s452979/mieszkania5
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
poprawki_ML
mieszkania5/model_regresji_liniowej.ipynb

1891 lines
58 KiB
Plaintext
Raw Permalink Normal View History

add files
2023-10-17 17:35:43 +02:00
{
"cells": [
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 2,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd"
]
},
Model modified, created pkl
2023-10-17 18:14:03 +02:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Wczytanie datasetów"
]
},
add files
2023-10-17 17:35:43 +02:00
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 11,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"train_dataset = pd.read_csv(\"./train.tsv\", sep = \"\\t\", header=None)"
add files
2023-10-17 17:35:43 +02:00
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 12,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"test_dataset = pd.read_csv(\"./in.tsv\", sep = \"\\t\", header=None)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Data exploration "
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>0</th>\n",
" <th>1</th>\n",
" <th>2</th>\n",
" <th>3</th>\n",
" <th>4</th>\n",
" <th>5</th>\n",
" <th>6</th>\n",
" <th>7</th>\n",
" <th>8</th>\n",
" <th>9</th>\n",
" <th>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",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 0 1 2 3 4 \\\n",
"0 309000.0 do zamieszkania 390 zł spółdzielcze własnościowe 7113 \n",
"\n",
" 5 6 7 8 9 \\\n",
"0 https://www.otodom.pl/oferta/niezalezny-uklad-... 2 NaN 43.44 wtórny \n",
"\n",
" 10 11 12 13 14 15 16 17 \\\n",
"0 4.0 blok NaN NaN Niezależny Układ W Nowoczesnym Wydaniu 1 NaN gazowe \n",
"\n",
" 18 19 20 21 22 \\\n",
"0 plastikowe NaN NaN NaN cegła \n",
"\n",
" 23 24 \\\n",
"0 Polecamy na sprzedaż dwupokojowe mieszkanie p... NaN \n",
"\n",
" 25 \n",
"0 telewizja kablowa, internet, meble, piwnica, g... "
]
},
"execution_count": 13,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_dataset.head(1)"
add files
2023-10-17 17:35:43 +02:00
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 6,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"4\n",
"7000 42\n",
"6750 42\n",
"7100 37\n",
"7500 29\n",
"7800 20\n",
" ..\n",
"9674 1\n",
"7565 1\n",
"8352 1\n",
"7511 1\n",
"5077 1\n",
"Name: count, Length: 1452, dtype: int64"
]
},
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 6,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_dataset[4].value_counts()"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 7,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
"pd.set_option(\"display.max_columns\", None)"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 8,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>0</th>\n",
" <th>4</th>\n",
" <th>7</th>\n",
" <th>10</th>\n",
" <th>12</th>\n",
" <th>13</th>\n",
" <th>16</th>\n",
" <th>19</th>\n",
" <th>20</th>\n",
" <th>24</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>2.547000e+03</td>\n",
" <td>2547.000000</td>\n",
" <td>0.0</td>\n",
" <td>2316.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" <td>1768.000000</td>\n",
" <td>0.0</td>\n",
" <td>0.0</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>4.210372e+05</td>\n",
" <td>7201.618767</td>\n",
" <td>NaN</td>\n",
" <td>5.015112</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2011.436086</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>2.663796e+05</td>\n",
" <td>1737.605837</td>\n",
" <td>NaN</td>\n",
" <td>2.797598</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>610.162290</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>4.500000e+04</td>\n",
" <td>36.000000</td>\n",
" <td>NaN</td>\n",
" <td>1.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>50.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>2.990000e+05</td>\n",
" <td>6200.000000</td>\n",
" <td>NaN</td>\n",
" <td>4.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>1976.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>3.590000e+05</td>\n",
" <td>7000.000000</td>\n",
" <td>NaN</td>\n",
" <td>4.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2011.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>4.570000e+05</td>\n",
" <td>7868.000000</td>\n",
" <td>NaN</td>\n",
" <td>5.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>2019.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>6.000000e+06</td>\n",
" <td>23005.000000</td>\n",
" <td>NaN</td>\n",
" <td>21.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>20120.000000</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" 0 4 7 10 12 13 16 \\\n",
"count 2.547000e+03 2547.000000 0.0 2316.000000 0.0 0.0 0.0 \n",
"mean 4.210372e+05 7201.618767 NaN 5.015112 NaN NaN NaN \n",
"std 2.663796e+05 1737.605837 NaN 2.797598 NaN NaN NaN \n",
"min 4.500000e+04 36.000000 NaN 1.000000 NaN NaN NaN \n",
