bryce first commit

compression_benchmark.ipynb

+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "from matplotlib import pyplot as plt\n",
+    "from itertools import product\n",
+    "import os\n",
+    "import sys\n",
+    "from PIL import Image\n",
+    "from scipy.optimize import minimize,linprog\n",
+    "import time\n",
+    "import seaborn as sns\n",
+    "from sklearn.neighbors import KernelDensity\n",
+    "import pandas as pd\n",
+    "from collections import Counter\n",
+    "import time\n",
+    "import numpy.linalg as la"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "Round 1 : Using PIL to compress the tiff file.\n",
+    "Conclusion : The best that I could get using the lzw compressor from PIL was 61.5%. This is worse than the other one at 40, which is likely because it is using multiple channels instead of just one."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def file_extractor(dirname=\"images\"):\n",
+    "    files = os.listdir(dirname)\n",
+    "    scenes = []\n",
+    "    for file in files:\n",
+    "        if file == '.DS_Store':\n",
+    "            continue\n",
+    "        else:\n",
+    "            scenes.append(os.path.join(dirname, file))\n",
+    "    return scenes\n",
+    "\n",
+    "def image_extractor(scenes):\n",
+    "    image_folder = []\n",
+    "    for scene in scenes:\n",
+    "        files = os.listdir(scene)\n",
+    "        for file in files:\n",
+    "            if file[-5:] != \".tiff\" or file[-7:] == \"_6.tiff\":\n",
+    "                continue\n",
+    "            else:\n",
+    "                image_folder.append(os.path.join(scene, file))\n",
+    "    return image_folder #returns a list of file paths to .tiff files in the specified directory given in file_extractor"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "scenes = file_extractor()\n",
+    "images = image_extractor(scenes)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(640, 513)\n"
+     ]
+    }
+   ],
+   "source": [
+    "first_example = images[0]\n",
+    "picture = Image.open(first_example)\n",
+    "print(picture.size)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "picture.save(\"Compressed_Test.tiff\",compression='tiff_lzw')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "compressed_location = \"Compressed_Test.tiff\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 33,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "compressed_image = Image.open(compressed_location)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 34,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "(640, 513)\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(compressed_image.size)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "True\n"
+     ]
+    }
+   ],
+   "source": [
+    "from PIL import features\n",
+    "print(features.check('libtiff'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 36,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "size = os.path.getsize(compressed_location)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "473404\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(size)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "oldsize = os.path.getsize(first_example)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.7203380417135197\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(size/oldsize)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from PIL import TiffTags\n",
+    "TiffTags.LIBTIFF_CORE.add(317)\n",
+    "picture.save('round_2.tiff', compression='tiff_lzw', tiffinfo={317: 2})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "404176\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(os.path.getsize('round_2.tiff'))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "0.6149997641498668\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(404176/oldsize)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "interpreter": {
+   "hash": "916dbcbb3f70747c44a77c7bcd40155683ae19c65e1c03b4aa3499c5328201f1"
+  },
+  "kernelspec": {
+   "display_name": "Python 3.8.10 64-bit",
+   "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": "3.8.10"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}