s487175/ium_z487175
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
dc90bec6be
ium_z487175/02_Dane-Zadanie01.ipynb

1875 lines
211 KiB
Plaintext
Raw Normal View History

add-file
2023-04-03 21:27:41 +02:00
{
"cells": [
{
"cell_type": "code",
"execution_count": 5,
"id": "d80a4450",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: pandas in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (1.5.3)\n",
"Requirement already satisfied: python-dateutil>=2.8.1 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from pandas) (2.8.2)\n",
"Requirement already satisfied: pytz>=2020.1 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from pandas) (2023.2)\n",
"Requirement already satisfied: numpy>=1.21.0 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from pandas) (1.24.2)\n",
"Requirement already satisfied: six>=1.5 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from python-dateutil>=2.8.1->pandas) (1.16.0)\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"%pip install --user pandas"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "350abc87",
"metadata": {
"scrolled": true
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: kaggle in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (1.5.13)\n",
"Requirement already satisfied: six>=1.10 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (1.16.0)\n",
"Requirement already satisfied: certifi in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (2022.12.7)\n",
"Requirement already satisfied: python-dateutil in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (2.8.2)\n",
"Requirement already satisfied: requests in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (2.28.2)\n",
"Requirement already satisfied: tqdm in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (4.65.0)\n",
"Requirement already satisfied: python-slugify in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (8.0.1)\n",
"Requirement already satisfied: urllib3 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from kaggle) (1.26.15)\n",
"Requirement already satisfied: text-unidecode>=1.3 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from python-slugify->kaggle) (1.3)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from requests->kaggle) (3.1.0)\n",
"Requirement already satisfied: idna<4,>=2.5 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from requests->kaggle) (3.4)\n",
"Requirement already satisfied: colorama in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from tqdm->kaggle) (0.4.6)\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"%pip install --user kaggle"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "0063a986",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"UsageError: Line magic function `%python` not found (But cell magic `%%python` exists, did you mean that instead?).\n"
]
}
],
"source": [
"%python -m kaggle datasets download -d ulrikthygepedersen/diamonds"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "5bc46bfd",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Downloading diamonds.zip to c:\\Users\\admin\\ium_z487175\n",
"\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
" 0%| | 0.00/733k [00:00<?, ?B/s]\n",
"100%|██████████| 733k/733k [00:00<00:00, 1.35MB/s]\n",
"100%|██████████| 733k/733k [00:00<00:00, 1.33MB/s]\n"
]
}
],
"source": [
"!kaggle datasets download -d shivam2503/diamonds"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "75024e0f",
"metadata": {},
"outputs": [],
"source": [
"!tar -xf diamonds.zip\n",
"## rozpakowanie archiwum .zip w windowsie"
]
},
{
"cell_type": "code",
"execution_count": 88,
"id": "99c20a95",
"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>Unnamed: 0</th>\n",
" <th>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0.23</td>\n",
" <td>Ideal</td>\n",
" <td>E</td>\n",
" <td>SI2</td>\n",
" <td>61.5</td>\n",
" <td>55.0</td>\n",
" <td>326</td>\n",
" <td>3.95</td>\n",
" <td>3.98</td>\n",
" <td>2.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>0.21</td>\n",
" <td>Premium</td>\n",
" <td>E</td>\n",
" <td>SI1</td>\n",
" <td>59.8</td>\n",
" <td>61.0</td>\n",
" <td>326</td>\n",
" <td>3.89</td>\n",
" <td>3.84</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>0.23</td>\n",
" <td>Good</td>\n",
" <td>E</td>\n",
" <td>VS1</td>\n",
" <td>56.9</td>\n",
" <td>65.0</td>\n",
" <td>327</td>\n",
" <td>4.05</td>\n",
" <td>4.07</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>0.29</td>\n",
" <td>Premium</td>\n",
" <td>I</td>\n",
" <td>VS2</td>\n",
" <td>62.4</td>\n",
" <td>58.0</td>\n",
" <td>334</td>\n",
" <td>4.20</td>\n",
" <td>4.23</td>\n",
" <td>2.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>0.31</td>\n",
" <td>Good</td>\n",
" <td>J</td>\n",
" <td>SI2</td>\n",
" <td>63.3</td>\n",
" <td>58.0</td>\n",
" <td>335</td>\n",
" <td>4.34</td>\n",
" <td>4.35</td>\n",
" <td>2.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53935</th>\n",
