{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# How To: Correct Grid Rotation\n",
    "\n",
    "Apply `GridAligner` to straighten plates that were scanned at a slight angle.\n",
    "This improves grid detection accuracy for downstream well-level analysis."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import phenotypic as pht\n",
    "from phenotypic.data import load_yeast_plate\n",
    "from phenotypic.correction import GridAligner\n",
    "from phenotypic.detect import OtsuDetector\n",
    "from phenotypic.enhance import GaussianBlur, CLAHE"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load and Detect"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "plate = load_yeast_plate()\n",
    "pipeline = pht.ImagePipeline(\n",
    "    ops=[GaussianBlur(sigma=2.0), CLAHE(clip_limit=0.01), OtsuDetector()]\n",
    ")\n",
    "plate = pipeline.apply(plate)\n",
    "plate.dash(overlay=True, show_grid=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Apply Grid Alignment\n",
    "\n",
    "`GridAligner` detects the dominant rotation angle from colony positions\n",
    "and rotates the image to straighten the grid."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "aligner = GridAligner()\n",
    "plate = aligner.apply(plate)\n",
    "plate.dash(overlay=True, show_grid=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "The gridlines should now align more closely with the colony rows and\n",
    "columns. Place `GridAligner` after initial detection in your pipeline\n",
    "so it can use detected colony positions to compute the rotation angle."
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "name": "python",
   "version": "3.11.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}