ium_464913/IUM_2.ipynb

3341 lines
126 KiB
Plaintext
Raw Permalink Normal View History

2024-03-16 14:35:44 +01:00
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"## IUM 2\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"### Installation of packages\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "code",
2024-03-16 14:45:16 +01:00
"execution_count": 86,
2024-03-16 14:35:44 +01:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Requirement already satisfied: kaggle in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (1.6.6)\n",
"Requirement already satisfied: six>=1.10 in c:\\users\\skype\\appdata\\roaming\\python\\python312\\site-packages (from kaggle) (1.16.0)\n",
"Requirement already satisfied: certifi in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from kaggle) (2024.2.2)\n",
"Requirement already satisfied: python-dateutil in c:\\users\\skype\\appdata\\roaming\\python\\python312\\site-packages (from kaggle) (2.9.0.post0)\n",
"Requirement already satisfied: requests in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from kaggle) (2.31.0)\n",
"Requirement already satisfied: tqdm in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from kaggle) (4.66.2)\n",
"Requirement already satisfied: python-slugify in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from kaggle) (8.0.4)\n",
"Requirement already satisfied: urllib3 in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from kaggle) (2.2.1)\n",
"Requirement already satisfied: bleach in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from kaggle) (6.1.0)\n",
"Requirement already satisfied: webencodings in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from bleach->kaggle) (0.5.1)\n",
"Requirement already satisfied: text-unidecode>=1.3 in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from python-slugify->kaggle) (1.3)\n",
"Requirement already satisfied: charset-normalizer<4,>=2 in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from requests->kaggle) (3.3.2)\n",
"Requirement already satisfied: idna<4,>=2.5 in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from requests->kaggle) (3.6)\n",
"Requirement already satisfied: colorama in c:\\users\\skype\\appdata\\roaming\\python\\python312\\site-packages (from tqdm->kaggle) (0.4.6)\n",
"Note: you may need to restart the kernel to use updated packages.\n",
"Requirement already satisfied: pandas in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (2.2.1)\n",
"Requirement already satisfied: numpy<2,>=1.26.0 in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from pandas) (1.26.3)\n",
"Requirement already satisfied: python-dateutil>=2.8.2 in c:\\users\\skype\\appdata\\roaming\\python\\python312\\site-packages (from pandas) (2.9.0.post0)\n",
"Requirement already satisfied: pytz>=2020.1 in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from pandas) (2024.1)\n",
"Requirement already satisfied: tzdata>=2022.7 in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from pandas) (2024.1)\n",
"Requirement already satisfied: six>=1.5 in c:\\users\\skype\\appdata\\roaming\\python\\python312\\site-packages (from python-dateutil>=2.8.2->pandas) (1.16.0)\n",
"Note: you may need to restart the kernel to use updated packages.\n",
"Requirement already satisfied: numpy in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (1.26.3)\n",
"Note: you may need to restart the kernel to use updated packages.\n",
"Requirement already satisfied: scikit-learn in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (1.4.1.post1)\n",
"Requirement already satisfied: numpy<2.0,>=1.19.5 in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from scikit-learn) (1.26.3)\n",
"Requirement already satisfied: scipy>=1.6.0 in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from scikit-learn) (1.12.0)\n",
"Requirement already satisfied: joblib>=1.2.0 in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from scikit-learn) (1.3.2)\n",
"Requirement already satisfied: threadpoolctl>=2.0.0 in c:\\users\\skype\\appdata\\local\\programs\\python\\python312\\lib\\site-packages (from scikit-learn) (3.3.0)\n",
"Note: you may need to restart the kernel to use updated packages.\n"
