Spaces:
Sleeping
Sleeping
File size: 52,450 Bytes
5a7775e |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 |
{
"cells": [
{
"cell_type": "markdown",
"id": "707b1a14",
"metadata": {},
"source": [
"Pre-process SVI Data from [CDC portal](https://www.atsdr.cdc.gov/place-health/php/svi/svi-data-documentation-download.html)\n",
"\n",
"- Tract data for United States from 2022, 2020, 2010, 2000. \n",
"- Data documentation"
]
},
{
"cell_type": "code",
"execution_count": 1,
"id": "803df305",
"metadata": {},
"outputs": [],
"source": [
"import ibis\n",
"from ibis import _\n",
"import streamlit as st\n",
"from utilities import generate_pmtiles\n",
"\n",
"con = ibis.duckdb.connect(\"duck.db\", extensions=['httpfs', 'spatial', 'h3'])\n"
]
},
{
"cell_type": "code",
"execution_count": 13,
"id": "7ac648e6",
"metadata": {},
"outputs": [
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "781a57e6e9004c5b8b7ae644aea77dbe",
"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": "9de6547cfe7e4b32af6852eadf27e53e",
"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": [
"For layer 0, using name \"svi\"\n",
"84120 features, 34922477 bytes of geometry, 5150225 bytes of string pool\n",
"tile 1/0/0 size is 673414 with detail 12, >500000 \n",
"Going to try keeping the sparsest 66.82% of the features to make it fit\n",
"tile 1/0/0 size is 654918 with detail 12, >500000 \n",
"Going to try keeping the sparsest 45.92% of the features to make it fit\n",
"tile 1/0/0 size is 627082 with detail 12, >500000 \n",
"Going to try keeping the sparsest 32.95% of the features to make it fit\n",
"tile 1/0/0 size is 571221 with detail 12, >500000 \n",
"Going to try keeping the sparsest 25.96% of the features to make it fit\n",
"tile 1/0/0 size is 515026 with detail 12, >500000 \n",
"Going to try keeping the sparsest 22.68% of the features to make it fit\n",
"tile 2/0/1 size is 556184 with detail 12, >500000 \n",
"Going to try keeping the sparsest 80.91% of the features to make it fit\n",
"tile 2/1/1 size is 680483 with detail 12, >500000 \n",
"Going to try keeping the sparsest 66.13% of the features to make it fit\n",
"tile 2/0/1 size is 544973 with detail 12, >500000 \n",
"Going to try keeping the sparsest 66.81% of the features to make it fit\n",
"tile 2/1/1 size is 633636 with detail 12, >500000 \n",
"Going to try keeping the sparsest 46.96% of the features to make it fit\n",
"tile 2/0/1 size is 529976 with detail 12, >500000 \n",
"Going to try keeping the sparsest 56.73% of the features to make it fit\n",
"tile 2/1/1 size is 562278 with detail 12, >500000 \n",
"Going to try keeping the sparsest 37.59% of the features to make it fit\n",
"tile 2/0/1 size is 509845 with detail 12, >500000 \n",
"Going to try keeping the sparsest 50.07% of the features to make it fit\n",
"tile 3/1/3 size is 614365 with detail 12, >500000 \n",
"Going to try keeping the sparsest 73.25% of the features to make it fit\n",
"tile 3/2/3 size is 828844 with detail 12, >500000 \n",
"Going to try keeping the sparsest 54.29% of the features to make it fit\n",
"tile 3/1/3 size is 557346 with detail 12, >500000 \n",
"Going to try keeping the sparsest 59.14% of the features to make it fit\n",
"tile 3/2/3 size is 622365 with detail 12, >500000 \n",
"Going to try keeping the sparsest 39.26% of the features to make it fit\n",
"tile 3/1/3 size is 507698 with detail 12, >500000 \n",
