Exploring the Lung (Non-Covid or Covid) Dataset with Data Visualizations.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from datasets import LungCovidDataset\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import random"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Import the train, test, and val datasets\n",
    "train_dataset = LungCovidDataset('train')\n",
    "test_dataset = LungCovidDataset('test')\n",
    "val_dataset = LungCovidDataset('val')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "This is the train dataset of the Lung (Non-Covid/Covid) Dataset used in the Small Project for the 50.039 Deep Learning class in Feb-March 2021. \n",
      "It contains a total of 3875 images of size 150 by 150.\n",
      "The images are split into the following classes and they are stored in the following locations:\n",
      " - infected_noncovid (2530 images), in './dataset/train/infected/non-covid'.\n",
      " - infected_covid (1345 images), in './dataset/train/infected/covid'.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "train_dataset.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "This is the test dataset of the Lung (Non-Covid/Covid) Dataset used in the Small Project for the 50.039 Deep Learning class in Feb-March 2021. \n",
      "It contains a total of 380 images of size 150 by 150.\n",
      "The images are split into the following classes and they are stored in the following locations:\n",
      " - infected_noncovid (242 images), in './dataset/test/infected/non-covid'.\n",
      " - infected_covid (138 images), in './dataset/test/infected/covid'.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "test_dataset.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "This is the val dataset of the Lung (Non-Covid/Covid) Dataset used in the Small Project for the 50.039 Deep Learning class in Feb-March 2021. \n",
      "It contains a total of 16 images of size 150 by 150.\n",
      "The images are split into the following classes and they are stored in the following locations:\n",
      " - infected_noncovid (8 images), in './dataset/val/infected/non-covid'.\n",
      " - infected_covid (8 images), in './dataset/val/infected/covid'.\n",
      "\n"
     ]
    }
   ],
   "source": [
    "val_dataset.describe()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Prepare data\n",
    "def prepare_data(train_dataset, test_dataset, val_dataset):\n",
    "    a1 = train_dataset.dataset_numbers['infected_noncovid']\n",
    "    a2 = train_dataset.dataset_numbers['infected_covid']\n",
    "    \n",
    "    b1 = test_dataset.dataset_numbers['infected_noncovid']\n",
    "    b2 = test_dataset.dataset_numbers['infected_covid']\n",
    "    \n",
    "    c1 = val_dataset.dataset_numbers['infected_noncovid']\n",
    "    c2 = val_dataset.dataset_numbers['infected_covid']\n",
    "    \n",
    "    types = {'Infected without Covid': np.asarray([a1, b1, c1]),\n",
    "             'Infected with Covid': np.asarray([a2, b2, c2])}\n",
    "    datasets = {'Train': np.asarray([a1, a2]),\n",
    "                'Test': np.asarray([b1, b2]),\n",
    "                'Validation': np.asarray([c1, c2])}\n",
    "    return types, datasets\n",
    "\n",
    "types, datasets = prepare_data(train_dataset, test_dataset, val_dataset)\n",
    "colors = ['steelblue', 'orange']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 3 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot the distribution of images across classes\n",
    "fig, axes = plt.subplots(nrows=1, ncols=3, figsize=(6, 4))\n",
    "\n",
    "X = np.arange(2)\n",
    "for i, (label, Y) in enumerate(datasets.items()):\n",
    "    axes[i].bar(X, Y, color=colors)\n",
    "    axes[i].set_xlabel(label)\n",
    "    axes[i].tick_params(which='both', bottom=False, labelbottom=False)\n",
    "\n",
    "fig.suptitle('Distribution Of Images Across Classes', x=0.55, y=1.02)\n",
    "fig.text(s='Number Of Images', x=0, y=0.5, ha='center', va='center', rotation='vertical')\n",
    "fig.tight_layout(w_pad=1)\n",
    "\n",
    "handles = [plt.Rectangle((0, 0), 1, 1, color=color) for color in colors]\n",
    "plt.legend(handles, types, bbox_to_anchor=(1.05, 1), loc='upper left')\n",
    "\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot the distribution of images across datasets\n",
    "X = list(datasets.keys())\n",
    "\n",
    "bottom = np.zeros(3)\n",
    "for i, (label, Y) in enumerate(types.items()):\n",
    "    plt.bar(X, Y, label=label, color=colors[i], bottom=bottom)\n",
    "    bottom += Y\n",
    "\n",
    "plt.title('Distribution Of Images Across Datasets')\n",
    "plt.ylabel('Number Of Images')\n",
    "plt.legend()\n",
    "\n",
    "plt.show()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.6.10"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}