" <td>53936</td>\n",
" <td>0.72</td>\n",
" <td>Ideal</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>60.8</td>\n",
" <td>57.0</td>\n",
" <td>2757</td>\n",
" <td>5.75</td>\n",
" <td>5.76</td>\n",
" <td>3.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53936</th>\n",
" <td>53937</td>\n",
" <td>0.72</td>\n",
" <td>Good</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>63.1</td>\n",
" <td>55.0</td>\n",
" <td>2757</td>\n",
" <td>5.69</td>\n",
" <td>5.75</td>\n",
" <td>3.61</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53937</th>\n",
" <td>53938</td>\n",
" <td>0.70</td>\n",
" <td>Very Good</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>62.8</td>\n",
" <td>60.0</td>\n",
" <td>2757</td>\n",
" <td>5.66</td>\n",
" <td>5.68</td>\n",
" <td>3.56</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53938</th>\n",
" <td>53939</td>\n",
" <td>0.86</td>\n",
" <td>Premium</td>\n",
" <td>H</td>\n",
" <td>SI2</td>\n",
" <td>61.0</td>\n",
" <td>58.0</td>\n",
" <td>2757</td>\n",
" <td>6.15</td>\n",
" <td>6.12</td>\n",
" <td>3.74</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53939</th>\n",
" <td>53940</td>\n",
" <td>0.75</td>\n",
" <td>Ideal</td>\n",
" <td>D</td>\n",
" <td>SI2</td>\n",
" <td>62.2</td>\n",
" <td>55.0</td>\n",
" <td>2757</td>\n",
" <td>5.83</td>\n",
" <td>5.87</td>\n",
" <td>3.64</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>53940 rows × 11 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 carat cut color clarity depth table price x \\\n",
"0 1 0.23 Ideal E SI2 61.5 55.0 326 3.95 \n",
"1 2 0.21 Premium E SI1 59.8 61.0 326 3.89 \n",
"2 3 0.23 Good E VS1 56.9 65.0 327 4.05 \n",
"3 4 0.29 Premium I VS2 62.4 58.0 334 4.20 \n",
"4 5 0.31 Good J SI2 63.3 58.0 335 4.34 \n",
"... ... ... ... ... ... ... ... ... ... \n",
"53935 53936 0.72 Ideal D SI1 60.8 57.0 2757 5.75 \n",
"53936 53937 0.72 Good D SI1 63.1 55.0 2757 5.69 \n",
"53937 53938 0.70 Very Good D SI1 62.8 60.0 2757 5.66 \n",
"53938 53939 0.86 Premium H SI2 61.0 58.0 2757 6.15 \n",
"53939 53940 0.75 Ideal D SI2 62.2 55.0 2757 5.83 \n",
"\n",
" y z \n",
"0 3.98 2.43 \n",
"1 3.84 2.31 \n",
"2 4.07 2.31 \n",
"3 4.23 2.63 \n",
"4 4.35 2.75 \n",
"... ... ... \n",
"53935 5.76 3.50 \n",
"53936 5.75 3.61 \n",
"53937 5.68 3.56 \n",
"53938 6.12 3.74 \n",
"53939 5.87 3.64 \n",
"\n",
"[53940 rows x 11 columns]"
]
},
"execution_count": 88,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import pandas as pd\n",
"diamonds = pd.read_csv('diamonds.csv')\n",
"#Wyświetlenie zbioru danych\n",
"diamonds"
]
},
{
"cell_type": "code",
"execution_count": 32,
"id": "122b0b57",
"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>id</th>\n",
" <th>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0.23</td>\n",
" <td>Ideal</td>\n",
" <td>E</td>\n",
" <td>SI2</td>\n",
" <td>61.5</td>\n",
" <td>55.0</td>\n",
" <td>326</td>\n",
" <td>3.95</td>\n",
" <td>3.98</td>\n",
" <td>2.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>0.21</td>\n",
" <td>Premium</td>\n",
" <td>E</td>\n",
" <td>SI1</td>\n",
" <td>59.8</td>\n",
" <td>61.0</td>\n",
" <td>326</td>\n",
" <td>3.89</td>\n",
" <td>3.84</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>0.23</td>\n",
" <td>Good</td>\n",
" <td>E</td>\n",
" <td>VS1</td>\n",
" <td>56.9</td>\n",
" <td>65.0</td>\n",
" <td>327</td>\n",
" <td>4.05</td>\n",
" <td>4.07</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>0.29</td>\n",
" <td>Premium</td>\n",
" <td>I</td>\n",
" <td>VS2</td>\n",
" <td>62.4</td>\n",
" <td>58.0</td>\n",
" <td>334</td>\n",
" <td>4.20</td>\n",
" <td>4.23</td>\n",
" <td>2.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>0.31</td>\n",
" <td>Good</td>\n",
" <td>J</td>\n",
" <td>SI2</td>\n",
" <td>63.3</td>\n",
" <td>58.0</td>\n",
" <td>335</td>\n",
" <td>4.34</td>\n",
" <td>4.35</td>\n",
" <td>2.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53935</th>\n",
" <td>53936</td>\n",
" <td>0.72</td>\n",
" <td>Ideal</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>60.8</td>\n",
" <td>57.0</td>\n",
" <td>2757</td>\n",
" <td>5.75</td>\n",
" <td>5.76</td>\n",
" <td>3.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53936</th>\n",
" <td>53937</td>\n",
" <td>0.72</td>\n",
" <td>Good</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>63.1</td>\n",
" <td>55.0</td>\n",
" <td>2757</td>\n",
" <td>5.69</td>\n",
" <td>5.75</td>\n",
" <td>3.61</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53937</th>\n",
" <td>53938</td>\n",
" <td>0.70</td>\n",
" <td>Very Good</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>62.8</td>\n",
" <td>60.0</td>\n",
" <td>2757</td>\n",
" <td>5.66</td>\n",
" <td>5.68</td>\n",
" <td>3.56</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53938</th>\n",
" <td>53939</td>\n",
" <td>0.86</td>\n",
" <td>Premium</td>\n",
" <td>H</td>\n",
" <td>SI2</td>\n",
" <td>61.0</td>\n",
" <td>58.0</td>\n",
" <td>2757</td>\n",
