s487175/ium_z487175
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
4b41879813
ium_z487175/02_Dane-Zadanie01.ipynb

1813 lines
214 KiB
Plaintext
Raw Normal View History

add-file
2023-04-03 21:27:41 +02:00
{
"cells": [
{
"cell_type": "code",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 1,
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 4,
add-file
2023-04-03 21:27:41 +02:00
"id": "5bc46bfd",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"diamonds.zip: Skipping, found more recently modified local copy (use --force to force download)\n"
add-file
2023-04-03 21:27:41 +02:00
]
}
],
"source": [
"!kaggle datasets download -d shivam2503/diamonds"
]
},
{
"cell_type": "code",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 28,
add-file
2023-04-03 21:27:41 +02:00
"id": "75024e0f",
"metadata": {},
"outputs": [],
"source": [
"!tar -xf diamonds.zip\n",
"## rozpakowanie archiwum .zip w windowsie"
]
},
{
"cell_type": "code",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 3,
add-file
2023-04-03 21:27:41 +02:00
"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]"
]
},
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 3,
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 4,
add-file
2023-04-03 21:27:41 +02:00
"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]"
]
},
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 4,
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 5,
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <th>id</th>\n",
add-file
2023-04-03 21:27:41 +02:00
" <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": [
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" 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",
add-file
2023-04-03 21:27:41 +02:00
"\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" 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",
add-file
2023-04-03 21:27:41 +02:00
"\n",
"[53940 rows x 11 columns]"
]
},
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 5,
add-file
2023-04-03 21:27:41 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Convert to lowerCase\n",
"\n",
"diamonds['cut'] = diamonds['cut'].str.lower()\n",
"diamonds\n",
"\n"
]
},
{
"cell_type": "code",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 6,
add-file
2023-04-03 21:27:41 +02:00
"id": "1836b2a3",
"metadata": {},
"outputs": [],
"source": [
"import sklearn\n",
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "code",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 7,
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 8,
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 9,
add-file
2023-04-03 21:27:41 +02:00
"id": "7e1f11cb",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" id carat depth table price \\\n",
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 10,
add-file
2023-04-03 21:27:41 +02:00
"id": "88a89b38",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" id carat depth table price \\\n",
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 11,
add-file
2023-04-03 21:27:41 +02:00
"id": "80b5060f",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" id carat depth table price \\\n",
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 12,
add-file
2023-04-03 21:27:41 +02:00
"id": "31f4af56",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" id carat depth table price \\\n",
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 13,
add-file
2023-04-03 21:27:41 +02:00
"id": "eab3e1f9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"ideal 17292\n",
"premium 10954\n",
"very good 9708\n",
"good 3929\n",
"fair 1269\n",
add-file
2023-04-03 21:27:41 +02:00
"Name: cut, dtype: int64"
]
},
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 13,
add-file
2023-04-03 21:27:41 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"#Wyświetlenie częstości przykładów dla poszczególnych klas diamentów\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"diamonds_train[\"cut\"].value_counts()"
add-file
2023-04-03 21:27:41 +02:00
]
},
{
"cell_type": "code",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 14,
add-file
2023-04-03 21:27:41 +02:00
"id": "2e7c37d9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"ideal 2184\n",
"premium 1385\n",
"very good 1183\n",
"good 473\n",
"fair 169\n",
add-file
2023-04-03 21:27:41 +02:00
"Name: cut, dtype: int64"
]
},
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 14,
add-file
2023-04-03 21:27:41 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds_test[\"cut\"].value_counts()"
]
},
{
"cell_type": "code",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 15,
add-file
2023-04-03 21:27:41 +02:00
"id": "a7ccece5",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"ideal 2075\n",
"premium 1452\n",
"very good 1191\n",
"good 504\n",
"fair 172\n",
add-file
2023-04-03 21:27:41 +02:00
"Name: cut, dtype: int64"
]
},
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 15,
add-file
2023-04-03 21:27:41 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds_dev[\"cut\"].value_counts()"
]
},
{
"cell_type": "code",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 16,