"25% 2.990000e+05 6200.000000 NaN 4.000000 NaN NaN NaN \n",
"50% 3.590000e+05 7000.000000 NaN 4.000000 NaN NaN NaN \n",
"75% 4.570000e+05 7868.000000 NaN 5.000000 NaN NaN NaN \n",
"max 6.000000e+06 23005.000000 NaN 21.000000 NaN NaN NaN \n",
"\n",
" 19 20 24 \n",
"count 1768.000000 0.0 0.0 \n",
"mean 2011.436086 NaN NaN \n",
"std 610.162290 NaN NaN \n",
"min 50.000000 NaN NaN \n",
"25% 1976.000000 NaN NaN \n",
"50% 2011.000000 NaN NaN \n",
"75% 2019.000000 NaN NaN \n",
"max 20120.000000 NaN NaN "
]
},
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 8,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_dataset.describe()"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 9,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"3\n",
"pełna własność 1515\n",
"spółdzielcze własnościowe 158\n",
"spółdzielcze wł. z KW 131\n",
"udział 15\n",
"Name: count, dtype: int64"
]
},
"execution_count": 9,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"train_dataset[3].value_counts()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Odfiltrowanie wartości liczbowych"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"filtered= train_dataset[[0,8,15,2]]"
]
},
{
"cell_type": "code",
"execution_count": 18,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>0</th>\n",
" <th>8</th>\n",
" <th>15</th>\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
" <th>2</th>\n",
add files
2023-10-17 17:35:43 +02:00
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>309000.0</td>\n",
" <td>43.44</td>\n",
" <td>1</td>\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
" <td>390 zł</td>\n",
add files
2023-10-17 17:35:43 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
Model modified, created pkl
2023-10-17 18:14:03 +02:00
" 0 8 15 2 \n",
"0 309000.0 43.44 1 390 zł"
add files
2023-10-17 17:35:43 +02:00
]
},
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 18,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"filtered.head(1)"
add files
2023-10-17 17:35:43 +02:00
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 19,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"15\n",
"1 569\n",
"parter 452\n",
"2 419\n",
"4 357\n",
"3 321\n",
"5 117\n",
"6 51\n",
"7 42\n",
"8 32\n",
"10 29\n",
"> 10 24\n",
"9 21\n",
"suterena 5\n",
"poddasze 3\n",
"Name: count, dtype: int64"
]
},
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 19,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"filtered[15].value_counts()"
]
},
Model modified, created pkl
2023-10-17 18:14:03 +02:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Zamiana wsyztskich wartości na wartosći liczbowe, odfiltrowanie wartości trudnych do zamiany oraz usunięcie brakujących wartości"
]
},
add files
2023-10-17 17:35:43 +02:00
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 20,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"C:\\Users\\s433445\\AppData\\Local\\temp\\ipykernel_7796\\2098381410.py:1: SettingWithCopyWarning: \n",
add files
2023-10-17 17:35:43 +02:00
"A value is trying to be set on a copy of a slice from a DataFrame.\n",
"Try using .loc[row_indexer,col_indexer] = value instead\n",
"\n",
"See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
" filtered[15] = filtered[15].replace({\"parter\": 0})\n"
]
}
],
"source": [
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"filtered[15] = filtered[15].replace({\"parter\": 0})\n",
"string = [\"> 10\", \"suterena\", \"poddasze\"]\n",
"filtered = filtered[~filtered[15].isin(string)]\n",
"filtered = filtered[~filtered[15].isna()]"
add files
2023-10-17 17:35:43 +02:00
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 21,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>0</th>\n",
" <th>8</th>\n",
" <th>15</th>\n",
" <th>2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>309000.0</td>\n",
" <td>43.44</td>\n",
" <td>1</td>\n",
" <td>390 zł</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>314900.0</td>\n",
" <td>42.60</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>249000.0</td>\n",
" <td>44.30</td>\n",
" <td>2</td>\n",
" <td>300 zł</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>419000.0</td>\n",
" <td>88</td>\n",
" <td>1</td>\n",
" <td>490 zł</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>499000.0</td>\n",
" <td>77</td>\n",
" <td>7</td>\n",
" <td>850 zł</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",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
" <th>2541</th>\n",
" <td>383680.0</td>\n",
" <td>70.40</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
add files
2023-10-17 17:35:43 +02:00
" <th>2542</th>\n",
" <td>507600.0</td>\n",
" <td>94</td>\n",
" <td>3</td>\n",
" <td>1 zł</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2543</th>\n",
" <td>342400.0</td>\n",
" <td>53.50</td>\n",
" <td>4</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2544</th>\n",