" <td>6.15</td>\n",
" <td>6.12</td>\n",
" <td>3.74</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53939</th>\n",
" <td>53940</td>\n",
" <td>0.75</td>\n",
" <td>Ideal</td>\n",
" <td>D</td>\n",
" <td>SI2</td>\n",
" <td>62.2</td>\n",
" <td>55.0</td>\n",
" <td>2757</td>\n",
" <td>5.83</td>\n",
" <td>5.87</td>\n",
" <td>3.64</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>53940 rows × 11 columns</p>\n",
"</div>"
],
"text/plain": [
" id carat cut color clarity depth table price x y \\\n",
"0 1 0.23 Ideal E SI2 61.5 55.0 326 3.95 3.98 \n",
"1 2 0.21 Premium E SI1 59.8 61.0 326 3.89 3.84 \n",
"2 3 0.23 Good E VS1 56.9 65.0 327 4.05 4.07 \n",
"3 4 0.29 Premium I VS2 62.4 58.0 334 4.20 4.23 \n",
"4 5 0.31 Good J SI2 63.3 58.0 335 4.34 4.35 \n",
"... ... ... ... ... ... ... ... ... ... ... \n",
"53935 53936 0.72 Ideal D SI1 60.8 57.0 2757 5.75 5.76 \n",
"53936 53937 0.72 Good D SI1 63.1 55.0 2757 5.69 5.75 \n",
"53937 53938 0.70 Very Good D SI1 62.8 60.0 2757 5.66 5.68 \n",
"53938 53939 0.86 Premium H SI2 61.0 58.0 2757 6.15 6.12 \n",
"53939 53940 0.75 Ideal D SI2 62.2 55.0 2757 5.83 5.87 \n",
"\n",
" z \n",
"0 2.43 \n",
"1 2.31 \n",
"2 2.31 \n",
"3 2.63 \n",
"4 2.75 \n",
"... ... \n",
"53935 3.50 \n",
"53936 3.61 \n",
"53937 3.56 \n",
"53938 3.74 \n",
"53939 3.64 \n",
"\n",
"[53940 rows x 11 columns]"
]
},
"execution_count": 32,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#przydzielanie nazwy kolumny z id\n",
"diamonds = diamonds.rename(columns={diamonds.columns[0]: 'id'})\n",
"diamonds"
]
},
{
"cell_type": "code",
"execution_count": 98,
"id": "a489dab8",
"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>Unnamed: 0</th>\n",
" <th>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0.23</td>\n",
" <td>ideal</td>\n",
" <td>E</td>\n",
" <td>SI2</td>\n",
" <td>61.5</td>\n",
" <td>55.0</td>\n",
" <td>326</td>\n",
" <td>3.95</td>\n",
" <td>3.98</td>\n",
" <td>2.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>0.21</td>\n",
" <td>premium</td>\n",
" <td>E</td>\n",
" <td>SI1</td>\n",
" <td>59.8</td>\n",
" <td>61.0</td>\n",
" <td>326</td>\n",
" <td>3.89</td>\n",
" <td>3.84</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>0.23</td>\n",
" <td>good</td>\n",
" <td>E</td>\n",
" <td>VS1</td>\n",
" <td>56.9</td>\n",
" <td>65.0</td>\n",
" <td>327</td>\n",
" <td>4.05</td>\n",
" <td>4.07</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>0.29</td>\n",
" <td>premium</td>\n",
" <td>I</td>\n",
" <td>VS2</td>\n",
" <td>62.4</td>\n",
" <td>58.0</td>\n",
" <td>334</td>\n",
" <td>4.20</td>\n",
" <td>4.23</td>\n",
" <td>2.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>0.31</td>\n",
" <td>good</td>\n",
" <td>J</td>\n",
" <td>SI2</td>\n",
" <td>63.3</td>\n",
" <td>58.0</td>\n",
" <td>335</td>\n",
" <td>4.34</td>\n",
" <td>4.35</td>\n",
" <td>2.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53935</th>\n",
" <td>53936</td>\n",
" <td>0.72</td>\n",
" <td>ideal</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>60.8</td>\n",
" <td>57.0</td>\n",
" <td>2757</td>\n",
" <td>5.75</td>\n",
" <td>5.76</td>\n",
" <td>3.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53936</th>\n",
" <td>53937</td>\n",
" <td>0.72</td>\n",
" <td>good</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>63.1</td>\n",
" <td>55.0</td>\n",
" <td>2757</td>\n",
" <td>5.69</td>\n",
" <td>5.75</td>\n",
" <td>3.61</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53937</th>\n",
" <td>53938</td>\n",
" <td>0.70</td>\n",
" <td>very good</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>62.8</td>\n",
" <td>60.0</td>\n",
" <td>2757</td>\n",
" <td>5.66</td>\n",
" <td>5.68</td>\n",
" <td>3.56</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53938</th>\n",
" <td>53939</td>\n",
" <td>0.86</td>\n",
" <td>premium</td>\n",
" <td>H</td>\n",
" <td>SI2</td>\n",
" <td>61.0</td>\n",
" <td>58.0</td>\n",
" <td>2757</td>\n",
" <td>6.15</td>\n",
" <td>6.12</td>\n",
" <td>3.74</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53939</th>\n",
" <td>53940</td>\n",
" <td>0.75</td>\n",
" <td>ideal</td>\n",
" <td>D</td>\n",
" <td>SI2</td>\n",
" <td>62.2</td>\n",
" <td>55.0</td>\n",
" <td>2757</td>\n",
" <td>5.83</td>\n",
" <td>5.87</td>\n",
" <td>3.64</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>53940 rows × 11 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 carat cut color clarity depth table price x \\\n",
"0 1 0.23 ideal E SI2 61.5 55.0 326 3.95 \n",
"1 2 0.21 premium E SI1 59.8 61.0 326 3.89 \n",
"2 3 0.23 good E VS1 56.9 65.0 327 4.05 \n",
"3 4 0.29 premium I VS2 62.4 58.0 334 4.20 \n",
"4 5 0.31 good J SI2 63.3 58.0 335 4.34 \n",
"... ... ... ... ... ... ... ... ... ... \n",
"53935 53936 0.72 ideal D SI1 60.8 57.0 2757 5.75 \n",
"53936 53937 0.72 good D SI1 63.1 55.0 2757 5.69 \n",
"53937 53938 0.70 very good D SI1 62.8 60.0 2757 5.66 \n",
"53938 53939 0.86 premium H SI2 61.0 58.0 2757 6.15 \n",
