zonal stats

get_zonal_stats.ipynb

@@ -0,0 +1,1052 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "39bf1de3-cba6-475a-a988-ad48e5af4a04",
+   "metadata": {},
+   "source": [
+    "# Get zonal stats "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "ba047a55-642d-4c27-a367-5f35f4406218",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import ibis\n",
+    "import ibis.selectors as s\n",
+    "from ibis import _\n",
+    "import fiona\n",
+    "import geopandas as gpd\n",
+    "import rioxarray\n",
+    "from shapely.geometry import box\n",
+    "\n",
+    "import rasterio\n",
+    "from rasterio.mask import mask\n",
+    "from rasterstats import zonal_stats\n",
+    "import pandas as pd\n",
+    "from joblib import Parallel, delayed\n",
+    "\n",
+    "con = ibis.duckdb.connect()\n",
+    "con.load_extension(\"spatial\")\n",
+    "threads = -1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "8b5656db-2d1d-4ca8-826d-7588126e52e8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# cropping US data to only CA \n",
+    "def crop_raster_to_bounds(tif_file, vector_gdf):\n",
+    "    with rasterio.open(tif_file) as src:\n",
+    "        # Get California's bounding box in the same CRS as the raster\n",
+    "        california_bounds = vector_gdf.total_bounds\n",
+    "        california_bounds = rasterio.coords.BoundingBox(\n",
+    "            *california_bounds\n",
+    "        )\n",
+    "        # Crop the raster to the California bounding box\n",
+    "        out_image, out_transform = mask(src, [california_bounds], crop=True)\n",
+    "        out_meta = src.meta.copy()\n",
+    "        out_meta.update({\n",
+    "            \"driver\": \"GTiff\",\n",
+    "            \"height\": out_image.shape[1],\n",
+    "            \"width\": out_image.shape[2],\n",
+    "            \"transform\": out_transform\n",
+    "        })\n",
+    "        print(\"Unique values in cropped raster:\", np.unique(out_image))\n",
+    "\n",
+    "    return out_image, out_meta\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "9a0e3446-16ac-40b0-9e34-db0157038c5a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def big_zonal_stats(vec_file, tif_file, stats, col_name, n_jobs, verbose=10, timeout=10000):\n",
+    "    gdf = gpd.read_parquet(vec_file)\n",
+    "    if gdf.crs is None:\n",
+    "        gdf = gdf.set_crs(\"EPSG:4326\")\n",
+    "    gdf = gdf.rename(columns={\"geom\": \"geometry\"})\n",
+    "    gdf = gdf.set_geometry(\"geometry\")\n",
+    "    gdf = gdf[gdf[\"geometry\"].notna()].copy()\n",
+    "\n",
+    "    with rasterio.open(tif_file) as src:\n",
+    "        raster_crs = src.crs\n",
+    "        gdf = gdf.to_crs(raster_crs)  # Transform vector to raster CRS\n",
+    "        \n",
+    "        # CA bounding box + convert it to a polygon in raster CRS\n",
+    "        california_polygon = box(*gdf.total_bounds)\n",
+    "        \n",
+    "        out_image, out_transform = mask(src, [california_polygon], crop=True, nodata=src.nodata)\n",
+    "\n",
+    "        # If raster is 3D, select the first band\n",
+    "        if out_image.ndim == 3:\n",
+    "            out_image = out_image[0]\n",
+    "\n",
+    "    # compute zonal statistics for each geometry slice\n",
+    "    def get_stats(geom_slice):\n",
+    "        geom = [geom_slice.geometry]\n",
+    "        stats_result = zonal_stats(\n",
+    "            geom, out_image, stats=stats, affine=out_transform, all_touched=True, nodata=src.nodata\n",
+    "        )\n",
+    "        return stats_result[0] if stats_result and stats_result[0].get(\"mean\") is not None else {'mean': None}\n",
+    "\n",
+    "    output = [get_stats(row) for row in gdf.itertuples()]\n",
+    "    gdf[col_name] = [res['mean'] for res in output]\n",
+    "\n",
+    "    return gdf"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "ce66bae6-bac5-4837-9b01-fde16a00c303",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# aws s3 cp s3://vizzuality/hfp-100/hfp_2021_100m_v1-2_cog.tif . --endpoint-url=https://data.source.coop\n",