]
}
],
"source": [
"%pip install kaggle\n",
"%pip install pandas\n",
"%pip install numpy\n",
"%pip install scikit-learn"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"### Importing libraries\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "code",
2024-03-16 14:45:16 +01:00
"execution_count": 87,
2024-03-16 14:35:44 +01:00
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import numpy as np\n",
"\n",
"# To preprocess the data\n",
"from sklearn.preprocessing import StandardScaler\n",
"\n",
"# To split the data\n",
"from sklearn.model_selection import train_test_split"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"### Downloading a dataset\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "code",
2024-03-16 14:45:16 +01:00
"execution_count": 88,
2024-03-16 14:35:44 +01:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"creditcardfraud.zip: Skipping, found more recently modified local copy (use --force to force download)\n"
]
}
],
"source": [
"!kaggle datasets download -d mlg-ulb/creditcardfraud"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"### Uncompress a file\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "code",
2024-03-16 14:45:16 +01:00
"execution_count": 89,
2024-03-16 14:35:44 +01:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Archive: creditcardfraud.zip\n",
" inflating: creditcard.csv \n"
]
}
],
"source": [
"!unzip -o creditcardfraud.zip"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"### Load the data\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "code",
2024-03-16 14:45:16 +01:00
"execution_count": 90,
2024-03-16 14:35:44 +01:00
"metadata": {},
"outputs": [],
"source": [
2024-04-01 19:14:34 +02:00
"df = pd.read_csv(\"creditcard.csv\")\n",
"pd.set_option(\"display.max_columns\", None)"
2024-03-16 14:35:44 +01:00
]
},
2024-03-16 14:45:16 +01:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"### Check missing values\n"
2024-03-16 14:45:16 +01:00
]
},
{
"cell_type": "code",
"execution_count": 91,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Time 0\n",
"V1 0\n",
"V2 0\n",
"V3 0\n",
"V4 0\n",
"V5 0\n",
"V6 0\n",
"V7 0\n",
"V8 0\n",
"V9 0\n",
"V10 0\n",
"V11 0\n",
"V12 0\n",
"V13 0\n",
"V14 0\n",
"V15 0\n",
"V16 0\n",
"V17 0\n",
"V18 0\n",
"V19 0\n",
"V20 0\n",
"V21 0\n",
"V22 0\n",
"V23 0\n",
"V24 0\n",
"V25 0\n",
"V26 0\n",
"V27 0\n",
"V28 0\n",
"Amount 0\n",
"Class 0\n",
"dtype: int64"
]
},
"execution_count": 91,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.isnull().sum()"
]
},
2024-03-16 14:35:44 +01:00
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"### Size of the dataset\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "code",
2024-03-16 14:45:16 +01:00
"execution_count": 92,
2024-03-16 14:35:44 +01:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
"RangeIndex: 284807 entries, 0 to 284806\n",
"Data columns (total 31 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 Time 284807 non-null float64\n",
" 1 V1 284807 non-null float64\n",
" 2 V2 284807 non-null float64\n",
" 3 V3 284807 non-null float64\n",
" 4 V4 284807 non-null float64\n",
" 5 V5 284807 non-null float64\n",
" 6 V6 284807 non-null float64\n",
" 7 V7 284807 non-null float64\n",
" 8 V8 284807 non-null float64\n",
" 9 V9 284807 non-null float64\n",
" 10 V10 284807 non-null float64\n",
" 11 V11 284807 non-null float64\n",
" 12 V12 284807 non-null float64\n",
" 13 V13 284807 non-null float64\n",
" 14 V14 284807 non-null float64\n",
" 15 V15 284807 non-null float64\n",
" 16 V16 284807 non-null float64\n",
" 17 V17 284807 non-null float64\n",
" 18 V18 284807 non-null float64\n",
" 19 V19 284807 non-null float64\n",
" 20 V20 284807 non-null float64\n",
" 21 V21 284807 non-null float64\n",
" 22 V22 284807 non-null float64\n",
" 23 V23 284807 non-null float64\n",
" 24 V24 284807 non-null float64\n",
" 25 V25 284807 non-null float64\n",
" 26 V26 284807 non-null float64\n",
" 27 V27 284807 non-null float64\n",
" 28 V28 284807 non-null float64\n",
" 29 Amount 284807 non-null float64\n",
" 30 Class 284807 non-null int64 \n",
"dtypes: float64(30), int64(1)\n",
"memory usage: 67.4 MB\n"
