{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Color analysis of pictures\n",
    "\n",
    "\n",
    "\n",
    "This notebook shows primary color analysis of color image using K-Means algorithm.\n",
    "The output are N primary colors and their corresponding percentage.\n",
    "\n",
    "The first cell is only run on google colab and installs the [ammico](https://github.com/ssciwr/AMMICO) package.\n",
    "\n",
    "After that, we can import `ammico` and read in the files given a folder path."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-09-04T04:49:36.691236Z",
     "iopub.status.busy": "2023-09-04T04:49:36.690967Z",
     "iopub.status.idle": "2023-09-04T04:49:36.700857Z",
     "shell.execute_reply": "2023-09-04T04:49:36.700057Z"
    }
   },
   "outputs": [],
   "source": [
    "# if running on google colab\n",
    "# flake8-noqa-cell\n",
    "import os\n",
    "\n",
    "if \"google.colab\" in str(get_ipython()):\n",
    "    # update python version\n",
    "    # install setuptools\n",
    "    # %pip install setuptools==61 -qqq\n",
    "    # install ammico\n",
    "    %pip install git+https://github.com/ssciwr/ammico.git -qqq\n",
    "    # mount google drive for data and API key\n",
    "    from google.colab import drive\n",
    "\n",
    "    drive.mount(\"/content/drive\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-09-04T04:49:36.704949Z",
     "iopub.status.busy": "2023-09-04T04:49:36.704460Z",
     "iopub.status.idle": "2023-09-04T04:49:49.569108Z",
     "shell.execute_reply": "2023-09-04T04:49:49.567973Z"
    }
   },
   "outputs": [],
   "source": [
    "import ammico\n",
    "from ammico import utils as mutils\n",
    "from ammico import display as mdisplay\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We select a subset of image files to try the color analysis on, see the `limit` keyword. The `find_files` function finds image files within a given directory:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-09-04T04:49:49.574134Z",
     "iopub.status.busy": "2023-09-04T04:49:49.573217Z",
     "iopub.status.idle": "2023-09-04T04:49:50.945532Z",
     "shell.execute_reply": "2023-09-04T04:49:50.944778Z"
    }
   },
   "outputs": [
    {
     "ename": "FileNotFoundError",
     "evalue": "No files found in /content/drive/MyDrive/misinformation-data/ with pattern '['png', 'jpg', 'jpeg', 'gif', 'webp', 'avif', 'tiff']'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mFileNotFoundError\u001b[0m                         Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[3], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;66;03m# Here you need to provide the path to your google drive folder\u001b[39;00m\n\u001b[1;32m      2\u001b[0m \u001b[38;5;66;03m# or local folder containing the images\u001b[39;00m\n\u001b[0;32m----> 3\u001b[0m images \u001b[38;5;241m=\u001b[39m \u001b[43mmutils\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfind_files\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m      4\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpath\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43m/content/drive/MyDrive/misinformation-data/\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m      5\u001b[0m \u001b[43m    \u001b[49m\u001b[43mlimit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m10\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m      6\u001b[0m \u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m~/work/AMMICO/AMMICO/ammico/utils.py:134\u001b[0m, in \u001b[0;36mfind_files\u001b[0;34m(path, pattern, recursive, limit, random_seed)\u001b[0m\n\u001b[1;32m    131\u001b[0m     results\u001b[38;5;241m.\u001b[39mextend(_match_pattern(path, p, recursive\u001b[38;5;241m=\u001b[39mrecursive))\n\u001b[1;32m    133\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(results) \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m0\u001b[39m:\n\u001b[0;32m--> 134\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mFileNotFoundError\u001b[39;00m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNo files found in \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpath\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m with pattern \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpattern\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m    136\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m random_seed \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    137\u001b[0m     random\u001b[38;5;241m.\u001b[39mseed(random_seed)\n",
      "\u001b[0;31mFileNotFoundError\u001b[0m: No files found in /content/drive/MyDrive/misinformation-data/ with pattern '['png', 'jpg', 'jpeg', 'gif', 'webp', 'avif', 'tiff']'"
     ]
    }
   ],
   "source": [
    "# Here you need to provide the path to your google drive folder\n",
    "# or local folder containing the images\n",
    "images = mutils.find_files(\n",
    "    path=\"/content/drive/MyDrive/misinformation-data/\",\n",
    "    limit=10,\n",
    ")\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We need to initialize the main dictionary that contains all information for the images and is updated through each subsequent analysis:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-09-04T04:49:50.996839Z",
     "iopub.status.busy": "2023-09-04T04:49:50.996138Z",
     "iopub.status.idle": "2023-09-04T04:49:51.037240Z",
     "shell.execute_reply": "2023-09-04T04:49:51.036387Z"
    }
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'images' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[4], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m mydict \u001b[38;5;241m=\u001b[39m mutils\u001b[38;5;241m.\u001b[39minitialize_dict(\u001b[43mimages\u001b[49m)\n",
      "\u001b[0;31mNameError\u001b[0m: name 'images' is not defined"
     ]
    }
   ],
