{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Solutions\n",
    "This notebook cannot be run on its own. It just serves as a helpful information container for another notebook. Copy the content of the cells below into GenesToPhenotypes.ipynb. **DO NOT RUN THE CELLS**."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Exercise 1\n",
    "The user loops through the images in the dataframe and thresholds each of the images.\n",
    "Each image is then saved as a TIFF file.\n",
    "We only use the ``df_filtered`` Data frame."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "for index, row in df_filtered.iterrows():\n",
    "    image_id = row['Image']\n",
    "    image = conn.getObject(\"Image\", image_id)\n",
    "    pixels = image.getPrimaryPixels()\n",
    "    image_plane = pixels.getPlane(0, 0, 0)\n",
    "    filtered = scipy.ndimage.median_filter(image_plane, size=3)\n",
    "    threshold = filters.threshold_otsu(filtered)\n",
    "    print('Threshold value is {}'.format(threshold))\n",
    "    predicted = numpy.uint8(filtered > threshold) * 255\n",
    "    name=\"%s/%s.tif\" % (home, image_id)\n",
    "    tifffile.imsave(name, predicted)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.8"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}