more tests

FullTester.ipynb

@@ -15,13 +15,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
+      "262\n",
       "262\n",
       "0.3968581030135283\n"
      ]
@@ -37,23 +38,25 @@
     "list_dic = np.load(\"first_dic.npy\", allow_pickle=\"TRUE\")\n",
     "bins = [21,32,48]\n",
     "for i in range(len(images)):\n",
-    "\n",
+    "    \n",
     "    if images[i][-5:] == \".tiff\":\n",
     "        newname = images[i][:-5]\n",
     "    else:\n",
     "        newname = images[i][:-4]\n",
+    "    if images[i][-18:] != \"Compressedlzw.tiff\":\n",
     "        newnamesforlater.append(newname + \"_Compressed.txt\")\n",
     "    # with open(newname + \"_Compressed.txt\", 'wb') as f:\n",
     "    #     f.write(inletters)\n",
     "        file_sizes_new.append((os.path.getsize(newname + \"_Compressed.txt\")))\n",
     "        file_sizes_old.append((os.path.getsize(images[i])))\n",
     "file_sizes_new.append(os.path.getsize(\"first_dic.npy\"))\n",
+    "print(len(newnamesforlater))\n",
     "print(np.sum(file_sizes_new)/np.sum(file_sizes_old))"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [
     {
@@ -115,7 +118,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 17,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -130,19 +133,19 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 31,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "0.34740136372336333\n"
+      "0.6104417990437042\n"
      ]
     }
    ],
    "source": [
-    "print((np.sum(pngsizes) - np.sum(file_sizes_new))/np.sum(pngsizes))"
+    "print((np.sum(pngsizes))/np.sum(file_sizes_old))"
    ]
   },
   {
@@ -154,7 +157,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -164,7 +167,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [
     {
@@ -185,6 +188,82 @@
     "print(np.sum(lwz_sizes)/np.sum(file_sizes_old))"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "524\n",
+      "262\n"
+     ]
+    }
+   ],
+   "source": [
+    "print(len(images))\n",
+    "for i, item in enumerate(images):\n",
+    "    # print(item[-18:])\n",
+    "    if item[-18:] == \"Compressedlzw.tiff\":\n",
+    "        os.remove(item)\n",
+    "scenes = file_extractor(folder_name)\n",
+    "images = image_extractor(scenes)\n",
+    "print(len(images))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def all_image_extractor(scenes):\n",
+    "    \"\"\"\n",
+    "    This function gives the list of all of the valid images\n",
+    "    Parameters:\n",
+    "        scenes (list): a list of all the files in the directory\n",
+    "    Returns:\n",
+    "        images (list): a list of all the images in the directory\n",
+    "    \"\"\"\n",
+    "    image_folder = []\n",
+    "    for scene in scenes:\n",
+    "        files = os.listdir(scene)\n",
+    "        for file in files:\n",
+    "            if 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": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "1178\n",
+      "1178\n"
+     ]
+    }
+   ],
+   "source": [
+    "all_files = all_image_extractor(scenes)\n",
+    "print(len(all_files))\n",
+    "for i, item in enumerate(all_files):\n",
+    "    # print(item[-18:])\n",
+    "    if item[-4:] == \"..png\":\n",
+    "        os.remove(item)\n",
+    "scenes = file_extractor(folder_name)\n",
+    "all_files = all_image_extractor(scenes)\n",
+    "print(len(all_files))"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": null,