"Going to try keeping the sparsest 52.42% of the features to make it fit\n",
"tile 4/4/5 size is 513228 with detail 12, >500000 \n",
"Going to try keeping the sparsest 87.68% of the features to make it fit\n",
"tile 4/3/6 size is 635333 with detail 12, >500000 \n",
"Going to try keeping the sparsest 70.83% of the features to make it fit\n",
"tile 4/3/6 size is 515357 with detail 12, >500000 \n",
"Going to try keeping the sparsest 61.85% of the features to make it fit\n",
"tile 4/4/6 size is 1080604 with detail 12, >500000 \n",
"Going to try keeping the sparsest 41.64% of the features to make it fit\n",
"tile 4/4/6 size is 614947 with detail 12, >500000 \n",
"Going to try keeping the sparsest 30.47% of the features to make it fit\n",
"tile 5/8/12 size is 784796 with detail 12, >500000 \n",
"Going to try keeping the sparsest 57.34% of the features to make it fit\n",
"tile 5/8/12 size is 540488 with detail 12, >500000 \n",
"Going to try keeping the sparsest 47.74% of the features to make it fit\n",
" 99.9% 12/973/1656 \n",
" 100.0% 12/4092/1352 \r"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Successfully generated PMTiles file: svi-data/2022/SVI2022_US_tract.pmtiles\n"
]
}
],
"source": [
"expr = con.read_geo(\"svi-data/2022/SVI2022_US_tract.gdb\")\n",
"expr.to_parquet(\"svi-data/2022/SVI2022_US_tract.parquet\")\n",
"\n",
"# tippecanoe requires geojson input to create PMTiles. Drop most additional variables in PMTiles creation.\n",
"query = ibis.to_sql(expr.select('STATE', 'COUNTY', 'LOCATION', 'FIPS', 'RPL_THEMES', 'Shape'))\n",
"con.raw_sql(f\"COPY ({query}) TO '/tmp/svi.json' WITH (FORMAT GDAL, DRIVER 'GeoJSON', LAYER_CREATION_OPTIONS 'WRITE_BBOX=YES');\")\n",
"\n",
"generate_pmtiles(\"/tmp/svi.json\", \"svi-data/2022/SVI2022_US_tract.pmtiles\")\n"
]
},
{
"cell_type": "code",
"execution_count": 15,
"id": "2e29cc6e",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<minio.helpers.ObjectWriteResult at 0x77886893f050>"
]
},
"execution_count": 15,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"import minio\n",
"import re\n",
"\n",
"minio_key = st.secrets[\"MINIO_KEY\"]\n",
"minio_secret = st.secrets[\"MINIO_SECRET\"]\n",
"mc = minio.Minio(\"minio.carlboettiger.info\", minio_key, minio_secret)\n",
"\n",
"mc.fput_object(\"public-data\", \"social-vulnerability/2022/SVI2022_US_tract.pmtiles\", \"svi-data/2022/SVI2022_US_tract.pmtiles\")\n",
"mc.fput_object(\"public-data\", \"social-vulnerability/2022/SVI2022_US_tract.parquet\", \"svi-data/2022/SVI2022_US_tract.parquet\")\n"
]
},
{
"cell_type": "code",
"execution_count": 19,
"id": "5fcd59bc-72a4-4de7-9cdb-1b6eca9407fb",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"<duckdb.duckdb.DuckDBPyConnection at 0x7edb2419f330>"
]
},
"execution_count": 19,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"\n",
"\n",
"\n",
"# Local cloud\n",
"minio_key = st.secrets[\"MINIO_KEY\"]\n",
"minio_secret = st.secrets[\"MINIO_SECRET\"]\n",
"query1 = f'''\n",
"CREATE OR REPLACE SECRET secret1 (\n",
" TYPE S3,\n",
" KEY_ID '{minio_key}',\n",
" SECRET '{minio_secret}',\n",
" ENDPOINT 'minio.carlboettiger.info',\n",
" URL_STYLE 'path',\n",
" SCOPE \"s3://public-gbif\"\n",
"\n",
");\n",
"'''\n",
"query2 = f'''\n",
"CREATE OR REPLACE SECRET secret2 (\n",
" TYPE S3,\n",
" KEY_ID '{minio_key}',\n",
" SECRET '{minio_secret}',\n",
" ENDPOINT 'minio.carlboettiger.info',\n",
" URL_STYLE 'path',\n",
" SCOPE \"s3://public-data\"\n",