+    "# aws s3 cp s3://vizzuality/lg-land-carbon-data/natcrop_bii_100m_cog.tif . --endpoint-url=https://data.source.coop\n",
+    "# aws s3 cp s3://vizzuality/lg-land-carbon-data/natcrop_fii_100m_cog.tif . --endpoint-url=https://data.source.coop\n",
+    "# aws s3 cp s3://vizzuality/lg-land-carbon-data/natcrop_expansion_100m_cog.tif . --endpoint-url=https://data.source.coop\n",
+    "# aws s3 cp s3://vizzuality/lg-land-carbon-data/natcrop_reduction_100m_cog.tif . --endpoint-url=https://data.source.coop\n",
+    "# aws s3 cp s3://cboettig/carbon/cogs/irrecoverable_c_total_2018.tif . --endpoint-url=https://data.source.coop\n",
+    "# aws s3 cp s3://cboettig/carbon/cogs/manageable_c_total_2018.tif . --endpoint-url=https://data.source.coop\n",
+    "# ! aws s3 cp s3://cboettig/justice40/disadvantaged-communities.parquet . --endpoint-url=https://data.source.coop\n",
+    "# minio/shared-biodiversity/redlist/cog/combined_sr_2022.tif\n",
+    "# /home/rstudio/minio/shared-biodiversity/redlist/cog/combined_rwr_2022.tif\n",
+    "# ! aws s3 cp s3://cboettig/social-vulnerability/svi2020_us_tract.parquet . --endpoint-url=https://data.source.coop\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "66dec912-ad8a-41cf-a5c2-6ec9cc350984",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 1min 52s, sys: 5.01 s, total: 1min 57s\n",
+      "Wall time: 1min 57s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "tif_file = 'SpeciesRichness_All.tif'\n",
+    "vec_file = \"/home/rstudio/github/ca-30x30/ca2024-30m.parquet\"\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'], col_name = \"richness\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "b081ec1a-ea91-485e-95f9-12cd06c2002a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 1min 50s, sys: 4.47 s, total: 1min 54s\n",
+      "Wall time: 1min 54s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "tif_file = 'RSR_All.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],\n",
+    "                      col_name = \"rsr\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "33ac0fb7-2cde-448d-a634-1973e34ac14f",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/venv/lib/python3.10/site-packages/rasterstats/io.py:335: NodataWarning: Setting nodata to -999; specify nodata explicitly\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 1min 58s, sys: 4.93 s, total: 2min 3s\n",
+      "Wall time: 2min 3s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "tif_file = 'deforest_carbon_100m_cog.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'], \n",
+    "                     col_name = \"deforest_carbon\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "d2a8c10f-e94b-4eef-940f-2af9599edee1",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 1min 53s, sys: 4.81 s, total: 1min 58s\n",
+      "Wall time: 1min 58s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "tif_file = 'natcrop_bii_100m_cog.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'], \n",
+    "                     col_name = \"biodiversity_intactness_loss\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "1c318f39-7ca0-4f3c-80fb-73f72202e4e0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 1min 53s, sys: 4.9 s, total: 1min 58s\n",
+      "Wall time: 1min 58s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "tif_file = 'natcrop_fii_100m_cog.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],\n",
+    "                     col_name = \"forest_integrity_loss\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "aef9070a-c87a-463e-81b8-3cc6c5c9d484",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/opt/conda/lib/python3.12/site-packages/rasterstats/io.py:335: NodataWarning: Setting nodata to -999; specify nodata explicitly\n",
+      "  warnings.warn(\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 3min 13s, sys: 55 s, total: 4min 8s\n",
