Spaces:
Sleeping
Sleeping
File size: 17,155 Bytes
b8c83d8 be7a922 b8c83d8 b1c508f b8c83d8 be7a922 b8c83d8 be7a922 b8c83d8 be7a922 b8c83d8 b1c508f b8c83d8 be7a922 b8c83d8 b1c508f b8c83d8 be7a922 b8c83d8 b1c508f b8c83d8 b1c508f b8c83d8 b1c508f b8c83d8 b1c508f b8c83d8 b1c508f b8c83d8 b1c508f be7a922 b1c508f be7a922 b1c508f be7a922 b8c83d8 be7a922 b1c508f b8c83d8 be7a922 b8c83d8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 |
{
"cells": [
{
"cell_type": "code",
"execution_count": 16,
"id": "d179ded1-6235-47ed-bbfb-6d72468188d5",
"metadata": {},
"outputs": [],
"source": [
"import ibis\n",
"from ibis import _\n",
"import streamlit as st\n",
"import ibis.expr.datatypes as dt # Make sure to import the necessary module\n",
"\n",
"\n",
"conn = ibis.duckdb.connect(extensions=[\"spatial\"])\n",
"\n",
"# pres = conn.read_csv(\"sources-president.csv\")\n",
"county = conn.read_csv(\"countypres_2000-2020.csv\")\n",
"votes = conn.read_parquet(\"vote.parquet\")"
]
},
{
"cell_type": "markdown",
"id": "170ba045-8848-4a99-a4f6-68bde22428af",
"metadata": {},
"source": [
"# Getting party affiliations for counties"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ab644102-c725-4cf4-915c-8550a0a74c32",
"metadata": {},
"outputs": [],
"source": [
"filtered = county.filter((_.mode == \"TOTAL\") & (_.totalvotes > 0))\n",
"\n",
"# Find the winning party for each year, state, and county\n",
"most_votes = (\n",
" filtered\n",
" .group_by(['year', 'state_po', 'county_name', 'party'])\n",
" .aggregate(winning_votes=_.candidatevotes.sum())\n",
")\n",
"\n",
"# For each year, state, and county, select the party with the highest total votes\n",
"winning_party = (\n",
" most_votes\n",
" .group_by('year', 'state_po', 'county_name')\n",
" .aggregate(\n",
" max_votes=_.winning_votes.max(), # Max votes in this group\n",
" )\n",
" .join(\n",
" most_votes,\n",
" [\"year\",\"state_po\",\"county_name\",most_votes['winning_votes'] == _.max_votes],\n",
" how='inner'\n",
" )\n",
" .select(\"year\",\"state_po\",\"county_name\",most_votes['party'].name('current_party')\n",
" )\n",
")\n",
"\n",
"# Self-join to get the previous year's winning party\n",
"previous_year = winning_party.view()\n",
"\n",
"joined = (\n",
" winning_party\n",
" .join(\n",
" previous_year, [\"county_name\",\"state_po\",winning_party['year'] == previous_year['year'] + 4],\n",
" how='left'\n",
" )\n",
" .rename(state_id = \"state_po\")\n",
" .mutate(key = _.county_name + ibis.literal(\" COUNTY-\") + _.state_id)\n",
" .select(\"year\",\"key\",\"current_party\",previous_year['current_party'].name('previous_party'))\n",
")\n",
"\n",
"county_parties = joined.filter(_.year >2000).order_by(\"year\")\n",
"\n",
"print(county_parties.execute())"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ce0d80bf-3b78-4aa9-8048-5cc0dbf970d9",
"metadata": {},
"outputs": [],
"source": [
"df = (votes\n",
" .mutate(key = _.key.upper())\n",
" .filter(_.jurisdiction == \"Municipal\")\n",
" .join(county_parties, [\"key\",\"year\"],how='inner'\n",
" )\n",
" .cast({\"geometry\": \"geometry\"})\n",
")"
]
},
{
"cell_type": "code",
"execution_count": 30,