"53939 53940 0.75 ideal D SI2 62.2 55.0 2757 5.83 \n",
"\n",
" y z \n",
"0 3.98 2.43 \n",
"1 3.84 2.31 \n",
"2 4.07 2.31 \n",
"3 4.23 2.63 \n",
"4 4.35 2.75 \n",
"... ... ... \n",
"53935 5.76 3.50 \n",
"53936 5.75 3.61 \n",
"53937 5.68 3.56 \n",
"53938 6.12 3.74 \n",
"53939 5.87 3.64 \n",
"\n",
"[53940 rows x 11 columns]"
]
},
"execution_count": 98,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Convert to lowerCase\n",
"\n",
"diamonds['cut'] = diamonds['cut'].str.lower()\n",
"diamonds\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 58,
"id": "1cc3a8af",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: scikit-learn in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (1.2.2)\n",
"Requirement already satisfied: numpy>=1.17.3 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from scikit-learn) (1.24.2)\n",
"Requirement already satisfied: scipy>=1.3.2 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from scikit-learn) (1.10.1)\n",
"Requirement already satisfied: joblib>=1.1.1 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from scikit-learn) (1.2.0)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in c:\\users\\admin\\appdata\\roaming\\python\\python311\\site-packages (from scikit-learn) (3.1.0)\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"%pip install scikit-learn"
]
},
{
"cell_type": "code",
"execution_count": 60,
"id": "1836b2a3",
"metadata": {},
"outputs": [],
"source": [
"import sklearn\n",
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "code",
"execution_count": 91,
"id": "fcf6448a",
"metadata": {},
"outputs": [],
"source": [
"#podział danych na train/test/dev w proporcji 4:1:1\n",
"#losować ustawiona na 10\n",
"\n",
"#1. Dzielimy na zbiór treningowy 80 % i resztę danych\n",
"diamonds_train, diamonds_test_dev = sklearn.model_selection.train_test_split(diamonds, test_size=0.2, random_state=10)\n",
"\n",
"#2. Podział reszty danych na zbiór testowy 10% i walidacyjny 10%\n",
"diamonds_test, diamonds_dev = train_test_split(diamonds_test_dev, test_size=0.5, random_state=10)\n"
]
},
{
"cell_type": "code",
"execution_count": 92,
"id": "9476846a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Rozmiar diamonds: (53940, 11)\n",
"Rozmiar diamonds_train: (43152, 11)\n",
"Rozmiar diamonds_test: (5394, 11)\n",
"Rozmiar diamonds_dev: (5394, 11)\n"
]
}
],
"source": [
"#Wyświetlenie rozmiarów zbiorów danych train/test/dev\n",
"print(\"Rozmiar diamonds: \", diamonds.shape)\n",
"print(\"Rozmiar diamonds_train: \", diamonds_train.shape)\n",
"print(\"Rozmiar diamonds_test: \", diamonds_test.shape)\n",
"print(\"Rozmiar diamonds_dev: \", diamonds_dev.shape)\n"
]
},
{
"cell_type": "code",
"execution_count": 99,
"id": "7e1f11cb",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Unnamed: 0 carat depth table price \\\n",
"count 53940.000000 53940.000000 53940.000000 53940.000000 53940.000000 \n",
"mean 26970.500000 0.797940 61.749405 57.457184 3932.799722 \n",
"std 15571.281097 0.474011 1.432621 2.234491 3989.439738 \n",
"min 1.000000 0.200000 43.000000 43.000000 326.000000 \n",
"25% 13485.750000 0.400000 61.000000 56.000000 950.000000 \n",
"50% 26970.500000 0.700000 61.800000 57.000000 2401.000000 \n",
"75% 40455.250000 1.040000 62.500000 59.000000 5324.250000 \n",
"max 53940.000000 5.010000 79.000000 95.000000 18823.000000 \n",
"\n",
" x y z \n",
"count 53940.000000 53940.000000 53940.000000 \n",
"mean 5.731157 5.734526 3.538734 \n",
"std 1.121761 1.142135 0.705699 \n",
"min 0.000000 0.000000 0.000000 \n",
"25% 4.710000 4.720000 2.910000 \n",
"50% 5.700000 5.710000 3.530000 \n",
"75% 6.540000 6.540000 4.040000 \n",
"max 10.740000 58.900000 31.800000 \n"
]
}
],
"source": [
"# średnią, minimum, maksimum, odchylenia standardowe, medianę wartości poszczególnych parametrów)\n",
"print(diamonds.describe())"
]
},
{
"cell_type": "code",
"execution_count": 100,
"id": "88a89b38",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Unnamed: 0 carat depth table price \\\n",
"count 43152.000000 43152.000000 43152.000000 43152.000000 43152.000000 \n",
"mean 26971.712111 0.795979 61.748241 57.448355 3920.786939 \n",
"std 15565.585777 0.472184 1.426394 2.224297 3975.894633 \n",
"min 3.000000 0.200000 43.000000 44.000000 327.000000 \n",
"25% 13469.750000 0.400000 61.000000 56.000000 946.000000 \n",
"50% 27019.500000 0.700000 61.800000 57.000000 2400.000000 \n",
"75% 40439.250000 1.040000 62.500000 59.000000 5313.250000 \n",
"max 53938.000000 5.010000 79.000000 76.000000 18823.000000 \n",
"\n",
" x y z \n",
"count 43152.000000 43152.000000 43152.000000 \n",
"mean 5.726933 5.731011 3.535791 \n",
"std 1.119635 1.147069 0.693846 \n",
"min 0.000000 0.000000 0.000000 \n",
"25% 4.710000 4.720000 2.910000 \n",
"50% 5.690000 5.710000 3.520000 \n",
"75% 6.540000 6.530000 4.030000 \n",
"max 10.740000 58.900000 8.060000 \n"
]
}
],
"source": [
"print(diamonds_train.describe())"