+      "Wall time: 4min 8s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "tif_file = 'natcrop_expansion_100m_cog.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"crop_expansion\", n_jobs=threads, verbose=0)\n",
+    "gpd.GeoDataFrame(df, geometry=\"geometry\").to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d94f937b-b32c-4de1-b4ac-93ce33f0919f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "tif_file = 'natcrop_reduction_100m_cog.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"crop_reduction\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "19c3e402-8712-450f-b3dd-af9d0c01689c",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "tif_file = 'irrecoverable_c_total_2018.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"irrecoverable_carbon\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c55c777a-48ce-4403-a171-cfc0d2351df6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "tif_file = 'manageable_c_total_2018.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"manageable_carbon\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "2ce56a66-34e3-4f61-95ae-65d1f06bc468",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "tif_file = 'combined_rwr_2022.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"all_species_rwr\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a3260b3a-d2eb-4cda-afac-679b362d8b71",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "tif_file = 'combined_sr_2022.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"all_species_richness\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d5133f36-404e-4f6a-a90b-eb5f098e6f06",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "%%time\n",
+    "tif_file = 'combined_sr_2022.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"all_species_richness\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "6bdaba61-30c1-49d6-a4e6-db68f1daafa3",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 3min 16s, sys: 57 s, total: 4min 13s\n",
+      "Wall time: 4min 12s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "tif_file = 'hfp_2021_100m_v1-2_cog.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"human_impact\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "f8e037d4-7a34-42bc-941f-0c09ee80ef3b",
+   "metadata": {},
+   "source": [
+    "# Convert vector to tif "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "c4a19013-65f1-4eef-be2d-0cf1be3d0f7f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import geopandas as gpd\n",
+    "import numpy as np\n",
+    "import rasterio\n",
+    "from rasterio.features import rasterize\n",
+    "from rasterio.transform import from_bounds\n",
+    "\n",
+    "def get_geotiff(gdf, output_file,col):\n",
+    "    gdf = gdf.set_geometry(\"geometry\")\n",
+    "    gdf = gdf.set_crs(\"EPSG:4326\")\n",
+    "    print(gdf.crs)\n",
+    "\n",
+    "    # Set raster properties\n",
+    "    minx, miny, maxx, maxy = gdf.total_bounds  # Get the bounds of the geometry\n",
+    "    pixel_size = 0.01  # Define the pixel size in units of the CRS\n",
+    "    width = int((maxx - minx) / pixel_size)\n",
+    "    height = int((maxy - miny) / pixel_size)\n",
+    "    transform = from_bounds(minx, miny, maxx, maxy, width, height)\n",
+    "    \n",
+    "    # Define rasterization with continuous values\n",
+    "    shapes = ((geom, value) for geom, value in zip(gdf.geometry, gdf[col]))\n",
+    "    raster = rasterize(\n",
+    "        shapes,\n",
+    "        out_shape=(height, width),\n",
+    "        transform=transform,\n",
+    "        fill=0.0,  # Background value for areas outside the geometry\n",
+    "        dtype=\"float32\"  # Set data type to handle continuous values\n",
+    "    )\n",
+    "    print(\"Unique values in raster:\", np.unique(raster))\n",
+    "\n",
+    "    # Define GeoTIFF metadata\n",
+    "    out_meta = {\n",
+    "        \"driver\": \"GTiff\",\n",
+    "        \"height\": height,\n",
+    "        \"width\": width,\n",
