781 lines
37 KiB
Plaintext
781 lines
37 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Requirement already satisfied: kaggle in c:\\users\\user\\anaconda3\\lib\\site-packages (1.5.12)\n",
|
||
"Requirement already satisfied: urllib3 in c:\\users\\user\\anaconda3\\lib\\site-packages (from kaggle) (1.26.7)\n",
|
||
"Requirement already satisfied: python-dateutil in c:\\users\\user\\anaconda3\\lib\\site-packages (from kaggle) (2.8.2)\n",
|
||
"Requirement already satisfied: python-slugify in c:\\users\\user\\anaconda3\\lib\\site-packages (from kaggle) (5.0.2)\n",
|
||
"Requirement already satisfied: requests in c:\\users\\user\\anaconda3\\lib\\site-packages (from kaggle) (2.26.0)\n",
|
||
"Requirement already satisfied: six>=1.10 in c:\\users\\user\\anaconda3\\lib\\site-packages (from kaggle) (1.16.0)\n",
|
||
"Requirement already satisfied: tqdm in c:\\users\\user\\anaconda3\\lib\\site-packages (from kaggle) (4.62.3)\n",
|
||
"Requirement already satisfied: certifi in c:\\users\\user\\anaconda3\\lib\\site-packages (from kaggle) (2021.10.8)\n",
|
||
"Requirement already satisfied: text-unidecode>=1.3 in c:\\users\\user\\anaconda3\\lib\\site-packages (from python-slugify->kaggle) (1.3)\n",
|
||
"Requirement already satisfied: charset-normalizer~=2.0.0 in c:\\users\\user\\anaconda3\\lib\\site-packages (from requests->kaggle) (2.0.4)\n",
|
||
"Requirement already satisfied: idna<4,>=2.5 in c:\\users\\user\\anaconda3\\lib\\site-packages (from requests->kaggle) (3.2)\n",
|
||
"Requirement already satisfied: colorama in c:\\users\\user\\anaconda3\\lib\\site-packages (from tqdm->kaggle) (0.4.4)\n",
|
||
"Requirement already satisfied: pandas in c:\\users\\user\\anaconda3\\lib\\site-packages (1.3.4)\n",
|
||
"Requirement already satisfied: pytz>=2017.3 in c:\\users\\user\\anaconda3\\lib\\site-packages (from pandas) (2021.3)\n",
|
||
"Requirement already satisfied: python-dateutil>=2.7.3 in c:\\users\\user\\anaconda3\\lib\\site-packages (from pandas) (2.8.2)\n",
|
||
"Requirement already satisfied: numpy>=1.17.3 in c:\\users\\user\\anaconda3\\lib\\site-packages (from pandas) (1.20.3)\n",
|
||
"Requirement already satisfied: six>=1.5 in c:\\users\\user\\anaconda3\\lib\\site-packages (from python-dateutil>=2.7.3->pandas) (1.16.0)\n",
|
||
"Requirement already satisfied: seaborn in c:\\users\\user\\anaconda3\\lib\\site-packages (0.11.2)\n",
|
||
"Requirement already satisfied: numpy>=1.15 in c:\\users\\user\\anaconda3\\lib\\site-packages (from seaborn) (1.20.3)\n",
|
||
"Requirement already satisfied: matplotlib>=2.2 in c:\\users\\user\\anaconda3\\lib\\site-packages (from seaborn) (3.4.3)\n",
|
||
"Requirement already satisfied: scipy>=1.0 in c:\\users\\user\\anaconda3\\lib\\site-packages (from seaborn) (1.7.1)\n",
|
||
"Requirement already satisfied: pandas>=0.23 in c:\\users\\user\\anaconda3\\lib\\site-packages (from seaborn) (1.3.4)\n",
|
||
"Requirement already satisfied: cycler>=0.10 in c:\\users\\user\\anaconda3\\lib\\site-packages (from matplotlib>=2.2->seaborn) (0.10.0)\n",
|
||
"Requirement already satisfied: pillow>=6.2.0 in c:\\users\\user\\anaconda3\\lib\\site-packages (from matplotlib>=2.2->seaborn) (8.4.0)\n",
|
||
"Requirement already satisfied: pyparsing>=2.2.1 in c:\\users\\user\\anaconda3\\lib\\site-packages (from matplotlib>=2.2->seaborn) (3.0.4)\n",
|
||
"Requirement already satisfied: kiwisolver>=1.0.1 in c:\\users\\user\\anaconda3\\lib\\site-packages (from matplotlib>=2.2->seaborn) (1.3.1)\n",
