adding justice40

get_zonal_stats.ipynb

@@ -36,7 +36,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 61,
    "id": "8b5656db-2d1d-4ca8-826d-7588126e52e8",
    "metadata": {},
    "outputs": [],
@@ -65,7 +65,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 62,
    "id": "9a0e3446-16ac-40b0-9e34-db0157038c5a",
    "metadata": {},
    "outputs": [],
@@ -112,6 +112,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
+    "# getting local copies of data \n",
     "# 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",
@@ -125,6 +126,14 @@
     "# ! aws s3 cp s3://cboettig/social-vulnerability/svi2020_us_tract.parquet . --endpoint-url=https://data.source.coop\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "531e7f88-1ce1-4027-b0ab-aab597e9a2b2",
+   "metadata": {},
+   "source": [
+    "# Biodiversity Data"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 21,
@@ -170,6 +179,67 @@
     "                      col_name = \"rsr\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")"
    ]
   },
+  {
+   "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": 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": "markdown",
+   "id": "6c129894-3775-4842-8767-f81a8f626d2c",
+   "metadata": {},
+   "source": [
+    "# Carbon Data"
+   ]
+  },
+  {
+   "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": 23,
@@ -201,6 +271,14 @@
     "                     col_name = \"deforest_carbon\", n_jobs=threads, verbose=0).to_parquet(\"cpad-stats-temp.parquet\")\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "096c00a8-57af-41d7-93cc-85d85414aa4f",
+   "metadata": {},
+   "source": [
+    "# Human Impact Data"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 24,
@@ -292,72 +370,6 @@
     "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,
@@ -385,12 +397,12 @@
    "id": "f8e037d4-7a34-42bc-941f-0c09ee80ef3b",
    "metadata": {},
    "source": [
-    "# Convert vector to tif "
+    "# Need to convert SVI & Justice40 files to tif"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 60,
    "id": "c4a19013-65f1-4eef-be2d-0cf1be3d0f7f",
    "metadata": {},
    "outputs": [],
@@ -443,6 +455,14 @@
     "        dest.update_tags(1, TIFFTAG_RESOLUTION_UNIT=\"Meter\")\n"
    ]
   },
+  {
+   "cell_type": "markdown",
+   "id": "f4925a74-5ed2-49a4-845b-6a0f0398a43e",
+   "metadata": {},
+   "source": [
+    "# SVI"
+   ]
+  },
   {
    "cell_type": "code",
    "execution_count": 25,
@@ -614,9 +634,130 @@
     "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": "markdown",
+   "id": "ff4b6604-9828-4882-90bd-554c21f5c6e6",
+   "metadata": {},
+   "source": [
+    "# Justice40 "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 56,
+   "id": "3678a91f-72f7-4339-a409-a97776cba043",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "EPSG:4326\n",
+      "Unique values in raster: [0. 1.]\n"
+     ]
+    }
+   ],
+   "source": [
+    "#clean up\n",
+    "justice40 =  (con\n",
+    "        .read_parquet(\"disadvantaged-communities.parquet\")\n",
+    "        .rename(geometry = \"SHAPE\",justice40=\"Disadvan\")\n",
+    "        .filter(_.StateName == \"California\")\n",
+    "        .mutate(geometry = _.geometry.convert(\"ESRI:102039\",\"EPSG:4326\"))\n",
+    "        .select(\"justice40\",\"geometry\")\n",
+    "        )\n",
+    "gdf = justice40.execute()\n",
+    "get_geotiff(gdf,\"ca_justice40.tif\",\"justice40\")\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 73,
+   "id": "8faa425f-6f9c-4189-a53a-24dd0250c539",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#justice40 is binary data so we want to get the percentage of polygon where justice40 = 1.  \n",
+    "\n",
+    "def big_zonal_stats_binary(vec_file, tif_file, 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) \n",
+    "        \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 out_image.ndim == 3:\n",
+    "            out_image = out_image[0]\n",
+    "\n",
+    "        def get_stats(geom_slice):\n",
+    "            geom = [geom_slice.geometry]\n",
+    "            masked_image, _ = mask(src, geom, crop=True, all_touched=True, nodata=src.nodata)\n",
+    "            \n",
+    "            # If the masked area is empty, return None\n",
+    "            if masked_image.size == 0:\n",
+    "                return {'percentage_1': None}\n",
+    "            \n",
+    "            # Count 1s and calculate percentage\n",
+    "            count_1 = (masked_image == 1).sum()\n",
+    "            total_count = (masked_image != src.nodata).sum()\n",
+    "            \n",
+    "            # Calculate percentage of justice40 = 1 within the polygon\n",
