fixed counties/cities

preprocess.ipynb

@@ -10,7 +10,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "id": "6452373c-d10f-472c-9174-cd05a3363587",
    "metadata": {},
    "outputs": [],
@@ -30,7 +30,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 2,
    "id": "dd9ffc64-b4cf-4e5b-9c96-703e91a77837",
    "metadata": {},
    "outputs": [],
@@ -74,14 +74,14 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 3,
    "id": "8fc40e96-fffd-4b23-9963-c931fdce96f6",
    "metadata": {},
    "outputs": [],
    "source": [
     "votes = (landvote\n",
-    "        .join(party,[\"state\",\"county\",\"municipal\",\"jurisdiction\",\"geometry\", _.elect_year == party[\"year\"]],how = \"inner\")\n",
-    "        .drop('elect_year','year_right')\n",
+    "        .join(party,[\"state\",\"county\",\"municipal\",\"jurisdiction\",\"geometry\", _.elect_year == party[\"year\"]],how = \"left\")\n",
+    "        .drop('elect_year','state_right','county_right','municipal_right','year_right',\"geometry_right\",\"jurisdiction_right\")\n",
     "        .mutate(municipal=ibis.case()\n",
     "                .when(_.municipal == ibis.literal(\"-\"), None) \n",
     "                .else_(_.municipal) \n",
@@ -105,10 +105,21 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 4,
    "id": "b1cd8f44-57fa-49a8-b438-f9e4aab747c5",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "The token has not been saved to the git credentials helper. Pass `add_to_git_credential=True` in this function directly or `--add-to-git-credential` if using via `huggingface-cli` if you want to set the git credential as well.\n",
+      "Token is valid (permission: write).\n",
+      "Your token has been saved to /home/rstudio/.cache/huggingface/token\n",
+      "Login successful\n"
+     ]
+    }
+   ],
    "source": [
     "import subprocess\n",
     "import os\n",
@@ -154,10 +165,85 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 5,
    "id": "7061577e-0632-4395-8ac5-241a1fab53b0",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "ff135769c16340f9a87905b600836afe",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "FloatProgress(value=0.0, layout=Layout(width='auto'), style=ProgressStyle(bar_color='black'))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "037e0563f82447998bbd438473a2017d",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "FloatProgress(value=0.0, layout=Layout(width='auto'), style=ProgressStyle(bar_color='black'))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "60716409890f4760a744123d4e6003de",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "FloatProgress(value=0.0, layout=Layout(width='auto'), style=ProgressStyle(bar_color='black'))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "2286 features, 17891307 bytes of geometry and attributes, 58357 bytes of string pool, 0 bytes of vertices, 0 bytes of nodes\n",
+      "Choosing a maxzoom of -z3 for features typically 83927 feet (25581 meters) apart, and at least 11120 feet (3390 meters) apart\n",
+      "Choosing a maxzoom of -z10 for resolution of about 278 feet (84 meters) within features\n",
+      "  99.9%  10/279/424  \n",
+      "  100.0%  10/55/448  \r"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Successfully generated PMTiles file: votes.pmtiles\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "c8a1a66665814dd8b0ad839929a6b30d",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "votes.pmtiles:   0%|          | 0.00/4.72M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "gdf_state = votes.filter(_.jurisdiction == 'State').execute().set_crs(\"EPSG:4326\")\n",
     "gdf_state.to_file(\"votes_state.geojson\")\n",
@@ -174,23 +260,44 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 6,
    "id": "f2979624-bcdf-4a8a-899a-c22fc3cdaf0e",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "6b928b70b56e45a8b1f59c727bd6879a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "FloatProgress(value=0.0, layout=Layout(width='auto'), style=ProgressStyle(bar_color='black'))"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "0f4fa7e221ff481697375deba7f34b94",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "votes.parquet:   0%|          | 0.00/43.1M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
    "source": [
     "# save as parquet\n",
     "votes.execute().set_crs(\"EPSG:4326\").to_parquet(\"votes.parquet\")\n",
     "hf_upload(\"votes.parquet\", \"boettiger-lab/landvote\")\n"
    ]
-  },
-  {
-   "cell_type": "markdown",
-   "id": "2ec22cf4-cfdc-4845-a793-ed9236054ff4",
-   "metadata": {},
-   "source": [
-    "# "
-   ]
   }
  ],
  "metadata": {