88788041,\n","        638797.47051695,  521922.40393947,  235305.67479634,\n","        238447.52001532,  465392.89368935,  272046.09327325,\n","        848434.43816552,  512546.27689188,  382253.07914128,\n","        781492.5027453 ,  531716.09929903,  442847.05008064,\n","        498968.43044048,  272108.82871587,  275556.44383868,\n","        307110.38376632,  373296.51037872,  320469.71865169,\n","        629040.94693472,  456886.14569235,  463535.64405524,\n","        356361.80264533,  387288.89243253,  249184.65490398,\n","        305443.0398691 ,  312129.77494706,  323562.90113092,\n","        286773.80808993,  338640.52949322,  265910.97279499,\n","        414803.86094421,  262352.30513363,  273562.29729465,\n","        959123.60494806,  476401.54226445,  463695.54142089,\n","        474293.99377424,  245933.92683679,  276309.90323886,\n","         95163.71086422,  410945.54601501,  377887.30507851,\n","        332477.49594204,  374627.25336918,  354168.19912956,\n","        369968.98599038,  311900.23521207,  275897.03611221,\n","        272224.40035237,  522497.33812211,  317135.7885512 ,\n","        317671.38126618,  357993.86137939,  352637.93422963,\n","        908358.15173798,  288551.8042999 ,  398779.94006055,\n","        279465.70834759,  310024.57586448,  367940.58322895,\n","        336039.07916333,  295296.8610478 ,  395408.55510658,\n","        289706.87506509,  461286.74212482,  959007.7502354 ,\n","        671918.16381992,  357151.93260828,  573837.44243868,\n","        286071.41108258,  453635.41762516,  294033.30766019,\n","        430106.50994353,  361819.52362922,  280070.72529348,\n","        820481.6050142 ,  349767.60269709,  364114.92097912,\n","        262468.15984629,  301183.86181458,  297937.65284535,\n","        285306.27863261,  393955.0865278 ,  666659.89980777,\n","        560179.02643777,  440551.36965458,  544315.22105819,\n","        460711.80794218,  281978.75424428,  380105.90610726,\n","        501187.31454538,  343001.78445802,  567830.35093743,\n","        262544.39001514,  332442.95664849,  703770.99332145,\n","        369470.84812889,  494101.3824478 ,  273562.29729465,\n","        180666.17730277,  452295.35099255,  331304.51667796,\n","        453635.41762516,  323108.3407589 ,  507194.68912278,\n","        326474.92353875,  334772.89329194,  335044.40697838,\n","        240054.29816025,  562052.51609502,  274404.22606576,\n","        375397.37008062,  253585.25133645,  311900.23521207,\n","        365811.99017143,  339834.65864991,  395408.55510658,\n","        567728.27402715,  336238.53613507,  490526.69290172,\n","        257086.66903124,  385858.46036054,  344082.22859239,\n","        533220.80053368,  295941.33661099,  220577.95997966,\n","        291229.76787478,  200262.6085879 ,  281213.62179431,\n","        338640.52949322,  267288.49428108,  439786.23720462,\n","        400076.14612753,  301183.86181458,  479730.95326697,\n","        319470.24429261,  470581.73347059,  336354.39084773,\n","        491317.10594082,  354168.19912956,  369551.88047185,\n","        435462.4370933 ,  514271.0794398 ,  331214.22563058,\n","        234999.90489251,  240207.32465024,  395408.55510658,\n","        305290.01337911,  265336.03861235,  349500.60810862,\n","        315911.57663126,  448585.54345538,  310063.91733215,\n","        414803.86094421,  521922.40393947,  768450.42872618,\n","        285306.27863261,  414228.92676157,  408188.43671135,\n","        262917.91567413,  530071.86630062,  284993.07170081,\n","        354168.19912956,  350852.56592942,  341174.72528252,\n","        174670.0129817 ,  346185.25798463,  308617.25469129,\n","        319206.16526408,  479496.61135786,  285306.27863261,\n","        338832.89745087,  238677.05975031,  300193.70872759,\n","        284350.94791532,  312129.77494706,  288864.94629397,\n","        447136.31089841,  468759.4764692 ,  311243.98561031,\n","        773841.17824564,  309069.24514719,  311818.91979295,\n","        303300.6690092 ,  249129.2915516 ,  317026.62262684,\n","        270578.56381593,  374826.77527865,  317632.03979852,\n","        218540.23357609,  336303.15819187,  364613.05884061,\n","        419438.51620964,  348842.0716669 ,  300494.95953345,\n","        245456.65579176,  632191.76778196,  342245.91071247,\n","        321241.94011573,  345941.94044726,  654441.17458326,\n","        594917.92628041,  403059.87960624,  295368.85519483,\n","        287144.48312671,  504057.36300177,  259834.05683704,\n","        356196.60189099,  671431.17127702,  221915.85692194,\n","        266766.67936848,  862139.34958591,  253061.54980967,\n","        278229.88831559,  360787.39659078,  819749.12524361,\n","        225938.68930354,  337453.4893506 ,  417419.08907647,\n","        433477.61182135,  428415.84646337,  369470.84812889,\n","        644948.32980378,  369778.78772305,  486728.1978552 ,\n","        220003.02579702,  372225.04187261,  533707.33028312,\n","        268312.96615313,  351337.20906469,  266766.67936848,\n","        433665.17760489,  291427.33823234,  681260.15179974,\n","        386155.25463611,  361819.52362922,  378283.64910587,\n","        312584.05224292,  262442.87925716,  347027.18675575,\n","        388599.15937804,  330653.06925032,  331214.22563058,\n","        392424.82162787,  581111.00288747,  510178.4226015 ,\n","        638681.61580429,  273562.29729465,  332934.68879784,\n","        370402.78487122,  251183.25797831,  454520.92388575,\n","        327814.99017136,  317446.36062915,  270745.3681083 ,\n","        568020.54920476, 1041637.53573378,  445984.0931255 ,\n","        246474.72195167,  353326.27035845,  456478.01580208,\n","        268245.71161255,  476014.4569415 ,  305276.23557673,\n","        590784.32443641,  441316.50210455,  265910.97279499,\n","        319470.24429261,  266451.36768408,  331214.22563058,\n","        327784.90740811,  319470.24429261,  244403.66193686,\n","        252780.99555724,  268449.97075841,  912139.95342218,\n","        430604.64780502,  536459.92048882, 1156407.40322869,\n","        395408.55510658,  221600.76337596,  327898.59243044,\n","        237907.12512623,  498752.66850787,  468835.9897142 ,\n","        350852.56592942,  300033.9934493 ,  232365.80188326,\n","        533897.52855045,  232365.80188326,  369329.42975094,\n","       -118069.19958188,  317722.33084589,  323601.95952243,\n","        369203.85354041,  268053.34365489, 1051697.65952951,\n","        254248.58995229,  303300.6690092 ,  273638.81053964,\n","        244461.9836068 ,  258111.42397945,  388332.16478956,\n","        429074.38290509,  536459.92048882,  800353.81940598,\n","        298918.26415178,  407917.66889452,  388332.16478956,\n","        414613.66267689, 1262607.50420783,  369329.42975094,\n","        319129.65201908,  334197.9591093 ,  286263.77904024,\n","        307993.25754312,  741174.54173005,  491064.17223088,\n","        298429.10191855,  292957.60313228,  315911.57663126,\n","        327478.85442812,  451544.27942111,  317135.7885512 ,\n","        724682.50318048,  509137.53807322,  361833.3014316 ,\n","        693810.21059336,  582168.1274389 ,  212609.37224369,\n","        260216.62306202,  710680.29626995,  264840.07044119,\n","        300877.52575844,  309268.70211893,  389929.9023685 ,\n","        464347.27192468,  347409.46990458,  693810.21059336,\n","        468363.13244184,  427977.91688601,  251373.45624563,\n","        427817.80138193,  352408.11141849,  728508.16543031,\n","        749166.7415794 ,  558648.76153784,  450512.15238267,\n","        571124.93957025,  592161.2797702 ,  418937.46278821,\n","        319398.53322173,  415378.79512685,  600960.30294481,\n","        263047.6131269 ,  364648.06092761,  325259.97032322,\n","        589476.22718124,  599471.54920288,  983410.6732152 ,\n","        