+    "        \"count\": 1,\n",
+    "        \"dtype\": raster.dtype,\n",
+    "        \"crs\": gdf.crs,\n",
+    "        \"transform\": transform,\n",
+    "        \"compress\": \"deflate\"  # Use compression to reduce file size\n",
+    "    }\n",
+    "    \n",
+    "    # Write to a GeoTIFF file with COG options\n",
+    "    with rasterio.open(output_file, \"w\", **out_meta) as dest:\n",
+    "        dest.write(raster, 1)\n",
+    "        dest.build_overviews([2, 4, 8, 16], rasterio.enums.Resampling.average)\n",
+    "        dest.update_tags(1, TIFFTAG_RESOLUTION_UNIT=\"Meter\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "4e678f01-73af-4f99-a565-e9b7f04d9547",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# clean up SVI data\n",
+    "svi_df =  (con\n",
+    " .read_parquet(\"svi2020_us_tract.parquet\")\n",
+    " .select(\"RPL_THEMES\",\"RPL_THEME1\",\"RPL_THEME2\",\"RPL_THEME3\",\"RPL_THEME4\",\"Shape\")\n",
+    " .rename(SVI = \"RPL_THEMES\", socioeconomic = \"RPL_THEME1\", \n",
+    "         household_char = \"RPL_THEME2\", racial_ethnic_minority =  \"RPL_THEME3\",\n",
+    "         housing_transit = \"RPL_THEME4\", geometry = \"Shape\")\n",
+    ".cast({\"geometry\":\"geometry\"})\n",
+    ")\n",
+    "svi_df.execute().to_parquet(\"svi2020_us_tract_clean.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "c5046d6b-9798-46d3-a1bc-548e29414007",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "EPSG:4326\n",
+      "Unique values in raster: [-9.990e+02  0.000e+00  1.000e-04 ...  9.998e-01  9.999e-01  1.000e+00]\n",
+      "EPSG:4326\n",
+      "Unique values in raster: [-9.990e+02  0.000e+00  4.000e-04 ...  9.998e-01  9.999e-01  1.000e+00]\n",
+      "EPSG:4326\n",
+      "Unique values in raster: [-9.990e+02  0.000e+00  3.000e-04 ...  9.998e-01  9.999e-01  1.000e+00]\n",
+      "EPSG:4326\n",
+      "Unique values in raster: [-9.990e+02  0.000e+00  2.400e-03 ...  9.943e-01  9.952e-01  9.959e-01]\n",
+      "EPSG:4326\n",
+      "Unique values in raster: [-9.990e+02  0.000e+00  9.000e-03 ...  9.998e-01  9.999e-01  1.000e+00]\n"
+     ]
+    }
+   ],
+   "source": [
+    "gdf = gpd.read_parquet(\"svi2020_us_tract_clean.parquet\")\n",
+    "svi = gdf[['SVI','geometry']]\n",
+    "socio = gdf[['socioeconomic','geometry']]\n",
+    "house = gdf[['household_char','geometry']]\n",
+    "minority = gdf[['racial_ethnic_minority','geometry']]\n",
+    "transit = gdf[['housing_transit','geometry']]\n",
+    "\n",
+    "#convert SVI parquet to tif\n",
+    "get_geotiff(svi,\"svi.tif\",\"SVI\")\n",
+    "get_geotiff(socio,\"svi_socioeconomic.tif\",\"socioeconomic\")\n",
+    "get_geotiff(house,\"svi_household.tif\",\"household_char\")\n",
+    "get_geotiff(minority,\"svi_minority.tif\",\"racial_ethnic_minority\")\n",
+    "get_geotiff(transit,\"svi_transit.tif\",\"housing_transit\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "6a36b77f-d0be-45bd-9318-da4b57eaf353",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 3min 26s, sys: 56.6 s, total: 4min 23s\n",
+      "Wall time: 4min 27s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "tif_file = 'svi.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"SVI\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "05ef74e2-3f23-4f69-8cd3-8862cb73a259",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 3min 22s, sys: 56.4 s, total: 4min 18s\n",
+      "Wall time: 4min 27s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "tif_file = 'svi_socioeconomic.tif'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"socioeconomic_status\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "23417a03-38c2-4b31-8340-f08ec8a11631",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 3min 11s, sys: 54.3 s, total: 4min 5s\n",
+      "Wall time: 4min 5s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "tif_file = 'svi_household.tif'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"household_char\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "de86d7f0-6cdc-4d05-bdee-d9803cbd83bd",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 3min 11s, sys: 54.1 s, total: 4min 5s\n",