add-file
2023-04-03 21:27:41 +02:00
"id": "17223f54",
"metadata": {},
"outputs": [
{
"data": {
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"image/png": "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
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 17,
add-file
2023-04-03 21:27:41 +02:00
"id": "8633ea7c",
"metadata": {},
"outputs": [
{
"data": {
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"image/png": "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
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 18,
add-file
2023-04-03 21:27:41 +02:00
"id": "ab567b6f",
"metadata": {},
"outputs": [
{
"data": {
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"image/png": "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
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 19,
add-file
2023-04-03 21:27:41 +02:00
"id": "18e61963",
"metadata": {},
"outputs": [
{
"data": {
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"image/png": "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
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 20,
add-file
2023-04-03 21:27:41 +02:00
"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"
]
},
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 20,
add-file
2023-04-03 21:27:41 +02:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"diamonds[[\"cut\",\"carat\"]].groupby(\"cut\").std()"
]
},
{
"cell_type": "code",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 21,
add-file
2023-04-03 21:27:41 +02:00
"id": "0d6e54d9",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<Axes: xlabel='cut'>"
]
},
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 21,
add-file
2023-04-03 21:27:41 +02:00
"metadata": {},
"output_type": "execute_result"
},
{
"data": {
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"image/png": "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
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 22,
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <th>id</th>\n",
add-file
2023-04-03 21:27:41 +02:00
" <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": [
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" id carat cut color clarity depth table price \\\n",
"0 1 0.006237 ideal E SI2 0.513889 0.230769 0.000000 \n",
"1 2 0.002079 premium E SI1 0.466667 0.346154 0.000000 \n",
"2 3 0.006237 good E VS1 0.386111 0.423077 0.000054 \n",
"3 4 0.018711 premium I VS2 0.538889 0.288462 0.000433 \n",
"4 5 0.022869 good J SI2 0.563889 0.288462 0.000487 \n",
"... ... ... ... ... ... ... ... ... \n",
"53935 53936 0.108108 ideal D SI1 0.494444 0.269231 0.131427 \n",
"53936 53937 0.108108 good D SI1 0.558333 0.230769 0.131427 \n",
"53937 53938 0.103950 very good D SI1 0.550000 0.326923 0.131427 \n",
"53938 53939 0.137214 premium H SI2 0.500000 0.288462 0.131427 \n",
"53939 53940 0.114345 ideal D SI2 0.533333 0.230769 0.131427 \n",
add-file
2023-04-03 21:27:41 +02:00
"\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" x y z \n",
"0 0.367784 0.067572 0.076415 \n",
"1 0.362197 0.065195 0.072642 \n",
"2 0.377095 0.069100 0.072642 \n",
"3 0.391061 0.071817 0.082704 \n",
"4 0.404097 0.073854 0.086478 \n",
"... ... ... ... \n",
"53935 0.535382 0.097793 0.110063 \n",
"53936 0.529795 0.097623 0.113522 \n",
"53937 0.527002 0.096435 0.111950 \n",
"53938 0.572626 0.103905 0.117610 \n",
"53939 0.542831 0.099660 0.114465 \n",
add-file
2023-04-03 21:27:41 +02:00
"\n",
"[53940 rows x 11 columns]"
]
},
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 22,
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 23,
add-file
2023-04-03 21:27:41 +02:00
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <th>id</th>\n",
add-file
2023-04-03 21:27:41 +02:00
" <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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <td>0.006237</td>\n",
" <td>ideal</td>\n",
add-file
2023-04-03 21:27:41 +02:00
" <td>E</td>\n",
" <td>SI2</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <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",
add-file
2023-04-03 21:27:41 +02:00
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>2</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <td>0.002079</td>\n",
" <td>premium</td>\n",
add-file
2023-04-03 21:27:41 +02:00
" <td>E</td>\n",
" <td>SI1</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <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",
add-file
2023-04-03 21:27:41 +02:00
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>3</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <td>0.006237</td>\n",
" <td>good</td>\n",
add-file
2023-04-03 21:27:41 +02:00
" <td>E</td>\n",
" <td>VS1</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <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",
add-file
2023-04-03 21:27:41 +02:00
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>4</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <td>0.018711</td>\n",
" <td>premium</td>\n",
add-file
2023-04-03 21:27:41 +02:00
" <td>I</td>\n",