" <td>335000.0</td>\n",
" <td>55.25</td>\n",
" <td>4</td>\n",
" <td>280 zł</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2545</th>\n",
" <td>260000.0</td>\n",
" <td>62</td>\n",
" <td>2</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"<p>2410 rows × 4 columns</p>\n",
add files
2023-10-17 17:35:43 +02:00
"</div>"
],
"text/plain": [
Model modified, created pkl
2023-10-17 18:14:03 +02:00
" 0 8 15 2 \n",
"0 309000.0 43.44 1 390 zł\n",
"1 314900.0 42.60 1 NaN\n",
"2 249000.0 44.30 2 300 zł\n",
"3 419000.0 88 1 490 zł\n",
"4 499000.0 77 7 850 zł\n",
"... ... ... .. ...\n",
"2541 383680.0 70.40 0 NaN\n",
"2542 507600.0 94 3 1 zł\n",
"2543 342400.0 53.50 4 NaN\n",
"2544 335000.0 55.25 4 280 zł\n",
"2545 260000.0 62 2 NaN\n",
add files
2023-10-17 17:35:43 +02:00
"\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"[2410 rows x 4 columns]"
add files
2023-10-17 17:35:43 +02:00
]
},
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 21,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"filtered"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 22,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"15\n",
"1 569\n",
"0 452\n",
"2 419\n",
"4 357\n",
"3 321\n",
"5 117\n",
"6 51\n",
"7 42\n",
"8 32\n",
"10 29\n",
"9 21\n",
"Name: count, dtype: int64"
]
},
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 22,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"filtered[15].value_counts()\n"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 23,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
"filtered[15] = filtered[15].apply(int)"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 24,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"8\n",
"38 59\n",
"48 40\n",
"50 35\n",
"53 28\n",
"43 26\n",
" ..\n",
"33.79 1\n",
"42.60 1\n",
"47.82 1\n",
"53.09 1\n",
"55.25 1\n",
"Name: count, Length: 1084, dtype: int64"
]
},
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 24,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"filtered[8].value_counts()"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 33,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"import numpy as np\n",
"\n",
add files
2023-10-17 17:35:43 +02:00
"def check_value(number):\n",
" try:\n",
" return float(number)\n",
" except:\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
" return str(np.nan)"
add files
2023-10-17 17:35:43 +02:00
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 40,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>0</th>\n",
" <th>8</th>\n",
" <th>15</th>\n",
" <th>2</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>309000.0</td>\n",
" <td>43.44</td>\n",
" <td>1</td>\n",
" <td>390 zł</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>314900.0</td>\n",
" <td>42.60</td>\n",
" <td>1</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>249000.0</td>\n",
" <td>44.30</td>\n",
" <td>2</td>\n",
" <td>300 zł</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>419000.0</td>\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
" <td>88.00</td>\n",
add files
2023-10-17 17:35:43 +02:00
" <td>1</td>\n",
" <td>490 zł</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>499000.0</td>\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
" <td>77.00</td>\n",
add files
2023-10-17 17:35:43 +02:00
" <td>7</td>\n",
" <td>850 zł</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2541</th>\n",
" <td>383680.0</td>\n",
" <td>70.40</td>\n",
" <td>0</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2542</th>\n",
" <td>507600.0</td>\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
" <td>94.00</td>\n",
add files
2023-10-17 17:35:43 +02:00
" <td>3</td>\n",
" <td>1 zł</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2543</th>\n",
" <td>342400.0</td>\n",
" <td>53.50</td>\n",
" <td>4</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2544</th>\n",
" <td>335000.0</td>\n",
" <td>55.25</td>\n",
" <td>4</td>\n",
" <td>280 zł</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2545</th>\n",
" <td>260000.0</td>\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
" <td>62.00</td>\n",
add files
2023-10-17 17:35:43 +02:00
" <td>2</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>2410 rows × 4 columns</p>\n",
"</div>"
],
"text/plain": [
" 0 8 15 2 \n",
"0 309000.0 43.44 1 390 zł\n",
"1 314900.0 42.60 1 NaN\n",
"2 249000.0 44.30 2 300 zł\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"3 419000.0 88.00 1 490 zł\n",
"4 499000.0 77.00 7 850 zł\n",
add files
2023-10-17 17:35:43 +02:00
"... ... ... .. ...\n",
"2541 383680.0 70.40 0 NaN\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"2542 507600.0 94.00 3 1 zł\n",
add files
2023-10-17 17:35:43 +02:00
"2543 342400.0 53.50 4 NaN\n",
"2544 335000.0 55.25 4 280 zł\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"2545 260000.0 62.00 2 NaN\n",