]
},
{
"cell_type": "code",
"execution_count": 101,
"id": "80b5060f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Unnamed: 0 carat depth table price \\\n",
"count 5394.000000 5394.000000 5394.000000 5394.000000 5394.000000 \n",
"mean 26951.351316 0.802666 61.760808 57.470189 3970.308676 \n",
"std 15565.740253 0.482062 1.464893 2.309900 4083.195823 \n",
"min 1.000000 0.210000 52.300000 43.000000 326.000000 \n",
"25% 13519.750000 0.400000 61.000000 56.000000 958.000000 \n",
"50% 27013.500000 0.700000 61.900000 57.000000 2375.500000 \n",
"75% 40342.250000 1.050000 62.500000 59.000000 5273.750000 \n",
"max 53930.000000 3.510000 78.200000 95.000000 18806.000000 \n",
"\n",
" x y z \n",
"count 5394.000000 5394.000000 5394.000000 \n",
"mean 5.738817 5.739106 3.542097 \n",
"std 1.132069 1.123925 0.701446 \n",
"min 3.840000 3.780000 0.000000 \n",
"25% 4.710000 4.710000 2.900000 \n",
"50% 5.690000 5.700000 3.530000 \n",
"75% 6.550000 6.540000 4.040000 \n",
"max 9.660000 9.630000 6.030000 \n"
]
}
],
"source": [
"print(diamonds_test.describe())"
]
},
{
"cell_type": "code",
"execution_count": 102,
"id": "31f4af56",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" Unnamed: 0 carat depth table price \\\n",
"count 5394.000000 5394.000000 5394.000000 5394.000000 5394.000000 \n",
"mean 26979.951798 0.808901 61.747312 57.514813 3991.393029 \n",
"std 15625.161644 0.480344 1.449816 2.238671 4002.742530 \n",
"min 2.000000 0.200000 53.200000 51.000000 326.000000 \n",
"25% 13525.500000 0.400000 61.000000 56.000000 961.000000 \n",
"50% 26529.500000 0.710000 61.850000 57.000000 2484.500000 \n",
"75% 40665.500000 1.050000 62.500000 59.000000 5465.250000 \n",
"max 53940.000000 3.040000 73.600000 68.000000 18779.000000 \n",
"\n",
" x y z \n",
"count 5394.000000 5394.000000 5394.000000 \n",
"mean 5.757290 5.758066 3.558910 \n",
"std 1.128191 1.120344 0.797759 \n",
"min 3.790000 3.750000 0.000000 \n",
"25% 4.730000 4.740000 2.930000 \n",
"50% 5.710000 5.730000 3.540000 \n",
"75% 6.560000 6.540000 4.040000 \n",
"max 9.510000 9.460000 31.800000 \n"
]
}
],
"source": [
"print(diamonds_dev.describe())"
]
},
{
"cell_type": "code",
"execution_count": 120,
"id": "eab3e1f9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Ideal 17292\n",
"Premium 10954\n",
"Very Good 9708\n",
"Good 3929\n",
"Fair 1269\n",
"Name: cut, dtype: int64"
]
},
"execution_count": 120,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Wyświetlenie częstości przykładów dla poszczególnych klas diamentów\n",
"diamonds_train[\"cut\"].value_counts()\n",
"\n"
]
},
{
"cell_type": "code",
"execution_count": 105,
"id": "2e7c37d9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Ideal 2184\n",
"Premium 1385\n",
"Very Good 1183\n",
"Good 473\n",
"Fair 169\n",
"Name: cut, dtype: int64"
]
},
"execution_count": 105,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds_test[\"cut\"].value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 106,
"id": "a7ccece5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Ideal 2075\n",
"Premium 1452\n",
"Very Good 1191\n",
"Good 504\n",
"Fair 172\n",
"Name: cut, dtype: int64"
]
},
"execution_count": 106,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds_dev[\"cut\"].value_counts()"
]
},
{
"cell_type": "code",
"execution_count": 109,
"id": "17223f54",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"plt.figure(figsize=(8, 6))\n",
"diamonds['cut'].value_counts().plot(kind='bar')\n",
"plt.title('Rozkład częstości dla szlifów diamentów dla zbioru diamonds')\n",
"plt.xlabel('Szlif')\n",
"plt.ylabel('Liczba wystąpień')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 110,
"id": "8633ea7c",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"plt.figure(figsize=(8, 6))\n",
"diamonds_train['cut'].value_counts().plot(kind='bar')\n",
"plt.title('Rozkład częstości dla szlifów diamentów dla zbioru diamonds tranującego')\n",
"plt.xlabel('Szlif')\n",
"plt.ylabel('Liczba wystąpień')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 111,
"id": "ab567b6f",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"plt.figure(figsize=(8, 6))\n",
"diamonds_test['cut'].value_counts().plot(kind='bar')\n",
"plt.title('Rozkład częstości dla szlifów diamentów dla zbioru diamonds testowego')\n",
"plt.xlabel('Szlif')\n",
"plt.ylabel('Liczba wystąpień')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 112,
"id": "18e61963",
"metadata": {},
"outputs": [
{
"data": {
"image/png": "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
"text/plain": [
"<Figure size 800x600 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"import matplotlib.pyplot as plt\n",
"\n",
"plt.figure(figsize=(8, 6))\n",
"diamonds_dev['cut'].value_counts().plot(kind='bar')\n",
"plt.title('Rozkład częstości dla szlifów diamentów dla zbioru diamonds walidacyjnego')\n",
"plt.xlabel('Szlif')\n",
"plt.ylabel('Liczba wystąpień')\n",
"plt.show()"
