651 lines
22 KiB
Plaintext
651 lines
22 KiB
Plaintext
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 14,
|
|
"id": "74524ede",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
" age gender height_cm weight_kg body fat_% diastolic systolic \\\n",
|
|
"0 27.0 M 172.3 75.24 21.3 80.0 130.0 \n",
|
|
"1 25.0 M 165.0 55.80 15.7 77.0 126.0 \n",
|
|
"2 31.0 M 179.6 78.00 20.1 92.0 152.0 \n",
|
|
"3 32.0 M 174.5 71.10 18.4 76.0 147.0 \n",
|
|
"4 28.0 M 173.8 67.70 17.1 70.0 127.0 \n",
|
|
"\n",
|
|
" gripForce sit and bend forward_cm sit-ups counts broad jump_cm class \\\n",
|
|
"0 54.9 18.4 60.0 217.0 C \n",
|
|
"1 36.4 16.3 53.0 229.0 A \n",
|
|
"2 44.8 12.0 49.0 181.0 C \n",
|
|
"3 41.4 15.2 53.0 219.0 B \n",
|
|
"4 43.5 27.1 45.0 217.0 B \n",
|
|
"\n",
|
|
" BMI \n",
|
|
"0 25.344179 \n",
|
|
"1 20.495868 \n",
|
|
"2 24.181428 \n",
|
|
"3 23.349562 \n",
|
|
"4 22.412439 \n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"import pandas as pd\n",
|
|
"import plotly.express as px\n",
|
|
"import seaborn as sns\n",
|
|
"from sklearn.model_selection import train_test_split\n",
|
|
"from sklearn.preprocessing import MinMaxScaler\n",
|
|
"\n",
|
|
"df = pd.read_csv(r'.\\body_performance.csv')\n",
|
|
"\n",
|
|
"df['BMI'] = df['weight_kg']/(0.0001*df['height_cm']*df['height_cm'])\n",
|
|
"print(df.head())"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "0177f243",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"df.duplicated().sum()\n",
|
|
"print(f'with duplicates:{df.shape}')\n",
|
|
"df.drop_duplicates(inplace=True)\n",
|
|
"print(f'without duplicates:{df.shape}')\n",
|
|
"df_copy = df.copy()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 3,
|
|
"id": "05f9442a",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"number of elements in data frame: 13393\n",
|
|
"train: 10715\n",
|
|
"test: 1339\n",
|
|
"valid: 1339\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"body_train, body_test = train_test_split(df, test_size=int(df[\"age\"].count()*0.2), random_state=1)\n",
|
|
"body_test, body_valid = train_test_split(body_test, test_size=int(body_test[\"age\"].count()*0.5), random_state=1)\n",
|
|
"\n",
|
|
"print(\"number of elements in data frame: {}\".format(df['age'].count()))\n",
|
|
"print(\"train: {}\".format(body_train[\"age\"].count()))\n",
|
|
"print(\"test: {}\".format(body_test[\"age\"].count()))\n",
|
|
"print(\"valid: {}\".format(body_valid[\"age\"].count()))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 12,
|
|
"id": "0f3ad57a",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
" age gender height_cm weight_kg body fat_% \\\n",
|
|
"count 13393.000000 13393 13393.000000 13393.000000 13393.000000 \n",
|
|
"unique NaN 2 NaN NaN NaN \n",
|
|
"top NaN M NaN NaN NaN \n",
|
|
"freq NaN 8467 NaN NaN NaN \n",
|
|
"mean 36.775106 NaN 168.559807 67.447316 23.240165 \n",
|
|
"std 13.625639 NaN 8.426583 11.949666 7.256844 \n",
|
|
"min 21.000000 NaN 125.000000 26.300000 3.000000 \n",
|
|
"25% 25.000000 NaN 162.400000 58.200000 18.000000 \n",
|
|
"50% 32.000000 NaN 169.200000 67.400000 22.800000 \n",
|
|
"75% 48.000000 NaN 174.800000 75.300000 28.000000 \n",
|
|
"max 64.000000 NaN 193.800000 138.100000 78.400000 \n",
|
|
"\n",
|
|
" diastolic systolic gripForce sit and bend forward_cm \\\n",
|
|
"count 13393.000000 13393.000000 13393.000000 13393.000000 \n",
|
|
"unique NaN NaN NaN NaN \n",
|
|
"top NaN NaN NaN NaN \n",
|
|
"freq NaN NaN NaN NaN \n",
|
|
"mean 78.796842 130.234817 36.963877 15.209268 \n",
|
|
"std 10.742033 14.713954 10.624864 8.456677 \n",
|
|
"min 0.000000 0.000000 0.000000 -25.000000 \n",
|
|
"25% 71.000000 120.000000 27.500000 10.900000 \n",
|
|
"50% 79.000000 130.000000 37.900000 16.200000 \n",
|
|
"75% 86.000000 141.000000 45.200000 20.700000 \n",
|
|
"max 156.200000 201.000000 70.500000 213.000000 \n",
|
|
"\n",
|
|
" sit-ups counts broad jump_cm class BMI \n",