405432.07327729,  442158.14779951,  491279.65108734,\n","        636692.27143438,  311900.23521207,  186643.53405465,\n","        454252.04268309,  348902.56302718,  335848.88089601,\n","        377701.62590915,  377701.62590915,  353370.41400023,\n","        376477.41398921,  560336.57202573,  556969.98924588,\n","        402990.3382257 ,  568449.1456857 ,  448323.35104102,\n","        517259.61509264,  688264.08517628,  606585.11129723,\n","       1137012.09739106,  327010.51625373,  361028.82751397,\n","        628428.55789859,  413554.08535898,  341098.21203752,\n","        401415.92968398,  455318.42593893, 1619425.93740436,\n","        451114.99963823,  267139.98688905,  342658.5597007 ,\n","        304976.87138504,  438573.91647287,  304976.87138504,\n","        392508.02366116,  458652.63911557,  547637.54304662,\n","        524873.76781497,  508805.98636568,  382751.50007893,\n","        366338.32418199,  645108.72838401,  532942.19783316])"]},"execution_count":231,"metadata":{},"output_type":"execute_result"}],"source":["model1.predict(df_test)"]},{"cell_type":"markdown","metadata":{},"source":["Saving the model to file"]},{"cell_type":"code","execution_count":233,"metadata":{},"outputs":[{"data":{"text/plain":["['ridge_model.sav']"]},"execution_count":233,"metadata":{},"output_type":"execute_result"}],"source":["filename = 'ridge_model.sav'\n","joblib.dump(model1, filename)"]}],"metadata":{"colab":{"authorship_tag":"ABX9TyMI6m3bAQGO+zYnw6aWIlMe","provenance":[],"toc_visible":true},"kernelspec":{"display_name":"Python 3","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":0}
+{"cells":[{"cell_type":"code","execution_count":232,"metadata":{"executionInfo":{"elapsed":422,"status":"ok","timestamp":1696951840697,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"veKEtGweNaXi"},"outputs":[],"source":["import pandas as pd\n","import numpy as np\n","import joblib\n"]},{"cell_type":"code","execution_count":191,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":4,"status":"ok","timestamp":1696952151344,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"w7poi-MONhxI","outputId":"379c3cbe-96bc-4d7e-d27f-dd56d02a817b"},"outputs":[],"source":["df_train = pd.read_csv('train.tsv', sep='\\t', header=None)"]},{"cell_type":"code","execution_count":192,"metadata":{"executionInfo":{"elapsed":226,"status":"ok","timestamp":1696952356655,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"8vT9n8oCPIhS"},"outputs":[],"source":["pd.set_option('display.max_columns', 500)"]},{"cell_type":"code","execution_count":193,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":643},"executionInfo":{"elapsed":254,"status":"ok","timestamp":1696952363298,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"hbfWxhoOOeQH","outputId":"3a4608d9-8d37-47c3-b28e-d64be0c43e2d"},"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>10</th>\n","      <th>11</th>\n","      <th>12</th>\n","      <th>13</th>\n","      <th>14</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","      <th>25</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>309000.0</td>\n","      <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","      <td>2</td>\n","      <td>NaN</td>\n","      <td>43.44</td>\n","      <td>wtórny</td>\n","      <td>4.0</td>\n","      <td>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Niezależny Układ W Nowoczesnym Wydaniu</td>\n","      <td>1</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>Polecamy na sprzedaż dwupokojowe mieszkanie p...</td>\n","      <td>NaN</td>\n","      <td>telewizja kablowa, internet, meble, piwnica, g...</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>314900.0</td>\n","      <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","      <td>2</td>\n","      <td>NaN</td>\n","      <td>42.60</td>\n","      <td>pierwotny</td>\n","      <td>2.0</td>\n","      <td>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Urokliwe mieszkanie 2 pokojowe Strzeszyn</td>\n","      <td>1</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>Kameralne 2 pokojowe mieszkanie z aneksem kuc...</td>\n","      <td>NaN</td>\n","      <td>telewizja kablowa, internet, telefon, drzwi / ...</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>249000.0</td>\n","      <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","      <td>2</td>\n","      <td>NaN</td>\n","      <td>44.30</td>\n","      <td>wtórny</td>\n","      <td>4.0</td>\n","      <td>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Mieszkanie do remontu ul. Klonowa, blisko tramwaj</td>\n","      <td>2</td>\n","      <td>NaN</td>\n","      <td>miejskie</td>\n","      <td>plastikowe</td>\n","      <td>1960.0</td>\n","      <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","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>419000.0</td>\n","      <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","      <td>4</td>\n","      <td>NaN</td>\n","      <td>88</td>\n","      <td>wtórny</td>\n","      <td>3.0</td>\n","      <td>szeregowiec</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>W szeregowcu 4 pokoje z garażem</td>\n","      <td>1</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","      <td>NaN</td>\n","      <td>telewizja kablowa, internet, zmywarka, lodówka...</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>499000.0</td>\n","      <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","      <td>3</td>\n","      <td>NaN</td>\n","      <td>77</td>\n","      <td>wtórny</td>\n","      <td>16.0</td>\n","      <td>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Komfortowe,Przestronne,3Pokoje, Armii Krajowej!!!</td>\n","      <td>7</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>plastikowe</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Biuro Immohouse ma przyjemność proponować do ...</td>\n","      <td>NaN</td>\n","      <td>balkon, piwnica, winda</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["         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","                                                  5  6   7      8          9   \\\n","0  https://www.otodom.pl/oferta/niezalezny-uklad-...  2 NaN  43.44     wtórny   \n","1  https://www.otodom.pl/oferta/urokliwe-mieszkan...  2 NaN  42.60  pierwotny   \n","2  https://www.otodom.pl/oferta/mieszkanie-do-rem...  2 NaN  44.30     wtórny   \n","3  https://www.otodom.pl/oferta/w-szeregowcu-4-po...  4 NaN     88     wtórny   \n","4  https://www.otodom.pl/oferta/komfortowe-przest...  3 NaN     77     wtórny   \n","\n","     10           11  12  13  \\\n","0   4.0         blok NaN NaN   \n","1   2.0         blok NaN NaN   \n","2   4.0         blok NaN NaN   \n","3   3.0  szeregowiec NaN NaN   \n","4  16.0         blok NaN NaN   \n","\n","                                                  14 15  16        17  \\\n","0             Niezależny Układ W Nowoczesnym Wydaniu  1 NaN    gazowe   \n","1           Urokliwe mieszkanie 2 pokojowe Strzeszyn  1 NaN    gazowe   \n","2  Mieszkanie do remontu ul. Klonowa, blisko tramwaj  2 NaN  miejskie   \n","3                    W szeregowcu 4 pokoje z garażem  1 NaN    gazowe   \n","4  Komfortowe,Przestronne,3Pokoje, Armii Krajowej!!!  7 NaN       NaN   \n","\n","           18      19  20          21     22  \\\n","0  plastikowe     NaN NaN         NaN  cegła   \n","1  plastikowe     NaN NaN         NaN  cegła   \n","2  plastikowe  1960.0 NaN  2019-06-30  cegła   \n","3  plastikowe     NaN NaN         NaN  cegła   \n","4  plastikowe     NaN NaN         NaN    NaN   \n","\n","                                                  23  24  \\\n","0   Polecamy na sprzedaż dwupokojowe mieszkanie p... NaN   \n","1   Kameralne 2 pokojowe mieszkanie z aneksem kuc... NaN   \n","2   Oferta bezpośrednio od właściciela - bez pośr... NaN   \n","3   Drodzy Państwo Zapraszam do zapoznania się z ... NaN   \n","4   Biuro Immohouse ma przyjemność proponować do ... NaN   \n","\n","                                                  25  \n","0  telewizja kablowa, internet, meble, piwnica, g...  \n","1  telewizja kablowa, internet, telefon, drzwi / ...  \n","2  telewizja kablowa, internet, telefon, domofon ...  \n","3  telewizja kablowa, internet, zmywarka, lodówka...  \n","4                             balkon, piwnica, winda  "]},"execution_count":193,"metadata":{},"output_type":"execute_result"}],"source":["df_train.head()"]},{"cell_type":"markdown","metadata":{"id":"nt0TOLw5RAqS"},"source":["1,2,6, 8, 9 - to bedziemy w aplikacji używać\n"]},{"cell_type":"code","execution_count":194,"metadata":{},"outputs":[],"source":["df_train = df_train.iloc[:, [0, 1, 2, 6, 8, 9]]"]},{"cell_type":"code","execution_count":195,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":3,"status":"ok","timestamp":1696952402833,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"QdXwQzPsOza0","outputId":"d5d231f0-da54-432f-9bd6-454d4063eaff"},"outputs":[{"name":"stdout","output_type":"stream","text":["<class 'pandas.core.frame.DataFrame'>\n","RangeIndex: 2547 entries, 0 to 2546\n","Data columns (total 6 columns):\n"," #   Column  Non-Null Count  Dtype  \n","---  ------  --------------  -----  \n"," 0   0       2547 non-null   float64\n"," 1   1       1519 non-null   object \n"," 2   2       929 non-null    object \n"," 3   6       2547 non-null   object \n"," 4   8       2547 non-null   object \n"," 5   9       2547 non-null   object \n","dtypes: float64(1), object(5)\n","memory usage: 119.5+ KB\n"]}],"source":["df_train.info()"]},{"cell_type":"code","execution_count":196,"metadata":{},"outputs":[],"source":["df_train.rename(columns={0: \"cena m\", 1: \"stan\", 2: \"czynsz\", 6: \"l pokoi\", 8: \"metraż\", 9: \"rynek\"}, inplace=True)"]},{"cell_type":"code","execution_count":197,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["<class 'pandas.core.frame.DataFrame'>\n","RangeIndex: 2547 entries, 0 to 2546\n","Data columns (total 6 columns):\n"," #   Column   Non-Null Count  Dtype  \n","---  ------   --------------  -----  \n"," 0   cena m   2547 non-null   float64\n"," 1   stan     1519 non-null   object \n"," 2   czynsz   929 non-null    object \n"," 3   l pokoi  2547 non-null   object \n"," 4   metraż   2547 non-null   object \n"," 5   rynek    2547 non-null   object \n","dtypes: float64(1), object(5)\n","memory usage: 119.5+ KB\n"]}],"source":["df_train.info()"]},{"cell_type":"markdown","metadata":{},"source":["Usunięcie kolumn, w których jest dużo pustych wartości"]},{"cell_type":"code","execution_count":198,"metadata":{"executionInfo":{"elapsed":249,"status":"ok","timestamp":1696953612119,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"x6jB9brYRSTJ"},"outputs":[],"source":["df_train.drop(columns = ['czynsz'], axis=1, inplace=True)"]},{"cell_type":"code","execution_count":199,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":608},"executionInfo":{"elapsed":339,"status":"ok","timestamp":1696953613765,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"NIzvOY2BQqTK","outputId":"ceaa0534-470a-4296-f51c-97f1b9904190"},"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 m</th>\n","      <th>stan</th>\n","      <th>l pokoi</th>\n","      <th>metraż</th>\n","      <th>rynek</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>309000.0</td>\n","      <td>do zamieszkania</td>\n","      <td>2</td>\n","      <td>43.44</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>314900.0</td>\n","      <td>do wykończenia</td>\n","      <td>2</td>\n","      <td>42.60</td>\n","      <td>pierwotny</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>249000.0</td>\n","      <td>do remontu</td>\n","      <td>2</td>\n","      <td>44.30</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>419000.0</td>\n","      <td>do zamieszkania</td>\n","      <td>4</td>\n","      <td>88</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>499000.0</td>\n","      <td>NaN</td>\n","      <td>3</td>\n","      <td>77</td>\n","      <td>wtórny</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["     cena m             stan l pokoi metraż      rynek\n","0  309000.0  do zamieszkania       2  43.44     wtórny\n","1  314900.0   do wykończenia       2  42.60  pierwotny\n","2  249000.0       do remontu       2  44.30     wtórny\n","3  419000.0  do zamieszkania       4     88     wtórny\n","4  499000.0              NaN       3     77     wtórny"]},"execution_count":199,"metadata":{},"output_type":"execute_result"}],"source":["df_train.head()"]},{"cell_type":"markdown","metadata":{},"source":["Uzupełnianie braków w danych "]},{"cell_type":"code","execution_count":200,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":3,"status":"ok","timestamp":1696953649491,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"qNqxEsnNUZcH","outputId":"33ce3384-6b79-4795-c582-0d8fd8457943"},"outputs":[{"name":"stdout","output_type":"stream","text":["<class 'pandas.core.frame.DataFrame'>\n","RangeIndex: 2547 entries, 0 to 2546\n","Data columns (total 5 columns):\n"," #   Column   Non-Null Count  Dtype  \n","---  ------   --------------  -----  \n"," 0   cena m   2547 non-null   float64\n"," 1   stan     1519 non-null   object \n"," 2   l pokoi  2547 non-null   object \n"," 3   metraż   2547 non-null   object \n"," 4   rynek    2547 non-null   object \n","dtypes: float64(1), object(4)\n","memory usage: 99.6+ KB\n"]}],"source":["df_train.info()"]},{"cell_type":"code","execution_count":201,"metadata":{"executionInfo":{"elapsed":245,"status":"ok","timestamp":1696953995554,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"5BTDYi_xUdGF"},"outputs":[],"source":["df_train['stan'].fillna('brak info', inplace=True)"]},{"cell_type":"code","execution_count":202,"metadata":{},"outputs":[],"source":["df_train = df_train[df_train['metraż'] != \"6 909\"]"]},{"cell_type":"code","execution_count":203,"metadata":{},"outputs":[],"source":["df_train = df_train[df_train['l pokoi'] != \"więcej niż 10\"]"]},{"cell_type":"code","execution_count":204,"metadata":{},"outputs":[],"source":["df_train['l pokoi'] = pd.to_numeric(df_train['l pokoi'])"]},{"cell_type":"code","execution_count":205,"metadata":{},"outputs":[],"source":["df_train['metraż'] = pd.to_numeric(df_train['metraż'])"]},{"cell_type":"code","execution_count":206,"metadata":{},"outputs":[],"source":["X_train = df_train.drop(columns = [\"cena m\"])\n","y_train = df_train[\"cena m\"]"]},{"cell_type":"code","execution_count":207,"metadata":{"executionInfo":{"elapsed":240,"status":"ok","timestamp":1696955504933,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"LW2CpZn6V5sl"},"outputs":[],"source":["number_cols = X_train.select_dtypes(exclude=[object]).columns\n","object_cols = X_train.select_dtypes(include=[object]).columns"]},{"cell_type":"code","execution_count":208,"metadata":{"executionInfo":{"elapsed":6,"status":"ok","timestamp":1696954577003,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"DJOcANTvXMjl"},"outputs":[],"source":["from sklearn.compose import ColumnTransformer\n","from sklearn.preprocessing import OneHotEncoder\n","from sklearn.preprocessing import StandardScaler\n","from sklearn.pipeline import make_pipeline"]},{"cell_type":"code","execution_count":209,"metadata":{"executionInfo":{"elapsed":240,"status":"ok","timestamp":1696955508626,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"5nvY10OHXjEw"},"outputs":[],"source":["ct = ColumnTransformer([\n","        (number_cols, StandardScaler()),\n","        (object_cols, OneHotEncoder())\n","    ],remainder='passthrough')\n"]},{"cell_type":"code","execution_count":210,"metadata":{"executionInfo":{"elapsed":529,"status":"ok","timestamp":1696954626952,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"wcGvPEZzYDPZ"},"outputs":[],"source":["from