]
}
],
"source": [
"df.info()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"### Normalising the data\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "code",
2024-03-16 14:45:16 +01:00
"execution_count": 93,
2024-03-16 14:35:44 +01:00
"metadata": {},
"outputs": [],
"source": [
"scaler = StandardScaler()\n",
"\n",
2024-04-01 19:14:34 +02:00
"df[\"Amount\"] = scaler.fit_transform(df[\"Amount\"].values.reshape(-1, 1))"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"### Summary statistics\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "code",
2024-03-16 14:45:16 +01:00
"execution_count": 94,
2024-03-16 14:35:44 +01:00
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Time</th>\n",
" <th>V1</th>\n",
" <th>V2</th>\n",
" <th>V3</th>\n",
" <th>V4</th>\n",
" <th>V5</th>\n",
" <th>V6</th>\n",
" <th>V7</th>\n",
" <th>V8</th>\n",
" <th>V9</th>\n",
" <th>V10</th>\n",
" <th>V11</th>\n",
" <th>V12</th>\n",
" <th>V13</th>\n",
" <th>V14</th>\n",
" <th>V15</th>\n",
" <th>V16</th>\n",
" <th>V17</th>\n",
" <th>V18</th>\n",
" <th>V19</th>\n",
" <th>V20</th>\n",
" <th>V21</th>\n",
" <th>V22</th>\n",
" <th>V23</th>\n",
" <th>V24</th>\n",
" <th>V25</th>\n",
" <th>V26</th>\n",
" <th>V27</th>\n",
" <th>V28</th>\n",
" <th>Amount</th>\n",
" <th>Class</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>284807.000000</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>2.848070e+05</td>\n",
" <td>284807.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
" <td>94813.859575</td>\n",
" <td>1.168375e-15</td>\n",
" <td>3.416908e-16</td>\n",
" <td>-1.379537e-15</td>\n",
" <td>2.074095e-15</td>\n",
" <td>9.604066e-16</td>\n",
" <td>1.487313e-15</td>\n",
" <td>-5.556467e-16</td>\n",
" <td>1.213481e-16</td>\n",
" <td>-2.406331e-15</td>\n",
" <td>2.239053e-15</td>\n",
" <td>1.673327e-15</td>\n",
" <td>-1.247012e-15</td>\n",
" <td>8.190001e-16</td>\n",
" <td>1.207294e-15</td>\n",
" <td>4.887456e-15</td>\n",
" <td>1.437716e-15</td>\n",
" <td>-3.772171e-16</td>\n",
" <td>9.564149e-16</td>\n",
" <td>1.039917e-15</td>\n",
" <td>6.406204e-16</td>\n",
" <td>1.654067e-16</td>\n",
" <td>-3.568593e-16</td>\n",
" <td>2.578648e-16</td>\n",
" <td>4.473266e-15</td>\n",
" <td>5.340915e-16</td>\n",
" <td>1.683437e-15</td>\n",
" <td>-3.660091e-16</td>\n",
" <td>-1.227390e-16</td>\n",
" <td>2.913952e-17</td>\n",
" <td>0.001727</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
" <td>47488.145955</td>\n",
" <td>1.958696e+00</td>\n",
" <td>1.651309e+00</td>\n",
" <td>1.516255e+00</td>\n",
" <td>1.415869e+00</td>\n",
" <td>1.380247e+00</td>\n",
" <td>1.332271e+00</td>\n",
" <td>1.237094e+00</td>\n",
" <td>1.194353e+00</td>\n",
" <td>1.098632e+00</td>\n",
" <td>1.088850e+00</td>\n",
" <td>1.020713e+00</td>\n",
" <td>9.992014e-01</td>\n",
" <td>9.952742e-01</td>\n",
" <td>9.585956e-01</td>\n",
" <td>9.153160e-01</td>\n",
" <td>8.762529e-01</td>\n",
" <td>8.493371e-01</td>\n",
" <td>8.381762e-01</td>\n",
" <td>8.140405e-01</td>\n",
" <td>7.709250e-01</td>\n",
" <td>7.345240e-01</td>\n",
" <td>7.257016e-01</td>\n",
" <td>6.244603e-01</td>\n",
" <td>6.056471e-01</td>\n",
" <td>5.212781e-01</td>\n",
" <td>4.822270e-01</td>\n",
" <td>4.036325e-01</td>\n",
" <td>3.300833e-01</td>\n",
" <td>1.000002e+00</td>\n",
" <td>0.041527</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
" <td>0.000000</td>\n",
" <td>-5.640751e+01</td>\n",
" <td>-7.271573e+01</td>\n",
" <td>-4.832559e+01</td>\n",
" <td>-5.683171e+00</td>\n",
" <td>-1.137433e+02</td>\n",
" <td>-2.616051e+01</td>\n",
" <td>-4.355724e+01</td>\n",
" <td>-7.321672e+01</td>\n",
" <td>-1.343407e+01</td>\n",
" <td>-2.458826e+01</td>\n",
" <td>-4.797473e+00</td>\n",
" <td>-1.868371e+01</td>\n",
" <td>-5.791881e+00</td>\n",
" <td>-1.921433e+01</td>\n",
" <td>-4.498945e+00</td>\n",
" <td>-1.412985e+01</td>\n",
" <td>-2.516280e+01</td>\n",
" <td>-9.498746e+00</td>\n",
" <td>-7.213527e+00</td>\n",
" <td>-5.449772e+01</td>\n",
" <td>-3.483038e+01</td>\n",
" <td>-1.093314e+01</td>\n",
" <td>-4.480774e+01</td>\n",
" <td>-2.836627e+00</td>\n",
" <td>-1.029540e+01</td>\n",
" <td>-2.604551e+00</td>\n",
" <td>-2.256568e+01</td>\n",
" <td>-1.543008e+01</td>\n",