|
|
"count 13393.000000 13393.000000 13393 13393.000000 \n",
|
|
"unique NaN NaN 4 NaN \n",
|
|
"top NaN NaN C NaN \n",
|
|
"freq NaN NaN 3349 NaN \n",
|
|
"mean 39.771224 190.129627 NaN 23.606014 \n",
|
|
"std 14.276698 39.868000 NaN 2.940936 \n",
|
|
"min 0.000000 0.000000 NaN 11.103976 \n",
|
|
"25% 30.000000 162.000000 NaN 21.612812 \n",
|
|
"50% 41.000000 193.000000 NaN 23.463513 \n",
|
|
"75% 50.000000 221.000000 NaN 25.341367 \n",
|
|
"max 80.000000 303.000000 NaN 42.906509 \n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print(df.describe(include='all'))\n",
|
|
"#sit and bend forward_cm jest na minusie!!!"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 15,
|
|
"id": "dacdd816",
|
|
"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>gender</th>\n",
|
|
" <th>height_cm</th>\n",
|
|
" <th>weight_kg</th>\n",
|
|
" <th>body fat_%</th>\n",
|
|
" <th>diastolic</th>\n",
|
|
" <th>systolic</th>\n",
|
|
" <th>gripForce</th>\n",
|
|
" <th>sit and bend forward_cm</th>\n",
|
|
" <th>sit-ups counts</th>\n",
|
|
" <th>broad jump_cm</th>\n",
|
|
" <th>class</th>\n",
|
|
" <th>BMI</th>\n",
|
|
" </tr>\n",
|
|
" </thead>\n",
|
|
" <tbody>\n",
|
|
" <tr>\n",
|
|
" <th>count</th>\n",
|
|
" <td>13393.000000</td>\n",
|
|
" <td>13393</td>\n",
|
|
" <td>13393.000000</td>\n",
|
|
" <td>13393.000000</td>\n",
|
|
" <td>13393.000000</td>\n",
|
|
" <td>13393.000000</td>\n",
|
|
" <td>13393.000000</td>\n",
|
|
" <td>13393.000000</td>\n",
|
|
" <td>13393.000000</td>\n",
|
|
" <td>13393.000000</td>\n",
|
|
" <td>13393.000000</td>\n",
|
|
" <td>13393</td>\n",
|
|
" <td>13393.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>unique</th>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>2</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>4</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>top</th>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>M</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>C</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>freq</th>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>8467</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>3349</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>mean</th>\n",
|
|
" <td>0.366863</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>0.633137</td>\n",
|
|
" <td>0.368044</td>\n",
|
|
" <td>0.268437</td>\n",
|
|
" <td>0.504461</td>\n",
|
|
" <td>0.647934</td>\n",
|
|
" <td>0.524310</td>\n",
|
|
" <td>-0.662107</td>\n",
|
|
" <td>0.497140</td>\n",
|
|
" <td>0.627491</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>0.393115</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>std</th>\n",
|
|
" <td>0.316875</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>0.122479</td>\n",
|
|
" <td>0.106884</td>\n",
|
|
" <td>0.096245</td>\n",
|
|
" <td>0.068771</td>\n",
|
|
" <td>0.073204</td>\n",
|
|
" <td>0.150707</td>\n",
|
|
" <td>0.071065</td>\n",
|
|
" <td>0.178459</td>\n",
|
|
" <td>0.131578</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>0.092475</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>min</th>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>-1.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>0.000000</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>25%</th>\n",
|
|
" <td>0.093023</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>0.543605</td>\n",
|
|
" <td>0.285331</td>\n",
|
|
" <td>0.198939</td>\n",
|
|
" <td>0.454545</td>\n",
|
|
" <td>0.597015</td>\n",
|
|
" <td>0.390071</td>\n",
|
|
" <td>-0.698319</td>\n",
|
|
" <td>0.375000</td>\n",
|
|
" <td>0.534653</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>0.330440</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>50%</th>\n",
|
|
" <td>0.255814</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>0.642442</td>\n",
|
|
" <td>0.367621</td>\n",
|
|
" <td>0.262599</td>\n",