"\n",
");\n",
"'''\n",
"# don't scope to a single bucket\n",
"# SCOPE 's3://public-gbif'\n",
"\n",
"con.raw_sql(query1)\n",
"con.raw_sql(query2)\n",
"## Limits are sometimes good \n",
"con.raw_sql(\"SET memory_limit = '20GB';\")\n",
"con.raw_sql(\"set threads=40;\")\n",
"\n",
"# can/should we add explicit spatial index to gbif first? using RTree takes too much memory"
]
},
{
"cell_type": "code",
"execution_count": 20,
"id": "dcf50375-75ee-4208-87b2-6ffef6361742",
"metadata": {},
"outputs": [],
"source": [
"overture = (\n",
" con.read_parquet('s3://overturemaps-us-west-2/release/2024-11-13.0/theme=divisions/type=division_area/*', \n",
" filename=True, hive_partitioning=1))\n",
"usa = overture.filter(_.subtype==\"country\").filter(_.country == \"US\").select(_.geometry).execute()"
]
},
{
"cell_type": "code",
"execution_count": 21,
"id": "ce86081b-a46f-426b-9432-9bce588156ee",
"metadata": {},
"outputs": [],
"source": [
"\n",
"gbif = con.read_parquet(\"s3://public-gbif/2024-10-01/**\")\n",
"svi = con.read_parquet(\"s3://public-data/social-vulnerability/2022/SVI2022_US_tract.parquet\").rename(geom = \"Shape\")\n"
]
},
{
"cell_type": "markdown",
"id": "3891abb6-3652-4217-8615-106d354ff131",
"metadata": {},
"source": [
"We iterate through the city list to do this efficiently. (Should we filter gbif down to US boundary as a one-off first? We will assume it is efficient to filter the full globe state by state)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"id": "69bf6dc6-4a13-4830-8c1a-87bb5899eb32",
"metadata": {},
"outputs": [],
"source": [
"all_states = svi.select(_.ST_ABBR).distinct().order_by(_.ST_ABBR).execute()[\"ST_ABBR\"]\n",
"#all_states"
]
},
{
"cell_type": "code",
"execution_count": 26,
"id": "32a2b4c1-e08b-4fbb-b891-ac19053a4585",
"metadata": {},
"outputs": [],
"source": [
"## select from the list we haven't yet written (allows resume).\n",
"import minio\n",
"import re\n",
"\n",
"minio_key = st.secrets[\"MINIO_KEY\"]\n",
"minio_secret = st.secrets[\"MINIO_SECRET\"]\n",
"mc = minio.Minio(\"minio.carlboettiger.info\", minio_key, minio_secret)\n",
"obj = mc.list_objects(\"public-gbif\", \"social-vulnerability\", recursive=True)\n",
"pattern = r\"social-vulnerability/|\\.parquet$\"\n",
"finished = [re.sub(pattern, \"\", i.object_name) for i in obj if not i.is_dir]\n",
"remaining = set(all_states) - set(finished)"
]
},
{
"cell_type": "code",
"execution_count": 27,
"id": "4ecc58a3",
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"{'AK',\n",
" 'AL',\n",
" 'AR',\n",
" 'AZ',\n",
" 'CA',\n",
" 'CO',\n",
" 'CT',\n",
" 'DC',\n",
" 'DE',\n",
" 'FL',\n",
" 'GA',\n",
" 'HI',\n",
" 'IA',\n",
" 'ID',\n",
" 'IL',\n",
" 'IN',\n",
" 'KS',\n",
" 'KY',\n",
" 'LA',\n",
" 'MA',\n",
" 'MD',\n",
" 'ME',\n",
" 'MI',\n",
" 'MN',\n",
" 'MO',\n",
" 'MS',\n",
" 'MT',\n",
" 'NC',\n",
" 'ND',\n",
" 'NE',\n",
" 'NH',\n",
" 'NJ',\n",
" 'NM',\n",
" 'NV',\n",
" 'NY',\n",
" 'OH',\n",
" 'OK',\n",
" 'OR',\n",
" 'PA',\n",
" 'RI',\n",
" 'SC',\n",
" 'SD',\n",
" 'TN',\n",
" 'TX',\n",
" 'UT',\n",
" 'VA',\n",
" 'VT',\n",
" 'WA',\n",
" 'WI',\n",
" 'WV',\n",
" 'WY'}"
]
},