" <td>-3.532294e-01</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
" <td>54201.500000</td>\n",
" <td>-9.203734e-01</td>\n",
" <td>-5.985499e-01</td>\n",
" <td>-8.903648e-01</td>\n",
" <td>-8.486401e-01</td>\n",
" <td>-6.915971e-01</td>\n",
" <td>-7.682956e-01</td>\n",
" <td>-5.540759e-01</td>\n",
" <td>-2.086297e-01</td>\n",
" <td>-6.430976e-01</td>\n",
" <td>-5.354257e-01</td>\n",
" <td>-7.624942e-01</td>\n",
" <td>-4.055715e-01</td>\n",
" <td>-6.485393e-01</td>\n",
" <td>-4.255740e-01</td>\n",
" <td>-5.828843e-01</td>\n",
" <td>-4.680368e-01</td>\n",
" <td>-4.837483e-01</td>\n",
" <td>-4.988498e-01</td>\n",
" <td>-4.562989e-01</td>\n",
" <td>-2.117214e-01</td>\n",
" <td>-2.283949e-01</td>\n",
" <td>-5.423504e-01</td>\n",
" <td>-1.618463e-01</td>\n",
" <td>-3.545861e-01</td>\n",
" <td>-3.171451e-01</td>\n",
" <td>-3.269839e-01</td>\n",
" <td>-7.083953e-02</td>\n",
" <td>-5.295979e-02</td>\n",
" <td>-3.308401e-01</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
" <td>84692.000000</td>\n",
" <td>1.810880e-02</td>\n",
" <td>6.548556e-02</td>\n",
" <td>1.798463e-01</td>\n",
" <td>-1.984653e-02</td>\n",
" <td>-5.433583e-02</td>\n",
" <td>-2.741871e-01</td>\n",
" <td>4.010308e-02</td>\n",
" <td>2.235804e-02</td>\n",
" <td>-5.142873e-02</td>\n",
" <td>-9.291738e-02</td>\n",
" <td>-3.275735e-02</td>\n",
" <td>1.400326e-01</td>\n",
" <td>-1.356806e-02</td>\n",
" <td>5.060132e-02</td>\n",
" <td>4.807155e-02</td>\n",
" <td>6.641332e-02</td>\n",
" <td>-6.567575e-02</td>\n",
" <td>-3.636312e-03</td>\n",
" <td>3.734823e-03</td>\n",
" <td>-6.248109e-02</td>\n",
" <td>-2.945017e-02</td>\n",
" <td>6.781943e-03</td>\n",
" <td>-1.119293e-02</td>\n",
" <td>4.097606e-02</td>\n",
" <td>1.659350e-02</td>\n",
" <td>-5.213911e-02</td>\n",
" <td>1.342146e-03</td>\n",
" <td>1.124383e-02</td>\n",
" <td>-2.652715e-01</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
" <td>139320.500000</td>\n",
" <td>1.315642e+00</td>\n",
" <td>8.037239e-01</td>\n",
" <td>1.027196e+00</td>\n",
" <td>7.433413e-01</td>\n",
" <td>6.119264e-01</td>\n",
" <td>3.985649e-01</td>\n",
" <td>5.704361e-01</td>\n",
" <td>3.273459e-01</td>\n",
" <td>5.971390e-01</td>\n",
" <td>4.539234e-01</td>\n",
" <td>7.395934e-01</td>\n",
" <td>6.182380e-01</td>\n",
" <td>6.625050e-01</td>\n",
" <td>4.931498e-01</td>\n",
" <td>6.488208e-01</td>\n",
" <td>5.232963e-01</td>\n",
" <td>3.996750e-01</td>\n",
" <td>5.008067e-01</td>\n",
" <td>4.589494e-01</td>\n",
" <td>1.330408e-01</td>\n",
" <td>1.863772e-01</td>\n",
" <td>5.285536e-01</td>\n",
" <td>1.476421e-01</td>\n",
" <td>4.395266e-01</td>\n",
" <td>3.507156e-01</td>\n",
" <td>2.409522e-01</td>\n",
" <td>9.104512e-02</td>\n",
" <td>7.827995e-02</td>\n",
" <td>-4.471707e-02</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
" <td>172792.000000</td>\n",
" <td>2.454930e+00</td>\n",
" <td>2.205773e+01</td>\n",
" <td>9.382558e+00</td>\n",
" <td>1.687534e+01</td>\n",
" <td>3.480167e+01</td>\n",
" <td>7.330163e+01</td>\n",
" <td>1.205895e+02</td>\n",
" <td>2.000721e+01</td>\n",
" <td>1.559499e+01</td>\n",
" <td>2.374514e+01</td>\n",
" <td>1.201891e+01</td>\n",
" <td>7.848392e+00</td>\n",
" <td>7.126883e+00</td>\n",
" <td>1.052677e+01</td>\n",
" <td>8.877742e+00</td>\n",
" <td>1.731511e+01</td>\n",
" <td>9.253526e+00</td>\n",
" <td>5.041069e+00</td>\n",
" <td>5.591971e+00</td>\n",
" <td>3.942090e+01</td>\n",
" <td>2.720284e+01</td>\n",
" <td>1.050309e+01</td>\n",
" <td>2.252841e+01</td>\n",
" <td>4.584549e+00</td>\n",
" <td>7.519589e+00</td>\n",
" <td>3.517346e+00</td>\n",
" <td>3.161220e+01</td>\n",
" <td>3.384781e+01</td>\n",
" <td>1.023622e+02</td>\n",
" <td>1.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Time V1 V2 V3 V4 \\\n",
"count 284807.000000 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 \n",
"mean 94813.859575 1.168375e-15 3.416908e-16 -1.379537e-15 2.074095e-15 \n",
"std 47488.145955 1.958696e+00 1.651309e+00 1.516255e+00 1.415869e+00 \n",
"min 0.000000 -5.640751e+01 -7.271573e+01 -4.832559e+01 -5.683171e+00 \n",
"25% 54201.500000 -9.203734e-01 -5.985499e-01 -8.903648e-01 -8.486401e-01 \n",
"50% 84692.000000 1.810880e-02 6.548556e-02 1.798463e-01 -1.984653e-02 \n",