add files
2023-10-17 17:35:43 +02:00
"\n",
"[2410 rows x 4 columns]"
]
},
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 40,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"filtered"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 41,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
"filtered[8] = filtered[8].apply(check_value)\n",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"filtered = filtered[~filtered[8].isna()]"
add files
2023-10-17 17:35:43 +02:00
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 42,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"filtered = filtered[[0, 15, 8]]"
add files
2023-10-17 17:35:43 +02:00
]
},
{
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"cell_type": "markdown",
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"source": [
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"## Model"
add files
2023-10-17 17:35:43 +02:00
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 43,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
"from sklearn.linear_model import LinearRegression\n",
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 44,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
"from sklearn.preprocessing import StandardScaler"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 45,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
"X = filtered.drop(0,axis=1)\n",
"y = filtered[[0]]\n",
"\n",
"scaler = StandardScaler()\n",
"trans_data = scaler.fit_transform(X)\n",
"\n",
"X_train, X_test, y_train, y_test = train_test_split(trans_data,y, test_size=0.33)"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 46,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
"reg = LinearRegression()"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 47,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
"reg.fit(X_train, y_train)\n",
"results = reg.predict(X_test)"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 49,
"metadata": {},
"outputs": [],
"source": [
"import pickle"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Zapis jako pkl"
]
},
{
"cell_type": "code",
"execution_count": 50,
"metadata": {},
"outputs": [],
"source": [
"pickle.dump(reg, open(\"model.pkl\", \"wb\"))"
]
},
{
"cell_type": "code",
"execution_count": 51,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"array([[ 593653.27660188],\n",
" [ 347445.92747813],\n",
" [ 405167.78785587],\n",
" [ 536368.93860499],\n",
" [ 285944.97361261],\n",
" [ 424034.91112136],\n",
" [ 272900.72398813],\n",
" [ 475401.99674084],\n",
" [ 314256.66427135],\n",
" [ 499602.00468798],\n",
" [ 319442.70363808],\n",
" [ 345408.47997727],\n",
" [ 324469.23238515],\n",
" [ 443182.15703217],\n",
" [ 250637.45215307],\n",
" [ 209585.7569203 ],\n",
" [ 270014.46501481],\n",
" [ 347445.92747813],\n",
" [ 200395.07888311],\n",
" [ 341165.63081938],\n",
" [ 358551.3301064 ],\n",
" [ 335193.80097933],\n",
" [ 614485.48015284],\n",
" [ 426332.58063066],\n",
" [ 683415.56543175],\n",
" [ 568532.08996689],\n",
" [ 269911.64274191],\n",
" [ 330600.57284487],\n",
" [ 340303.25136243],\n",
" [ 203970.63870921],\n",
" [ 443440.26815648],\n",
" [ 343360.47805578],\n",
" [1329699.64270264],\n",
" [ 620229.65392608],\n",
" [ 312930.52914428],\n",
" [ 314256.66427135],\n",
" [ 539430.38706659],\n",
" [ 327534.90261501],\n",
" [ 445735.82678165],\n",
" [ 593552.5652131 ],\n",
" [ 200904.96847936],\n",
" [ 390845.64791458],\n",
" [ 309151.43565651],\n",
" [ 319541.30414273],\n",
" [ 483778.54013134],\n",
" [ 406679.66689186],\n",
" [ 295877.4190811 ],\n",
" [ 256561.03718286],\n",
" [ 524622.47993419],\n",
" [ 269861.28704753],\n",
" [1478921.21612892],\n",
" [ 350791.7203533 ],\n",
" [ 479690.97982487],\n",
" [ 550662.73437289],\n",
" [ 289240.41079339],\n",
" [ 672183.21812545],\n",
" [ 655845.64220431],\n",
" [ 538408.49698997],\n",
" [ 354085.04664996],\n",
" [ 656867.53228093],\n",
" [1157759.4853077 ],\n",
" [ 383569.69446848],\n",
" [ 432510.05501651],\n",
" [ 381147.19116528],\n",
" [ 256561.03718286],\n",
" [ 308387.6567042 ],\n",
" [ 352934.10101118],\n",
" [ 232562.45201327],\n",
" [ 537896.4965096 ],\n",
" [ 467438.85332607],\n",
" [ 837615.42279484],\n",
" [ 204992.52878583],\n",
" [ 418853.09352288],\n",
" [ 388803.97864547],\n",
" [ 732128.26991297],\n",
" [ 963910.65682254],\n",
" [ 108998.18810747],\n",
" [ 387528.19921279],\n",
" [ 287196.63064015],\n",
" [ 202443.0808046 ],\n",
" [ 276045.09408575],\n",
" [ 329040.44899862],\n",
" [ 448619.97487084],\n",
" [ 163632.36673436],\n",
" [ 623091.79049426],\n",
" [ 924084.38532806],\n",
" [ 259674.95222298],\n",
" [ 357253.53915271],\n",
" [ 571597.76019675],\n",
" [ 243287.02060745],\n",
" [ 374508.07199344],\n",
" [ 757196.98996944],\n",
" [ 334171.91090272],\n",