" <td>VS2</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <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",
add-file
2023-04-03 21:27:41 +02:00
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>5</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <td>0.022869</td>\n",
" <td>good</td>\n",
add-file
2023-04-03 21:27:41 +02:00
" <td>J</td>\n",
" <td>SI2</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <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",
add-file
2023-04-03 21:27:41 +02:00
" </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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <td>0.108108</td>\n",
" <td>ideal</td>\n",
add-file
2023-04-03 21:27:41 +02:00
" <td>D</td>\n",
" <td>SI1</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <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",
add-file
2023-04-03 21:27:41 +02:00
" </tr>\n",
" <tr>\n",
" <th>53936</th>\n",
" <td>53937</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <td>0.108108</td>\n",
" <td>good</td>\n",
add-file
2023-04-03 21:27:41 +02:00
" <td>D</td>\n",
" <td>SI1</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <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",
add-file
2023-04-03 21:27:41 +02:00
" </tr>\n",
" <tr>\n",
" <th>53937</th>\n",
" <td>53938</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <td>0.103950</td>\n",
" <td>very good</td>\n",
add-file
2023-04-03 21:27:41 +02:00
" <td>D</td>\n",
" <td>SI1</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <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",
add-file
2023-04-03 21:27:41 +02:00
" </tr>\n",
" <tr>\n",
" <th>53938</th>\n",
" <td>53939</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <td>0.137214</td>\n",
" <td>premium</td>\n",
add-file
2023-04-03 21:27:41 +02:00
" <td>H</td>\n",
" <td>SI2</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <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",
add-file
2023-04-03 21:27:41 +02:00
" </tr>\n",
" <tr>\n",
" <th>53939</th>\n",
" <td>53940</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <td>0.114345</td>\n",
" <td>ideal</td>\n",
add-file
2023-04-03 21:27:41 +02:00
" <td>D</td>\n",
" <td>SI2</td>\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" <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",
add-file
2023-04-03 21:27:41 +02:00
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>53940 rows × 11 columns</p>\n",
"</div>"
],
"text/plain": [
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" id carat cut color clarity depth table price \\\n",
"0 1 0.006237 ideal E SI2 0.513889 0.230769 0.000000 \n",
"1 2 0.002079 premium E SI1 0.466667 0.346154 0.000000 \n",
"2 3 0.006237 good E VS1 0.386111 0.423077 0.000054 \n",
"3 4 0.018711 premium I VS2 0.538889 0.288462 0.000433 \n",
"4 5 0.022869 good J SI2 0.563889 0.288462 0.000487 \n",
"... ... ... ... ... ... ... ... ... \n",
"53935 53936 0.108108 ideal D SI1 0.494444 0.269231 0.131427 \n",
"53936 53937 0.108108 good D SI1 0.558333 0.230769 0.131427 \n",
"53937 53938 0.103950 very good D SI1 0.550000 0.326923 0.131427 \n",
"53938 53939 0.137214 premium H SI2 0.500000 0.288462 0.131427 \n",
"53939 53940 0.114345 ideal D SI2 0.533333 0.230769 0.131427 \n",
add-file
2023-04-03 21:27:41 +02:00
"\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
" x y z \n",
"0 0.367784 0.067572 0.076415 \n",
"1 0.362197 0.065195 0.072642 \n",
"2 0.377095 0.069100 0.072642 \n",
"3 0.391061 0.071817 0.082704 \n",
"4 0.404097 0.073854 0.086478 \n",
"... ... ... ... \n",
"53935 0.535382 0.097793 0.110063 \n",
"53936 0.529795 0.097623 0.113522 \n",
"53937 0.527002 0.096435 0.111950 \n",
"53938 0.572626 0.103905 0.117610 \n",
"53939 0.542831 0.099660 0.114465 \n",
add-file
2023-04-03 21:27:41 +02:00
"\n",
"[53940 rows x 11 columns]"
]
},
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"execution_count": 23,
add-file
2023-04-03 21:27:41 +02:00
"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"
]
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
},
{
"attachments": {},
"cell_type": "markdown",
"id": "4e91548a",
"metadata": {},
"source": [
"#### Zapisanie zbiorów danych do pliku csv (na potrzeby zadania z LAB 5 - BIBLIOTEKI DL)"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "37f739a6",
"metadata": {},
"outputs": [],
"source": [
"import os\n",
"\n",
"directory ='dane'\n",
"if not os.path.exists(directory):\n",
" os.makedirs('dane')\n",
"\n",
add: update
2023-06-04 15:39:17 +02:00
"diamonds.to_csv('dane/diamonds.csv', index=False)\n",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"diamonds_train.to_csv('dane/diamonds_train.csv', index=False)\n",
"diamonds_test.to_csv('dane/diamonds_test.csv', index=False)\n",
"diamonds_dev.to_csv('dane/diamonds_dev.csv', index=False)"
]
add-file
2023-04-03 21:27:41 +02:00
}
],
"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",
add: dodano katalog dane z plikam csv do trenowania modelu
2023-06-04 15:38:21 +02:00
"version": "3.10.9"
add-file
2023-04-03 21:27:41 +02:00
}
},
"nbformat": 4,
"nbformat_minor": 5
}
Reference in New Issue Copy Permalink