+      "Wall time: 4min 5s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "tif_file = 'svi_minority.tif'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"racial_ethnic_minority\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "0c49dd50-7dd3-4240-9af8-3e32ec656bc0",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 3min 13s, sys: 54.7 s, total: 4min 8s\n",
+      "Wall time: 4min 7s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "tif_file = 'svi_transit.tif'\n",
+    "df = big_zonal_stats(vec_file, tif_file, stats = ['mean'],  col_name = \"housing_transit\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "2e4de199-82d4-4e2b-8572-6fe19b57d1ee",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>established</th>\n",
+       "      <th>reGAP</th>\n",
+       "      <th>name</th>\n",
+       "      <th>access_type</th>\n",
+       "      <th>manager</th>\n",
+       "      <th>manager_type</th>\n",
+       "      <th>Easement</th>\n",
+       "      <th>Acres</th>\n",
+       "      <th>id</th>\n",
+       "      <th>type</th>\n",
+       "      <th>...</th>\n",
+       "      <th>all_species_rwr</th>\n",
+       "      <th>all_species_richness</th>\n",
+       "      <th>crop_expansion</th>\n",
+       "      <th>human_impact</th>\n",
+       "      <th>svi</th>\n",
+       "      <th>svi_socioeconomic_status</th>\n",
+       "      <th>svi_household_char</th>\n",
+       "      <th>svi_racial_ethnic_minority</th>\n",
+       "      <th>svi_housing_transit</th>\n",
+       "      <th>geom</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>2024</td>\n",
+       "      <td>2</td>\n",
+       "      <td>Six Rivers National Forest</td>\n",
+       "      <td>Open Access</td>\n",
+       "      <td>United States Forest Service</td>\n",
+       "      <td>Federal</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.191763</td>\n",
+       "      <td>100001</td>\n",
+       "      <td>Land</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.355</td>\n",
+       "      <td>346.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>2339.00</td>\n",
+       "      <td>0.521</td>\n",
+       "      <td>0.29</td>\n",
+       "      <td>0.522</td>\n",
+       "      <td>0.428</td>\n",
+       "      <td>0.816</td>\n",
+       "      <td>MULTIPOLYGON Z (((-123.94358 41.95869 0, -123....</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>2024</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Six Rivers National Forest</td>\n",
+       "      <td>Open Access</td>\n",
+       "      <td>United States Forest Service</td>\n",
+       "      <td>Federal</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.247565</td>\n",
+       "      <td>100002</td>\n",
+       "      <td>Land</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.355</td>\n",
+       "      <td>346.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>870.50</td>\n",
+       "      <td>0.521</td>\n",
+       "      <td>0.29</td>\n",
+       "      <td>0.522</td>\n",
+       "      <td>0.428</td>\n",
+       "      <td>0.816</td>\n",
+       "      <td>MULTIPOLYGON Z (((-123.98793 41.94847 0, -123....</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>2024</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Six Rivers National Forest</td>\n",
+       "      <td>Open Access</td>\n",
+       "      <td>United States Forest Service</td>\n",
+       "      <td>Federal</td>\n",
+       "      <td>0</td>\n",
+       "      <td>1.046992</td>\n",
+       "      <td>100003</td>\n",
+       "      <td>Land</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.355</td>\n",
+       "      <td>346.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>429.00</td>\n",
+       "      <td>0.521</td>\n",
+       "      <td>0.29</td>\n",
+       "      <td>0.522</td>\n",
+       "      <td>0.429</td>\n",