+    "            percentage_1 = (count_1 / total_count) * 100 if total_count > 0 else None\n",
+    "            \n",
+    "            return {'percentage_1': percentage_1}\n",
+    "\n",
+    "        output = [get_stats(row) for row in gdf.itertuples()]\n",
+    "    \n",
+    "    gdf[col_name] = [res['percentage_1'] for res in output]\n",
+    "    return gdf\n",
+    "\n",
+    "# Run the function\n"
+   ]
+  },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 74,
+   "id": "f5f7297a-e31b-4d3c-ae1c-7e3d78bc141a",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "CPU times: user 2min 2s, sys: 29.1 s, total: 2min 31s\n",
+      "Wall time: 2min 32s\n"
+     ]
+    }
+   ],
+   "source": [
+    "%%time\n",
+    "tif_file = 'ca_justice40.tif'\n",
+    "vec_file = './cpad-stats-temp.parquet'\n",
+    "df = big_zonal_stats_binary(vec_file, tif_file, col_name=\"justice40\", n_jobs=threads, verbose=0)\n",
+    "df.to_parquet(\"cpad-stats-temp.parquet\")\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "e3083b85-1322-4188-ac08-e73c2570978c",
+   "metadata": {},
+   "source": [
+    "# Cleaning up"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 130,
    "id": "2e4de199-82d4-4e2b-8572-6fe19b57d1ee",
    "metadata": {},
    "outputs": [
@@ -654,9 +795,9 @@
        "      <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>justice40</th>\n",
        "      <th>svi_socioeconomic_status</th>\n",
        "      <th>svi_household_char</th>\n",
        "      <th>svi_racial_ethnic_minority</th>\n",
@@ -680,14 +821,14 @@
        "      <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>0.0</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",
+       "      <td>MULTIPOLYGON Z (((-123.94358 41.95869 0.00000,...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>1</th>\n",
@@ -704,14 +845,14 @@
        "      <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>0.0</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",
+       "      <td>MULTIPOLYGON Z (((-123.98793 41.94847 0.00000,...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>2</th>\n",
@@ -728,14 +869,14 @@
        "      <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>0.0</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",
+       "      <td>MULTIPOLYGON Z (((-123.87957 41.97172 0.00000,...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>3</th>\n",
@@ -752,14 +893,14 @@
        "      <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>0.0</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",
+       "      <td>MULTIPOLYGON Z (((-123.84466 41.99139 0.00000,...</td>\n",
        "    </tr>\n",
        "    <tr>\n",
        "      <th>4</th>\n",
@@ -776,18 +917,18 @@
        "      <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>0.0</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",
+       "      <td>MULTIPOLYGON Z (((-123.86194 41.98176 0.00000,...</td>\n",
        "    </tr>\n",
        "  </tbody>\n",
        "</table>\n",
-       "<p>5 rows × 28 columns</p>\n",
+       "<p>5 rows × 25 columns</p>\n",
        "</div>"
       ],
       "text/plain": [
@@ -805,19 +946,19 @@
        "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",
+       "   type  ...  all_species_rwr  all_species_richness  human_impact    svi  \\\n",
+       "0  Land  ...            0.355                 346.0       2339.00  0.521   \n",
+       "1  Land  ...            0.355                 346.0        870.50  0.521   \n",
+       "2  Land  ...            0.355                 346.0        429.00  0.521   \n",
+       "3  Land  ...            0.355                 346.0       3907.00  0.521   \n",
+       "4  Land  ...            0.355                 346.0        698.25  0.521   \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",
+       "   justice40  svi_socioeconomic_status  svi_household_char  \\\n",
+       "0        0.0                      0.29               0.522   \n",
+       "1        0.0                      0.29               0.522   \n",
+       "2        0.0                      0.29               0.522   \n",
+       "3        0.0                      0.29               0.522   \n",
+       "4        0.0                      0.29               0.522   \n",
        "\n",
        "   svi_racial_ethnic_minority  svi_housing_transit  \\\n",
        "0                       0.428                0.816   \n",
@@ -827,56 +968,57 @@
        "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",
+       "0  MULTIPOLYGON Z (((-123.94358 41.95869 0.00000,...  \n",
+       "1  MULTIPOLYGON Z (((-123.98793 41.94847 0.00000,...  \n",