"execution_count": 27,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"remaining"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "c3a4005c-1e8c-4f2a-a93c-1c158c9c26ab",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"NV/Eureka County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6fd7b6e6fe1a4e3b9c8d476e0e757644",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Lander County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "80f08f9cc267481996667dd1e383a3fb",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Clark County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "872f806c983d4804b399881eac7d3bd9",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Storey County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9927ce307cc8413f973891b388c89288",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Churchill County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "a5d573d2766c41fbbfde5af9ed19ab76",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Esmeralda County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "bda8ee87bd1340f1b666c61b5d6bc716",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Lyon County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "460041e4c2a745d5b0ff6dff64f26343",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Nye County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "7690f211b2e2418e876898369d3b04ef",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Douglas County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "fb3235545ac04933ae82d95b5783657e",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Elko County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "9c72bf43115f4c65b9b7bdfb44c2fc67",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Pershing County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "2e7d1ff419fe4bf4ae07c1d4288d0259",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Washoe County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "c57a17eaf70941a9968ad2db89e2c98d",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Humboldt County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "958d00b68de94acaa96d63871daa356b",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Carson City\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "a162c535a70f4dc89b7e708f2fc8633b",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Lincoln County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "e4ca31b6f6b64667bc8c1e5dfac7ab03",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/White Pine County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "b89cd3441e714d5983daffa6c93cc0ee",
"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": "stdout",
"output_type": "stream",
"text": [
"NV/Mineral County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "c05bb3bbd3434373a068a489410beb4a",
"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": "stdout",
"output_type": "stream",
"text": [
"NE/Blaine County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "f88979e7186546f3be239f901393ab8a",
"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": "stdout",
"output_type": "stream",
"text": [
"NE/Butler County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "c4bfcd9ba81944b29907ccf3c6d3783e",
"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": "stdout",
"output_type": "stream",
"text": [
"NE/Custer County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6cd52ae08b7b4dea931ff2ffa5d6c7f6",
"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": "stdout",
"output_type": "stream",
"text": [
"NE/Dakota County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "b3a2e7411b69407ba76c06b0d083a961",