+       "      <td>0.816</td>\n",
+       "      <td>MULTIPOLYGON Z (((-123.87957 41.97172 0, -123....</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>2024</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Six Rivers National Forest</td>\n",
+       "      <td>Open Access</td>\n",
+       "      <td>United States Forest Service</td>\n",
+       "      <td>Federal</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.293964</td>\n",
+       "      <td>100004</td>\n",
+       "      <td>Land</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.355</td>\n",
+       "      <td>346.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>3907.00</td>\n",
+       "      <td>0.521</td>\n",
+       "      <td>0.29</td>\n",
+       "      <td>0.522</td>\n",
+       "      <td>0.428</td>\n",
+       "      <td>0.816</td>\n",
+       "      <td>MULTIPOLYGON Z (((-123.84466 41.99139 0, -123....</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>2024</td>\n",
+       "      <td>1</td>\n",
+       "      <td>Six Rivers National Forest</td>\n",
+       "      <td>Open Access</td>\n",
+       "      <td>United States Forest Service</td>\n",
+       "      <td>Federal</td>\n",
+       "      <td>0</td>\n",
+       "      <td>0.912564</td>\n",
+       "      <td>100005</td>\n",
+       "      <td>Land</td>\n",
+       "      <td>...</td>\n",
+       "      <td>0.355</td>\n",
+       "      <td>346.0</td>\n",
+       "      <td>0</td>\n",
+       "      <td>698.25</td>\n",
+       "      <td>0.521</td>\n",
+       "      <td>0.29</td>\n",
+       "      <td>0.522</td>\n",
+       "      <td>0.428</td>\n",
+       "      <td>0.816</td>\n",
+       "      <td>MULTIPOLYGON Z (((-123.86194 41.98176 0, -123....</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5 rows × 28 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   established  reGAP                        name  access_type  \\\n",
+       "0         2024      2  Six Rivers National Forest  Open Access   \n",
+       "1         2024      1  Six Rivers National Forest  Open Access   \n",
+       "2         2024      1  Six Rivers National Forest  Open Access   \n",
+       "3         2024      1  Six Rivers National Forest  Open Access   \n",
+       "4         2024      1  Six Rivers National Forest  Open Access   \n",
+       "\n",
+       "                        manager manager_type  Easement     Acres      id  \\\n",
+       "0  United States Forest Service      Federal         0  0.191763  100001   \n",
+       "1  United States Forest Service      Federal         0  0.247565  100002   \n",
+       "2  United States Forest Service      Federal         0  1.046992  100003   \n",
+       "3  United States Forest Service      Federal         0  0.293964  100004   \n",
+       "4  United States Forest Service      Federal         0  0.912564  100005   \n",
+       "\n",
+       "   type  ...  all_species_rwr  all_species_richness  crop_expansion  \\\n",
+       "0  Land  ...            0.355                 346.0               0   \n",
+       "1  Land  ...            0.355                 346.0               0   \n",
+       "2  Land  ...            0.355                 346.0               0   \n",
+       "3  Land  ...            0.355                 346.0               0   \n",
+       "4  Land  ...            0.355                 346.0               0   \n",
+       "\n",
+       "   human_impact    svi  svi_socioeconomic_status  svi_household_char  \\\n",
+       "0       2339.00  0.521                      0.29               0.522   \n",
+       "1        870.50  0.521                      0.29               0.522   \n",
+       "2        429.00  0.521                      0.29               0.522   \n",
+       "3       3907.00  0.521                      0.29               0.522   \n",
+       "4        698.25  0.521                      0.29               0.522   \n",
+       "\n",
+       "   svi_racial_ethnic_minority  svi_housing_transit  \\\n",
