example of masked and unmasked arrays and how they work with nodata values

masked_arrays.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "/Users/mitchellgritts/Documents/projects/vp-airflow/dags\n"
     ]
    }
   ],
   "source": [
    "cd ../.."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "import rasterio\n",
    "from rasterio import transform, CRS\n",
    "from rasterio.plot import show\n",
    "import numpy as np\n",
    "import operator\n",
    "import random\n",
    "from rasterio import CRS\n",
    "\n",
    "def make_raster(filename, profile, data):\n",
    "    default_profile = {\n",
    "        \"count\": 1,\n",
    "        \"compress\": \"lzw\",\n",
    "        \"crs\": CRS.from_epsg(3310),\n",
    "        \"driver\": \"GTiff\",\n",
    "        \"dtype\": data.dtype,\n",
    "        \"height\": data.shape[0],\n",
    "        \"interleave\": \"band\",\n",
    "        \"nodata\": 0.0,\n",
    "        \"tiled\": False,\n",
    "        \"transform\": transform.Affine.translation(0, 5)\n",
    "        * transform.Affine.scale(-5, 5),\n",
    "        \"width\": data.shape[1],\n",
    "    } | profile\n",
    "\n",
    "    with rasterio.open(filename, 'w', **default_profile) as dataset:\n",
    "        dataset.write(data)\n",
    "\n",
    "    return filename"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "zero_nodata_filename = make_raster(\n",
    "    filename=\"/Users/mitchellgritts/Downloads/multiband_raster.tif\",\n",
    "    profile={\n",
    "        \"count\": 3,\n",
    "        \"nodata\": 999,\n",
    "    },\n",
    "    data=np.array(\n",
    "        [\n",
    "            [\n",
    "                [999, 999, 1, 1],\n",
    "                [999, 999, 1, 1],\n",
    "                [999, 999, 1, 1],\n",
    "                [999, 999, 1, 1],\n",
    "            ],\n",
    "            [\n",
    "                [999, 999, 1, 1],\n",
    "                [999, 999, 1, 1],\n",
    "                [999, 999, 1, 1],\n",
    "                [999, 999, 1, 1],\n",
    "            ],\n",
    "            [\n",
    "                [999, 999, 1, 1],\n",
    "                [999, 999, 1, 1],\n",
    "                [999, 999, 1, 1],\n",
    "                [999, 999, 1, 1],\n",
    "            ],\n",
    "        ],\n",
    "        dtype=np.int16,\n",
    "    ),\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [],
   "source": [
    "with rasterio.open(zero_nodata_filename) as src:\n",
    "    array_unmasked = src.read()\n",
    "    array_masked = src.read(masked=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "masked_array(\n",
       "  data=[[[--, --, 1, 1],\n",
       "         [--, --, 1, 1],\n",
       "         [--, --, 1, 1]],\n",
       "\n",
       "        [[--, --, 1, 1],\n",
       "         [--, --, 1, 1],\n",
       "         [--, --, 1, 1]],\n",
       "\n",
       "        [[--, --, 1, 1],\n",
       "         [--, --, 1, 1],\n",
       "         [--, --, 1, 1]]],\n",
       "  mask=[[[ True,  True, False, False],\n",
       "         [ True,  True, False, False],\n",
       "         [ True,  True, False, False]],\n",
       "\n",
       "        [[ True,  True, False, False],\n",
       "         [ True,  True, False, False],\n",
       "         [ True,  True, False, False]],\n",
       "\n",
       "        [[ True,  True, False, False],\n",
       "         [ True,  True, False, False],\n",
       "         [ True,  True, False, False]]],\n",
       "  fill_value=999,\n",
       "  dtype=int16)"
      ]
     },
     "execution_count": 19,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "array_masked"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[[999, 999,   1,   1],\n",
       "        [999, 999,   1,   1],\n",
       "        [999, 999,   1,   1]],\n",
       "\n",
       "       [[999, 999,   1,   1],\n",
       "        [999, 999,   1,   1],\n",
       "        [999, 999,   1,   1]],\n",
       "\n",
       "       [[999, 999,   1,   1],\n",
       "        [999, 999,   1,   1],\n",
       "        [999, 999,   1,   1]]], dtype=int16)"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "array_unmasked"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[2997, 2997,    3,    3],\n",
       "       [2997, 2997,    3,    3],\n",
       "       [2997, 2997,    3,    3]])"
      ]
     },
     "execution_count": 23,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum_unmasked = np.sum(array_unmasked, axis=0)\n",
    "sum_unmasked"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "masked_array(\n",
       "  data=[[--, --, 3, 3],\n",
       "        [--, --, 3, 3],\n",
       "        [--, --, 3, 3]],\n",
       "  mask=[[ True,  True, False, False],\n",
       "        [ True,  True, False, False],\n",
       "        [ True,  True, False, False]],\n",
       "  fill_value=999999)"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "sum_masked = np.sum(array_masked, axis=0)\n",
    "sum_masked"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[3., 3., 3., 3.],\n",
       "       [3., 3., 3., 3.],\n",
       "       [3., 3., 3., 3.]])"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "compare_array = np.ones(sum_unmasked.shape) * 3\n",
    "compare_array"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[False False  True  True]\n",
      " [False False  True  True]\n",
      " [False False  True  True]]\n",
      "False\n"
     ]
    }
   ],
   "source": [
    "print(np.isclose(compare_array, sum_unmasked))\n",
    "print(np.isclose(compare_array, sum_unmasked).all())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[-- -- True True]\n",
      " [-- -- True True]\n",
      " [-- -- True True]]\n",
      "True\n"
     ]
    }
   ],
   "source": [
    "print(np.isclose(compare_array, sum_masked))\n",
    "print(np.isclose(compare_array, sum_masked).all())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "vp-notebooks",
   "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": "3.10.10"
  },
  "orig_nbformat": 4
 },
 "nbformat": 4,
 "nbformat_minor": 2
}