|
|
" <td>0.505762</td>\n",
|
|
" <td>0.646766</td>\n",
|
|
" <td>0.537589</td>\n",
|
|
" <td>-0.653782</td>\n",
|
|
" <td>0.512500</td>\n",
|
|
" <td>0.636964</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>0.388634</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>75%</th>\n",
|
|
" <td>0.627907</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>0.723837</td>\n",
|
|
" <td>0.438283</td>\n",
|
|
" <td>0.331565</td>\n",
|
|
" <td>0.550576</td>\n",
|
|
" <td>0.701493</td>\n",
|
|
" <td>0.641135</td>\n",
|
|
" <td>-0.615966</td>\n",
|
|
" <td>0.625000</td>\n",
|
|
" <td>0.729373</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>0.447681</td>\n",
|
|
" </tr>\n",
|
|
" <tr>\n",
|
|
" <th>max</th>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>1.000000</td>\n",
|
|
" <td>NaN</td>\n",
|
|
" <td>1.000000</td>\n",
|
|
" </tr>\n",
|
|
" </tbody>\n",
|
|
"</table>\n",
|
|
"</div>"
|
|
],
|
|
"text/plain": [
|
|
" age gender height_cm weight_kg body fat_% \\\n",
|
|
"count 13393.000000 13393 13393.000000 13393.000000 13393.000000 \n",
|
|
"unique NaN 2 NaN NaN NaN \n",
|
|
"top NaN M NaN NaN NaN \n",
|
|
"freq NaN 8467 NaN NaN NaN \n",
|
|
"mean 0.366863 NaN 0.633137 0.368044 0.268437 \n",
|
|
"std 0.316875 NaN 0.122479 0.106884 0.096245 \n",
|
|
"min 0.000000 NaN 0.000000 0.000000 0.000000 \n",
|
|
"25% 0.093023 NaN 0.543605 0.285331 0.198939 \n",
|
|
"50% 0.255814 NaN 0.642442 0.367621 0.262599 \n",
|
|
"75% 0.627907 NaN 0.723837 0.438283 0.331565 \n",
|
|
"max 1.000000 NaN 1.000000 1.000000 1.000000 \n",
|
|
"\n",
|
|
" diastolic systolic gripForce sit and bend forward_cm \\\n",
|
|
"count 13393.000000 13393.000000 13393.000000 13393.000000 \n",
|
|
"unique NaN NaN NaN NaN \n",
|
|
"top NaN NaN NaN NaN \n",
|
|
"freq NaN NaN NaN NaN \n",
|
|
"mean 0.504461 0.647934 0.524310 -0.662107 \n",
|
|
"std 0.068771 0.073204 0.150707 0.071065 \n",
|
|
"min 0.000000 0.000000 0.000000 -1.000000 \n",
|
|
"25% 0.454545 0.597015 0.390071 -0.698319 \n",
|
|
"50% 0.505762 0.646766 0.537589 -0.653782 \n",
|
|
"75% 0.550576 0.701493 0.641135 -0.615966 \n",
|
|
"max 1.000000 1.000000 1.000000 1.000000 \n",
|
|
"\n",
|
|
" sit-ups counts broad jump_cm class BMI \n",
|
|
"count 13393.000000 13393.000000 13393 13393.000000 \n",
|
|
"unique NaN NaN 4 NaN \n",
|
|
"top NaN NaN C NaN \n",
|
|
"freq NaN NaN 3349 NaN \n",
|
|
"mean 0.497140 0.627491 NaN 0.393115 \n",
|
|
"std 0.178459 0.131578 NaN 0.092475 \n",
|
|
"min 0.000000 0.000000 NaN 0.000000 \n",
|
|
"25% 0.375000 0.534653 NaN 0.330440 \n",
|
|
"50% 0.512500 0.636964 NaN 0.388634 \n",
|
|
"75% 0.625000 0.729373 NaN 0.447681 \n",
|
|
"max 1.000000 1.000000 NaN 1.000000 "
|
|
]
|
|
},
|
|
"execution_count": 15,
|
|
"metadata": {},
|
|
"output_type": "execute_result"
|
|
}
|
|
],
|
|
"source": [
|
|
"scaler = MinMaxScaler()\n",
|
|
"df[['age', 'height_cm', 'weight_kg','body fat_%',\n",
|
|
" 'diastolic','systolic','gripForce','sit-ups counts',\n",
|
|
" 'broad jump_cm','BMI']] = scaler.fit_transform(df[[\n",
|
|
" 'age', 'height_cm', 'weight_kg','body fat_%',\n",
|
|
" 'diastolic','systolic','gripForce','sit-ups counts',\n",
|
|
" 'broad jump_cm','BMI']])\n",
|
|
"\n",
|
|
"scaler = MinMaxScaler(feature_range=(-1, 1))\n",
|
|
"df['sit and bend forward_cm'] = scaler.fit_transform(df[['sit and bend forward_cm']])\n",
|
|
"df.describe(include='all')\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 16,
|
|
"id": "5cd376cf",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"<class 'pandas.core.frame.DataFrame'>\n",
|
|
"RangeIndex: 13393 entries, 0 to 13392\n",
|
|
"Data columns (total 13 columns):\n",
|
|
" # Column Non-Null Count Dtype \n",
|
|
"--- ------ -------------- ----- \n",
|
|
" 0 age 13393 non-null float64\n",
|
|
" 1 gender 13393 non-null object \n",
|
|
" 2 height_cm 13393 non-null float64\n",
|
|
" 3 weight_kg 13393 non-null float64\n",