+       "0                       0.428                0.816   \n",
+       "1                       0.428                0.816   \n",
+       "2                       0.429                0.816   \n",
+       "3                       0.428                0.816   \n",
+       "4                       0.428                0.816   \n",
+       "\n",
+       "                                                geom  \n",
+       "0  MULTIPOLYGON Z (((-123.94358 41.95869 0, -123....  \n",
+       "1  MULTIPOLYGON Z (((-123.98793 41.94847 0, -123....  \n",
+       "2  MULTIPOLYGON Z (((-123.87957 41.97172 0, -123....  \n",
+       "3  MULTIPOLYGON Z (((-123.84466 41.99139 0, -123....  \n",
+       "4  MULTIPOLYGON Z (((-123.86194 41.98176 0, -123....  \n",
+       "\n",
+       "[5 rows x 28 columns]"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "## clean up\n",
+    "\n",
+    "con = ibis.duckdb.connect(extensions=[\"spatial\"])\n",
+    "ca_geom = con.read_parquet(\"ca2024-30m.parquet\").cast({\"geom\":\"geometry\"}).select(\"id\",\"geom\")\n",
+    "\n",
+    "\n",
+    "\n",
+    "ca = (con\n",
+    "      .read_parquet(\"cpad-stats-temp.parquet\")\n",
+    "      .mutate(richness = _.richness.round(3))\n",
+    "      .mutate(rsr = _.rsr.round(3))\n",
+    "      .mutate(deforest_carbon = _.deforest_carbon.round(3))\n",
+    "      .mutate(biodiversity_intactness_loss = _.biodiversity_intactness_loss.round(3))\n",
+    "      .mutate(forest_integrity_loss = _.forest_integrity_loss.round(3))\n",
+    "      .cast({\"crop_expansion\": \"int64\"})\n",
+    "      .cast({\"crop_reduction\": \"int64\"})\n",
+    "      .cast({\"manageable_carbon\": \"int64\"})\n",
+    "      .cast({\"irrecoverable_carbon\": \"int64\"})\n",
+    "      .mutate(all_species_rwr = _.all_species_rwr.round(3))\n",
+    "      .mutate(all_species_richness = _.all_species_richness.round(3))\n",
+    "      .mutate(human_impact = _.human_impact.round(3))\n",
+    "      .mutate(svi = _.SVI.round(3))\n",
+    "      .mutate(svi_socioeconomic_status = _.socioeconomic_status.round(3))\n",
+    "      .mutate(svi_household_char = _.household_char.round(3))\n",
+    "      .mutate(svi_racial_ethnic_minority = _.racial_ethnic_minority.round(3))\n",
+    "      .mutate(svi_housing_transit = _.housing_transit.round(3))\n",
+    "      .drop(\"geometry\",\"__index_level_0__\")\n",
+    "      # .rename(geom = \"geometry\")\n",
+    "      # .cast({\"geom\":\"geometry\"})\n",
+    "      # .mutate(geom=_.geom.convert('EPSG:3857', 'EPSG:4326'))\n",
+    "      .join(ca_geom, \"id\", how = \"inner\")\n",
+    "      .drop(\"SVI\", \"socioeconomic_status\",\"household_char\",\"racial_ethnic_minority\",\"housing_transit\" )\n",
+    "\n",
+    "     )\n",
+    "# \n",
+    "ca.head(5).execute()\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3780de2c-3a68-442c-bb3b-64c792418979",
+   "metadata": {},
+   "source": [
+    "# Save as PMTiles + Upload data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "05c791c9-888a-483a-9dbb-a2ba7eb1bce2",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Note: Environment variable`HF_TOKEN` is set and is the current active token independently from the token you've just configured.\n"
+     ]
+    }
+   ],
+   "source": [
+    "import subprocess\n",
+    "import os\n",
+    "from huggingface_hub import HfApi, login\n",
+    "import streamlit as st\n",
+    "\n",
+    "login(st.secrets[\"HF_TOKEN\"])\n",
+    "# api = HfApi(add_to_git_credential=False)\n",
+    "api = HfApi()\n",
+    "\n",
+    "def hf_upload(file, repo_id):\n",
+    "    info = api.upload_file(\n",
+    "            path_or_fileobj=file,\n",
+    "            path_in_repo=file,\n",
+    "            repo_id=repo_id,\n",
+    "            repo_type=\"dataset\",\n",
+    "        )\n",
+    "def generate_pmtiles(input_file, output_file, max_zoom=12):\n",
+    "    # Ensure Tippecanoe is installed\n",