"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": "stdout",
"output_type": "stream",
"text": [
"NE/Kearney County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "e0ccf52489a3467ba172afef3e36f2f0",
"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": "stdout",
"output_type": "stream",
"text": [
"NE/Keith County\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "e6f8cd9d59284e7aaa9eabe117a69079",
"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"
}
],
"source": [
"## And here we go, long-running loop over each city\n",
"for i in remaining:\n",
" counties = svi.filter(_.ST_ABBR == i).select(_.COUNTY).distinct().execute()[\"COUNTY\"].to_numpy()\n",
" for county in counties:\n",
" gdf = (svi\n",
" .filter(_.ST_ABBR == i, _.COUNTY== county)\n",
" .mutate(area = _.geom.area())\n",
" )\n",
"\n",
" print(i + \"/\" + county)\n",
" \n",
" bounds = gdf.execute().total_bounds\n",
" points = (gbif\n",
" .filter(_.decimallongitude >= bounds[0], \n",
" _.decimallongitude < bounds[2], \n",
" _.decimallatitude >= bounds[1], \n",
" _.decimallatitude < bounds[3])\n",
" )\n",
" \n",
" (gdf\n",
" .join(points, gdf.geom.intersects(points.geom))\n",
" .to_parquet(f\"s3://public-gbif/social-vulnerability/state={i}/{county}.parquet\")\n",
" )\n"
]
},
{
"cell_type": "markdown",
"id": "050a358f-e2de-49bd-a80d-4f8c47e36bab",
"metadata": {},
"source": [
"gbif_usa = con.read_parquet(\"s3://cboettig/gbif/svi/**\")\n"
]
},
{
"cell_type": "code",
"execution_count": 43,
"id": "9bd1299b-af6b-4d85-97fb-ba83a5c26c70",
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">DatabaseTable: ibis_read_parquet_msislo4d7fcgdfh2pyoxvxjkdu\n",
" OBJECTID int64\n",
" ST string\n",
" STATE string\n",
" ST_ABBR string\n",
" STCNTY string\n",
" COUNTY string\n",
" FIPS string\n",
" LOCATION string\n",
" AREA_SQMI float64\n",
" E_TOTPOP int32\n",
" M_TOTPOP int32\n",
" E_HU int32\n",
" M_HU int32\n",
" E_HH int32\n",
" M_HH int32\n",
" E_POV150 int32\n",
" M_POV150 int32\n",
" E_UNEMP int32\n",
" M_UNEMP int32\n",
" E_HBURD int32\n",
" M_HBURD int32\n",
" E_NOHSDP int32\n",
" M_NOHSDP int32\n",
" E_UNINSUR int32\n",
" M_UNINSUR int32\n",
" E_AGE65 int32\n",
" M_AGE65 int32\n",
" E_AGE17 int32\n",
" M_AGE17 int32\n",
" E_DISABL int32\n",
" M_DISABL int32\n",
" E_SNGPNT int32\n",
" M_SNGPNT int32\n",
" E_LIMENG int32\n",
" M_LIMENG int32\n",
" E_MINRTY int32\n",
" M_MINRTY int32\n",
" E_MUNIT int32\n",
" M_MUNIT int32\n",
" E_MOBILE int32\n",
" M_MOBILE int32\n",
" E_CROWD int32\n",
" M_CROWD int32\n",
" E_NOVEH int32\n",
" M_NOVEH int32\n",
" E_GROUPQ int32\n",
" M_GROUPQ int32\n",
" EP_POV150 float64\n",
" MP_POV150 float64\n",
" EP_UNEMP float64\n",
" MP_UNEMP float64\n",
" EP_HBURD float64\n",
" MP_HBURD float64\n",
" EP_NOHSDP float64\n",
" MP_NOHSDP float64\n",
" EP_UNINSUR float64\n",
" MP_UNINSUR float64\n",
" EP_AGE65 float64\n",
" MP_AGE65 float64\n",
" EP_AGE17 float64\n",
" MP_AGE17 float64\n",
" EP_DISABL float64\n",
" MP_DISABL float64\n",
" EP_SNGPNT float64\n",
" MP_SNGPNT float64\n",
" EP_LIMENG float64\n",
" MP_LIMENG float64\n",
" EP_MINRTY float64\n",
" MP_MINRTY float64\n",
" EP_MUNIT float64\n",
" MP_MUNIT float64\n",
" EP_MOBILE float64\n",
" MP_MOBILE float64\n",
" EP_CROWD float64\n",
" MP_CROWD float64\n",
" EP_NOVEH float64\n",
" MP_NOVEH float64\n",
" EP_GROUPQ float64\n",
" MP_GROUPQ float64\n",
" EPL_POV150 float64\n",
