Tabular-GAN-Project-5Y-INSA/fake_data_analysis.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Fake Data Analysis"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "from scipy.stats import norm\n",
    "from data_treatment import DataAtts\n",
    "import ipywidgets as widgets\n",
    "import matplotlib.pyplot as plt\n",
    "import glob\n",
    "from compare_data import *\n",
    "from IPython.display import display"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "folder_name = 'original_data/diabetes.csv'[14:-4]\n",
    "fake_files_dropdown = widgets.Dropdown(\n",
    "    options=glob.glob(\"fake_data/\" + folder_name + \"/*.csv\"),\n",
    "    description='Fake file:',\n",
    "    disabled=False,\n",
    ")\n",
    "display(fake_files_dropdown)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "file_name='original_data/diabetes.csv'\n",
    "dataAtts = DataAtts(file_name)\n",
    "    \n",
    "    \n",
    "data = pd.read_csv(file_name)\n",
    "fake_data = pd.read_csv(fake_files_dropdown.value)\n",
    "fake_data.loc[getattr(fake_data, dataAtts.class_name) >= 0.5, dataAtts.class_name] = 1\n",
    "fake_data.loc[getattr(fake_data, dataAtts.class_name) < 0.5, dataAtts.class_name] = 0\n",
    "\n",
    "print(dataAtts.message)\n",
    "print(dataAtts.values_names[0], round(data[dataAtts.class_name].value_counts()[0]/len(data) * 100,2), '%  of the dataset')\n",
    "print(dataAtts.values_names[1], round(data[dataAtts.class_name].value_counts()[1]/len(data) * 100,2), '%  of the dataset')\n",
    "\n",
    "print(\"\\nFake Data\")\n",
    "try:\n",
    "    positive=str(round(fake_data[dataAtts.class_name].value_counts()[0]/len(fake_data) * 100,2))\n",
    "except:\n",
    "    positive=\"0\"\n",
    "try:\n",
    "    negative=str(round(fake_data[dataAtts.class_name].value_counts()[1]/len(fake_data) * 100,2))\n",
    "except:\n",
    "    negative=\"0\"\n",
    "    \n",
    "\n",
    "print(\"Outcome = 0: \", positive, '%  of the dataset')\n",
    "print(\"Outcome = 1: \", negative, '%  of the dataset')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "classes = list(data)\n",
    "\n",
    "for name in classes:\n",
    "    if name==\"Unnamed: 32\":\n",
    "        continue\n",
    "        \n",
    "    plt.xlabel('Values')\n",
    "    plt.ylabel('Probability')\n",
    "    plt.title(name + \" distribution\")\n",
    "    real_dist = data[name].values\n",
    "    fake_dist = fake_data[name].values\n",
    "    plt.hist(real_dist, 50, density=True, alpha=0.5)\n",
    "    plt.hist(fake_dist, 50, density=True, alpha=0.5, facecolor='r')\n",
    "    #plt.savefig('fake_data/'+ dataAtts.fname + \"/\"+name+'_distribution.png')\n",
    "    plt.show()\n",
    "    plt.clf()\n"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "tabular_gan",
   "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": "3.10.8 | packaged by conda-forge | (main, Nov 24 2022, 14:07:00) [MSC v.1916 64 bit (AMD64)]"
  },
  "vscode": {
   "interpreter": {
    "hash": "2f1136a7f15cd1225735fd9261403f7c342baa42a12d30e4630e4cfef11f2512"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}