sklearn.linear_model import Ridge"]},{"cell_type":"code","execution_count":211,"metadata":{"executionInfo":{"elapsed":343,"status":"ok","timestamp":1696955511401,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"4z3w4bzbYseK"},"outputs":[],"source":["scaler = StandardScaler()\n","encoder = OneHotEncoder()\n","# putting numeric columns to scaler and categorical to encoder\n","num_transformer = make_pipeline(scaler)\n","cat_transformer = make_pipeline(encoder)\n","\n","# getting together our scaler and encoder with preprocessor\n","preprocessor = ColumnTransformer(\n","      transformers=[('num', num_transformer, number_cols),\n","                    ('cat', cat_transformer, object_cols)])"]},{"cell_type":"code","execution_count":212,"metadata":{"executionInfo":{"elapsed":354,"status":"ok","timestamp":1696955513049,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"QXvbFrmXYLtR"},"outputs":[],"source":["clf = Ridge(alpha=1.0)"]},{"cell_type":"code","execution_count":213,"metadata":{"executionInfo":{"elapsed":428,"status":"ok","timestamp":1696955515987,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"pytR_osgX5Lb"},"outputs":[],"source":["model1 = make_pipeline(preprocessor, clf)"]},{"cell_type":"code","execution_count":214,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":608},"executionInfo":{"elapsed":233,"status":"ok","timestamp":1696955309653,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"vzR7OGK8Z-lD","outputId":"6aa1623d-b9fb-46ad-a200-f185708542ac"},"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>stan</th>\n","      <th>l pokoi</th>\n","      <th>metraż</th>\n","      <th>rynek</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>do zamieszkania</td>\n","      <td>2</td>\n","      <td>43.44</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>do wykończenia</td>\n","      <td>2</td>\n","      <td>42.60</td>\n","      <td>pierwotny</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>do remontu</td>\n","      <td>2</td>\n","      <td>44.30</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>do zamieszkania</td>\n","      <td>4</td>\n","      <td>88.00</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>brak info</td>\n","      <td>3</td>\n","      <td>77.00</td>\n","      <td>wtórny</td>\n","    </tr>\n","  </tbody>\n","</table>\n","</div>"],"text/plain":["              stan  l pokoi  metraż      rynek\n","0  do zamieszkania        2   43.44     wtórny\n","1   do wykończenia        2   42.60  pierwotny\n","2       do remontu        2   44.30     wtórny\n","3  do zamieszkania        4   88.00     wtórny\n","4        brak info        3   77.00     wtórny"]},"execution_count":214,"metadata":{},"output_type":"execute_result"}],"source":["X_train.head()"]},{"cell_type":"code","execution_count":215,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":7,"status":"ok","timestamp":1696955419804,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"vcg92-RtbLSH","outputId":"457f8462-c2d8-4721-a19a-fb855998472c"},"outputs":[{"data":{"text/plain":["0       309000.0\n","1       314900.0\n","2       249000.0\n","3       419000.0\n","4       499000.0\n","          ...   \n","2541    383680.0\n","2542    507600.0\n","2543    342400.0\n","2544    335000.0\n","2545    260000.0\n","Name: cena m, Length: 2540, dtype: float64"]},"execution_count":215,"metadata":{},"output_type":"execute_result"}],"source":["y_train"]},{"cell_type":"markdown","metadata":{"id":"GY_ZQICKc__t"},"source":["## Model Ridge - regresja liniowa"]},{"cell_type":"code","execution_count":216,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":191},"executionInfo":{"elapsed":236,"status":"ok","timestamp":1696955526976,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"cFvgBYD5YYz7","outputId":"008e021f-cb56-4458-99e8-ca95df32e68d"},"outputs":[{"data":{"text/html":["<style>#sk-container-id-7 {color: black;}#sk-container-id-7 pre{padding: 0;}#sk-container-id-7 div.sk-toggleable {background-color: white;}#sk-container-id-7 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-7 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-7 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-7 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-7 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-7 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-7 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-7 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-7 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 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-7 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-7 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-7 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-7 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-7 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-7 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-7 div.sk-item {position: relative;z-index: 1;}#sk-container-id-7 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-7 div.sk-item::before, #sk-container-id-7 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-7 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-7 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-7 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-7 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-7 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-7 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-7 div.sk-label-container {text-align: center;}#sk-container-id-7 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-7 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-7\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;columntransformer&#x27;,\n","                 ColumnTransformer(transformers=[(&#x27;num&#x27;,\n","                                                  Pipeline(steps=[(&#x27;standardscaler&#x27;,\n","                                                                   StandardScaler())]),\n","                                                  Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)),\n","                                                 (&#x27;cat&#x27;,\n","                                                  Pipeline(steps=[(&#x27;onehotencoder&#x27;,\n","                                                                   OneHotEncoder())]),\n","                                                  Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;))])),\n","                (&#x27;ridge&#x27;, Ridge())])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-43\" type=\"checkbox\" ><label for=\"sk-estimator-id-43\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;columntransformer&#x27;,\n","                 ColumnTransformer(transformers=[(&#x27;num&#x27;,\n","                                                  Pipeline(steps=[(&#x27;standardscaler&#x27;,\n","                                                                   StandardScaler())]),\n","                                                  Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)),\n","                                                 (&#x27;cat&#x27;,\n","                                                  Pipeline(steps=[(&#x27;onehotencoder&#x27;,\n","                                                                   OneHotEncoder())]),\n","                                                  Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;))])),\n","                (&#x27;ridge&#x27;, Ridge())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-44\" type=\"checkbox\" ><label for=\"sk-estimator-id-44\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">columntransformer: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(transformers=[(&#x27;num&#x27;,\n","                                 