|
||
"Requirement already satisfied: python-dateutil>=2.7 in c:\\users\\user\\anaconda3\\lib\\site-packages (from matplotlib>=2.2->seaborn) (2.8.2)\n",
|
||
"Requirement already satisfied: six in c:\\users\\user\\anaconda3\\lib\\site-packages (from cycler>=0.10->matplotlib>=2.2->seaborn) (1.16.0)\n",
|
||
"Requirement already satisfied: pytz>=2017.3 in c:\\users\\user\\anaconda3\\lib\\site-packages (from pandas>=0.23->seaborn) (2021.3)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"!pip install kaggle\n",
|
||
"!pip install pandas\n",
|
||
"!pip install seaborn"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"adult-income-dataset.zip: Skipping, found more recently modified local copy (use --force to force download)\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"!kaggle datasets download -d wenruliu/adult-income-dataset\n",
|
||
"\n",
|
||
" "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"'unzip' is not recognized as an internal or external command,\n",
|
||
"operable program or batch file.\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"!unzip -o adult-income-dataset.zip"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 12,
|
||
"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>age</th>\n",
|
||
" <th>workclass</th>\n",
|
||
" <th>fnlwgt</th>\n",
|
||
" <th>education</th>\n",
|
||
" <th>educational-num</th>\n",
|
||
" <th>marital-status</th>\n",
|
||
" <th>occupation</th>\n",
|
||
" <th>relationship</th>\n",
|
||
" <th>race</th>\n",
|
||
" <th>gender</th>\n",
|
||
" <th>capital-gain</th>\n",
|
||
" <th>capital-loss</th>\n",
|
||
" <th>hours-per-week</th>\n",
|
||
" <th>native-country</th>\n",
|
||
" <th>income</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>0</th>\n",
|
||
" <td>25</td>\n",
|
||
" <td>Private</td>\n",
|
||
" <td>226802</td>\n",
|
||
" <td>11th</td>\n",
|
||
" <td>7</td>\n",
|
||
" <td>Never-married</td>\n",
|
||
" <td>Machine-op-inspct</td>\n",
|
||
" <td>Own-child</td>\n",
|
||
" <td>Black</td>\n",
|
||
" <td>Male</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>40</td>\n",
|
||
" <td>United-States</td>\n",
|
||
" <td><=50K</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>1</th>\n",
|
||
" <td>38</td>\n",
|
||
" <td>Private</td>\n",
|
||
" <td>89814</td>\n",
|
||
" <td>HS-grad</td>\n",
|
||
" <td>9</td>\n",
|
||
" <td>Married-civ-spouse</td>\n",
|
||
" <td>Farming-fishing</td>\n",
|
||
" <td>Husband</td>\n",
|
||
" <td>White</td>\n",
|
||
" <td>Male</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>50</td>\n",
|
||
" <td>United-States</td>\n",
|
||
" <td><=50K</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>2</th>\n",
|
||
" <td>28</td>\n",
|
||
" <td>Local-gov</td>\n",
|
||
" <td>336951</td>\n",
|
||
" <td>Assoc-acdm</td>\n",
|
||
" <td>12</td>\n",
|
||
" <td>Married-civ-spouse</td>\n",
|
||
" <td>Protective-serv</td>\n",
|
||
" <td>Husband</td>\n",
|
||
" <td>White</td>\n",
|
||
" <td>Male</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>40</td>\n",
|
||
" <td>United-States</td>\n",
|
||
" <td>>50K</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>3</th>\n",
|
||
" <td>44</td>\n",
|
||
" <td>Private</td>\n",
|
||
" <td>160323</td>\n",
|
||
" <td>Some-college</td>\n",
|
||
" <td>10</td>\n",
|
||
" <td>Married-civ-spouse</td>\n",
|
||
" <td>Machine-op-inspct</td>\n",
|
||
" <td>Husband</td>\n",
|
