{
 "nbformat": 4,
 "nbformat_minor": 5,
 "metadata": {
  "kernelspec": {"display_name": "Python 3", "language": "python", "name": "python3"},
  "language_info": {"name": "python", "version": "3.10.0"}
 },
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": ["# ANN Assignment\nStudent: Sample Student\nDate: 2025-01-15"]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "# Load dataset\n",
    "np.random.seed(42)\n",
    "data = {\n",
    "    'age': np.random.randint(20, 60, 100),\n",
    "    'salary': np.random.normal(50000, 15000, 100),\n",
    "    'department': np.random.choice(['HR', 'Eng', 'Sales', None], 100),\n",
    "    'years_exp': np.random.randint(0, 20, 100)\n",
    "}\n",
    "df = pd.DataFrame(data)\n",
    "print(df.shape)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Data cleaning — using fillna(0) incorrectly\n",
    "df2 = df.fillna(0)\n",
    "print(df2.isnull().sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Single visualisation — missing second plot\n",
    "plt.hist(df2['salary'], bins=20, color='steelblue')\n",
    "plt.show()"
   ]
  }
 ]
}