"75% 139320.500000 1.315642e+00 8.037239e-01 1.027196e+00 7.433413e-01 \n",
"max 172792.000000 2.454930e+00 2.205773e+01 9.382558e+00 1.687534e+01 \n",
"\n",
" V5 V6 V7 V8 V9 \\\n",
"count 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 \n",
"mean 9.604066e-16 1.487313e-15 -5.556467e-16 1.213481e-16 -2.406331e-15 \n",
"std 1.380247e+00 1.332271e+00 1.237094e+00 1.194353e+00 1.098632e+00 \n",
"min -1.137433e+02 -2.616051e+01 -4.355724e+01 -7.321672e+01 -1.343407e+01 \n",
"25% -6.915971e-01 -7.682956e-01 -5.540759e-01 -2.086297e-01 -6.430976e-01 \n",
"50% -5.433583e-02 -2.741871e-01 4.010308e-02 2.235804e-02 -5.142873e-02 \n",
"75% 6.119264e-01 3.985649e-01 5.704361e-01 3.273459e-01 5.971390e-01 \n",
"max 3.480167e+01 7.330163e+01 1.205895e+02 2.000721e+01 1.559499e+01 \n",
"\n",
" V10 V11 V12 V13 V14 \\\n",
"count 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 \n",
"mean 2.239053e-15 1.673327e-15 -1.247012e-15 8.190001e-16 1.207294e-15 \n",
"std 1.088850e+00 1.020713e+00 9.992014e-01 9.952742e-01 9.585956e-01 \n",
"min -2.458826e+01 -4.797473e+00 -1.868371e+01 -5.791881e+00 -1.921433e+01 \n",
"25% -5.354257e-01 -7.624942e-01 -4.055715e-01 -6.485393e-01 -4.255740e-01 \n",
"50% -9.291738e-02 -3.275735e-02 1.400326e-01 -1.356806e-02 5.060132e-02 \n",
"75% 4.539234e-01 7.395934e-01 6.182380e-01 6.625050e-01 4.931498e-01 \n",
"max 2.374514e+01 1.201891e+01 7.848392e+00 7.126883e+00 1.052677e+01 \n",
"\n",
" V15 V16 V17 V18 V19 \\\n",
"count 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 \n",
"mean 4.887456e-15 1.437716e-15 -3.772171e-16 9.564149e-16 1.039917e-15 \n",
"std 9.153160e-01 8.762529e-01 8.493371e-01 8.381762e-01 8.140405e-01 \n",
"min -4.498945e+00 -1.412985e+01 -2.516280e+01 -9.498746e+00 -7.213527e+00 \n",
"25% -5.828843e-01 -4.680368e-01 -4.837483e-01 -4.988498e-01 -4.562989e-01 \n",
"50% 4.807155e-02 6.641332e-02 -6.567575e-02 -3.636312e-03 3.734823e-03 \n",
"75% 6.488208e-01 5.232963e-01 3.996750e-01 5.008067e-01 4.589494e-01 \n",
"max 8.877742e+00 1.731511e+01 9.253526e+00 5.041069e+00 5.591971e+00 \n",
"\n",
" V20 V21 V22 V23 V24 \\\n",
"count 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 \n",
"mean 6.406204e-16 1.654067e-16 -3.568593e-16 2.578648e-16 4.473266e-15 \n",
"std 7.709250e-01 7.345240e-01 7.257016e-01 6.244603e-01 6.056471e-01 \n",
"min -5.449772e+01 -3.483038e+01 -1.093314e+01 -4.480774e+01 -2.836627e+00 \n",
"25% -2.117214e-01 -2.283949e-01 -5.423504e-01 -1.618463e-01 -3.545861e-01 \n",
"50% -6.248109e-02 -2.945017e-02 6.781943e-03 -1.119293e-02 4.097606e-02 \n",
"75% 1.330408e-01 1.863772e-01 5.285536e-01 1.476421e-01 4.395266e-01 \n",
"max 3.942090e+01 2.720284e+01 1.050309e+01 2.252841e+01 4.584549e+00 \n",
"\n",
" V25 V26 V27 V28 Amount \\\n",
"count 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 2.848070e+05 \n",
"mean 5.340915e-16 1.683437e-15 -3.660091e-16 -1.227390e-16 2.913952e-17 \n",
"std 5.212781e-01 4.822270e-01 4.036325e-01 3.300833e-01 1.000002e+00 \n",
"min -1.029540e+01 -2.604551e+00 -2.256568e+01 -1.543008e+01 -3.532294e-01 \n",
"25% -3.171451e-01 -3.269839e-01 -7.083953e-02 -5.295979e-02 -3.308401e-01 \n",
"50% 1.659350e-02 -5.213911e-02 1.342146e-03 1.124383e-02 -2.652715e-01 \n",
"75% 3.507156e-01 2.409522e-01 9.104512e-02 7.827995e-02 -4.471707e-02 \n",
"max 7.519589e+00 3.517346e+00 3.161220e+01 3.384781e+01 1.023622e+02 \n",
"\n",
" Class \n",
"count 284807.000000 \n",
"mean 0.001727 \n",
"std 0.041527 \n",
"min 0.000000 \n",
"25% 0.000000 \n",
"50% 0.000000 \n",
"75% 0.000000 \n",
"max 1.000000 "
]
},
2024-03-16 14:45:16 +01:00
"execution_count": 94,
2024-03-16 14:35:44 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df.describe()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"### Distribution of legitimate and fraudulent transactions\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "code",
2024-03-16 14:45:16 +01:00
"execution_count": 95,
2024-03-16 14:35:44 +01:00
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"Class\n",
"0 284315\n",
"1 492\n",
"Name: count, dtype: int64"
]
},
2024-03-16 14:45:16 +01:00
"execution_count": 95,