||
" <td>Black</td>\n",
|
||
" <td>Male</td>\n",
|
||
" <td>7688</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>40</td>\n",
|
||
" <td>United-States</td>\n",
|
||
" <td>>50K</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>4</th>\n",
|
||
" <td>18</td>\n",
|
||
" <td>?</td>\n",
|
||
" <td>103497</td>\n",
|
||
" <td>Some-college</td>\n",
|
||
" <td>10</td>\n",
|
||
" <td>Never-married</td>\n",
|
||
" <td>?</td>\n",
|
||
" <td>Own-child</td>\n",
|
||
" <td>White</td>\n",
|
||
" <td>Female</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>30</td>\n",
|
||
" <td>United-States</td>\n",
|
||
" <td><=50K</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>...</th>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" <td>...</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>48837</th>\n",
|
||
" <td>27</td>\n",
|
||
" <td>Private</td>\n",
|
||
" <td>257302</td>\n",
|
||
" <td>Assoc-acdm</td>\n",
|
||
" <td>12</td>\n",
|
||
" <td>Married-civ-spouse</td>\n",
|
||
" <td>Tech-support</td>\n",
|
||
" <td>Wife</td>\n",
|
||
" <td>White</td>\n",
|
||
" <td>Female</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>38</td>\n",
|
||
" <td>United-States</td>\n",
|
||
" <td><=50K</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>48838</th>\n",
|
||
" <td>40</td>\n",
|
||
" <td>Private</td>\n",
|
||
" <td>154374</td>\n",
|
||
" <td>HS-grad</td>\n",
|
||
" <td>9</td>\n",
|
||
" <td>Married-civ-spouse</td>\n",
|
||
" <td>Machine-op-inspct</td>\n",
|
||
" <td>Husband</td>\n",
|
||
" <td>White</td>\n",
|
||
" <td>Male</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>40</td>\n",
|
||
" <td>United-States</td>\n",
|
||
" <td>>50K</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>48839</th>\n",
|
||
" <td>58</td>\n",
|
||
" <td>Private</td>\n",
|
||
" <td>151910</td>\n",
|
||
" <td>HS-grad</td>\n",
|
||
" <td>9</td>\n",
|
||
" <td>Widowed</td>\n",
|
||
" <td>Adm-clerical</td>\n",
|
||
" <td>Unmarried</td>\n",
|
||
" <td>White</td>\n",
|
||
" <td>Female</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>40</td>\n",
|
||
" <td>United-States</td>\n",
|
||
" <td><=50K</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>48840</th>\n",
|
||
" <td>22</td>\n",
|
||
" <td>Private</td>\n",
|
||
" <td>201490</td>\n",
|
||
" <td>HS-grad</td>\n",
|
||
" <td>9</td>\n",
|
||
" <td>Never-married</td>\n",
|
||
" <td>Adm-clerical</td>\n",
|
||
" <td>Own-child</td>\n",
|
||
" <td>White</td>\n",
|
||
" <td>Male</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>20</td>\n",
|
||
" <td>United-States</td>\n",
|
||
" <td><=50K</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>48841</th>\n",
|
||
" <td>52</td>\n",
|
||
" <td>Self-emp-inc</td>\n",
|
||
" <td>287927</td>\n",
|
||
" <td>HS-grad</td>\n",
|
||
" <td>9</td>\n",
|
||
" <td>Married-civ-spouse</td>\n",
|
||
" <td>Exec-managerial</td>\n",
|
||
" <td>Wife</td>\n",
|
||
" <td>White</td>\n",
|
||
" <td>Female</td>\n",
|
||
" <td>15024</td>\n",
|
||
" <td>0</td>\n",
|
||
" <td>40</td>\n",
|
||
" <td>United-States</td>\n",
|
||
" <td>>50K</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"<p>48842 rows × 15 columns</p>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" age workclass fnlwgt education educational-num \\\n",
|
||
"0 25 Private 226802 11th 7 \n",
|
||
"1 38 Private 89814 HS-grad 9 \n",
|
||
"2 28 Local-gov 336951 Assoc-acdm 12 \n",
|
||
"3 44 Private 160323 Some-college 10 \n",