" [ 345839.66970574],\n",
" [ 361741.83413015],\n",
" [ 169886.43010385],\n",
" [ 212419.5493151 ],\n",
" [1100061.74733508],\n",
" [ 809023.60949078],\n",
" [ 465213.55103217],\n",
" [ 409739.00446933],\n",
" [ 375733.49573174],\n",
" [ 668097.7687031 ],\n",
" [ 992837.17023455],\n",
" [ 824341.40621943],\n",
" [ 791662.0326089 ],\n",
" [ 405526.61036896],\n",
" [ 262692.37764257],\n",
" [ 609354.01824874],\n",
" [ 652779.97197445],\n",
" [ 249668.02865497],\n",
" [ 420207.57282333],\n",
" [ 612520.39986737],\n",
" [ 336263.93586621],\n",
" [ 435523.25866785],\n",
" [ 336060.40220454],\n",
" [ 599756.2728882 ],\n",
" [ 308129.54557989],\n",
" [ 304558.20752204],\n",
" [ 426078.6912746 ],\n",
" [ 316810.33402083],\n",
" [ 328451.8595346 ],\n",
" [ 427124.70375635],\n",
" [ 998452.28844564],\n",
" [ 700777.14231363],\n",
" [ 249924.02889515],\n",
" [ 281323.40130476],\n",
" [ 349104.65182902],\n",
" [ 737283.8542222 ],\n",
" [ 108232.29827104],\n",
" [ 638484.06532243],\n",
" [ 630825.1669581 ],\n",
" [ 256561.03718286],\n",
" [ 652882.79424735],\n",
" [ 274942.39325724],\n",
" [ 415741.28936689],\n",
" [ 348594.76223277],\n",
" [ 339710.44013016],\n",
" [ 262692.37764257],\n",
" [ 396462.8770098 ],\n",
" [ 336217.80194008],\n",
" [ 208563.86684368],\n",
" [ 431617.22050204],\n",
" [ 429039.42834743],\n",
" [ 641344.09100648],\n",
" [ 194394.90486968],\n",
" [ 451709.76750583],\n",
" [ 236650.01231974],\n",
" [ 422452.77575411],\n",
" [ 475553.063824 ],\n",
" [ 262692.37764257],\n",
" [1148566.69638638],\n",
" [ 512342.00926201],\n",
" [ 294573.29547504],\n",
" [ 306089.9871949 ],\n",
" [ 279336.30949828],\n",
" [ 355872.82656301],\n",
" [ 348467.81755474],\n",
" [ 496284.55598619],\n",
" [ 431849.0983371 ],\n",
" [ 317832.22409745],\n",
" [ 685969.23518123],\n",
" [ 293424.46072039],\n",
" [ 334432.13291115],\n",
" [ 747752.42257619],\n",
" [ 268226.68510176],\n",
" [ 366851.28451325],\n",
" [ 448619.97487084],\n",
" [ 499602.00468798],\n",
" [ 353675.86844248],\n",
" [ 336390.88054424],\n",
" [ 341830.80926704],\n",
" [ 501645.78484122],\n",
" [ 298175.08859039],\n",
" [ 116276.25243771],\n",
" [ 379103.41101204],\n",
" [ 228888.29168252],\n",
" [ 635420.5059767 ],\n",
" [ 330213.4061584 ],\n",
" [ 348467.81755474],\n",
" [ 286126.49575328],\n",
" [ 385893.59726703],\n",
" [ 195806.07251689],\n",
" [ 505733.34514769],\n",
" [ 479178.97934449],\n",
" [ 518318.06087031],\n",
" [ 379871.4117326 ],\n",
" [ 319493.05933247],\n",
" [ 192046.879666 ],\n",
" [1035724.89019064],\n",
" [ 539940.27666284],\n",
" [ 297203.55420816],\n",
" [ 351785.26625653],\n",
" [ 336929.11431387],\n",
" [ 316810.33402083],\n",
" [ 390847.75879871],\n",
" [ 640628.55686444],\n",
" [ 512114.35319521],\n",
" [ 937233.56810956],\n",
" [ 312470.99524242],\n",
" [ 426078.6912746 ],\n",
" [ 294855.52900448],\n",
" [ 387784.19945298],\n",
" [ 390388.22489685],\n",
" [ 367768.24143284],\n",
" [ 409483.00422915],\n",
" [ 247880.24874192],\n",
" [ 229625.83734557],\n",
" [ 287732.75352566],\n",
" [ 231693.73990394],\n",
" [1115379.54406373],\n",
" [ 169582.1850534 ],\n",
" [ 689800.79524752],\n",
" [ 448033.49629095],\n",
" [ 258604.8173361 ],\n",
" [ 292811.74885124],\n",
" [ 302768.31672486],\n",
" [ 362457.3682722 ],\n",
" [ 447527.82846296],\n",
" [ 230291.01579323],\n",
" [ 531259.48822189],\n",
" [ 295877.4190811 ],\n",
" [ 341828.69838291],\n",
" [ 247880.24874192],\n",
" [ 404478.48700308],\n",
" [ 341830.80926704],\n",
" [1492963.23342489],\n",
" [ 463095.29277941],\n",
" [ 202948.74863259],\n",
" [ 257582.92725948],\n",
" [ 403305.5298433 ],\n",
" [ 499602.00468798],\n",
" [ 625207.93786289],\n",
" [ 449385.86470727],\n",
" [ 370424.73345522],\n",
" [ 651171.60331795],\n",
" [ 369505.6656515 ],\n",
" [ 534325.15845175],\n",
" [ 442420.48896399],\n",
" [ 310173.32573313],\n",
" [ 688139.9600125 ],\n",
" [ 305577.98671453],\n",
" [ 325745.01181783],\n",
" [ 369912.73297485],\n",
" [ 475553.063824 ],\n",
" [ 311195.21580974],\n",
" [ 402005.62800549],\n",
" [ 293424.46072039],\n",
" [ 471979.61488203],\n",
" [1004581.51802122],\n",
" [ 791841.44386544],\n",
" [ 312217.10588636],\n",
" [ 691074.46379607],\n",
" [ 511320.1191854 ],\n",
" [ 257582.92725948],\n",
" [ 476625.30959501],\n",
" [ 529370.99692007],\n",
" [ 241499.2406944 ],\n",
" [ 258604.8173361 ],\n",
" [ 567000.31029403],\n",
" [ 915226.2965147 ],\n",
" [ 692096.35387269],\n",
" [ 425056.80119798],\n",
" [ 527355.56094021],\n",
" [ 533303.26837513],\n",
" [ 206778.19781476],\n",
" [ 346502.73726928],\n",
" [ 464627.07245228],\n",
" [ 294855.52900448],\n",
" [ 344128.47877634],\n",
" [ 433737.58963892],\n",
" [ 607848.47186513],\n",
" [ 217244.65528462],\n",
" [ 186609.06182733],\n",
" [ 423932.08884846],\n",
" [ 550559.91209999],\n",
" [ 286583.91877101],\n",
" [ 374328.6607369 ],\n",