]
},
{
"cell_type": "code",
"execution_count": 119,
"id": "1bf608c2",
"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>carat</th>\n",
" </tr>\n",
" <tr>\n",
" <th>cut</th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>fair</th>\n",
" <td>0.516404</td>\n",
" </tr>\n",
" <tr>\n",
" <th>good</th>\n",
" <td>0.454054</td>\n",
" </tr>\n",
" <tr>\n",
" <th>ideal</th>\n",
" <td>0.432876</td>\n",
" </tr>\n",
" <tr>\n",
" <th>premium</th>\n",
" <td>0.515262</td>\n",
" </tr>\n",
" <tr>\n",
" <th>very good</th>\n",
" <td>0.459435</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" carat\n",
"cut \n",
"fair 0.516404\n",
"good 0.454054\n",
"ideal 0.432876\n",
"premium 0.515262\n",
"very good 0.459435"
]
},
"execution_count": 119,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds[[\"cut\",\"carat\"]].groupby(\"cut\").std()"
]
},
{
"cell_type": "code",
"execution_count": 118,
"id": "0d6e54d9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Axes: xlabel='cut'>"
]
},
"execution_count": 118,
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
"image/png": "iVBORw0KGgoAAAANSUhEUgAAAiMAAAHoCAYAAACb7e9bAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjcuMSwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/bCgiHAAAACXBIWXMAAA9hAAAPYQGoP6dpAAAw7UlEQVR4nO3deVTU9f7H8dcMCIgibixKJO6auOLVcPlVv7hael3ydg+pCblQVmY/SVNScSnTvInWyfKKmvr7ZVLerqfSQxlFZZKmhlqJ5kK4gZhXUUlBht8fHqfmgibmzAeY5+MczpEv3+/MG0fl6Xw3S2lpaakAAAAMsZoeAAAAuDdiBAAAGEWMAAAAo4gRAABgFDECAACMIkYAAIBRxAgAADDK0/QAN8Jms+n48ePy8/OTxWIxPQ4AALgBpaWlOnfunBo3biyr9drvf1SJGDl+/LhCQ0NNjwEAAG7CkSNHdNttt13z61UiRvz8/CRd+Wbq1KljeBoAAHAjCgoKFBoaav85fi1VIkau7pqpU6cOMQIAQBXze4dYcAArAAAwihgBAABGESMAAMCoKnHMCAAAt4rNZlNRUZHpMaqFGjVqyMPD4w8/DjECAHAbRUVFOnz4sGw2m+lRqo26desqODj4D10HjBgBALiF0tJSnThxQh4eHgoNDb3uRbjw+0pLS1VYWKiTJ09Kkho1anTTj0WMAADcwuXLl1VYWKjGjRvL19fX9DjVQs2aNSVJJ0+eVGBg4E3vsiELAQBuoaSkRJLk5eVleJLq5WrYFRcX3/RjECMAALfCPc5urVvx+0mMAAAAo4gRAABgFAewAgDcWtiUDS59vux5/V36fFUB74wAAIAysrOzZbFYlJmZ6fTnIkYAAHAjlfHqs8QIAACVnM1m0/z589WiRQt5e3vr9ttv15w5cyRJkydPVqtWreTr66tmzZpp+vTpDqfZzpw5U506ddKyZcvUtGlT+fj4SJJSU1PVq1cv1a1bVw0aNNBf/vIXHTx40L5d06ZNJUmdO3eWxWLR3Xff7bTvj2NGfsPV+w2dgX2RAFD9JCQkKDk5WQsXLlSvXr104sQJZWVlSZL8/Py0cuVKNW7cWHv27FFcXJz8/Pz07LPP2rc/cOCA/vnPf+q9996zX5jswoULio+PV4cOHXT+/HklJibqgQceUGZmpqxWq7Zt26Zu3brpk08+Ubt27Zx6fRZiBACASuzcuXN65ZVX9Nprryk2NlaS1Lx5c/Xq1UuSNG3aNPu6YWFhmjhxotauXesQI0VFRVq9erUCAgLsy/761786PM+KFSsUEBCgH374QeHh4fZ1GzRooODgYKd9fxK7aQAAqNT27t2rS5cu6d577y336ykpKerZs6eCg4NVu3ZtTZs2TTk5OQ7rNGnSxCFEJOnHH3/U0KFD1axZM9WpU0dhYWGSVGZbVyBGAACoxK7e/6U8GRkZGj58uPr166cPP/xQ3377raZOnVrmINVatWqV2XbAgAE6ffq0kpOTtXXrVm3dulWSmQNc2U0DAEAl1rJlS9WsWVNpaWkaM2aMw9e2bNmiJk2aaOrUqfZlP/300+8+5s8//6x9+/YpOTlZvXv3liRt3rzZYZ2rx4hcvaePMxEjAABUYj4+Ppo8ebKeffZZeXl5qWfPnsrPz9f333+vli1bKicnR2vXrtWf/vQnbdiwQf/6179+9zHr1aunBg0aaOnSpWrUqJFycnI0ZcoUh3UCAwNVs2ZNpaam6rbbbpOPj4/8/f2d8j0SIwAAt1YVzkKcPn26PD09lZiYqOPHj6tRo0YaO3asRo8erQkTJmjcuHG6dOmS+vfvr+nTp2vmzJnXfTyr1aq1a9dq/PjxCg8PV+vWrfXqq686nL7r6empV199VbNnz1ZiYqJ69+6t9PR0p3x/ltLS0lKnPPItVFBQIH9/f509e1Z16tRx2vNwai8AVF8XL17U4cOHHa61gT/uer+vN/rzmwNYAQCAUcQIAAAwihgBAABGESMAAMCoCsfIF198oQEDBqhx48ayWCxav379726Tnp6uLl26yNvbWy1atNDKlStvYlQAAP64KnDeRpVis9n+8GNU+NTeCxcuqGPHjho1apSGDBnyu+sfPnxY/fv319ixY/XWW2/ZL9rSqFEj9e3b96aGBgCgomrUqCGLxaL8/HwFBATIYrGYHqlKKy0tVVFRkfLz82W1Wv/QjfQqHCP333+/7r///htef8mSJWratKkWLFggSWrbtq02b96shQsXXjNGLl26pEuXLtk/LygoqOiYAAA48PDw0G233aajR48qOzvb9DjVhq+vr26//XZZrTd/5IfTL3qWkZGhqKgoh2V9+/bV//zP/1xzm7lz52rWrFlOngwA4G5q166tli1bqri42PQo1YKHh4c8PT3/8LtMTo+R3NxcBQUFOSwLCgpSQUGBfvnll3JvAJSQkKD4+Hj75wUFBQoNDXX2qAAAN+Dh4SEPDw/TY+A3KuXl4L29veXt7W16DAAA4AJOP7U3ODhYeXl5Dsvy8vJUp06d694WGQAAuAenx0hkZKTS0tIclm3atEmRkZHOfmoAAFAFVDhGzp8/r8zMTGVmZkq6cupuZmamcnJyJF053iMmJsa+/tixY3Xo0CE9++yzysrK0uuvv6533nlHEyZMuDXfAQAAqNIqHCPbt29X586d1blzZ0lSfHy8OnfurMTEREnSiRMn7GEiSU2bNtWGDRu0adMmdezYUQsWLNCyZcu4xggAAJAkWUqrwKXobvQWxH9U2JQNTntsV8me19/0CAAASLrxn9/cmwYAABhFjAAAAKOIEQAAYBQxAgAAjCJGAACAUcQIAAAwihgBAABGESMAAMAoYgQAABhFjAAAAKOIEQAAYBQxAgAAjCJGAACAUcQIAAAwihgBAABGESMAAMAoYgQAABhFjAAAAKOIEQAAYBQxAgAAjCJGAACAUcQIAAAwihgBAABGESMAAMAoYgQAABhFjAAAAKOIEQAAYBQxAgAAjCJGAACAUZ6mBwAA3JiwKRtMj3BLZM/rb3oEVDK8MwIAAIwiRgAAgFHECAAAMIoYAQAARhEjAADAKGIEAAAYRYwAAACjiBEAAGAUMQIAAIwiRgAAgFHECAAAMIoYAQAARhEjAADAKO7ai0qpOtydlDuTAsCN4Z0RAABgFDECAACMIkYAAIBRxAgAADCKGAEAAEYRIwAAwChiBAAAGEWMAAAAo4gRAABgFDECAACMIkYAAIBRxAgAADDqpmJk8eLFCgsLk4+Pj7p3765t27Zdd/1FixapdevWqlmzpkJDQzVhwgRdvHjxpgYGAADVS4VjJCUlRfHx8ZoxY4Z27typjh07qm/fvjp58mS5669Zs0ZTpkzRjBkztHfvXi1fvlwpKSl67rnn/vDwAACg6vOs6AZJSUmKi4vTyJEjJUlLlizRhg0btGLFCk2ZMqXM+lu2bFHPnj01bNgwSVJYWJiGDh2qrVu3/sHRAQAwI2zKBtMj3BLZ8/qbHkFSBd8ZKSoq0o4dOxQVFfXrA1itioqKUkZGRrnb9OjRQzt27LDvyjl06JA2btyofv36XfN5Ll26pIKCAocPAABQPVXonZFTp06ppKREQUFBDsuDgoKUlZVV7jbDhg3TqVOn1KtXL5WWlury5csaO3bsdXfTzJ07V7NmzarIaAAAoIpy+tk06enpevHFF/X6669r586deu+997RhwwY9//zz19wmISFBZ8+etX8cOXLE2WMCAABDKvTOSMOGDeXh4aG8vDyH5Xl5eQoODi53m+nTp2vEiBEaM2aMJKl9+/a6cOGCHn30UU2dOlVWa9ke8vb2lre3d0VGAwAAVVSF3hnx8vJSRESE0tLS7MtsNpvS0tIUGRlZ7jaFhYVlgsPDw0OSVFpaWtF5AQBANVPhs2ni4+MVGxurrl27qlu3blq0aJEuXLhgP7smJiZGISEhmjt3riRpwIABSkpKUufOndW9e3cdOHBA06dP14ABA+xRAgAA3FeFYyQ6Olr5+flKTExUbm6uOnXqpNTUVPtBrTk5OQ7vhEybNk0Wi0XTpk3TsWPHFBAQoAEDBmjOnDm