" EPL_UNEMP float64\n",
" EPL_HBURD float64\n",
" EPL_NOHSDP float64\n",
" EPL_UNINSUR float64\n",
" SPL_THEME1 float64\n",
" RPL_THEME1 float64\n",
" EPL_AGE65 float64\n",
" EPL_AGE17 float64\n",
" EPL_DISABL float64\n",
" EPL_SNGPNT float64\n",
" EPL_LIMENG float64\n",
" SPL_THEME2 float64\n",
" RPL_THEME2 float64\n",
" EPL_MINRTY float64\n",
" SPL_THEME3 float64\n",
" RPL_THEME3 float64\n",
" EPL_MUNIT float64\n",
" EPL_MOBILE float64\n",
" EPL_CROWD float64\n",
" EPL_NOVEH float64\n",
" EPL_GROUPQ float64\n",
" SPL_THEME4 float64\n",
" RPL_THEME4 float64\n",
" SPL_THEMES float64\n",
" RPL_THEMES float64\n",
" F_POV150 int16\n",
" F_UNEMP int16\n",
" F_HBURD int16\n",
" F_NOHSDP int16\n",
" F_UNINSUR int16\n",
" F_THEME1 int16\n",
" F_AGE65 int16\n",
" F_AGE17 int16\n",
" F_DISABL int16\n",
" F_SNGPNT int16\n",
" F_LIMENG int16\n",
" F_THEME2 int16\n",
" F_MINRTY int16\n",
" F_THEME3 int16\n",
" F_MUNIT int16\n",
" F_MOBILE int16\n",
" F_CROWD int16\n",
" F_NOVEH int16\n",
" F_GROUPQ int16\n",
" F_THEME4 int16\n",
" F_TOTAL int16\n",
" E_DAYPOP int32\n",
" E_NOINT int32\n",
" M_NOINT int32\n",
" E_AFAM int32\n",
" M_AFAM int32\n",
" E_HISP int32\n",
" M_HISP int32\n",
" E_ASIAN int32\n",
" M_ASIAN int32\n",
" E_AIAN int32\n",
" M_AIAN int32\n",
" E_NHPI int32\n",
" M_NHPI int32\n",
" E_TWOMORE int32\n",
" M_TWOMORE int32\n",
" E_OTHERRACE int32\n",
" M_OTHERRACE int32\n",
" EP_NOINT float64\n",
" MP_NOINT float64\n",
" EP_AFAM float64\n",
" MP_AFAM float64\n",
" EP_HISP float64\n",
" MP_HISP float64\n",
" EP_ASIAN float64\n",
" MP_ASIAN float64\n",
" EP_AIAN float64\n",
" MP_AIAN float64\n",
" EP_NHPI float64\n",
" MP_NHPI float64\n",
" EP_TWOMORE float64\n",
" MP_TWOMORE float64\n",
" EP_OTHERRACE float64\n",
" MP_OTHERRACE float64\n",
" Shape_Length float64\n",
" Shape_Area float64\n",
" geom geospatial:geometry\n",
" area float64\n",
" gbifid string\n",
" datasetkey string\n",
" occurrenceid string\n",
" kingdom string\n",
" phylum string\n",
" class string\n",
" order string\n",
" family string\n",
" genus string\n",
" species string\n",
" infraspecificepithet string\n",
" taxonrank string\n",
" scientificname string\n",
" verbatimscientificname string\n",
" verbatimscientificnameauthorship string\n",
" countrycode string\n",
" locality string\n",
" stateprovince string\n",
" occurrencestatus string\n",
" individualcount int32\n",
" publishingorgkey string\n",
" decimallatitude float64\n",
" decimallongitude float64\n",
" coordinateuncertaintyinmeters float64\n",
" coordinateprecision float64\n",
" elevation float64\n",
" elevationaccuracy float64\n",
" depth float64\n",
" depthaccuracy float64\n",
" eventdate timestamp(6)\n",
" day int32\n",
" month int32\n",
" year int32\n",
" taxonkey int32\n",
" specieskey int32\n",
" basisofrecord string\n",
" institutioncode string\n",
" collectioncode string\n",
" catalognumber string\n",
" recordnumber string\n",
" identifiedby array<string>\n",
" dateidentified timestamp(6)\n",
" license string\n",
" rightsholder string\n",
" recordedby array<string>\n",
" typestatus array<string>\n",
" establishmentmeans string\n",
" lastinterpreted timestamp(6)\n",
" mediatype array<string>\n",
" issue array<string>\n",
" geom_right geospatial:geometry\n",
" h0 string\n",
" h1 string\n",
" h2 string\n",
" h3 string\n",
" h4 string\n",
" h5 string\n",
" h6 string\n",
" h7 string\n",
" h8 string\n",