|
||
"4 18 ? 103497 Some-college 10 \n",
|
||
"... ... ... ... ... ... \n",
|
||
"48837 27 Private 257302 Assoc-acdm 12 \n",
|
||
"48838 40 Private 154374 HS-grad 9 \n",
|
||
"48839 58 Private 151910 HS-grad 9 \n",
|
||
"48840 22 Private 201490 HS-grad 9 \n",
|
||
"48841 52 Self-emp-inc 287927 HS-grad 9 \n",
|
||
"\n",
|
||
" marital-status occupation relationship race gender \\\n",
|
||
"0 Never-married Machine-op-inspct Own-child Black Male \n",
|
||
"1 Married-civ-spouse Farming-fishing Husband White Male \n",
|
||
"2 Married-civ-spouse Protective-serv Husband White Male \n",
|
||
"3 Married-civ-spouse Machine-op-inspct Husband Black Male \n",
|
||
"4 Never-married ? Own-child White Female \n",
|
||
"... ... ... ... ... ... \n",
|
||
"48837 Married-civ-spouse Tech-support Wife White Female \n",
|
||
"48838 Married-civ-spouse Machine-op-inspct Husband White Male \n",
|
||
"48839 Widowed Adm-clerical Unmarried White Female \n",
|
||
"48840 Never-married Adm-clerical Own-child White Male \n",
|
||
"48841 Married-civ-spouse Exec-managerial Wife White Female \n",
|
||
"\n",
|
||
" capital-gain capital-loss hours-per-week native-country income \n",
|
||
"0 0 0 40 United-States <=50K \n",
|
||
"1 0 0 50 United-States <=50K \n",
|
||
"2 0 0 40 United-States >50K \n",
|
||
"3 7688 0 40 United-States >50K \n",
|
||
"4 0 0 30 United-States <=50K \n",
|
||
"... ... ... ... ... ... \n",
|
||
"48837 0 0 38 United-States <=50K \n",
|
||
"48838 0 0 40 United-States >50K \n",
|
||
"48839 0 0 40 United-States <=50K \n",
|
||
"48840 0 0 20 United-States <=50K \n",
|
||
"48841 15024 0 40 United-States >50K \n",
|
||
"\n",
|
||
"[48842 rows x 15 columns]"
|
||
]
|
||
},
|
||
"execution_count": 12,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"import pandas as pd\n",
|
||
"df=pd.read_csv('adult-income-dataset.csv')\n",
|
||
"df\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 23,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"#usunięcie nie pełnych danych \n",
|
||
"df = df[df.workclass != '?']"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import torch\n",
|
||
"\n",
|
||
"train_size = int(0.8 * len(df))\n",
|
||
"test_size = (len(df) - train_size)\n",
|
||
"df_train, df_test = torch.utils.data.random_split(df, [train_size, test_size])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Wielkosc zbioru: 48842, podzbiór train: 39073, podzbiór test 9769.\n"
|
||
]
|
||
},
|
||
{
|
||
"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>age</th>\n",
|
||
" <th>workclass</th>\n",
|
||
" <th>fnlwgt</th>\n",
|
||
" <th>education</th>\n",
|
||
" <th>educational-num</th>\n",
|
||
" <th>marital-status</th>\n",
|
||
" <th>occupation</th>\n",
|
||
" <th>relationship</th>\n",
|
||
" <th>race</th>\n",
|
||
" <th>gender</th>\n",
|
||
" <th>capital-gain</th>\n",
|
||
" <th>capital-loss</th>\n",
|
||
" <th>hours-per-week</th>\n",
|
||
" <th>native-country</th>\n",
|
||
" <th>income</th>\n",
|
||
" </tr>\n",
|
||
" </thead>\n",
|
||
" <tbody>\n",
|
||
" <tr>\n",
|
||
" <th>count</th>\n",
|
||
" <td>48842.000000</td>\n",
|
||
" <td>48842</td>\n",
|
||
" <td>4.884200e+04</td>\n",
|
||
" <td>48842</td>\n",
|
||
" <td>48842.000000</td>\n",
|
||
" <td>48842</td>\n",
|
||
" <td>48842</td>\n",
|
||
" <td>48842</td>\n",
|
||
" <td>48842</td>\n",
|
||
" <td>48842</td>\n",
|
||
" <td>48842.000000</td>\n",
|
||
" <td>48842.000000</td>\n",
|
||
" <td>48842.000000</td>\n",