Pipeline(steps=[(&#x27;standardscaler&#x27;,\n","                                                  StandardScaler())]),\n","                                 Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)),\n","                                (&#x27;cat&#x27;,\n","                                 Pipeline(steps=[(&#x27;onehotencoder&#x27;,\n","                                                  OneHotEncoder())]),\n","                                 Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;))])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-45\" type=\"checkbox\" ><label for=\"sk-estimator-id-45\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">num</label><div class=\"sk-toggleable__content\"><pre>Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-46\" type=\"checkbox\" ><label for=\"sk-estimator-id-46\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-47\" type=\"checkbox\" ><label for=\"sk-estimator-id-47\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">cat</label><div class=\"sk-toggleable__content\"><pre>Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-48\" type=\"checkbox\" ><label for=\"sk-estimator-id-48\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder()</pre></div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-49\" type=\"checkbox\" ><label for=\"sk-estimator-id-49\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Ridge</label><div class=\"sk-toggleable__content\"><pre>Ridge()</pre></div></div></div></div></div></div></div>"],"text/plain":["Pipeline(steps=[('columntransformer',\n","                 ColumnTransformer(transformers=[('num',\n","                                                  Pipeline(steps=[('standardscaler',\n","                                                                   StandardScaler())]),\n","                                                  Index(['l pokoi', 'metraż'], dtype='object')),\n","                                                 ('cat',\n","                                                  Pipeline(steps=[('onehotencoder',\n","                                                                   OneHotEncoder())]),\n","                                                  Index(['stan', 'rynek'], dtype='object'))])),\n","                ('ridge', Ridge())])"]},"execution_count":216,"metadata":{},"output_type":"execute_result"}],"source":["model1.fit(X_train, y_train)"]},{"cell_type":"code","execution_count":217,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":451,"status":"ok","timestamp":1696955647207,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"M7X8ScQobnwG","outputId":"a30f27eb-2e34-4a91-fae0-a9ab53505322"},"outputs":[],"source":["df_test = pd.read_csv('in.tsv', sep='\\t', header=None)"]},{"cell_type":"code","execution_count":218,"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":573},"executionInfo":{"elapsed":5,"status":"ok","timestamp":1696955652118,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"x3qN4TMKcDfL","outputId":"ed2fa477-65e6-494e-9423-de6894c47ef8"},"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>10</th>\n","      <th>11</th>\n","      <th>12</th>\n","      <th>13</th>\n","      <th>14</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>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>idealne mieszkanie do zamieszkania od zaraz</td>\n","      <td>2</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>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>2 pokoje / 38m2 / po remoncie / Winogrady</td>\n","      <td>4</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>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>3 pokoje na Jeżycach blisko Rusałki</td>\n","      <td>4</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>blok</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Uniwersytet Przyrodniczy - 4 pokoje - ROI 8-10%</td>\n","      <td>10</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>NaN</td>\n","      <td>NaN</td>\n","      <td>NaN</td>\n","      <td>Mieszkanie blisko centrum w kameralnej okolicy.</td>\n","      <td>1</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","  </tbody>\n","</table>\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","                                                  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","          8     9     10  11  12  \\\n","0     wtórny   4.0  blok NaN NaN   \n","1     wtórny  12.0  blok NaN NaN   \n","2     wtórny   4.0  blok NaN NaN   \n","3     wtórny  10.0  blok NaN NaN   \n","4  pierwotny   3.0   NaN NaN NaN   \n","\n","                                                13  14  15        16  \\\n","0      idealne mieszkanie do zamieszkania od zaraz   2 NaN  miejskie   \n","1        2 pokoje / 38m2 / po remoncie / Winogrady   4 NaN      inne   \n","2              3 pokoje na Jeżycach blisko Rusałki   4 NaN  miejskie   \n","3  Uniwersytet Przyrodniczy - 4 pokoje - ROI 8-10%  10 NaN  miejskie   \n","4  Mieszkanie blisko centrum w kameralnej okolicy.   1 NaN       NaN   \n","\n","           17      18  19          20            21  \\\n","0  plastikowe     NaN NaN         NaN  wielka płyta   \n","1  plastikowe     NaN NaN         NaN           NaN   \n","2  plastikowe  1958.0 NaN         NaN         cegła   \n","3  plastikowe  1975.0 NaN  2019-06-30  wielka płyta   \n","4         NaN  2020.0 NaN  2020-01-01           NaN   \n","\n","                                                  22  23  \\\n","0   Zamieszkaj od zaraz – idealna lokalizacja OFE... NaN   \n","1   Na sprzedaż mieszkanie dwupokojowe na osiedlu... NaN   \n","2   !! Oferta dostępna tylko u nas !! Polecam ofe... NaN   \n","3   Oferta  bezpośrednio od właściciela  - bez po... NaN   \n","4   MIESZKANIE 3-POKOJOWE O POW.65,62M2 Mieszkani... 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  "]},"execution_count":218,"metadata":{},"output_type":"execute_result"}],"source":["df_test.head()"]},{"cell_type":"code","execution_count":219,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":244,"status":"ok","timestamp":1696955801209,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"UybULQjXcMbT","outputId":"1bd9cb56-50cf-4040-f797-0d54e0293ef5"},"outputs":[],"source":["y_test = pd.read_csv('expected.tsv', sep='\\t', header=None)"]},{"cell_type":"code","execution_count":220,"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>stan</th>\n","      <th>l pokoi</th>\n","      <th>metraż</th>\n","      <th>rynek</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <th>0</th>\n","      <td>do zamieszkania</td>\n","      <td>2</td>\n","      <td>43.44</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>1</th>\n","      <td>do wykończenia</td>\n","      <td>2</td>\n","      <td>42.60</td>\n","      <td>pierwotny</td>\n","    </tr>\n","    <tr>\n","      <th>2</th>\n","      <td>do remontu</td>\n","      <td>2</td>\n","      <td>44.30</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>3</th>\n","      <td>do zamieszkania</td>\n","      <td>4</td>\n","      <td>88.00</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>4</th>\n","      <td>brak info</td>\n","      <td>3</td>\n","      <td>77.00</td>\n","      <td>wtórny</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>do wykończenia</td>\n","      <td>3</td>\n","      <td>70.40</td>\n","      <td>pierwotny</td>\n","    </tr>\n","    <tr>\n","      <th>2542</th>\n","      <td>do wykończenia</td>\n","      <td>4</td>\n","      <td>94.00</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>2543</th>\n","      <td>brak info</td>\n","      <td>2</td>\n","      <td>53.50</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>2544</th>\n","      <td>brak info</td>\n","      <td>3</td>\n","      <td>55.25</td>\n","      <td>wtórny</td>\n","    </tr>\n","    <tr>\n","      <th>2545</th>\n","      <td>brak info</td>\n","      <td>3</td>\n","      <td>62.00</td>\n","      <td>wtórny</td>\n","    </tr>\n","  </tbody>\n","</table>\n","<p>2540 rows × 4 columns</p>\n","</div>"],"text/plain":["                 stan  l pokoi  metraż      rynek\n","0     do zamieszkania        2   43.44     wtórny\n","1      do wykończenia        2   42.60  pierwotny\n","2          do remontu        2   44.30     wtórny\n","3     do zamieszkania        4   88.00     wtórny\n","4           brak info        3   77.00     wtórny\n","...               ...      ...     ...        ...\n","2541   do wykończenia        3   70.40  pierwotny\n","2542   do wykończenia        4   94.00     wtórny\n","2543        brak info        2   53.50     wtórny\n","2544        brak info        3   55.25     wtórny\n","2545        brak info        3   62.00     wtórny\n","\n","[2540 rows x 4 columns]"]},"execution_count":220,"metadata":{},"output_type":"execute_result"}],"source":["X_train"]},{"cell_type":"code","execution_count":221,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":8,"status":"ok","timestamp":1696955946495,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"WMsGxdMwdMM8","outputId":"d2a8f0ac-4051-465e-d43c-e1fb7b9a3034"},"outputs":[],"source":["df_test.rename(columns={0: \"stan\", 1: \"czynsz\", 5: \"l pokoi\", 7: \"metraż\", 8: \"rynek\"}, inplace=True)"]},{"cell_type":"code","execution_count":222,"metadata":{"executionInfo":{"elapsed":226,"status":"ok","timestamp":1696956067214,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"TNHLwq_5daGO"},"outputs":[{"data":{"text/plain":["Index([   'stan',  'czynsz',         2,         3,         4, 'l pokoi',\n","               6,  'metraż',   'rynek',         9,        10,        11,\n","              12,        13,        14,        15,        16,        17,\n","              18,        19,        20,        21,        22,        23,\n","              24],\n","      dtype='object')"]},"execution_count":222,"metadata":{},"output_type":"execute_result"}],"source":["df_test.columns"]},{"cell_type":"code","execution_count":223,"metadata":{},"outputs":[],"source":["df_test = df_test[['stan', 'l pokoi', 'metraż',  'rynek']] "]},{"cell_type":"code","execution_count":224,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"elapsed":6,"status":"ok","timestamp":1696956090162,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"tbcOpXendvZv","outputId":"93eddcd2-b741-4aa6-b185-59c96dc2e833"},"outputs":[{"name":"stdout","output_type":"stream","text":["<class 'pandas.core.frame.DataFrame'>\n","RangeIndex: 462 entries, 0 to 461\n","Data columns (total 4 columns):\n"," #   Column   Non-Null Count  Dtype  \n","---  ------   --------------  -----  \n"," 0   stan     275 non-null    object \n"," 1   l pokoi  462 non-null    int64  \n"," 2   metraż   462 non-null    float64\n"," 3   rynek    462 non-null    object \n","dtypes: float64(1), int64(1), object(2)\n","memory usage: 14.6+ KB\n"]}],"source":["df_test.info()"]},{"cell_type":"code","execution_count":225,"metadata":{"executionInfo":{"elapsed":323,"status":"ok","timestamp":1696956241887,"user":{"displayName":"Aneta Tlałka","userId":"13389112088336863360"},"user_tz":-120},"id":"j5IFS4YQdKPW"},"outputs":[],"source":["df_test['stan'].fillna('brak info', inplace=True)"]},{"cell_type":"code","execution_count":226,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["<class 'pandas.core.frame.DataFrame'>\n","RangeIndex: 462 entries, 0 to 461\n","Data columns (total 4 columns):\n"," #   Column   Non-Null Count  Dtype  \n","---  ------   --------------  -----  \n"," 0   stan     462 non-null    object \n"," 1   l pokoi  462 non-null    int64  \n"," 2   metraż   462 non-null    float64\n"," 3   rynek    462 non-null    object \n","dtypes: float64(1), int64(1), object(2)\n","memory usage: 14.6+ KB\n"]}],"source":["df_test.info()"]},{"cell_type":"code","execution_count":227,"metadata":{},"outputs":[{"data":{"text/plain":["0      59.10\n","1      38.00\n","2      63.84\n","3      50.00\n","4      65.62\n","       ...  \n","457    72.78\n","458    51.23\n","459    54.16\n","460    90.10\n","461    71.90\n","Name: metraż, Length: 462, dtype: float64"]},"execution_count":227,"metadata":{},"output_type":"execute_result"}],"source":["df_test['metraż']"]},{"cell_type":"code","execution_count":228,"metadata":{},"outputs":[],"source":["df_test.reset_index(drop=True, inplace=True)"]},{"cell_type":"code","execution_count":229,"metadata":{},"outputs":[{"name":"stdout","output_type":"stream","text":["<class 'pandas.core.frame.DataFrame'>\n","RangeIndex: 462 entries, 0 to 461\n","Data columns (total 4 columns):\n"," #   Column   Non-Null Count  Dtype  \n","---  ------   --------------  -----  \n"," 0   stan     462 non-null    object \n"," 1   l pokoi  462 non-null    int64  \n"," 2   metraż   462 non-null    float64\n"," 3   rynek    462 non-null    object \n","dtypes: float64(1), int64(1), object(2)\n","memory usage: 14.6+ KB\n"]}],"source":["df_test.info()"]},{"cell_type":"code","execution_count":230,"metadata":{},"outputs":[{"data":{"text/html":["<style>#sk-container-id-8 {color: black;}#sk-container-id-8 pre{padding: 0;}#sk-container-id-8 div.sk-toggleable {background-color: white;}#sk-container-id-8 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-8 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-8 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-8 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-8 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-8 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-8 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-8 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-8 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 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-8 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-8 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-8 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-8 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-8 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-8 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-8 div.sk-item {position: relative;z-index: 1;}#sk-container-id-8 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-8 div.sk-item::before, #sk-container-id-8 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-8 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-8 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-8 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-8 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-8 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-8 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-8 div.sk-label-container {text-align: center;}#sk-container-id-8 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-8 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-8\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>Pipeline(steps=[(&#x27;columntransformer&#x27;,\n","                 ColumnTransformer(transformers=[(&#x27;num&#x27;,\n","                                                  Pipeline(steps=[(&#x27;standardscaler&#x27;,\n","                                                                   StandardScaler())]),\n","                                                  Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)),\n","                                                 (&#x27;cat&#x27;,\n","                                                  Pipeline(steps=[(&#x27;onehotencoder&#x27;,\n","                                                                   OneHotEncoder())]),\n","                                                  Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;))])),\n","                (&#x27;ridge&#x27;, Ridge())])</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-50\" type=\"checkbox\" ><label for=\"sk-estimator-id-50\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Pipeline</label><div class=\"sk-toggleable__content\"><pre>Pipeline(steps=[(&#x27;columntransformer&#x27;,\n","                 ColumnTransformer(transformers=[(&#x27;num&#x27;,\n","                                                  Pipeline(steps=[(&#x27;standardscaler&#x27;,\n","                                                                   StandardScaler())]),\n","                                                  Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)),\n","                                                 (&#x27;cat&#x27;,\n","                                                  Pipeline(steps=[(&#x27;onehotencoder&#x27;,\n","                                                                   OneHotEncoder())]),\n","                                                  Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;))])),\n","                (&#x27;ridge&#x27;, Ridge())])</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-51\" type=\"checkbox\" ><label for=\"sk-estimator-id-51\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">columntransformer: ColumnTransformer</label><div class=\"sk-toggleable__content\"><pre>ColumnTransformer(transformers=[(&#x27;num&#x27;,\n","                                 Pipeline(steps=[(&#x27;standardscaler&#x27;,\n","                                                  StandardScaler())]),\n","                                 Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)),\n","                                (&#x27;cat&#x27;,\n","                                 Pipeline(steps=[(&#x27;onehotencoder&#x27;,\n","                                                  OneHotEncoder())]),\n","                                 Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;))])</pre></div></div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-52\" type=\"checkbox\" ><label for=\"sk-estimator-id-52\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">num</label><div class=\"sk-toggleable__content\"><pre>Index([&#x27;l pokoi&#x27;, &#x27;metraż&#x27;], dtype=&#x27;object&#x27;)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-53\" type=\"checkbox\" ><label for=\"sk-estimator-id-53\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">StandardScaler</label><div class=\"sk-toggleable__content\"><pre>StandardScaler()</pre></div></div></div></div></div></div></div></div><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-54\" type=\"checkbox\" ><label for=\"sk-estimator-id-54\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">cat</label><div class=\"sk-toggleable__content\"><pre>Index([&#x27;stan&#x27;, &#x27;rynek&#x27;], dtype=&#x27;object&#x27;)</pre></div></div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-55\" type=\"checkbox\" ><label for=\"sk-estimator-id-55\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">OneHotEncoder</label><div class=\"sk-toggleable__content\"><pre>OneHotEncoder()</pre></div></div></div></div></div></div></div></div></div></div><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-56\" type=\"checkbox\" ><label for=\"sk-estimator-id-56\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">Ridge</label><div class=\"sk-toggleable__content\"><pre>Ridge()</pre></div></div></div></div></div></div></div>"],"text/plain":["Pipeline(steps=[('columntransformer',\n","                 ColumnTransformer(transformers=[('num',\n","                                                  Pipeline(steps=[('standardscaler',\n","                                                                   StandardScaler())]),\n","                                                  Index(['l pokoi', 'metraż'], dtype='object')),\n","                                                 ('cat',\n","                                                  Pipeline(steps=[('onehotencoder',\n","                                                                   OneHotEncoder())]),\n","                                                  Index(['stan', 'rynek'], dtype='object'))])),\n","                ('ridge', Ridge())])"]},"execution_count":230,"metadata":{},"output_type":"execute_result"}],"source":["model1"]},{"cell_type":"markdown","metadata":{},"source":["Przykład - przewidywanie cen na danych testowych"]},{"cell_type":"code","execution_count":231,"metadata":{},"outputs":[{"data":{"text/plain":["array([ 407917.66889452,  285306.27863261,  444184.94702291,\n","        299459.05926666,  459271.83408962,  614055.95902743,\n","        311243.98561031,  361244.58944658,  329238.65906305,\n","        369470.84812889,  285350.13919824,  329238.65906305,\n","        420020.53940636,  399085.99304054,  368717.32379097,\n","        339834.65864991,  335512.74515277,  304524.88092914,\n","        367036.20209137,  286773.80808993,  354525.20168926,\n","        282085.35025252,  386303.76202814,  477660.29347794,\n","        407152.53644455,  490742.17175818,  529758.94244497,\n","        335044.40697838,  399501.21194489,  431641.29394143,\n","        331214.22563058,  334772.89329194,  404282.20491201,\n","        369968.98599038,  392538.22357404,  354476.13872373,\n","        531690.53563375,  428309.25045513,  298510.41733766,\n","        551966.54555785,  332974.0302655 ,  474293.99377424,\n","        247049.65613431,  383931.85143325,  546789.20856336,\n","        438766.28443053,  275556.44383868,  325403.7381088 ,\n","        319934.12593671,  277654.95413295,  294800.60980049,\n","        285306.27863261,  283776.01373268,  282811.35937324,\n","        511210.54963994,  327121.56879228,  335039.88788041,\n","        638797.47051695,  521922.40393947,  235305.67479634,\n","        238447.52001532,  465392.89368935,  272046.09327325,\n","        848434.43816552,  512546.27689188,  382253.07914128,\n","        781492.5027453 ,  531716.09929903,  442847.05008064,\n","        498968.43044048,  272108.82871587,  275556.44383868,\n","        307110.38376632,  373296.51037872,  320469.71865169,\n","        629040.94693472,  456886.14569235,  463535.64405524,\n","        356361.80264533,  387288.89243253,  249184.65490398,\n","        305443.0398691 ,  312129.77494706,  323562.90113092,\n","        286773.80808993,  338640.52949322,  265910.97279499,\n","        414803.86094421,  262352.30513363,  273562.29729465,\n","        959123.60494806,  476401.54226445,  463695.54142089,\n","        474293.99377424,  245933.92683679,  276309.90323886,\n","         95163.71086422,  410945.54601501,  377887.30507851,\n","        332477.49594204,  374627.25336918,  354168.19912956,\n","        369968.98599038,  311900.23521207,  275897.03611221,\n","        272224.40035237,  522497.33812211,  317135.7885512 ,\n","        317671.38126618,  357993.86137939,  352637.93422963,\n","        908358.15173798,  288551.8042999 ,  398779.94006055,\n","        279465.70834759,  310024.57586448,  367940.58322895,\n","        336039.07916333,  295296.8610478 ,  395408.55510658,\n","        289706.87506509,  461286.74212482,  959007.7502354 ,\n","        671918.16381992,  357151.93260828,  573837.44243868,\n","        286071.41108258,  453635.41762516,  294033.30766019,\n","        430106.50994353,  361819.52362922,  280070.72529348,\n","        820481.6050142 ,  349767.60269709,  364114.92097912,\n","        262468.15984629,  301183.86181458,  297937.65284535,\n","        285306.27863261,  393955.0865278 ,  666659.89980777,\n","        560179.02643777,  440551.36965458,  544315.22105819,\n","        460711.80794218,  281978.75424428,  380105.90610726,\n","        501187.31454538,  343001.78445802,  567830.35093743,\n","        262544.39001514,  332442.95664849,  703770.99332145,\n","        369470.84812889,  