{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Tutorial about example datasets"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "import sys\n",
    "from pathlib import Path\n",
    "import shutil\n",
    "import logging\n",
    "\n",
    "import httpx\n",
    "\n",
    "import locan as lc"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "lc.show_versions(system=False, dependencies=False, verbose=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "logging.basicConfig(stream=sys.stdout, level=logging.INFO, format='%(asctime)s - %(name)s - %(levelname)s - %(message)s')\n",
    "logger = logging.getLogger()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load SMLM data from ShareLoc.XYZ"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "SMLM data can e.g. be found on [ShareLoc.XYZ](https://shareloc.xyz), an open platform for sharing single-molecule localization microscopy data.\n",
    "\n",
    "Copy a specific download link for downloading a smlm-file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://zenodo.org/records/7182242/files/UniWue_Tubulin_AF647_3/data.smlm\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "response = httpx.get(url)\n",
    "print(\"Response is ok: \", response.status_code == httpx.codes.ok)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "file_path = Path.home() / Path(url).name\n",
    "\n",
    "with open(file_path, 'wb') as file:\n",
    "    for chunk in response.iter_bytes(chunk_size=128):\n",
    "        file.write(chunk)\n",
    "        \n",
    "file_path"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load data and visualize"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "locdata = lc.load_SMLM_file(file_path)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Print information about the data: "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "print('Data head:')\n",
    "print(locdata.data.head(), '\\n')\n",
    "print('Summary:')\n",
    "locdata.print_summary()\n",
    "print('Properties:')\n",
    "print(locdata.properties)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "lc.render_2d(locdata, bin_size=100, rescale=lc.Trafo.EQUALIZE_0P3);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "lc.render_2d(locdata, bin_size=10, rescale=lc.Trafo.EQUALIZE_0P3,\n",
    "             bin_range=((15_000, 20_200), (10_000, 15_000)));"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load SMLM data from LocanDatasets"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Selected example datasets are provided in a separate directory (repository) called `LocanDatasets`.\n",
    "\n",
    "These datasets can be loaded by ready-to-go utility functions."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Set up a datasets directory"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "lc.DATASETS_DIR = Path.home() / 'LocanDatasets'\n",
    "lc.DATASETS_DIR.mkdir(exist_ok=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Load dSTORM data of nuclear pore complexes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is a rather large 2D dataset with > 2 mio localizations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://raw.githubusercontent.com/super-resolution/LocanDatasets/main/smlm_data/npc_gp210.asdf\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "response = httpx.get(url)\n",
    "print(\"Response is ok: \", response.status_code == httpx.codes.ok)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "response.status_code"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "file_path = lc.DATASETS_DIR / 'npc_gp210.asdf'\n",
    "\n",
    "with open(file_path, 'wb') as file:\n",
    "    for chunk in response.iter_bytes(chunk_size=128):\n",
    "        file.write(chunk)\n",
    "        \n",
    "file_path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "dat = lc.load_npc()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Print information about the data: "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "print('Data head:')\n",
    "print(dat.data.head(), '\\n')\n",
    "print('Summary:')\n",
    "dat.print_summary()\n",
    "print('Properties:')\n",
    "print(dat.properties)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "lc.render_2d(dat, bin_size=100, rescale=lc.Trafo.EQUALIZE_0P3);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "lc.render_2d(dat, bin_size=10, rescale=lc.Trafo.EQUALIZE_0P3,\n",
    "             bin_range=((0, 5000), (0, 5000)));"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "tags": []
   },
   "source": [
    "### Load dSTORM data of microtubules"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "This is a rather large 2D dataset with about 1.5 mio localizations."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "url = \"https://raw.githubusercontent.com/super-resolution/LocanDatasets/main/smlm_data/tubulin_cos7.asdf\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "response = httpx.get(url)\n",
    "print(\"Response is ok: \", response.status_code == httpx.codes.ok)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "file_path = lc.DATASETS_DIR / 'tubulin_cos7.asdf'\n",
    "\n",
    "with open(file_path, 'wb') as file:\n",
    "    for chunk in response.iter_bytes(chunk_size=128):\n",
    "        file.write(chunk)\n",
    "        \n",
    "file_path"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "dat = lc.load_tubulin()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Print information about the data: "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "print('Data head:')\n",
    "print(dat.data.head(), '\\n')\n",
    "print('Summary:')\n",
    "dat.print_summary()\n",
    "print('Properties:')\n",
    "print(dat.properties)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "lc.render_2d(dat, bin_size=100, rescale=lc.Trafo.EQUALIZE_0P3);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "tags": []
   },
   "outputs": [],
   "source": [
    "lc.render_2d(dat, bin_size=10, rescale=lc.Trafo.EQUALIZE_0P3,\n",
    "             bin_range=((0, 4000), (6000, 10_000)));"
   ]
  }
 ],
 "metadata": {
  "execution": {
   "timeout": 360
  },
  "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": "3.12.6"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "state": {},
    "version_major": 2,
    "version_minor": 0
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}