"id": "87bef5e2-a40a-4aff-aa27-e7d49ec68aac",
"metadata": {},
"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",
"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",
" input_file\n",
" ]\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": null,
"id": "b086e76c-4285-4036-8033-e4e45cb6966b",
"metadata": {},
"outputs": [],
"source": [
"gdf= df.execute()\n",
"gdf = gdf.set_crs(\"EPSG:4326\")\n",
"\n",
"# gdf.to_parquet(\"county_parties.parquet\")\n",
"# hf_upload(\"county_parties.parquet\", \"boettiger-lab/landvote\")\n",
"\n",
"# gdf.to_file(\"county_parties.geojson\")\n",
"# hf_upload(\"county_parties.geojson\", \"boettiger-lab/landvote\")\n",
"\n",
"# generate_pmtiles(\"county_parties.geojson\", \"county_parties.pmtiles\")\n",
"# hf_upload(\"county_parties.pmtiles\", \"boettiger-lab/landvote\")\n"
]
},
{
"cell_type": "markdown",
"id": "6193c4b9-0183-4aae-9a25-899a748fd65e",
"metadata": {},
"source": [
"# Checking map"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c2ae8ada-c73e-4b2e-938e-70a29584f199",
"metadata": {},
"outputs": [],
"source": [
"import leafmap.maplibregl as leafmap\n",
"m = leafmap.Map(style=\"positron\")\n",
"\n",
"\n",
"url_states = \"https://huggingface.co/datasets/boettiger-lab/landvote/resolve/main/county_parties.pmtiles\"\n",
"\n",
"outcome = [\n",
" 'match',\n",
" ['get', 'Status'], \n",
" \"Pass\", '#2E865F',\n",
" \"Fail\", '#FF3300', \n",
" '#ccc'\n",
" ]\n",
"paint_states = {\"fill-color\": outcome, \n",
" # \"fill-opacity\": 0.2,\n",
" }\n",
"style_states = {\n",
" \"layers\": [\n",
" {\n",
" \"id\": \"county_parties\",\n",
" \"source\": \"county_parties\",\n",
" \"source-layer\": \"county_parties\",\n",
" \"type\": \"fill\",\n",
" \"filter\": [\n",
" \"==\",\n",
" [\"get\", \"year\"],\n",
" 2008,\n",
" ], # only show buildings with height info\n",
" \"paint\": paint_states\n",
" },\n",
" ],\n",
"}\n",
"\n",
"m.add_pmtiles(\n",
" url_states,\n",
" style=style_states,\n",
" visible=True,\n",
" opacity=0.4,\n",
" tooltip=True,\n",
" fit_bounds=False,\n",
")\n",
"\n",
"m\n"
]
},
{
"cell_type": "markdown",
"id": "8c12fd16-a953-4273-9e0f-44b50eacf633",
"metadata": {},
"source": [
"# Getting Municipals "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "b3429fea-7c0d-4838-bcbb-6552079dc3b6",
"metadata": {},
"outputs": [],
"source": [
"\n",
"localities_boundaries = \"us_localities.parquet\"\n",
"locality = conn.read_parquet(localities_boundaries)\n",
"landvote = conn.read_csv(\"landvote.csv\")\n",
"\n",
"#needed to redo this, since I didn't save county in \"votes.parquet\". \n",
"vote_local = (landvote\n",
" .filter(_[\"Jurisdiction Type\"] == \"Municipal\")\n",
" .rename(city = \"Jurisdiction Name\", state_id = \"State\")\n",
" .mutate(key = _.city + ibis.literal('-') + _.state_id)\n",
" .rename(amount = 'Conservation Funds at Stake', yes = '% Yes')\n",
" .mutate(amount_n=_.amount.replace('$', '').replace(',', '').cast('float'))\n",
" .mutate(log_amount=_.amount_n.log())\n",
" .mutate(year=_['Date'].year().cast('int32'))\n",
" .mutate(\n",
" yes=ibis.case()\n",
" .when(_.yes.isin(['Pass', 'None','Fail']), None) # Handle non-numeric cases\n",
