adding in justice40

preprocess/preprocess.ipynb

@@ -41,8 +41,10 @@
     "ca_all_parquet = path + \"ca-all.parquet\"\n",
     "ca_all_stats =  path + \"ca-all-stats.parquet\"\n",
     "ca_final_parquet = \"ca_30x30_stats.parquet\"\n",
+    "\n",
     "#vector data \n",
     "svi = path + 'SVI2022_US_tract' #4326\n",
+    "justice40 = path + 'disadvantaged-communities'\n",
     "fire = path + 'calfire-2023'#4326\n",
     "rxburn = path + 'calfire-rxburn-2023'#4326\n",
     "\n",
@@ -322,8 +324,8 @@
    "outputs": [],
    "source": [
     "%%time\n",
-    "vectors = [svi,fire,rxburn]\n",
-    "names = ['svi','fire','rxburn']\n",
+    "vectors = [svi,justice40 ,fire,rxburn]\n",
+    "names = ['svi','disadvantaged_communities','fire','rxburn']\n",
     "\n",
     "gdf = gpd.read_parquet(ca_all_parquet) # CA Nature data \n",
     "gdf = gdf.set_index('id') # set the index to the col we are joining on for gpd.join()\n",
@@ -339,7 +341,9 @@
     "     # filter: only want CA data, not nationwide. \n",
     "    if name == 'svi': \n",
     "        gdf_temp = gdf_temp[gdf_temp['STATE']==\"California\"]\n",
-    "        \n",
+    "    if name == 'disadvantaged_communities':\n",
+    "        gdf_temp = gdf_temp[gdf_temp['StateName']==\"California\"]\n",
+    "\n",
     "    reproject_vectors(file, gdf_temp) # change projection to match CA Nature data \n",
     "    gdf_zonal = vector_vector_stats(ca_all_parquet, file + '-epsg3310.parquet') #compute zonal stats \n",
     "    gdf_zonal = gdf_zonal.rename(columns ={'overlap_fraction':name}) \n",