AMMICO/notebooks/get-text-from-image.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "dcaa3da1",
   "metadata": {},
   "source": [
    "# Notebook for text extraction on image\n",
    "Inga Ulusoy, SSC, July 2022"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "f43f327c",
   "metadata": {},
   "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 misinformation\n",
    "    !pip install git+https://github.com/ssciwr/misinformation.git@set-up-colab -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": null,
   "id": "cf362e60",
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "from IPython.display import Image, display\n",
    "import misinformation\n",
    "\n",
    "# download the models if they are not there yet\n",
    "!python -m spacy download en_core_web_md\n",
    "!python -m textblob.download_corpora"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "6da3a7aa",
   "metadata": {},
   "outputs": [],
   "source": [
    "images = misinformation.find_files(\n",
    "    path=\"drive/MyDrive/misinformation-data/\", limit=1000\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bf811ce0",
   "metadata": {},
   "outputs": [],
   "source": [
    "for i in images[0:3]:\n",
    "    display(Image(filename=i))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "8b32409f",
   "metadata": {},
   "outputs": [],
   "source": [
    "mydict = misinformation.utils.initialize_dict(images[0:10])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7b8b929f",
   "metadata": {},
   "source": [
    "# google cloud vision API\n",
    "First 1000 images per month are free."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "cbf74c0b-52fe-4fb8-b617-f18611e8f986",
   "metadata": {},
   "outputs": [],
   "source": [
    "os.environ[\n",
    "    \"GOOGLE_APPLICATION_CREDENTIALS\"\n",
    "] = \"drive/MyDrive/misinformation-data/misinformation-campaign-981aa55a3b13.json\""
   ]
  },
  {
   "cell_type": "markdown",
   "id": "0891b795-c7fe-454c-a45d-45fadf788142",
   "metadata": {},
   "source": [
    "## Inspect the elements per image"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "7c6ecc88",
   "metadata": {},
   "outputs": [],
   "source": [
    "misinformation.explore_analysis(mydict, identify=\"text-on-image\", analyse_text=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "9c3e72b5-0e57-4019-b45e-3e36a74e7f52",
   "metadata": {},
   "source": [
    "## Or directly analyze for further processing"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "365c78b1-7ff4-4213-86fa-6a0a2d05198f",
   "metadata": {},
   "outputs": [],
   "source": [
    "for key in mydict:\n",
    "    print(key)\n",
    "    mydict[key] = misinformation.text.TextDetector(\n",
    "        mydict[key], analyse_text=True\n",
    "    ).analyse_image()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3c063eda",
   "metadata": {},
   "source": [
    "## Convert to dataframe and write csv"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5709c2cd",
   "metadata": {},
   "outputs": [],
   "source": [
    "outdict = misinformation.utils.append_data_to_dict(mydict)\n",
    "df = misinformation.utils.dump_df(outdict)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "c4f05637",
   "metadata": {},
   "outputs": [],
   "source": [
    "# check the dataframe\n",
    "df.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "bf6c9ddb",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Write the csv\n",
    "df.to_csv(\"drive/MyDrive/misinformation-data/data_out.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "568537df",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "misinf",
   "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": "3.10.6 (main, Oct 24 2022, 16:07:47) [GCC 11.2.0]"
  },
  "vscode": {
   "interpreter": {
    "hash": "da98320027a74839c7141b42ef24e2d47d628ba1f51115c13da5d8b45a372ec2"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}