" .when(_.yes.notnull(), (_.yes.replace('%', '').cast('float').round(2).cast(dt.float64)).cast(dt.string) + '%') # Convert valid percentages and add %\n",
" .else_(None) # Default to None for other cases\n",
" .end()\n",
" )\n",
" .mutate(log_amount = _.log_amount.round(4))\n",
" .select('key', 'Status', 'yes', 'year', 'amount', 'log_amount', )\n",
" )\n",
"\n",
"# getting the county parties for each municipal \n",
"df_municipals = (locality \n",
" .mutate(key_municipal = _.name + ibis.literal('-') + _.state_id) \n",
" .mutate(key = (_.county + ibis.literal('-') + _.state_id).upper()) \n",
" .select('key', 'geometry','key_municipal','name')\n",
" .right_join(vote_local, [_.key_municipal == vote_local[\"key\"]])\n",
" .mutate(jurisdiction = ibis.literal(\"Municipal\"))\n",
" .cast({\"geometry\": \"geometry\"})\n",
" .mutate(geometry = _.geometry.buffer(.07))\n",
" .join(county_parties, [\"key\",\"year\"],how='inner')\n",
" .rename(county = \"key\")\n",
" .rename(key = \"key_municipal\")\n",
" .select('key','geometry','Status','yes','year','amount','log_amount','jurisdiction','current_party','previous_party')\n",
" )\n",
"\n",
"\n",
"gdf_municipals = df_municipals.execute()\n",
"gdf_municipals = gdf_municipals.set_crs(\"EPSG:4326\")\n",
"gdf_municipals\n",
"\n",
"\n",
"# gdf_municipals.to_parquet(\"municipal_parties.parquet\")\n",
"# hf_upload(\"municipal_parties.parquet\", \"boettiger-lab/landvote\")\n",
"\n",
"# gdf_municipals.to_file(\"municipal_parties.geojson\")\n",
"# hf_upload(\"municipal_parties.geojson\", \"boettiger-lab/landvote\")\n",
"\n",
"# generate_pmtiles(\"municipal_parties.geojson\", \"municipal_parties.pmtiles\")\n",
"# hf_upload(\"municipal_parties.pmtiles\", \"boettiger-lab/landvote\")\n"
]
},
{
"cell_type": "markdown",
"id": "06e24a7e-5f7f-42bc-b515-43082016d496",
"metadata": {},
"source": [
"# Get States"
]
},
{
"cell_type": "code",
"execution_count": 28,
"id": "217170ca-b732-4875-b4cb-f8a8cd2fc405",
"metadata": {},
"outputs": [],
"source": [
"states = (conn\n",
" .read_csv(\"1976-2020-president.csv\")\n",
" .filter(_. year >=2000)\n",
" )\n",
"# states.execute()"
]
},
{
"cell_type": "code",
"execution_count": 18,
"id": "322b9a85-bdf9-45f9-9b19-695cc1b996e8",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
" year key current_party previous_party\n",
"0 2004 HI DEMOCRAT DEMOCRAT\n",
"1 2004 ME DEMOCRAT DEMOCRAT\n",
"2 2004 NJ DEMOCRAT DEMOCRAT\n",
"3 2004 NM REPUBLICAN DEMOCRAT\n",
"4 2004 ND REPUBLICAN REPUBLICAN\n",
".. ... .. ... ...\n",
"250 2020 VT DEMOCRAT DEMOCRAT\n",
"251 2020 AL REPUBLICAN REPUBLICAN\n",
"252 2020 IA REPUBLICAN REPUBLICAN\n",
"253 2020 SD REPUBLICAN REPUBLICAN\n",
"254 2020 GA DEMOCRAT REPUBLICAN\n",
"\n",
"[255 rows x 4 columns]\n"
]
}
],
"source": [
"# filtered = county.filter((_.mode == \"TOTAL\") & (_.totalvotes > 0))\n",
"\n",
"# Find the winning party for each year, state, and county\n",
"most_votes= (\n",
" states\n",
" .group_by(['year', 'state_po', 'party_simplified'])\n",
" .aggregate(winning_votes=_.candidatevotes.sum())\n",
")\n",
"\n",
"# For each year, state, and county, select the party with the highest total votes\n",