+    "    if subprocess.call([\"which\", \"tippecanoe\"], stdout=subprocess.DEVNULL) != 0:\n",
+    "        raise RuntimeError(\"Tippecanoe is not installed or not in PATH\")\n",
+    "\n",
+    "    # Construct the Tippecanoe command\n",
+    "    command = [\n",
+    "        \"tippecanoe\",\n",
+    "        \"-o\", output_file,\n",
+    "        \"-zg\",\n",
+    "        \"--extend-zooms-if-still-dropping\",\n",
+    "        \"--force\",\n",
+    "        \"--projection\", \"EPSG:4326\",  \n",
+    "        \"-L\",\"layer:\"+input_file,\n",
+    "    ]\n",
+    "    # Run Tippecanoe\n",
+    "    try:\n",
+    "        subprocess.run(command, check=True)\n",
+    "        print(f\"Successfully generated PMTiles file: {output_file}\")\n",
+    "    except subprocess.CalledProcessError as e:\n",
+    "        print(f\"Error running Tippecanoe: {e}\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "1f2d179d-6d47-4e84-83c6-7cb3d969fc00",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "cpad-stats.geojson:6: ignoring dimensions beyond two: in JSON object [-123.94358428532209,41.95869046159588,0]\n",
+      "cpad-stats.geojson:6: ignoring dimensions beyond two: in JSON object {\"type\":\"Feature\",\"properties\":{\"established\":2024,\"reGAP\":2,\"name\":\"Six Rivers National Forest\",\"access_type\":\"Open Access\",\"manager\":\"United States Forest Service\",\"manager_type\":\"Federal\",\"Easement\":0,\"Acres\":0.19176257,\"id\":100001,\"type\":\"Land\",\"richness\":4,\"rsr\":0.007,\"deforest_carbon\":0,\"biodiversity_intactness_loss\":0,\"forest_integrity_loss\":0,\"crop_reduction\":0,\"irrecoverable_carbon\":4,\"manageable_carbon\":85,\"all_species_rwr\":0.355,\"all_species_richness\":346,\"crop_expansion\":0,\"human_...\n",
+      "81196 features, 78827308 bytes of geometry and attributes, 2702235 bytes of string pool, 0 bytes of vertices, 0 bytes of nodes\n",
+      "Choosing a maxzoom of -z10 for features typically 1205 feet (368 meters) apart, and at least 78 feet (24 meters) apart\n",
+      "Choosing a maxzoom of -z13 for resolution of about 39 feet (11 meters) within features\n",
+      "tile 4/2/6 size is 801307 with detail 12, >500000    \n",
+      "tile 5/5/12 size is 1313015 with detail 12, >500000    \n",
+      "tile 5/5/12 size is 780845 with detail 11, >500000    \n",
+      "tile 6/11/25 size is 603643 with detail 12, >500000    \n",
+      "tile 6/10/24 size is 1087317 with detail 12, >500000    \n",
+      "tile 6/10/24 size is 742154 with detail 11, >500000    \n",
+      "tile 7/20/49 size is 704536 with detail 12, >500000    \n",
+      "tile 7/20/49 size is 504066 with detail 11, >500000    \n",
+      "tile 7/22/51 size is 655744 with detail 12, >500000    \n",
+      "  99.9%  13/1332/3068  \n",
+      "  100.0%  13/1278/3041  \r"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Successfully generated PMTiles file: cpad-stats.pmtiles\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "82d13b05559b4f32a947f75fb2391e6a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "cpad-stats.pmtiles:   0%|          | 0.00/95.3M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "61b3432b09064da4a46762eb514face4",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "cpad-stats.parquet:   0%|          | 0.00/204M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "gdf = ca.execute().set_crs(\"EPSG:4326\")\n",
+    "gdf.to_file(\"cpad-stats.geojson\")\n",
+    "\n",
+    "generate_pmtiles(\"cpad-stats.geojson\", \"cpad-stats.pmtiles\")\n",
+    "hf_upload(\"cpad-stats.pmtiles\", \"boettiger-lab/ca-30x30\")\n",
+    "\n",
+    "gdf.to_parquet(\"cpad-stats.parquet\")\n",
+    "hf_upload(\"cpad-stats.parquet\", \"boettiger-lab/ca-30x30\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "bf53bfe6-2175-4aa8-b3cb-be2c1db86b1b",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "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": "3.12.7"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}