ComparingPCAImages.ipynb

{
 "cells": [
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
     "**ANALYZING THE IMAGE OUTPUTS**\n",
     "\n",
     "We look at the differences in the images produced after dimensionality reduction. In order to do that, we visualize the reduced images, using only the retained principal components."
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 367,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "image/png": "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\n",
       "text/plain": [
        "<Figure size 1440x288 with 10 Axes>"
       ]
      },
      "metadata": {},
      "output_type": "display_data"
     }
    ],
    "source": [
     "fig, axes = plt.subplots(2,5,figsize=(20,4),\n",
     " subplot_kw={'xticks':[], 'yticks':[]},\n",
     " gridspec_kw=dict(hspace=0.01, wspace=0.01))\n",
     "for i, ax in enumerate(axes.flat):\n",
     "    ax.imshow(pca.components_[i].reshape(12,8), cmap='gray')"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": 377,
    "metadata": {},
    "outputs": [
     {
      "data": {
       "image/png": "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\n",
       "text/plain": [
        "<Figure size 1440x288 with 10 Axes>"
       ]
      },
      "metadata": {},
      "output_type": "display_data"
     }
    ],
    "source": [
     "fig, axes = plt.subplots(2,5,figsize=(20,4),\n",
     " subplot_kw={'xticks':[], 'yticks':[]},\n",
     " gridspec_kw=dict(hspace=0.01, wspace=0.01))\n",
     "for i, ax in enumerate(axes.flat):\n",
     "    ax.imshow(pca2.components_[i].reshape(12,8), cmap='gray')"
    ]
   }
 ],
"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
}