" [ 330213.4061584 ],\n",
" [ 250816.86340962],\n",
" [ 323576.39787069],\n",
" [ 334760.50036673],\n",
" [ 264736.15779581],\n",
" [ 377317.74198311],\n",
" [ 174127.16837761],\n",
" [ 351533.4877846 ],\n",
" [ 363785.61428339],\n",
" [ 786046.91439781],\n",
" [ 505733.34514769],\n",
" [ 448543.3858872 ],\n",
" [ 346143.91475619],\n",
" [ 266465.13847797],\n",
" [1011549.00464863],\n",
" [ 355104.82584245],\n",
" [ 620334.5870831 ],\n",
" [ 270856.94383489],\n",
" [ 161997.76478859],\n",
" [ 212651.42715015],\n",
" [ 297409.19875396],\n",
" [ 298457.32211984],\n",
" [ 479690.97982487],\n",
" [ 571188.58198928],\n",
" [ 255539.14710624],\n",
" [ 453648.61450204],\n",
" [ 618573.04045931],\n",
" [ 370424.73345522],\n",
" [ 284439.427229 ],\n",
" [ 396972.76660604],\n",
" [ 286174.74056354],\n",
" [1070448.04395441],\n",
" [ 223371.77397608],\n",
" [ 315788.44394421],\n",
" [ 366085.39467681],\n",
" [ 415303.76698603],\n",
" [ 502667.67491784],\n",
" [ 306597.76590702],\n",
" [ 733456.51592417],\n",
" [ 769963.22783273],\n",
" [ 192379.46888983],\n",
" [ 281686.44558609],\n",
" [ 731412.73577093],\n",
" [ 703586.8123033 ],\n",
" [ 418496.38189392],\n",
" [ 204581.23969423],\n",
" [ 260648.59748933],\n",
" [ 560367.52377458],\n",
" [ 170269.37502206],\n",
" [ 373488.29280095],\n",
" [ 745734.87571221],\n",
" [ 326513.01253839],\n",
" [ 512342.00926201],\n",
" [ 289496.41103358],\n",
" [ 341828.69838291],\n",
" [ 409739.00446933],\n",
" [ 343542.00019645],\n",
" [ 541113.23382262],\n",
" [ 386635.36469833],\n",
" [ 771751.00774578],\n",
" [ 384208.63962688],\n",
" [ 318090.33522176],\n",
" [ 394421.20774069],\n",
" [ 347445.92747813],\n",
" [ 371444.51264772],\n",
" [ 110223.61184576],\n",
" [ 282730.34718372],\n",
" [ 218778.54584161],\n",
" [ 444462.1582331 ],\n",
" [ 290439.60124243],\n",
" [ 266263.71570042],\n",
" [ 298505.5669301 ],\n",
" [ 281607.74571832],\n",
" [ 380891.19092509],\n",
" [ 141677.561718 ],\n",
" [ 351660.43246263],\n",
" [ 258604.8173361 ],\n",
" [ 386812.66507075],\n",
" [ 411603.37336603],\n",
" [ 255539.14710624],\n",
" [ 373155.70357712],\n",
" [ 275351.57146471],\n",
" [ 450077.27644419],\n",
" [ 361231.94453391],\n",
" [ 338331.83842458],\n",
" [ 553730.51548687],\n",
" [ 419441.68298689],\n",
" [ 549310.36595657],\n",
" [ 220564.21487054],\n",
" [ 524213.30172672],\n",
" [ 342850.58845953],\n",
" [ 279537.73227583],\n",
" [ 245711.63479478],\n",
" [ 493732.99712083],\n",
" [ 281684.33470197],\n",
" [ 288218.52071677],\n",
" [ 646142.96368675],\n",
" [ 450075.16556006],\n",
" [ 348467.81755474],\n",
" [ 335193.80097933],\n",
" [ 653801.86205107],\n",
" [ 421203.22961069],\n",
" [ 486839.98859294],\n",
" [ 743666.97315385],\n",
" [1687753.14123477],\n",
" [ 372466.40272433],\n",
" [ 740627.53621325],\n",
" [ 424034.91112136],\n",
" [ 318420.81356146],\n",
" [ 177928.27338639],\n",
" [ 470754.19114374],\n",
" [ 255539.14710624],\n",
" [ 432641.22146279],\n",
" [ 370424.73345522],\n",
" [ 318854.11417407],\n",
" [ 348623.10640616],\n",
" [ 791662.0326089 ],\n",
" [ 915226.2965147 ],\n",
" [ 379998.35641063],\n",
" [ 108998.18810747],\n",
" [ 283111.18121781],\n",
" [ 233098.57489877],\n",
" [ 348467.81755474],\n",
" [ 292428.80393303],\n",
" [ 345863.79211087],\n",
" [1648436.75933653],\n",
" [ 331108.35155699],\n",
" [ 380889.08004096],\n",
" [ 403664.35235639],\n",
" [1031131.66205617],\n",
" [1244558.92618062],\n",
" [ 271036.35509143],\n",
" [ 694628.01210117],\n",
" [ 486583.98835276],\n",
" [ 486610.22164201],\n",
" [ 311604.39401722],\n",
" [ 647648.51007036],\n",
" [ 344892.25772864],\n",
" [ 286174.74056354],\n",
" [ 158017.24852327],\n",
" [ 170269.37502206],\n",
" [ 330600.57284487],\n",
" [ 354082.93576583],\n",
" [ 915226.2965147 ],\n",
" [ 333585.43232283],\n",
" [ 385613.47462171],\n",
" [ 436289.14850428],\n",
" [ 380125.30108866],\n",
" [ 118930.63357596],\n",
" [ 370422.6225711 ],\n",
" [ 305324.09735847],\n",
" [ 454287.55966044],\n",
" [ 449055.38636757],\n",
" [1110784.20504514],\n",
" [ 218546.66800656],\n",
" [ 233584.34208989],\n",
" [ 906545.50807375],\n",
" [ 391178.23713841],\n",
" [1062021.14486953],\n",
" [ 616273.26006589],\n",
" [ 312980.88483867],\n",
" [ 231081.02803479],\n",
" [ 212651.42715015],\n",
" [ 231540.56193665],\n",
" [ 272900.72398813],\n",
" [ 479944.86918093],\n",
" [ 292306.08102325],\n",
" [ 474710.58500393],\n",
" [ 341500.33092734],\n",
" [ 351533.4877846 ],\n",
" [ 365829.39443663],\n",
" [ 361741.83413015],\n",
" [ 260318.11914963],\n",
" [ 255287.36863431],\n",
" [ 605296.91299977],\n",
" [ 363785.61428339],\n",
" [ 483518.3181229 ],\n",
" [ 538918.38658622],\n",
" [ 289851.01177841],\n",
" [ 233584.34208989],\n",
" [ 731412.73577093],\n",
" [ 196055.7401047 ],\n",
" [ 294599.52876429],\n",
" [ 278314.41942167],\n",
" [ 461307.51286636],\n",