"winning_party = (\n",
" most_votes\n",
" .group_by('year', 'state_po')\n",
" .aggregate(\n",
" max_votes=_.winning_votes.max(), # Max votes in this group\n",
" )\n",
" .join(\n",
" most_votes,\n",
" [\"year\",\"state_po\",most_votes['winning_votes'] == _.max_votes],\n",
" how='inner'\n",
" )\n",
" .select(\"year\",\"state_po\",most_votes['party_simplified'].name('current_party')\n",
" )\n",
")\n",
"\n",
"# Self-join to get the previous year's winning party\n",
"previous_year = winning_party.view()\n",
"\n",
"joined = (\n",
" winning_party\n",
" .join(\n",
" previous_year, [\"state_po\",winning_party['year'] == previous_year['year'] + 4],\n",
" how='left'\n",
" )\n",
" .rename(key = \"state_po\")\n",
" # .mutate(key = _.county_name + ibis.literal(\" COUNTY-\") + _.state_id)\n",
" .select(\"year\",\"key\",\"current_party\",previous_year['current_party'].name('previous_party'))\n",
")\n",
"\n",
"state_parties = joined.filter(_.year >2000).order_by(\"year\")\n",
"\n",
"print(state_parties.execute())"
]
},
{
"cell_type": "code",
"execution_count": 31,
"id": "2c03920e-76da-4034-8eaf-1e80a56f5b0d",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "3574af6546ff4cd1949e27c63cd15cd7",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"states_parties.parquet: 0%| | 0.00/2.36M [00:00<?, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"For layer 0, using name \"states_parties\"\n",
"12 features, 833591 bytes of geometry and attributes, 542 bytes of string pool, 0 bytes of vertices, 0 bytes of nodes\n",
"Choosing a maxzoom of -z0 for features typically 7514540 feet (2290432 meters) apart, and at least 2073685 feet (632060 meters) apart\n",
"Choosing a maxzoom of -z10 for resolution of about 376 feet (114 meters) within features\n",
" 99.9% 10/271/383 \n",
" 100.0% 10/187/380 \r"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Successfully generated PMTiles file: states_parties.pmtiles\n"
]
}
],
"source": [
"# state_boundaries = \"https://data.source.coop/cboettig/us-boundaries/us-state-territory.parquet\"\n",
"states = conn.read_parquet(\"vote_states.parquet\")\n",
"\n",
"df_states = (states\n",
" .mutate(key = _.key.upper())\n",
" # .filter(_.jurisdiction == \"Municipal\")\n",
" .join(state_parties, [\"key\",\"year\"],how='inner'\n",
" )\n",
" .cast({\"geometry\": \"geometry\"})\n",
")\n",
"\n",
"gdf_states = df_states.execute()\n",
"gdf_states = gdf_states.set_crs(\"EPSG:4326\")\n",
"gdf_states\n",
"\n",
"\n",
"gdf_states.to_parquet(\"states_parties.parquet\")\n",
"hf_upload(\"states_parties.parquet\", \"boettiger-lab/landvote\")\n",
"\n",
"gdf_states.to_file(\"states_parties.geojson\")\n",
"hf_upload(\"states_parties.geojson\", \"boettiger-lab/landvote\")\n",
"\n",
"generate_pmtiles(\"states_parties.geojson\", \"states_parties.pmtiles\")\n",
"hf_upload(\"states_parties.pmtiles\", \"boettiger-lab/landvote\")\n"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "dcf5d049-68ae-4d73-be77-72d985c9ed1c",
"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": "3.10.12"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|