" h9 string\n",
" h10 string\n",
" h11 string\n",
"</pre>\n"
],
"text/plain": [
"DatabaseTable: ibis_read_parquet_msislo4d7fcgdfh2pyoxvxjkdu\n",
" OBJECTID int64\n",
" ST string\n",
" STATE string\n",
" ST_ABBR string\n",
" STCNTY string\n",
" COUNTY string\n",
" FIPS string\n",
" LOCATION string\n",
" AREA_SQMI float64\n",
" E_TOTPOP int32\n",
" M_TOTPOP int32\n",
" E_HU int32\n",
" M_HU int32\n",
" E_HH int32\n",
" M_HH int32\n",
" E_POV150 int32\n",
" M_POV150 int32\n",
" E_UNEMP int32\n",
" M_UNEMP int32\n",
" E_HBURD int32\n",
" M_HBURD int32\n",
" E_NOHSDP int32\n",
" M_NOHSDP int32\n",
" E_UNINSUR int32\n",
" M_UNINSUR int32\n",
" E_AGE65 int32\n",
" M_AGE65 int32\n",
" E_AGE17 int32\n",
" M_AGE17 int32\n",
" E_DISABL int32\n",
" M_DISABL int32\n",
" E_SNGPNT int32\n",
" M_SNGPNT int32\n",
" E_LIMENG int32\n",
" M_LIMENG int32\n",
" E_MINRTY int32\n",
" M_MINRTY int32\n",
" E_MUNIT int32\n",
" M_MUNIT int32\n",
" E_MOBILE int32\n",
" M_MOBILE int32\n",
" E_CROWD int32\n",
" M_CROWD int32\n",
" E_NOVEH int32\n",
" M_NOVEH int32\n",
" E_GROUPQ int32\n",
" M_GROUPQ int32\n",
" EP_POV150 float64\n",
" MP_POV150 float64\n",
" EP_UNEMP float64\n",
" MP_UNEMP float64\n",
" EP_HBURD float64\n",
" MP_HBURD float64\n",
" EP_NOHSDP float64\n",
" MP_NOHSDP float64\n",
" EP_UNINSUR float64\n",
" MP_UNINSUR float64\n",
" EP_AGE65 float64\n",
" MP_AGE65 float64\n",
" EP_AGE17 float64\n",
" MP_AGE17 float64\n",
" EP_DISABL float64\n",
" MP_DISABL float64\n",
" EP_SNGPNT float64\n",
" MP_SNGPNT float64\n",
" EP_LIMENG float64\n",
" MP_LIMENG float64\n",
" EP_MINRTY float64\n",
" MP_MINRTY float64\n",
" EP_MUNIT float64\n",
" MP_MUNIT float64\n",
" EP_MOBILE float64\n",
" MP_MOBILE float64\n",
" EP_CROWD float64\n",
" MP_CROWD float64\n",
" EP_NOVEH float64\n",
" MP_NOVEH float64\n",
" EP_GROUPQ float64\n",
" MP_GROUPQ float64\n",
" EPL_POV150 float64\n",
" EPL_UNEMP float64\n",
" EPL_HBURD float64\n",
" EPL_NOHSDP float64\n",
" EPL_UNINSUR float64\n",
" SPL_THEME1 float64\n",
" RPL_THEME1 float64\n",
" EPL_AGE65 float64\n",
" EPL_AGE17 float64\n",
" EPL_DISABL float64\n",
" EPL_SNGPNT float64\n",
" EPL_LIMENG float64\n",
" SPL_THEME2 float64\n",
" RPL_THEME2 float64\n",
" EPL_MINRTY float64\n",
" SPL_THEME3 float64\n",
" RPL_THEME3 float64\n",
" EPL_MUNIT float64\n",
" EPL_MOBILE float64\n",
" EPL_CROWD float64\n",
" EPL_NOVEH float64\n",
" EPL_GROUPQ float64\n",
" SPL_THEME4 float64\n",
" RPL_THEME4 float64\n",
" SPL_THEMES float64\n",
" RPL_THEMES float64\n",
" F_POV150 int16\n",
" F_UNEMP int16\n",
" F_HBURD int16\n",
" F_NOHSDP int16\n",
" F_UNINSUR int16\n",
" F_THEME1 int16\n",
" F_AGE65 int16\n",
" F_AGE17 int16\n",
" F_DISABL int16\n",
" F_SNGPNT int16\n",
" F_LIMENG int16\n",
" F_THEME2 int16\n",
" F_MINRTY int16\n",
" F_THEME3 int16\n",
" F_MUNIT int16\n",
" F_MOBILE int16\n",
" F_CROWD int16\n",
" F_NOVEH int16\n",
" F_GROUPQ int16\n",
" F_THEME4 int16\n",
" F_TOTAL int16\n",
" E_DAYPOP int32\n",
" E_NOINT int32\n",
" M_NOINT int32\n",
" E_AFAM int32\n",
" M_AFAM int32\n",
" E_HISP int32\n",
" M_HISP int32\n",
" E_ASIAN int32\n",
" M_ASIAN int32\n",
" E_AIAN int32\n",
" M_AIAN int32\n",
" E_NHPI int32\n",
" M_NHPI int32\n",
" E_TWOMORE int32\n",
" M_TWOMORE int32\n",
" E_OTHERRACE int32\n",
" M_OTHERRACE int32\n",
" EP_NOINT float64\n",
" MP_NOINT float64\n",
" EP_AFAM float64\n",
" MP_AFAM float64\n",
" EP_HISP float64\n",
" MP_HISP float64\n",