" [ 380816.71282557],\n",
" [ 258604.8173361 ],\n",
" [ 329066.68228787],\n",
" [ 521915.63221742],\n",
" [ 379026.8220284 ],\n",
" [ 222325.76149433],\n",
" [ 448033.49629095],\n",
" [ 631847.05703472],\n",
" [ 492916.75159001],\n",
" [ 369400.73249448],\n",
" [ 232818.45225346],\n",
" [ 815154.94995049],\n",
" [ 842466.76205362],\n",
" [ 142699.45179462],\n",
" [ 415612.23380473],\n",
" [ 932229.0508835 ],\n",
" [ 231540.56193665],\n",
" [ 539430.38706659],\n",
" [ 377317.74198311],\n",
" [ 362124.77904837],\n",
" [ 339710.44013016],\n",
" [ 279207.25393613],\n",
" [ 456714.28473189],\n",
" [ 303024.31696505],\n",
" [ 195112.54989585],\n",
" [ 403664.35235639],\n",
" [ 260902.48684539],\n",
" [ 322659.4409511 ],\n",
" [ 308129.54557989],\n",
" [ 377317.74198311],\n",
" [ 623166.26859378],\n",
" [ 349441.4628211 ],\n",
" [ 563938.86183243],\n",
" [ 381578.38089375],\n",
" [ 534325.15845175],\n",
" [ 208999.27834041],\n",
" [ 205323.00712553],\n",
" [ 292306.08102325],\n",
" [ 374328.6607369 ],\n",
" [ 551938.51380557],\n",
" [ 508282.79312892],\n",
" [ 374125.12707523],\n",
" [ 424034.91112136],\n",
" [ 294522.93978065],\n",
" [ 426231.86924189],\n",
" [ 345660.2584492 ],\n",
" [ 530753.8203939 ],\n",
" [ 388547.97840529],\n",
" [ 368124.9530618 ],\n",
" [ 609277.4292651 ],\n",
" [ 328810.68204769],\n",
" [ 455186.72682728],\n",
" [ 445659.23779801],\n",
" [ 315788.44394421],\n",
" [ 180431.58744148],\n",
" [ 311882.40577841],\n",
" [ 305580.09759866],\n",
" [ 269835.05375827],\n",
" [ 250945.91897177],\n",
" [ 234352.34281045],\n",
" [ 532281.37829851],\n",
" [ 301365.59261415],\n",
" [ 731412.73577093],\n",
" [ 335550.51260829],\n",
" [ 397484.76708642],\n",
" [ 387834.55514737],\n",
" [ 335193.80097933],\n",
" [ 234297.76534781],\n",
" [ 162610.47665774],\n",
" [ 298046.03302824],\n",
" [ 449055.38636757],\n",
" [ 350995.25401497],\n",
" [ 273664.50294043],\n",
" [ 262692.37764257],\n",
" [ 373333.00394954],\n",
" [ 605450.09096706],\n",
" [ 416378.12364116],\n",
" [ 511348.46335878],\n",
" [ 108232.29827104],\n",
" [ 325491.12246177],\n",
" [ 368892.95378236],\n",
" [ 164094.01152034],\n",
" [ 439022.22951031],\n",
" [ 837615.42279484],\n",
" [ 245074.8005205 ],\n",
" [ 232562.45201327],\n",
" [ 538918.38658622],\n",
" [ 694628.01210117],\n",
" [ 298457.32211984],\n",
" [ 319620.0040105 ],\n",
" [ 269835.05375827],\n",
" [ 388193.37766045],\n",
" [ 755411.32094052],\n",
" [ 196311.74034489],\n",
" [ 437030.91593558],\n",
" [ 329550.33859486],\n",
" [ 358170.4960723 ],\n",
" [ 321915.56263567],\n",
" [ 264014.29100138],\n",
" [ 403101.99618163],\n",
" [ 456714.28473189],\n",
" [ 234043.87599175],\n",
" [ 333915.91066253],\n",
" [ 293271.2827531 ],\n",
" [ 604019.02268297],\n",
" [ 414257.75450428],\n",
" [ 283520.35942528],\n",
" [ 682651.78647944],\n",
" [ 319212.93668715],\n",
" [ 349669.11888791],\n",
" [ 338229.01615168],\n",
" [ 255539.14710624],\n",
" [ 224724.1423924 ],\n",
" [ 838355.07934202],\n",
" [ 787578.69407068],\n",
" [ 475553.063824 ],\n",
" [ 341828.69838291],\n",
" [ 885612.59313402],\n",
" [ 291028.19070644],\n",
" [ 306601.98767528],\n",
" [ 329066.68228787],\n",
" [ 347445.92747813],\n",
" [ 332690.48692424],\n",
" [ 367818.59712723],\n",
" [ 296899.30915772],\n",
" [ 319366.11465444],\n",
" [ 331209.06294576],\n",
" [ 160006.45121387],\n",
" [ 578494.99049289],\n",
" [ 331106.24067286],\n",
" [ 325491.12246177],\n",
" [ 270064.8207092 ],\n",
" [ 307930.23368647],\n",
" [ 371444.51264772],\n",
" [ 260648.59748933],\n",
" [ 427787.77131988],\n",
" [ 367615.06346555],\n",
" [ 302514.4273688 ],\n",
" [ 310429.32597331],\n",
" [ 448545.49677132],\n",
" [ 299067.92310486],\n",
" [ 424034.91112136],\n",
" [ 348467.81755474],\n",
" [ 620794.12098496],\n",
" [ 225822.62145267],\n",
" [ 302258.42712862],\n",
" [ 274686.39301705],\n",
" [ 339710.44013016],\n",
" [ 289393.58876068],\n",
" [ 167461.81591652],\n",
" [ 341325.14143904],\n",
" [ 641805.73579247],\n",
" [ 210607.64699692],\n",
" [ 294676.11774794],\n",
" [ 837615.42279484],\n",
" [ 332128.13074948],\n",
" [ 309409.54678082],\n",
" [ 426205.63595263],\n",
" [ 378591.41053167],\n",
" [ 465213.55103217],\n",
" [ 196412.45173366],\n",
" [ 503919.33194538],\n",
" [ 353933.9795668 ],\n",
" [ 261670.48756595],\n",
" [ 262692.37764257],\n",
" [ 430164.14069695],\n",
" [ 517985.47164648],\n",
" [ 350559.84251824],\n",
" [ 349003.94044025],\n",
" [ 362354.5459993 ],\n",
" [ 200904.96847936],\n",
" [ 179103.34143029],\n",
" [ 912928.6270054 ],\n",
" [ 302232.19383936],\n",
" [ 365829.39443663],\n",
" [ 277725.82995765],\n",
" [ 487349.87818919],\n",
" [ 455186.72682728],\n",
" [ 531259.48822189],\n",
" [1997172.63515345],\n",
" [ 542008.1792212 ],\n",
" [ 250945.91897177],\n",
" [ 370422.6225711 ],\n",
" [ 740093.52421187],\n",
