ld2daps/Notebooks/Split First.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import triskele\n",
    "import ld2dap\n",
    "\n",
    "figsize = np.array((16, 9)) * 2"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Split First for JURSE\n",
    "\n",
    "Load raster, $n$ split along dimension $d$, describe and merge in description stack."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "n = 1; d = 0"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "layers_files = [\n",
    "    '../Data/phase1_rasters/DEM+B_C123/UH17_GEM051_TR.tif',\n",
    "    '../Data/phase1_rasters/DEM_C123_3msr/UH17_GEG051_TR.tif',\n",
    "    '../Data/phase1_rasters/DEM_C123_TLI/UH17_GEG05_TR.tif',\n",
    "    '../Data/phase1_rasters/DSM_C12/UH17c_GEF051_TR.tif',\n",
    "    '../Data/phase1_rasters/Intensity_C1/UH17_GI1F051_TR.tif',\n",
    "    '../Data/phase1_rasters/Intensity_C2/UH17_GI2F051_TR.tif',\n",
    "    '../Data/phase1_rasters/Intensity_C3/UH17_GI3F051_TR.tif'\n",
    "]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "load = ld2dap.LoadTIFF(layers_files)\n",
    "trsh = ld2dap.Treshold(1e4)\n",
    "norm = ld2dap.Normalize(dtype=np.uint8)\n",
    "rout = ld2dap.RawOutput()\n",
    "\n",
    "rout.input = norm\n",
    "norm.input = trsh\n",
    "trsh.input = load\n",
    "\n",
    "rout.run()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Split"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "step = int(rout.data.shape[d] / n)\n",
    "\n",
    "fig, axs = plt.subplots(n, figsize=figsize * n)\n",
    "\n",
    "view = np.moveaxis(rout.data, d, 0)\n",
    "\n",
    "cuts = list()\n",
    "for i in range(n):\n",
    "    cut = np.moveaxis(view[i*step:(i+1)*step+1], 0, d)\n",
    "    cuts.append(cut)\n",
    "    \n",
    "    # Disp\n",
    "    axs[i].imshow(cut[:,:,0], cmap=plt.get_cmap('GnBu'))\n",
    "    axs[i].set_title('Cut {}'.format(i))\n",
    "    \n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Describe"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "dcuts = list()\n",
    "\n",
    "for cut in cuts:\n",
    "    rinp = ld2dap.RawInput(cut, rout.metadata)\n",
    "    aps = ld2dap.SelfDualAttributeProfiles(area=[100,1e3,1e4,1e5], normalize_to_dtype=False)\n",
    "    vout = ld2dap.RawOutput()\n",
    "    \n",
    "    vout.input = aps\n",
    "    aps.input = rinp\n",
    "    \n",
    "    vout.run()\n",
    "    \n",
    "    dcuts.append(vout.data)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Merge"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "descriptors = np.zeros(rout.data.shape[:2] + (dcuts[0].shape[-1],))\n",
    "view = np.moveaxis(descriptors, d, 0)\n",
    "\n",
    "for i, cut in enumerate(dcuts):\n",
    "    view[i*step:(i+1)*step+1] = np.moveaxis(cut, 0, d)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Visual test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "t_inp = ld2dap.RawInput(descriptors, vout.metadata)\n",
    "t_dsp = ld2dap.ShowFig(stack_id=3, symb=False)\n",
    "\n",
    "t_dsp.input = t_inp\n",
    "\n",
    "t_dsp.run()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Split cross val"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "d = 0\n",
    "s = 2\n",
    "n = 3\n",
    "\n",
    "\n",
    "step = int(descriptors.shape[d] / n)\n",
    "size = descriptors.shape[d]\n",
    "cfilter = (np.arange(size) - step * s) % size < step\n",
    "\n",
    "test_filter = np.zeros_like(descriptors[:,:,0], dtype=np.bool)\n",
    "view = np.moveaxis(test_filter, d, 0)\n",
    "view[cfilter] = True\n",
    "\n",
    "plt.imshow(test_filter)\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "descriptors[test_filter].shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "descriptors.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "f = np.zeros_like(test_filter, dtype=np.bool)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_filter |= f\n",
    "test_filter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_filter"
   ]
  }
 ],
 "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}