494101.3824478 ,  273562.29729465,\n","        180666.17730277,  452295.35099255,  331304.51667796,\n","        453635.41762516,  323108.3407589 ,  507194.68912278,\n","        326474.92353875,  334772.89329194,  335044.40697838,\n","        240054.29816025,  562052.51609502,  274404.22606576,\n","        375397.37008062,  253585.25133645,  311900.23521207,\n","        365811.99017143,  339834.65864991,  395408.55510658,\n","        567728.27402715,  336238.53613507,  490526.69290172,\n","        257086.66903124,  385858.46036054,  344082.22859239,\n","        533220.80053368,  295941.33661099,  220577.95997966,\n","        291229.76787478,  200262.6085879 ,  281213.62179431,\n","        338640.52949322,  267288.49428108,  439786.23720462,\n","        400076.14612753,  301183.86181458,  479730.95326697,\n","        319470.24429261,  470581.73347059,  336354.39084773,\n","        491317.10594082,  354168.19912956,  369551.88047185,\n","        435462.4370933 ,  514271.0794398 ,  331214.22563058,\n","        234999.90489251,  240207.32465024,  395408.55510658,\n","        305290.01337911,  265336.03861235,  349500.60810862,\n","        315911.57663126,  448585.54345538,  310063.91733215,\n","        414803.86094421,  521922.40393947,  768450.42872618,\n","        285306.27863261,  414228.92676157,  408188.43671135,\n","        262917.91567413,  530071.86630062,  284993.07170081,\n","        354168.19912956,  350852.56592942,  341174.72528252,\n","        174670.0129817 ,  346185.25798463,  308617.25469129,\n","        319206.16526408,  479496.61135786,  285306.27863261,\n","        338832.89745087,  238677.05975031,  300193.70872759,\n","        284350.94791532,  312129.77494706,  288864.94629397,\n","        447136.31089841,  468759.4764692 ,  311243.98561031,\n","        773841.17824564,  309069.24514719,  311818.91979295,\n","        303300.6690092 ,  249129.2915516 ,  317026.62262684,\n","        270578.56381593,  374826.77527865,  317632.03979852,\n","        218540.23357609,  336303.15819187,  364613.05884061,\n","        419438.51620964,  348842.0716669 ,  300494.95953345,\n","        245456.65579176,  632191.76778196,  342245.91071247,\n","        321241.94011573,  345941.94044726,  654441.17458326,\n","        594917.92628041,  403059.87960624,  295368.85519483,\n","        287144.48312671,  504057.36300177,  259834.05683704,\n","        356196.60189099,  671431.17127702,  221915.85692194,\n","        266766.67936848,  862139.34958591,  253061.54980967,\n","        278229.88831559,  360787.39659078,  819749.12524361,\n","        225938.68930354,  337453.4893506 ,  417419.08907647,\n","        433477.61182135,  428415.84646337,  369470.84812889,\n","        644948.32980378,  369778.78772305,  486728.1978552 ,\n","        220003.02579702,  372225.04187261,  533707.33028312,\n","        268312.96615313,  351337.20906469,  266766.67936848,\n","        433665.17760489,  291427.33823234,  681260.15179974,\n","        386155.25463611,  361819.52362922,  378283.64910587,\n","        312584.05224292,  262442.87925716,  347027.18675575,\n","        388599.15937804,  330653.06925032,  331214.22563058,\n","        392424.82162787,  581111.00288747,  510178.4226015 ,\n","        638681.61580429,  273562.29729465,  332934.68879784,\n","        370402.78487122,  251183.25797831,  454520.92388575,\n","        327814.99017136,  317446.36062915,  270745.3681083 ,\n","        568020.54920476, 1041637.53573378,  445984.0931255 ,\n","        246474.72195167,  353326.27035845,  456478.01580208,\n","        268245.71161255,  476014.4569415 ,  305276.23557673,\n","        590784.32443641,  441316.50210455,  265910.97279499,\n","        319470.24429261,  266451.36768408,  331214.22563058,\n","        327784.90740811,  319470.24429261,  244403.66193686,\n","        252780.99555724,  268449.97075841,  912139.95342218,\n","        430604.64780502,  536459.92048882, 1156407.40322869,\n","        395408.55510658,  221600.76337596,  327898.59243044,\n","        237907.12512623,  498752.66850787,  468835.9897142 ,\n","        350852.56592942,  300033.9934493 ,  232365.80188326,\n","        533897.52855045,  232365.80188326,  369329.42975094,\n","       -118069.19958188,  317722.33084589,  323601.95952243,\n","        369203.85354041,  268053.34365489, 1051697.65952951,\n","        254248.58995229,  303300.6690092 ,  273638.81053964,\n","        244461.9836068 ,  258111.42397945,  388332.16478956,\n","        429074.38290509,  536459.92048882,  800353.81940598,\n","        298918.26415178,  407917.66889452,  388332.16478956,\n","        414613.66267689, 1262607.50420783,  369329.42975094,\n","        319129.65201908,  334197.9591093 ,  286263.77904024,\n","        307993.25754312,  741174.54173005,  491064.17223088,\n","        298429.10191855,  292957.60313228,  315911.57663126,\n","        327478.85442812,  451544.27942111,  317135.7885512 ,\n","        724682.50318048,  509137.53807322,  361833.3014316 ,\n","        693810.21059336,  582168.1274389 ,  212609.37224369,\n","        260216.62306202,  710680.29626995,  264840.07044119,\n","        300877.52575844,  309268.70211893,  389929.9023685 ,\n","        464347.27192468,  347409.46990458,  693810.21059336,\n","        468363.13244184,  427977.91688601,  251373.45624563,\n","        427817.80138193,  352408.11141849,  728508.16543031,\n","        749166.7415794 ,  558648.76153784,  450512.15238267,\n","        571124.93957025,  592161.2797702 ,  418937.46278821,\n","        319398.53322173,  415378.79512685,  600960.30294481,\n","        263047.6131269 ,  364648.06092761,  325259.97032322,\n","        589476.22718124,  599471.54920288,  983410.6732152 ,\n","        405432.07327729,  442158.14779951,  491279.65108734,\n","        636692.27143438,  311900.23521207,  186643.53405465,\n","        454252.04268309,  348902.56302718,  335848.88089601,\n","        377701.62590915,  377701.62590915,  353370.41400023,\n","        376477.41398921,  560336.57202573,  556969.98924588,\n","        402990.3382257 ,  568449.1456857 ,  448323.35104102,\n","        517259.61509264,  688264.08517628,  606585.11129723,\n","       1137012.09739106,  327010.51625373,  361028.82751397,\n","        628428.55789859,  413554.08535898,  341098.21203752,\n","        401415.92968398,  455318.42593893, 1619425.93740436,\n","        451114.99963823,  267139.98688905,  342658.5597007 ,\n","        304976.87138504,  438573.91647287,  304976.87138504,\n","        392508.02366116,  458652.63911557,  547637.54304662,\n","        524873.76781497,  508805.98636568,  382751.50007893,\n","        366338.32418199,  645108.72838401,  532942.19783316])"]},"execution_count":231,"metadata":{},"output_type":"execute_result"}],"source":["model1.predict(df_test)"]},{"cell_type":"code","execution_count":234,"metadata":{},"outputs":[{"data":{"text/plain":["Index(['stan', 'l pokoi', 'metraż', 'rynek'], dtype='object')"]},"execution_count":234,"metadata":{},"output_type":"execute_result"}],"source":["df_test.columns"]},{"cell_type":"code","execution_count":237,"metadata":{},"outputs":[{"data":{"text/plain":["array(['wtórny', 'pierwotny'], dtype=object)"]},"execution_count":237,"metadata":{},"output_type":"execute_result"}],"source":["X_train['rynek'].unique()"]},{"cell_type":"markdown","metadata":{},"source":["Saving the model to file"]},{"cell_type":"code","execution_count":233,"metadata":{},"outputs":[{"data":{"text/plain":["['ridge_model.sav']"]},"execution_count":233,"metadata":{},"output_type":"execute_result"}],"source":["filename = 'ridge_model.sav'\n","joblib.dump(model1, filename)"]}],"metadata":{"colab":{"authorship_tag":"ABX9TyMI6m3bAQGO+zYnw6aWIlMe","provenance":[],"toc_visible":true},"kernelspec":{"display_name":"Python 3","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":0}