|
||
" <td>48842</td>\n",
|
||
" <td>48842</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>unique</th>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>9</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>16</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>7</td>\n",
|
||
" <td>15</td>\n",
|
||
" <td>6</td>\n",
|
||
" <td>5</td>\n",
|
||
" <td>2</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>42</td>\n",
|
||
" <td>2</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>top</th>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>Private</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>HS-grad</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>Married-civ-spouse</td>\n",
|
||
" <td>Prof-specialty</td>\n",
|
||
" <td>Husband</td>\n",
|
||
" <td>White</td>\n",
|
||
" <td>Male</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>United-States</td>\n",
|
||
" <td><=50K</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>freq</th>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>33906</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>15784</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>22379</td>\n",
|
||
" <td>6172</td>\n",
|
||
" <td>19716</td>\n",
|
||
" <td>41762</td>\n",
|
||
" <td>32650</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>43832</td>\n",
|
||
" <td>37155</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>mean</th>\n",
|
||
" <td>38.643585</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1.896641e+05</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>10.078089</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1079.067626</td>\n",
|
||
" <td>87.502314</td>\n",
|
||
" <td>40.422382</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>std</th>\n",
|
||
" <td>13.710510</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1.056040e+05</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>2.570973</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>7452.019058</td>\n",
|
||
" <td>403.004552</td>\n",
|
||
" <td>12.391444</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>min</th>\n",
|
||
" <td>17.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1.228500e+04</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>0.000000</td>\n",
|
||
" <td>0.000000</td>\n",
|
||
" <td>1.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>25%</th>\n",
|
||
" <td>28.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1.175505e+05</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>9.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>0.000000</td>\n",
|
||
" <td>0.000000</td>\n",
|
||
" <td>40.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>50%</th>\n",
|
||
" <td>37.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1.781445e+05</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>10.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>0.000000</td>\n",
|
||
" <td>0.000000</td>\n",
|
||
" <td>40.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>75%</th>\n",
|
||
" <td>48.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>2.376420e+05</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>12.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>0.000000</td>\n",
|
||
" <td>0.000000</td>\n",
|
||
" <td>45.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" <tr>\n",
|
||
" <th>max</th>\n",
|
||