2024-03-16 14:35:44 +01:00
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
2024-04-01 19:14:34 +02:00
"df[\"Class\"].value_counts()"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Undersampling the data\n",
2024-04-01 19:14:34 +02:00
"\n",
"We will employ undersampling as one class significantly dominates the other.\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "code",
2024-03-16 14:45:16 +01:00
"execution_count": 96,
2024-03-16 14:35:44 +01:00
"metadata": {},
"outputs": [],
"source": [
"# Determine the number of instances in the minority class\n",
"fraud_count = len(df[df.Class == 1])\n",
"fraud_indices = np.array(df[df.Class == 1].index)\n",
"\n",
"# Select indices corresponding to majority class instances\n",
"normal_indices = df[df.Class == 0].index\n",
"\n",
"# Randomly sample the same number of instances from the majority class\n",
"random_normal_indices = np.random.choice(normal_indices, fraud_count, replace=False)\n",
"random_normal_indices = np.array(random_normal_indices)\n",
"\n",
"# Combine indices of both classes\n",
"undersample_indice = np.concatenate([fraud_indices, random_normal_indices])\n",
"\n",
"# Undersample dataset\n",
"undersample_data = df.iloc[undersample_indice, :]\n",
"\n",
2024-04-01 19:14:34 +02:00
"X_undersample = undersample_data.iloc[:, undersample_data.columns != \"Class\"]\n",
"y_undersample = undersample_data.iloc[:, undersample_data.columns == \"Class\"]"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"### Size of undersampled dataset\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "code",
2024-03-16 14:45:16 +01:00
"execution_count": 97,
2024-03-16 14:35:44 +01:00
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"<class 'pandas.core.frame.DataFrame'>\n",
2024-03-16 14:45:16 +01:00
"Index: 984 entries, 541 to 141412\n",
2024-03-16 14:35:44 +01:00
"Data columns (total 31 columns):\n",
" # Column Non-Null Count Dtype \n",
"--- ------ -------------- ----- \n",
" 0 Time 984 non-null float64\n",
" 1 V1 984 non-null float64\n",
" 2 V2 984 non-null float64\n",
" 3 V3 984 non-null float64\n",
" 4 V4 984 non-null float64\n",
" 5 V5 984 non-null float64\n",
" 6 V6 984 non-null float64\n",
" 7 V7 984 non-null float64\n",
" 8 V8 984 non-null float64\n",
" 9 V9 984 non-null float64\n",
" 10 V10 984 non-null float64\n",
" 11 V11 984 non-null float64\n",
" 12 V12 984 non-null float64\n",
" 13 V13 984 non-null float64\n",
" 14 V14 984 non-null float64\n",
" 15 V15 984 non-null float64\n",
" 16 V16 984 non-null float64\n",
" 17 V17 984 non-null float64\n",
" 18 V18 984 non-null float64\n",
" 19 V19 984 non-null float64\n",
" 20 V20 984 non-null float64\n",
" 21 V21 984 non-null float64\n",
" 22 V22 984 non-null float64\n",
" 23 V23 984 non-null float64\n",
" 24 V24 984 non-null float64\n",
" 25 V25 984 non-null float64\n",
" 26 V26 984 non-null float64\n",
" 27 V27 984 non-null float64\n",
" 28 V28 984 non-null float64\n",
" 29 Amount 984 non-null float64\n",
" 30 Class 984 non-null int64 \n",
"dtypes: float64(30), int64(1)\n",
"memory usage: 246.0 KB\n"
]
}
],
"source": [
"undersample_data.info()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
2024-04-01 19:14:34 +02:00
"### Summary statistics of the undersampled dataset\n"
2024-03-16 14:35:44 +01:00
]
},
{
"cell_type": "code",
2024-03-16 14:45:16 +01:00
"execution_count": 98,
2024-03-16 14:35:44 +01:00
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>Time</th>\n",
" <th>V1</th>\n",
" <th>V2</th>\n",
" <th>V3</th>\n",
" <th>V4</th>\n",
" <th>V5</th>\n",
" <th>V6</th>\n",
" <th>V7</th>\n",
" <th>V8</th>\n",
" <th>V9</th>\n",
" <th>V10</th>\n",
" <th>V11</th>\n",
" <th>V12</th>\n",
" <th>V13</th>\n",
" <th>V14</th>\n",
" <th>V15</th>\n",
" <th>V16</th>\n",
" <th>V17</th>\n",
" <th>V18</th>\n",
" <th>V19</th>\n",
" <th>V20</th>\n",
" <th>V21</th>\n",
" <th>V22</th>\n",
" <th>V23</th>\n",
" <th>V24</th>\n",
" <th>V25</th>\n",
" <th>V26</th>\n",
" <th>V27</th>\n",
" <th>V28</th>\n",
" <th>Amount</th>\n",
" <th>Class</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>count</th>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" <td>984.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>mean</th>\n",
