Tensorflow_COVID-19_Classification_by_Chest X-Ray_Part3.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Visualize these two contribution ratios of COVID19 and Normal."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "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": [
    "data = pd.DataFrame({\"Class\": labels, \"Label\": \"Positive\", \"Value\": freq_pos})\n",
    "data = data.append([{\"Class\": labels[l], \"Label\": \"Negative\", \"Value\": v} for l,v in enumerate(freq_neg)], ignore_index=True)\n",
    "plt.xticks(rotation=90)\n",
    "f = sns.barplot(x=\"Class\", y=\"Value\", hue=\"Label\" ,data=data)"
   ]
  }
 ],
 "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": "3.7.4"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}