+       "2  MULTIPOLYGON Z (((-123.87957 41.97172 0.00000,...  \n",
+       "3  MULTIPOLYGON Z (((-123.84466 41.99139 0.00000,...  \n",
+       "4  MULTIPOLYGON Z (((-123.86194 41.98176 0.00000,...  \n",
        "\n",
-       "[5 rows x 28 columns]"
+       "[5 rows x 25 columns]"
       ]
      },
-     "execution_count": 3,
+     "execution_count": 130,
      "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",
+    "        .read_parquet(\"cpad-stats-temp.parquet\")\n",
+    "        .cast({\n",
+    "            \"crop_expansion\": \"int64\",\n",
+    "            \"crop_reduction\": \"int64\",\n",
+    "            \"manageable_carbon\": \"int64\",\n",
+    "            \"irrecoverable_carbon\": \"int64\"\n",
+    "        })\n",
+    "        .rename(svi = \"SVI\")\n",
+    "        .mutate(\n",
+    "            richness=_.richness.round(3),\n",
+    "            rsr=_.rsr.round(3),\n",
+    "            all_species_rwr=_.all_species_rwr.round(3),\n",
+    "            all_species_richness=_.all_species_richness.round(3),\n",
+    "            svi=_.svi.round(3),\n",
+    "            justice40=(_.justice40/100).round(3),\n",
+    "            svi_socioeconomic_status=_.socioeconomic_status.round(3),\n",
+    "            svi_household_char=_.household_char.round(3),\n",
+    "            svi_racial_ethnic_minority=_.racial_ethnic_minority.round(3),\n",
+    "            svi_housing_transit=_.housing_transit.round(3),\n",
+    "            human_impact=_.human_impact.round(3),\n",
+    "            deforest_carbon=_.deforest_carbon.round(3),\n",
+    "            biodiversity_intactness_loss=_.biodiversity_intactness_loss.round(3),\n",
+    "            forest_integrity_loss=_.forest_integrity_loss.round(3),\n",
+    "        )\n",
+    "        .drop(\"geometry\", \"__index_level_0__\",\"socioeconomic_status\", \"household_char\", \"racial_ethnic_minority\", \"housing_transit\", \n",
+    "              \"biodiversity_intactness_loss\",\"forest_integrity_loss\",\"crop_reduction\",\"crop_expansion\"\n",
+    "             )    \n",
+    "        .join(ca_geom, \"id\", how=\"inner\")\n",
+    "    )\n",
+    "\n",
     "\n",
-    "     )\n",
-    "# \n",
     "ca.head(5).execute()\n"
    ]
   },
@@ -890,7 +1032,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 131,
    "id": "05c791c9-888a-483a-9dbb-a2ba7eb1bce2",
    "metadata": {},
    "outputs": [
@@ -945,7 +1087,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 132,
    "id": "1f2d179d-6d47-4e84-83c6-7cb3d969fc00",
    "metadata": {},
    "outputs": [
@@ -954,20 +1096,19 @@
      "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",
+      "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\":0.19176256656646729,\"id\":100001,\"type\":\"Land\",\"richness\":4,\"rsr\":0.007,\"deforest_carbon\":0,\"irrecoverable_carbon\":4,\"manageable_carbon\":85,\"all_species_rwr\":0.355,\"all_species_richness\":346,\"human_impact\":2339,\"svi\":0.521,\"justice40\":0,\"svi_socioeconomic_status\":0.29,\"svi_household_ch...\n",
+      "81196 features, 77613888 bytes of geometry, 3021623 bytes of string pool\n",
+      "Choosing a maxzoom of -z10 for features typically 1202 feet (367 meters) apart, and at least 77 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",
+      "tile 4/2/6 size is 739078 with detail 12, >500000    \n",
+      "tile 5/5/12 size is 1225784 with detail 12, >500000    \n",
+      "tile 5/5/12 size is 720473 with detail 11, >500000    \n",
+      "tile 6/11/25 size is 559822 with detail 12, >500000    \n",
+      "tile 6/10/24 size is 1012378 with detail 12, >500000    \n",
+      "tile 6/10/24 size is 686077 with detail 11, >500000    \n",
+      "tile 7/20/49 size is 642314 with detail 12, >500000    \n",
+      "tile 7/22/51 size is 600090 with detail 12, >500000    \n",
+      "  99.9%  13/1335/3225  \n",
       "  100.0%  13/1278/3041  \r"
      ]
     },
@@ -981,12 +1122,12 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "82d13b05559b4f32a947f75fb2391e6a",
+       "model_id": "0cb245402c8d42e4ab020ace580d13eb",
        "version_major": 2,
        "version_minor": 0
       },
       "text/plain": [
-       "cpad-stats.pmtiles:   0%|          | 0.00/95.3M [00:00<?, ?B/s]"
+       "cpad-stats.pmtiles:   0%|          | 0.00/90.4M [00:00<?, ?B/s]"
       ]
      },
      "metadata": {},
@@ -995,7 +1136,7 @@
     {
      "data": {
       "application/vnd.jupyter.widget-view+json": {
-       "model_id": "61b3432b09064da4a46762eb514face4",
+       "model_id": "78f91869800d474ebd77500c15db063f",
        "version_major": 2,
        "version_minor": 0
       },