2024-03-16 14:45:16 +01:00
" <td>88501.498984</td>\n",
" <td>-2.445079</td>\n",
" <td>1.781022</td>\n",
" <td>-3.509406</td>\n",
" <td>2.214004</td>\n",
" <td>-1.477993</td>\n",
" <td>-0.713150</td>\n",
" <td>-2.787427</td>\n",
" <td>0.279073</td>\n",
" <td>-1.253108</td>\n",
" <td>-2.841500</td>\n",
" <td>1.930697</td>\n",
" <td>-3.124120</td>\n",
" <td>-0.026229</td>\n",
" <td>-3.502384</td>\n",
" <td>-0.039494</td>\n",
" <td>-2.097294</td>\n",
" <td>-3.304208</td>\n",
" <td>-1.128950</td>\n",
" <td>0.343668</td>\n",
" <td>0.175905</td>\n",
" <td>0.331911</td>\n",
" <td>0.049631</td>\n",
" <td>-0.031264</td>\n",
" <td>-0.037389</td>\n",
" <td>0.022812</td>\n",
" <td>0.027632</td>\n",
" <td>0.086286</td>\n",
" <td>0.046738</td>\n",
" <td>0.039676</td>\n",
2024-03-16 14:35:44 +01:00
" <td>0.500000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>std</th>\n",
2024-03-16 14:45:16 +01:00
" <td>48996.269445</td>\n",
" <td>5.512352</td>\n",
" <td>3.713232</td>\n",
" <td>6.223001</td>\n",
" <td>3.231076</td>\n",
" <td>4.274632</td>\n",
" <td>1.789350</td>\n",
" <td>5.856197</td>\n",
" <td>4.857643</td>\n",
" <td>2.371055</td>\n",
" <td>4.563067</td>\n",
" <td>2.764745</td>\n",
" <td>4.595103</td>\n",
" <td>1.054377</td>\n",
" <td>4.653202</td>\n",
" <td>1.002911</td>\n",
" <td>3.465619</td>\n",
" <td>5.990033</td>\n",
" <td>2.412032</td>\n",
" <td>1.290973</td>\n",
" <td>1.126258</td>\n",
" <td>2.787884</td>\n",
" <td>1.167097</td>\n",
" <td>1.177562</td>\n",
" <td>0.551518</td>\n",
" <td>0.677541</td>\n",
" <td>0.476480</td>\n",
" <td>1.023332</td>\n",
" <td>0.479168</td>\n",
" <td>0.851800</td>\n",
2024-03-16 14:35:44 +01:00
" <td>0.500254</td>\n",
" </tr>\n",
" <tr>\n",
" <th>min</th>\n",
2024-03-16 14:45:16 +01:00
" <td>60.000000</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-30.552380</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-15.799625</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-31.103685</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-3.863126</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-22.105532</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-10.261990</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-43.557242</td>\n",
" <td>-41.044261</td>\n",
" <td>-13.434066</td>\n",
" <td>-24.588262</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-2.613374</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-18.683715</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-3.223045</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-19.214325</td>\n",
" <td>-4.498945</td>\n",
" <td>-14.129855</td>\n",
" <td>-25.162799</td>\n",
" <td>-9.498746</td>\n",
" <td>-3.681904</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-7.242879</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-22.797604</td>\n",
" <td>-8.887017</td>\n",
" <td>-19.254328</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-2.028024</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-4.781606</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-1.214960</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-7.263482</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-2.735623</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-0.353229</td>\n",
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>25%</th>\n",
2024-03-16 14:45:16 +01:00
" <td>45531.000000</td>\n",
" <td>-2.867222</td>\n",
" <td>-0.155438</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-5.084967</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-0.172018</td>\n",
" <td>-1.700260</td>\n",
" <td>-1.619179</td>\n",
" <td>-3.066415</td>\n",
" <td>-0.204192</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-2.279453</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-4.572043</td>\n",
" <td>-0.187147</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-5.495221</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-0.784589</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-6.721799</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-0.627097</td>\n",
2024-03-16 14:35:44 +01:00