"text/plain": [
"<Figure size 640x480 with 1 Axes>"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"diamonds[[\"cut\",\"carat\"]].groupby(\"cut\").mean().plot(kind=\"bar\")"
]
},
{
"cell_type": "code",
"execution_count": 124,
"id": "4598d9cf",
"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>Unnamed: 0</th>\n",
" <th>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0.006237</td>\n",
" <td>ideal</td>\n",
" <td>E</td>\n",
" <td>SI2</td>\n",
" <td>0.513889</td>\n",
" <td>0.230769</td>\n",
" <td>0.000000</td>\n",
" <td>0.367784</td>\n",
" <td>0.067572</td>\n",
" <td>0.076415</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>0.002079</td>\n",
" <td>premium</td>\n",
" <td>E</td>\n",
" <td>SI1</td>\n",
" <td>0.466667</td>\n",
" <td>0.346154</td>\n",
" <td>0.000000</td>\n",
" <td>0.362197</td>\n",
" <td>0.065195</td>\n",
" <td>0.072642</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>0.006237</td>\n",
" <td>good</td>\n",
" <td>E</td>\n",
" <td>VS1</td>\n",
" <td>0.386111</td>\n",
" <td>0.423077</td>\n",
" <td>0.000054</td>\n",
" <td>0.377095</td>\n",
" <td>0.069100</td>\n",
" <td>0.072642</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>0.018711</td>\n",
" <td>premium</td>\n",
" <td>I</td>\n",
" <td>VS2</td>\n",
" <td>0.538889</td>\n",
" <td>0.288462</td>\n",
" <td>0.000433</td>\n",
" <td>0.391061</td>\n",
" <td>0.071817</td>\n",
" <td>0.082704</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>0.022869</td>\n",
" <td>good</td>\n",
" <td>J</td>\n",
" <td>SI2</td>\n",
" <td>0.563889</td>\n",
" <td>0.288462</td>\n",
" <td>0.000487</td>\n",
" <td>0.404097</td>\n",
" <td>0.073854</td>\n",
" <td>0.086478</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53935</th>\n",
" <td>53936</td>\n",
" <td>0.108108</td>\n",
" <td>ideal</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>0.494444</td>\n",
" <td>0.269231</td>\n",
" <td>0.131427</td>\n",
" <td>0.535382</td>\n",
" <td>0.097793</td>\n",
" <td>0.110063</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53936</th>\n",
" <td>53937</td>\n",
" <td>0.108108</td>\n",
" <td>good</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>0.558333</td>\n",
" <td>0.230769</td>\n",
" <td>0.131427</td>\n",
" <td>0.529795</td>\n",
" <td>0.097623</td>\n",
" <td>0.113522</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53937</th>\n",
" <td>53938</td>\n",
" <td>0.103950</td>\n",
" <td>very good</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>0.550000</td>\n",
" <td>0.326923</td>\n",
" <td>0.131427</td>\n",
" <td>0.527002</td>\n",
" <td>0.096435</td>\n",
" <td>0.111950</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53938</th>\n",
" <td>53939</td>\n",
" <td>0.137214</td>\n",
" <td>premium</td>\n",
" <td>H</td>\n",
" <td>SI2</td>\n",
" <td>0.500000</td>\n",
" <td>0.288462</td>\n",
" <td>0.131427</td>\n",
" <td>0.572626</td>\n",
" <td>0.103905</td>\n",
" <td>0.117610</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53939</th>\n",
" <td>53940</td>\n",
" <td>0.114345</td>\n",
" <td>ideal</td>\n",
" <td>D</td>\n",
" <td>SI2</td>\n",
" <td>0.533333</td>\n",
" <td>0.230769</td>\n",
" <td>0.131427</td>\n",
" <td>0.542831</td>\n",
" <td>0.099660</td>\n",
" <td>0.114465</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>53940 rows × 11 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 carat cut color clarity depth table \\\n",
"0 1 0.006237 ideal E SI2 0.513889 0.230769 \n",
"1 2 0.002079 premium E SI1 0.466667 0.346154 \n",
"2 3 0.006237 good E VS1 0.386111 0.423077 \n",
"3 4 0.018711 premium I VS2 0.538889 0.288462 \n",
"4 5 0.022869 good J SI2 0.563889 0.288462 \n",
"... ... ... ... ... ... ... ... \n",
"53935 53936 0.108108 ideal D SI1 0.494444 0.269231 \n",
"53936 53937 0.108108 good D SI1 0.558333 0.230769 \n",
"53937 53938 0.103950 very good D SI1 0.550000 0.326923 \n",
"53938 53939 0.137214 premium H SI2 0.500000 0.288462 \n",
"53939 53940 0.114345 ideal D SI2 0.533333 0.230769 \n",
"\n",
" price x y z \n",
"0 0.000000 0.367784 0.067572 0.076415 \n",
"1 0.000000 0.362197 0.065195 0.072642 \n",
"2 0.000054 0.377095 0.069100 0.072642 \n",
"3 0.000433 0.391061 0.071817 0.082704 \n",
"4 0.000487 0.404097 0.073854 0.086478 \n",
"... ... ... ... ... \n",
"53935 0.131427 0.535382 0.097793 0.110063 \n",
"53936 0.131427 0.529795 0.097623 0.113522 \n",
"53937 0.131427 0.527002 0.096435 0.111950 \n",
"53938 0.131427 0.572626 0.103905 0.117610 \n",
"53939 0.131427 0.542831 0.099660 0.114465 \n",
"\n",
"[53940 rows x 11 columns]"
]
},
"execution_count": 124,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#normalizacja wartości typu float do zakrsu 0.0 - 1.0\n",
