{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "2c5baf8e",
   "metadata": {},
   "source": [
    "# 📊 Exploratory Data Analysis: Fraud Detection Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "2f3e6a97",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "df = pd.read_csv(\"fraudTest.csv\")\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2bcadae6",
   "metadata": {},
   "source": [
    "## 🧾 Basic Overview of the Dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "820cb0e9",
   "metadata": {},
   "outputs": [],
   "source": [
    "print(\"Shape:\", df.shape)\n",
    "print(\"\\nData Types:\\n\", df.dtypes)\n",
    "print(\"\\nMissing Values:\\n\", df.isnull().sum())\n",
    "print(\"\\nDuplicate Rows:\", df.duplicated().sum())"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "caa22db9",
   "metadata": {},
   "source": [
    "## ⚖️ Class Balance"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7fb75259",
   "metadata": {},
   "outputs": [],
   "source": [
    "sns.countplot(data=df, x=\"is_fraud\")\n",
    "plt.title(\"Fraud vs Non-Fraud Transactions\")\n",
    "plt.show()\n",
    "\n",
    "fraud_ratio = df[\"is_fraud\"].mean()\n",
    "print(f\"Fraudulent transactions: {fraud_ratio:.4%}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "658e9cd2",
   "metadata": {},
   "source": [
    "## 📊 Statistical Summary"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "202e2612",
   "metadata": {},
   "outputs": [],
   "source": [
    "df.describe(include='all')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "12d24a95",
   "metadata": {},
   "source": [
    "## 🔗 Correlation Matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "3c02acf0",
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(12, 8))\n",
    "sns.heatmap(df.corr(numeric_only=True), annot=True, fmt=\".2f\", cmap=\"coolwarm\")\n",
    "plt.title(\"Feature Correlation Matrix\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fce8183a",
   "metadata": {},
   "source": [
    "## 💵 Transaction Amount Distribution by Fraud"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "ea72b131",
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.figure(figsize=(10, 6))\n",
    "sns.boxplot(data=df, x='is_fraud', y='amt')\n",
    "plt.yscale('log')\n",
    "plt.title(\"Transaction Amount by Fraud Status\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "a7d7d378",
   "metadata": {},
   "source": [
    "## 🕒 Transaction Timing (Hourly)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5f26f36f",
   "metadata": {},
   "outputs": [],
   "source": [
    "df['trans_date_trans_time'] = pd.to_datetime(df['trans_date_trans_time'])\n",
    "df['hour'] = df['trans_date_trans_time'].dt.hour\n",
    "\n",
    "plt.figure(figsize=(12, 6))\n",
    "sns.histplot(data=df, x='hour', hue='is_fraud', multiple='stack', bins=24)\n",
    "plt.title(\"Transaction Hour Distribution\")\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {},
 "nbformat": 4,
 "nbformat_minor": 5
}