|
|
" 4 body fat_% 13393 non-null float64\n",
|
|
" 5 diastolic 13393 non-null float64\n",
|
|
" 6 systolic 13393 non-null float64\n",
|
|
" 7 gripForce 13393 non-null float64\n",
|
|
" 8 sit and bend forward_cm 13393 non-null float64\n",
|
|
" 9 sit-ups counts 13393 non-null float64\n",
|
|
" 10 broad jump_cm 13393 non-null float64\n",
|
|
" 11 class 13393 non-null object \n",
|
|
" 12 BMI 13393 non-null float64\n",
|
|
"dtypes: float64(11), object(2)\n",
|
|
"memory usage: 1.3+ MB\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"df.info()"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": 10,
|
|
"id": "93dcf330",
|
|
"metadata": {},
|
|
"outputs": [
|
|
{
|
|
"name": "stdout",
|
|
"output_type": "stream",
|
|
"text": [
|
|
"Each class in data frame: \n",
|
|
"C 3349\n",
|
|
"D 3349\n",
|
|
"A 3348\n",
|
|
"B 3347\n",
|
|
"Name: class, dtype: int64\n",
|
|
"Each class in train data: \n",
|
|
"A 2703\n",
|
|
"B 2681\n",
|
|
"C 2671\n",
|
|
"D 2660\n",
|
|
"Name: class, dtype: int64\n",
|
|
"Each class in test data: \n",
|
|
"D 353\n",
|
|
"C 332\n",
|
|
"B 328\n",
|
|
"A 326\n",
|
|
"Name: class, dtype: int64\n",
|
|
"Each class in valid data: \n",
|
|
"C 346\n",
|
|
"B 338\n",
|
|
"D 336\n",
|
|
"A 319\n",
|
|
"Name: class, dtype: int64\n"
|
|
]
|
|
}
|
|
],
|
|
"source": [
|
|
"print('Each class in data frame: \\n{}'.format(df['class'].value_counts()))\n",
|
|
"print('Each class in train data: \\n{}'.format(body_train['class'].value_counts()))\n",
|
|
"print('Each class in test data: \\n{}'.format(body_test['class'].value_counts()))\n",
|
|
"print('Each class in valid data: \\n{}'.format(body_valid['class'].value_counts()))"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "b5620509",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "3e9bbbe7",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"\n",
|
|
"\n"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "4857a167",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#df[\"class\"].value_counts().plot(kind=\"bar\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "779157c0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#df[[\"class\",\"body fat_%\"]].groupby(\"class\").mean().plot(kind=\"bar\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "da14bf43",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#sns.set_theme()\n",
|
|
"\n",
|
|
"#sns.relplot(data = df.head(200), x = 'broad jump_cm', y = 'sit-ups counts', hue = 'class')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "6597e57c",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#sns.relplot(data = df[df['gender'] == 'M'].head(200), x = 'body fat_%', y = 'BMI', hue = 'class')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "957e1b2e",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#sns.relplot(data = df[df['gender'] == 'F'].head(200), x = 'body fat_%', y = 'BMI', hue = 'class')"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "9f0394f0",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"#px.box(df, y=['height_cm',\n",
|
|
"# 'weight_kg',\n",
|
|
"# 'body fat_%',\n",
|
|
"# 'diastolic',\n",
|
|
"# 'systolic',\n",
|
|
"# 'gripForce',\n",
|
|
"# 'sit and bend forward_cm',\n",
|
|
"# 'sit-ups counts',\n",
|
|
"# 'broad jump_cm',\n",
|
|
"# 'BMI'])"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "22542bba",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": [
|
|
"# this is taking too long time\n",
|
|
"#sns.pairplot(data=df.drop(columns=[\"gender\"]).head(500), hue=\"class\")"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "29730d20",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"execution_count": null,
|
|
"id": "dc21a9cb",
|
|
"metadata": {},
|
|
"outputs": [],
|
|
"source": []
|
|
}
|
|
],
|
|
"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": "3.10.9"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|