   "source": [
    "mydict = mutils.initialize_dict(images)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "To check the analysis, you can inspect the analyzed elements here. Loading the results takes a moment, so please be patient. If you are sure of what you are doing, you can skip this and directly export a csv file in the step below.\n",
    "Here, we display the color detection results provided by `colorgram` and `colour` libraries. Click on the tabs to see the results in the right sidebar. You may need to increment the `port` number if you are already running several notebook instances on the same server."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-09-04T04:49:51.040964Z",
     "iopub.status.busy": "2023-09-04T04:49:51.040535Z",
     "iopub.status.idle": "2023-09-04T04:49:51.080501Z",
     "shell.execute_reply": "2023-09-04T04:49:51.079560Z"
    }
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'mydict' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[5], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m analysis_explorer \u001b[38;5;241m=\u001b[39m mdisplay\u001b[38;5;241m.\u001b[39mAnalysisExplorer(\u001b[43mmydict\u001b[49m, identify\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcolors\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m      2\u001b[0m analysis_explorer\u001b[38;5;241m.\u001b[39mrun_server(port \u001b[38;5;241m=\u001b[39m \u001b[38;5;241m8057\u001b[39m)\n",
      "\u001b[0;31mNameError\u001b[0m: name 'mydict' is not defined"
     ]
    }
   ],
   "source": [
    "analysis_explorer = mdisplay.AnalysisExplorer(mydict, identify=\"colors\")\n",
    "analysis_explorer.run_server(port = 8057)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Instead of inspecting each of the images, you can also directly carry out the analysis and export the result into a csv. This may take a while depending on how many images you have loaded."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-09-04T04:49:51.085917Z",
     "iopub.status.busy": "2023-09-04T04:49:51.085303Z",
     "iopub.status.idle": "2023-09-04T04:49:51.127676Z",
     "shell.execute_reply": "2023-09-04T04:49:51.126768Z"
    }
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'mydict' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[6], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m key \u001b[38;5;129;01min\u001b[39;00m \u001b[43mmydict\u001b[49m\u001b[38;5;241m.\u001b[39mkeys():\n\u001b[1;32m      2\u001b[0m     mydict[key] \u001b[38;5;241m=\u001b[39m ammico\u001b[38;5;241m.\u001b[39mcolors\u001b[38;5;241m.\u001b[39mColorDetector(mydict[key])\u001b[38;5;241m.\u001b[39manalyse_image()\n",
      "\u001b[0;31mNameError\u001b[0m: name 'mydict' is not defined"
     ]
    }
   ],
   "source": [
    "for key in mydict.keys():\n",
    "    mydict[key] = ammico.colors.ColorDetector(mydict[key]).analyse_image()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "These steps are required to convert the dictionary of dictionarys into a dictionary with lists, that can be converted into a pandas dataframe and exported to a csv file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-09-04T04:49:51.131793Z",
     "iopub.status.busy": "2023-09-04T04:49:51.131520Z",
     "iopub.status.idle": "2023-09-04T04:49:51.172052Z",
     "shell.execute_reply": "2023-09-04T04:49:51.171284Z"
    }
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'mydict' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[7], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m outdict \u001b[38;5;241m=\u001b[39m mutils\u001b[38;5;241m.\u001b[39mappend_data_to_dict(\u001b[43mmydict\u001b[49m)\n\u001b[1;32m      2\u001b[0m df \u001b[38;5;241m=\u001b[39m mutils\u001b[38;5;241m.\u001b[39mdump_df(outdict)\n",
      "\u001b[0;31mNameError\u001b[0m: name 'mydict' is not defined"
     ]
    }
   ],
   "source": [
    "outdict = mutils.append_data_to_dict(mydict)\n",
    "df = mutils.dump_df(outdict)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Check the dataframe:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-09-04T04:49:51.176060Z",
     "iopub.status.busy": "2023-09-04T04:49:51.175538Z",
     "iopub.status.idle": "2023-09-04T04:49:51.213570Z",
     "shell.execute_reply": "2023-09-04T04:49:51.212763Z"
    }
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'df' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[8], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mdf\u001b[49m\u001b[38;5;241m.\u001b[39mhead(\u001b[38;5;241m10\u001b[39m)\n",
      "\u001b[0;31mNameError\u001b[0m: name 'df' is not defined"
     ]
    }
   ],
   "source": [
    "df.head(10)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Write the csv file - here you should provide a file path and file name for the csv file to be written."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "execution": {
     "iopub.execute_input": "2023-09-04T04:49:51.217692Z",
     "iopub.status.busy": "2023-09-04T04:49:51.217149Z",
     "iopub.status.idle": "2023-09-04T04:49:51.256482Z",
     "shell.execute_reply": "2023-09-04T04:49:51.255618Z"
    }
   },
   "outputs": [
    {
     "ename": "NameError",
     "evalue": "name 'df' is not defined",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[9], line 1\u001b[0m\n\u001b[0;32m----> 1\u001b[0m \u001b[43mdf\u001b[49m\u001b[38;5;241m.\u001b[39mto_csv(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m/content/drive/MyDrive/misinformation-data/data_out.csv\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
      "\u001b[0;31mNameError\u001b[0m: name 'df' is not defined"
     ]
    }
   ],
   "source": [
    "df.to_csv(\"/content/drive/MyDrive/misinformation-data/data_out.csv\")"
   ]
  }
 ],
 "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": "3.9.17"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}