" EP_ASIAN float64\n",
" MP_ASIAN float64\n",
" EP_AIAN float64\n",
" MP_AIAN float64\n",
" EP_NHPI float64\n",
" MP_NHPI float64\n",
" EP_TWOMORE float64\n",
" MP_TWOMORE float64\n",
" EP_OTHERRACE float64\n",
" MP_OTHERRACE float64\n",
" Shape_Length float64\n",
" Shape_Area float64\n",
" geom geospatial:geometry\n",
" area float64\n",
" gbifid string\n",
" datasetkey string\n",
" occurrenceid string\n",
" kingdom string\n",
" phylum string\n",
" class string\n",
" order string\n",
" family string\n",
" genus string\n",
" species string\n",
" infraspecificepithet string\n",
" taxonrank string\n",
" scientificname string\n",
" verbatimscientificname string\n",
" verbatimscientificnameauthorship string\n",
" countrycode string\n",
" locality string\n",
" stateprovince string\n",
" occurrencestatus string\n",
" individualcount int32\n",
" publishingorgkey string\n",
" decimallatitude float64\n",
" decimallongitude float64\n",
" coordinateuncertaintyinmeters float64\n",
" coordinateprecision float64\n",
" elevation float64\n",
" elevationaccuracy float64\n",
" depth float64\n",
" depthaccuracy float64\n",
" eventdate timestamp(6)\n",
" day int32\n",
" month int32\n",
" year int32\n",
" taxonkey int32\n",
" specieskey int32\n",
" basisofrecord string\n",
" institutioncode string\n",
" collectioncode string\n",
" catalognumber string\n",
" recordnumber string\n",
" identifiedby array<string>\n",
" dateidentified timestamp(6)\n",
" license string\n",
" rightsholder string\n",
" recordedby array<string>\n",
" typestatus array<string>\n",
" establishmentmeans string\n",
" lastinterpreted timestamp(6)\n",
" mediatype array<string>\n",
" issue array<string>\n",
" geom_right geospatial:geometry\n",
" h0 string\n",
" h1 string\n",
" h2 string\n",
" h3 string\n",
" h4 string\n",
" h5 string\n",
" h6 string\n",
" h7 string\n",
" h8 string\n",
" h9 string\n",
" h10 string\n",
" h11 string"
]
},
"execution_count": 43,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"gbif_usa"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a6ce4d65-6f93-4725-87fa-29bf413398ad",
"metadata": {},
"outputs": [],
"source": [
"The four summary theme ranking variables, detailed in the Data Dictionary below, are:\n",
"• Socioeconomic Status - RPL_THEME1\n",
"• Household Characteristics - RPL_THEME2\n",
"• Racial & Ethnic Minority Status - RPL_THEME3\n",
"• Housing Type & Transportation - RPL_THEME4 "
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "d2e85529-348b-4f33-b09d-f8424299dc8d",
"metadata": {},
"outputs": [],
"source": [
"import seaborn.objects as so\n",
"\n",
"#df = gbif_usa.group_by(_.FIPS).agg(n = _.count().log(), svi = _.RPL_THEMES.mean()).execute()\n",
"df = gbif_usa.group_by(_.STATE, _.COUNTY).agg(n = _.count() / _.Shape_Area.sum(), svi1 = _.RPL_THEME1.mean(), svi3 = _.RPL_THEME3.mean()).execute()\n",
"\n",
"so.Plot(df, x = \"svi1\", y=\"n\", color = \"svi3\").add(so.Dots()).scale(y=\"log\")"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "9030d3dc-e2fb-41b7-8fe9-80ee76739b78",
"metadata": {},
"outputs": [],
"source": [
"import altair as alt\n",
"\n",
"alt.Chart(df).mark_point().encode(\n",
" x='svi1',\n",
" y='n',\n",
" color='svi3',\n",
" tooltip = ['STATE', 'COUNTY']\n",
")\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"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": "3.12.8"
}
},
"nbformat": 4,
"nbformat_minor": 5
}
|