" <td>-3.543426</td>\n",
" <td>-5.302111</td>\n",
" <td>-1.809496</td>\n",
2024-03-16 14:45:16 +01:00
" <td>-0.412430</td>\n",
" <td>-0.187708</td>\n",
" <td>-0.157259</td>\n",
" <td>-0.509376</td>\n",
" <td>-0.240064</td>\n",
" <td>-0.379825</td>\n",
" <td>-0.321251</td>\n",
" <td>-0.281187</td>\n",
" <td>-0.061809</td>\n",
" <td>-0.050194</td>\n",
" <td>-0.347302</td>\n",
2024-03-16 14:35:44 +01:00
" <td>0.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>50%</th>\n",
2024-03-16 14:45:16 +01:00
" <td>83076.500000</td>\n",
" <td>-0.823244</td>\n",
" <td>0.957399</td>\n",
" <td>-1.381998</td>\n",
" <td>1.287041</td>\n",
" <td>-0.394605</td>\n",
" <td>-0.689473</td>\n",
" <td>-0.668321</td>\n",
" <td>0.147397</td>\n",
" <td>-0.694910</td>\n",
" <td>-0.948441</td>\n",
" <td>1.170286</td>\n",
" <td>-0.858094</td>\n",
" <td>-0.000686</td>\n",
" <td>-1.110717</td>\n",
" <td>-0.006070</td>\n",
" <td>-0.677801</td>\n",
" <td>-0.513640</td>\n",
" <td>-0.383038</td>\n",
" <td>0.221049</td>\n",
" <td>0.040630</td>\n",
" <td>0.155404</td>\n",
" <td>0.080270</td>\n",
" <td>-0.030318</td>\n",
" <td>0.009379</td>\n",
" <td>0.049923</td>\n",
" <td>-0.007475</td>\n",
" <td>0.063100</td>\n",
" <td>0.039464</td>\n",
" <td>-0.280984</td>\n",
2024-03-16 14:35:44 +01:00
" <td>0.500000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>75%</th>\n",
2024-03-16 14:45:16 +01:00
" <td>135051.500000</td>\n",
" <td>0.919444</td>\n",
" <td>2.791569</td>\n",
" <td>0.356911</td>\n",
" <td>4.175332</td>\n",
" <td>0.616305</td>\n",
" <td>0.069620</td>\n",
" <td>0.265089</td>\n",
" <td>0.877002</td>\n",
" <td>0.134399</td>\n",
" <td>-0.016047</td>\n",
" <td>3.586502</td>\n",
" <td>0.190356</td>\n",
" <td>0.683977</td>\n",
" <td>0.110541</td>\n",
" <td>0.672903</td>\n",
" <td>0.250353</td>\n",
" <td>0.313841</td>\n",
" <td>0.334927</td>\n",
" <td>0.978754</td>\n",
" <td>0.445616</td>\n",
" <td>0.642724</td>\n",
" <td>0.624948</td>\n",
" <td>0.180735</td>\n",
" <td>0.365624</td>\n",
" <td>0.395001</td>\n",
" <td>0.324059</td>\n",
" <td>0.457194</td>\n",
" <td>0.226492</td>\n",
" <td>0.046539</td>\n",
2024-03-16 14:35:44 +01:00
" <td>1.000000</td>\n",
" </tr>\n",
" <tr>\n",
" <th>max</th>\n",
2024-03-16 14:45:16 +01:00
" <td>172733.000000</td>\n",
" <td>2.335833</td>\n",
2024-03-16 14:35:44 +01:00
" <td>22.057729</td>\n",
2024-03-16 14:45:16 +01:00
" <td>3.476268</td>\n",
2024-03-16 14:35:44 +01:00
" <td>12.114672</td>\n",
2024-03-16 14:45:16 +01:00
" <td>14.103918</td>\n",
" <td>6.474115</td>\n",
" <td>5.802537</td>\n",
2024-03-16 14:35:44 +01:00
" <td>20.007208</td>\n",
2024-03-16 14:45:16 +01:00
" <td>6.816732</td>\n",
" <td>11.732926</td>\n",
2024-03-16 14:35:44 +01:00
" <td>12.018913</td>\n",
2024-03-16 14:45:16 +01:00
" <td>2.534876</td>\n",
" <td>3.091328</td>\n",
2024-03-16 14:35:44 +01:00
" <td>3.442422</td>\n",
" <td>2.471358</td>\n",
" <td>3.139656</td>\n",
" <td>6.739384</td>\n",
" <td>3.790316</td>\n",
" <td>5.228342</td>\n",
2024-03-16 14:45:16 +01:00
" <td>11.059004</td>\n",
2024-03-16 14:35:44 +01:00
" <td>27.202839</td>\n",
" <td>8.361985</td>\n",
2024-03-16 14:45:16 +01:00
" <td>5.466230</td>\n",
" <td>1.208141</td>\n",
" <td>2.208209</td>\n",
2024-03-16 14:35:44 +01:00
" <td>2.745261</td>\n",
" <td>3.052358</td>\n",
2024-03-16 14:45:16 +01:00
" <td>4.975792</td>\n",
" <td>8.146182</td>\n",
2024-03-16 14:35:44 +01:00
" <td>1.000000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
" Time V1 V2 V3 V4 \\\n",
"count 984.000000 984.000000 984.000000 984.000000 984.000000 \n",
2024-03-16 14:45:16 +01:00
"mean 88501.498984 -2.445079 1.781022 -3.509406 2.214004 \n",
"std 48996.269445 5.512352 3.713232 6.223001 3.231076 \n",
"min 60.000000 -30.552380 -15.799625 -31.103685 -3.863126 \n",
"25% 45531.000000 -2.867222 -0.155438 -5.084967 -0.172018 \n",
"50% 83076.500000 -0.823244 0.957399 -1.381998 1.287041 \n",
"75% 135051.500000 0.919444 2.791569 0.356911 4.175332 \n",
"max 172733.000000 2.335833 22.057729 3.476268 12.114672 \n",
2024-03-16 14:35:44 +01:00
"\n",
" V5 V6 V7 V8 V9 V10 \\\n",
"count 984.000000 984.000000 984.000000 984.000000 984.000000 984.000000 \n",
2024-03-16 14:45:16 +01:00 </