" [ 304556.09663791],\n",
" [ 325235.12222159],\n",
" [ 274942.39325724],\n",
" [ 117908.74349934],\n",
" [ 488802.95799428],\n",
" [ 209561.63451517],\n",
" [ 121508.42573058],\n",
" [ 356642.93816769],\n",
" [ 298943.08931095],\n",
" [ 235628.12224313],\n",
" [ 445989.71613772],\n",
" [ 445989.71613772],\n",
" [ 535347.04852837],\n",
" [ 193246.07011503],\n",
" [ 286966.86368922],\n",
" [ 373488.29280095],\n",
" [ 383033.57158297],\n",
" [ 203382.0492452 ],\n",
" [ 212038.71528101],\n",
" [ 320742.60547589],\n",
" [ 765877.77841038],\n",
" [ 161028.34129049],\n",
" [ 344128.47877634],\n",
" [ 423932.08884846],\n",
" [ 354341.04689014],\n",
" [ 261563.4435248 ],\n",
" [ 400624.91541579],\n",
" [ 456714.28473189],\n",
" [ 225925.44372557],\n",
" [ 267285.60577704],\n",
" [ 476883.42071932],\n",
" [ 461565.62399067],\n",
" [ 347395.57178374],\n",
" [ 240221.35037759],\n",
" [ 387657.25477495],\n",
" [ 442726.84489856],\n",
" [ 529727.70854903],\n",
" [ 833785.97361268],\n",
" [1609505.43324064],\n",
" [ 391103.7590389 ],\n",
" [ 476117.53088289],\n",
" [ 339710.44013016],\n",
" [ 404708.25395401],\n",
" [ 255156.20218803],\n",
" [ 312217.10588636],\n",
" [ 477393.31031557],\n",
" [ 339710.44013016],\n",
" [ 407695.2243161 ],\n",
" [ 379103.41101204],\n",
" [ 358170.4960723 ],\n",
" [ 340325.26288343],\n",
" [ 343616.47829596],\n",
" [ 209894.223739 ],\n",
" [ 350203.13088928],\n",
" [ 292811.74885124],\n",
" [ 373258.52585002],\n",
" [ 255539.14710624],\n",
" [ 454670.50457866],\n",
" [ 344997.19088567],\n",
" [ 212421.66019923],\n",
" [ 224800.73137605],\n",
" [ 390845.64791458],\n",
" [ 398351.36831162],\n",
" [ 620284.23138872],\n",
" [ 652193.49339457],\n",
" [ 241549.59638879],\n",
" [ 329578.68276825],\n",
" [ 657095.18834773],\n",
" [ 579307.01425546],\n",
" [ 438588.9288977 ],\n",
" [ 543005.94689269],\n",
" [ 345914.14780526],\n",
" [ 273922.61406474],\n",
" [ 335193.80097933],\n",
" [ 288218.52071677],\n",
" [ 117908.74349934],\n",
" [ 572361.53914906],\n",
" [ 541419.58975719],\n",
" [ 280865.97828702],\n",
" [ 289750.30038964],\n",
" [ 264736.15779581],\n",
" [ 655845.64220431],\n",
" [ 263198.04547057],\n",
" [ 569553.98004351],\n",
" [ 291284.19094663],\n",
" [ 119952.52365258],\n",
" [ 787578.69407068],\n",
" [ 682651.78647944],\n",
" [1686731.25115815],\n",
" [ 200904.96847936],\n",
" [ 183059.73529048],\n",
" [ 431949.80972587],\n",
" [ 400445.50415925],\n",
" [ 158960.43873212],\n",
" [ 176400.71548177],\n",
" [ 601721.35317367],\n",
" [ 273922.61406474],\n",
" [ 524876.36929025],\n",
" [ 372311.11387292],\n",
" [ 854543.69906412],\n",
" [ 745708.64242296],\n",
" [ 332128.13074948],\n",
" [ 245227.97848779],\n",
" [ 270014.46501481],\n",
" [ 292811.74885124],\n",
" [ 548185.65360705],\n",
" [ 990793.39008132],\n",
" [ 475553.063824 ],\n",
" [ 305223.3859697 ],\n",
" [ 346424.03740151],\n",
" [ 654823.75212769],\n",
" [ 206931.37578204],\n",
" [ 661486.99370465],\n",
" [ 250945.91897177],\n",
" [ 258604.8173361 ],\n",
" [ 316810.33402083],\n",
" [ 661235.21523272],\n",
" [ 259626.70741272],\n",
" [ 671673.3285292 ],\n",
" [ 356715.30538308],\n",
" [ 472032.08146054],\n",
" [ 717116.8291189 ],\n",
" [ 303030.64961743],\n",
" [ 358680.38566855],\n",
" [ 361897.12298157],\n",
" [ 258604.8173361 ],\n",
" [ 345918.36957351],\n",
" [ 300470.64721557],\n",
" [ 508028.90377286],\n",
" [ 383674.6276255 ],\n",
" [ 426689.29225962],\n",
" [ 712519.37921618],\n",
" [ 511348.46335878],\n",
" [ 345150.36885295],\n",
" [2265236.1887889 ],\n",
" [ 354341.04689014],\n",
" [ 272082.36757318],\n",
" [ 294855.52900448],\n",
" [ 268176.32940738],\n",
" [ 363785.61428339],\n",
" [ 324957.1104604 ],\n",
" [ 241243.24045421],\n",
" [ 369300.0211057 ],\n",
" [ 469555.0006947 ],\n",
" [ 406167.66641148],\n",
" [ 467180.74220176],\n",
" [ 188245.77465722],\n",
" [ 258604.8173361 ]])"
add files
2023-10-17 17:35:43 +02:00
]
},
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 51,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"results"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 52,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [],
"source": [
"from sklearn.metrics import r2_score"
]
},
{
"cell_type": "code",
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 53,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"0.5878080999086976"
add files
2023-10-17 17:35:43 +02:00
]
},
Model modified, created pkl
2023-10-17 18:14:03 +02:00
"execution_count": 53,
add files
2023-10-17 17:35:43 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"r2_score(y_test, results)"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.10.11"
},
"vscode": {
"interpreter": {
"hash": "1b132c2ed43285dcf39f6d01712959169a14a721cf314fe69015adab49bb1fd1"
}
}
},
"nbformat": 4,
"nbformat_minor": 2
}
Reference in New Issue Copy Permalink