v17.0.1

01 - Clean Images.ipynb

@@ -0,0 +1,82 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "80f3d28e-8319-4249-8fcd-cd00a1ca3cad",
+   "metadata": {},
+   "source": [
+    "## Remove Duplicates"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "9fe06b5a-33d3-45ce-9caa-51c8d98c84d8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from collectmeterdigits.collect import ziffer_data_files, remove_similar_images"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "edc70529-736c-496e-95e4-48b58c30425d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "target_raw_path =  \"./ziffer_sortiert_raw\"   # here all raw images are stored"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "3c680b18-231e-4892-8698-9f0cb83e408b",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Find similar images now in 1519 images ...\n",
+      "...1000\n",
+      "273 duplicates will be removed.\n"
+     ]
+    }
+   ],
+   "source": [
+    "files = ziffer_data_files(target_raw_path)\n",
+    "remove_similar_images(files, \"abc\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "22b0a110-7f4e-4e1f-a6cc-97078cb18adf",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.11.8"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

.ipynb_checkpoints/Image_Preparation-checkpoint.ipynb → 02 - Image_Preparation.ipynb

@@ -41,7 +41,7 @@
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "1554 files have been deleted.\n"
+      "1573 files have been deleted.\n"
      ]
     }
    ],
@@ -59,14 +59,6 @@
    "execution_count": 3,
    "metadata": {},
    "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "C:\\Users\\Muell\\AppData\\Local\\Temp\\ipykernel_17672\\2984607959.py:11: DeprecationWarning: NEAREST is deprecated and will be removed in Pillow 10 (2023-07-01). Use Resampling.NEAREST or Dither.NONE instead.\n",
-      "  test_image = test_image.resize((target_size_x, target_size_y), Image.NEAREST)\n"
-     ]
-    },
     {
      "name": "stdout",
      "output_type": "stream",
@@ -76,8 +68,7 @@
       "750 ...\n",
       "1000 ...\n",
       "1250 ...\n",
-      "1500 ...\n",
-      "1573\n"
+      "1300\n"
      ]
     }
    ],
@@ -97,7 +88,7 @@
     "    base = os.path.splitext(base)[0] + \".jpg\"\n",
     "    save_name = Output_dir + '/' + base\n",
     "#    print(\"in: \" + aktfile + \"  -  out: \" + save_name)\n",
-    "    test_image.save(save_name, \"JPEG\")\n",
+    "    test_image.save(save_name, \"JPEG\", quality=100)\n",
     "print(count)"
    ]
   },
@@ -125,7 +116,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.11.8"
   }
  },
  "nbformat": 4,