"#Powyżej wykonano jeszcze konwersję danych typu string na lowerCase\n",
"\n",
"from sklearn.preprocessing import MinMaxScaler\n",
"scaler = MinMaxScaler()\n",
"diamonds[['carat', 'depth', 'table', 'price', 'x', 'y', 'z']] = scaler.fit_transform(diamonds[['carat', 'depth', 'table', 'price', 'x', 'y', 'z']])\n",
"\n",
"#wyświetlenie zbioru\n",
"diamonds"
]
},
{
"cell_type": "code",
"execution_count": 96,
"id": "97350bed",
"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>Unnamed: 0</th>\n",
" <th>carat</th>\n",
" <th>cut</th>\n",
" <th>color</th>\n",
" <th>clarity</th>\n",
" <th>depth</th>\n",
" <th>table</th>\n",
" <th>price</th>\n",
" <th>x</th>\n",
" <th>y</th>\n",
" <th>z</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>1</td>\n",
" <td>0.23</td>\n",
" <td>Ideal</td>\n",
" <td>E</td>\n",
" <td>SI2</td>\n",
" <td>61.5</td>\n",
" <td>55.0</td>\n",
" <td>326</td>\n",
" <td>3.95</td>\n",
" <td>3.98</td>\n",
" <td>2.43</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
" <td>0.21</td>\n",
" <td>Premium</td>\n",
" <td>E</td>\n",
" <td>SI1</td>\n",
" <td>59.8</td>\n",
" <td>61.0</td>\n",
" <td>326</td>\n",
" <td>3.89</td>\n",
" <td>3.84</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
" <td>0.23</td>\n",
" <td>Good</td>\n",
" <td>E</td>\n",
" <td>VS1</td>\n",
" <td>56.9</td>\n",
" <td>65.0</td>\n",
" <td>327</td>\n",
" <td>4.05</td>\n",
" <td>4.07</td>\n",
" <td>2.31</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
" <td>0.29</td>\n",
" <td>Premium</td>\n",
" <td>I</td>\n",
" <td>VS2</td>\n",
" <td>62.4</td>\n",
" <td>58.0</td>\n",
" <td>334</td>\n",
" <td>4.20</td>\n",
" <td>4.23</td>\n",
" <td>2.63</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
" <td>0.31</td>\n",
" <td>Good</td>\n",
" <td>J</td>\n",
" <td>SI2</td>\n",
" <td>63.3</td>\n",
" <td>58.0</td>\n",
" <td>335</td>\n",
" <td>4.34</td>\n",
" <td>4.35</td>\n",
" <td>2.75</td>\n",
" </tr>\n",
" <tr>\n",
" <th>...</th>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" <td>...</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53935</th>\n",
" <td>53936</td>\n",
" <td>0.72</td>\n",
" <td>Ideal</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>60.8</td>\n",
" <td>57.0</td>\n",
" <td>2757</td>\n",
" <td>5.75</td>\n",
" <td>5.76</td>\n",
" <td>3.50</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53936</th>\n",
" <td>53937</td>\n",
" <td>0.72</td>\n",
" <td>Good</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>63.1</td>\n",
" <td>55.0</td>\n",
" <td>2757</td>\n",
" <td>5.69</td>\n",
" <td>5.75</td>\n",
" <td>3.61</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53937</th>\n",
" <td>53938</td>\n",
" <td>0.70</td>\n",
" <td>Very Good</td>\n",
" <td>D</td>\n",
" <td>SI1</td>\n",
" <td>62.8</td>\n",
" <td>60.0</td>\n",
" <td>2757</td>\n",
" <td>5.66</td>\n",
" <td>5.68</td>\n",
" <td>3.56</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53938</th>\n",
" <td>53939</td>\n",
" <td>0.86</td>\n",
" <td>Premium</td>\n",
" <td>H</td>\n",
" <td>SI2</td>\n",
" <td>61.0</td>\n",
" <td>58.0</td>\n",
" <td>2757</td>\n",
" <td>6.15</td>\n",
" <td>6.12</td>\n",
" <td>3.74</td>\n",
" </tr>\n",
" <tr>\n",
" <th>53939</th>\n",
" <td>53940</td>\n",
" <td>0.75</td>\n",
" <td>Ideal</td>\n",
" <td>D</td>\n",
" <td>SI2</td>\n",
" <td>62.2</td>\n",
" <td>55.0</td>\n",
" <td>2757</td>\n",
" <td>5.83</td>\n",
" <td>5.87</td>\n",
" <td>3.64</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>53940 rows × 11 columns</p>\n",
"</div>"
],
"text/plain": [
" Unnamed: 0 carat cut color clarity depth table price x \\\n",
"0 1 0.23 Ideal E SI2 61.5 55.0 326 3.95 \n",
"1 2 0.21 Premium E SI1 59.8 61.0 326 3.89 \n",
"2 3 0.23 Good E VS1 56.9 65.0 327 4.05 \n",
"3 4 0.29 Premium I VS2 62.4 58.0 334 4.20 \n",
"4 5 0.31 Good J SI2 63.3 58.0 335 4.34 \n",
"... ... ... ... ... ... ... ... ... ... \n",
"53935 53936 0.72 Ideal D SI1 60.8 57.0 2757 5.75 \n",
"53936 53937 0.72 Good D SI1 63.1 55.0 2757 5.69 \n",
"53937 53938 0.70 Very Good D SI1 62.8 60.0 2757 5.66 \n",
"53938 53939 0.86 Premium H SI2 61.0 58.0 2757 6.15 \n",
"53939 53940 0.75 Ideal D SI2 62.2 55.0 2757 5.83 \n",
"\n",
" y z \n",
"0 3.98 2.43 \n",
"1 3.84 2.31 \n",
"2 4.07 2.31 \n",
"3 4.23 2.63 \n",
"4 4.35 2.75 \n",
"... ... ... \n",
"53935 5.76 3.50 \n",
"53936 5.75 3.61 \n",
"53937 5.68 3.56 \n",
"53938 6.12 3.74 \n",
"53939 5.87 3.64 \n",
"\n",
"[53940 rows x 11 columns]"
]
},
"execution_count": 96,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"# Usuwanie artefaktów\n",
"diamonds = diamonds.dropna() ## usuwanie pustych wierszy, które posiadają przynajmniej jedno wystąpienie NULL or NaN\n",
"diamonds"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"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": "3.11.2"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue Copy Permalink