" <td>90.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>1.490400e+06</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>16.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>99999.000000</td>\n",
|
||
" <td>4356.000000</td>\n",
|
||
" <td>99.000000</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" <td>NaN</td>\n",
|
||
" </tr>\n",
|
||
" </tbody>\n",
|
||
"</table>\n",
|
||
"</div>"
|
||
],
|
||
"text/plain": [
|
||
" age workclass fnlwgt education educational-num \\\n",
|
||
"count 48842.000000 48842 4.884200e+04 48842 48842.000000 \n",
|
||
"unique NaN 9 NaN 16 NaN \n",
|
||
"top NaN Private NaN HS-grad NaN \n",
|
||
"freq NaN 33906 NaN 15784 NaN \n",
|
||
"mean 38.643585 NaN 1.896641e+05 NaN 10.078089 \n",
|
||
"std 13.710510 NaN 1.056040e+05 NaN 2.570973 \n",
|
||
"min 17.000000 NaN 1.228500e+04 NaN 1.000000 \n",
|
||
"25% 28.000000 NaN 1.175505e+05 NaN 9.000000 \n",
|
||
"50% 37.000000 NaN 1.781445e+05 NaN 10.000000 \n",
|
||
"75% 48.000000 NaN 2.376420e+05 NaN 12.000000 \n",
|
||
"max 90.000000 NaN 1.490400e+06 NaN 16.000000 \n",
|
||
"\n",
|
||
" marital-status occupation relationship race gender \\\n",
|
||
"count 48842 48842 48842 48842 48842 \n",
|
||
"unique 7 15 6 5 2 \n",
|
||
"top Married-civ-spouse Prof-specialty Husband White Male \n",
|
||
"freq 22379 6172 19716 41762 32650 \n",
|
||
"mean NaN NaN NaN NaN NaN \n",
|
||
"std NaN NaN NaN NaN NaN \n",
|
||
"min NaN NaN NaN NaN NaN \n",
|
||
"25% NaN NaN NaN NaN NaN \n",
|
||
"50% NaN NaN NaN NaN NaN \n",
|
||
"75% NaN NaN NaN NaN NaN \n",
|
||
"max NaN NaN NaN NaN NaN \n",
|
||
"\n",
|
||
" capital-gain capital-loss hours-per-week native-country income \n",
|
||
"count 48842.000000 48842.000000 48842.000000 48842 48842 \n",
|
||
"unique NaN NaN NaN 42 2 \n",
|
||
"top NaN NaN NaN United-States <=50K \n",
|
||
"freq NaN NaN NaN 43832 37155 \n",
|
||
"mean 1079.067626 87.502314 40.422382 NaN NaN \n",
|
||
"std 7452.019058 403.004552 12.391444 NaN NaN \n",
|
||
"min 0.000000 0.000000 1.000000 NaN NaN \n",
|
||
"25% 0.000000 0.000000 40.000000 NaN NaN \n",
|
||
"50% 0.000000 0.000000 40.000000 NaN NaN \n",
|
||
"75% 0.000000 0.000000 45.000000 NaN NaN \n",
|
||
"max 99999.000000 4356.000000 99.000000 NaN NaN "
|
||
]
|
||
},
|
||
"execution_count": 6,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"print(f\"Wielkosc zbioru: {len(df)}, podzbiór train: {train_size}, podzbiór test {test_size}.\")\n",
|
||
"df.describe(include='all')\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"<AxesSubplot:title={'center':'income'}>"
|
||
]
|
||
},
|
||
"execution_count": 7,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
},
|
||
{
|
||
"data": {
|
||
"image/png": "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",
|
||
"text/plain": [
|
||
"<Figure size 432x288 with 1 Axes>"
|
||
]
|
||
},
|
||
"metadata": {
|
||
"needs_background": "light"
|
||
},
|
||
"output_type": "display_data"
|
||
}
|
||
],
|
||
"source": [
|
||
"df[\"income\"].value_counts().plot(kind=\"bar\", title=\"income\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
}
|
||
],
|
||
"metadata": {
|
||
"interpreter": {
|
||
"hash": "2647ea34e536f865ab67ff9ddee7fd78773d956cec0cab53c79b32cd10da5d83"
|
||
},
|
||
"kernelspec": {
|
||
"display_name": "Python 3.9.11 64-bit",
|
||
"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": "3.9.7"
|
||
},
|
||
"orig_nbformat": 2
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 2
|
||
}
|