mirror of
https://github.com/DOI-DO/j40-cejst-2.git
synced 2025-07-26 19:11:16 -07:00
Score F, testing methodology (#510)
* fixing dependency issue * fixing more dependencies * including fraction of state AMI * wip * nitpick whitespace * etl working now * wip on scoring * fix rename error * reducing metrics * fixing score f * fixing readme * adding dependency * passing tests; * linting/black * removing unnecessary sample * fixing error * adding verify flag on etl/base Co-authored-by: Jorge Escobar <jorge.e.escobar@omb.eop.gov>
This commit is contained in:
Lucas Merrill Brown
GitHub
parent
043ed983ea
commit
65ceb7900f
23 changed files with 557 additions and 153 deletions
|
|
@ -3,9 +3,6 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "0491828b",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"import pandas as pd\n",
|
||||
"import censusdata\n",
|
||||
|
|
@ -32,30 +29,26 @@
|
|||
"# Some display settings to make pandas outputs more readable.\n",
|
||||
"pd.set_option(\"display.expand_frame_repr\", False)\n",
|
||||
"pd.set_option(\"display.precision\", 2)"
|
||||
]
|
||||
],
|
||||
"outputs": [],
|
||||
"metadata": {}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "654f25a1",
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"# Following the tutorial at https://jtleider.github.io/censusdata/example1.html.\n",
|
||||
"# Full list of fields is at https://www2.census.gov/programs-surveys/acs/summary_file/2019/documentation/user_tools/ACS2019_Table_Shells.xlsx\n",
|
||||
"censusdata.printtable(censusdata.censustable(src=\"acs5\", year=ACS_YEAR, table=\"B19013\"))"
|
||||
]
|
||||
],
|
||||
"outputs": [],
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8999cea4",
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"def fips_from_censusdata_censusgeo(censusgeo: censusdata.censusgeo) -> str:\n",
|
||||
" \"\"\"Create a FIPS code from the proprietary censusgeo index.\"\"\"\n",
|
||||
|
|
@ -85,31 +78,33 @@
|
|||
"df[GEOID_FIELD_NAME] = df.index.to_series().apply(func=fips_from_censusdata_censusgeo)\n",
|
||||
"\n",
|
||||
"df.head()"
|
||||
]
|
||||
],
|
||||
"outputs": [],
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "2a269bb1",
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"columns_to_include = [\"GEOID2\", \"Median household income (State)\"]\n",
|
||||
"\n",
|
||||
"df.rename(columns={\"GEOID10\": \"GEOID2\", \"B19013_001E\": \"Median household income (State)\"}, inplace=True)\n",
|
||||
"\n",
|
||||
"df[columns_to_include].to_csv(path_or_buf= \"/Users/lucas/Documents/usds/repos/justice40-tool/data/data-pipeline/data_pipeline/data/needs_to_be_moved_to_s3/2014_to_2019_state_median_income.csv\", index=False)"
|
||||
]
|
||||
"# df[columns_to_include].to_csv(path_or_buf= \"/Users/lucas/Documents/usds/repos/justice40-tool/data/data-pipeline/data_pipeline/data/needs_to_be_moved_to_s3/2014_to_2019_state_median_income.csv\", index=False)"
|
||||
],
|
||||
"outputs": [],
|
||||
"metadata": {
|
||||
"scrolled": true
|
||||
}
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "91932af5",
|
||||
"metadata": {},
|
||||
"source": [],
|
||||
"outputs": [],
|
||||
"source": []
|
||||
"metadata": {}
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
|
@ -133,4 +128,4 @@
|
|||
},
|
||||
"nbformat": 4,
|
||||
"nbformat_minor": 5
|
||||
}
|
||||
}
|
||||
|
|
@ -28,7 +28,7 @@
|
|||
"from datetime import datetime\n",
|
||||
"from tqdm.notebook import tqdm_notebook\n",
|
||||
"\n",
|
||||
"module_path = os.path.abspath(os.path.join(\"..\"))\n",
|
||||
"module_path = os.path.abspath(os.path.join(\"../..\"))\n",
|
||||
"if module_path not in sys.path:\n",
|
||||
" sys.path.append(module_path)\n",
|
||||
"\n",
|
||||
|
|
@ -215,7 +215,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "8b795fb4",
|
||||
"id": "274f6bc6",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -234,6 +234,21 @@
|
|||
"# (`census_tract_indices`).\n",
|
||||
"census_block_group_indices = [\n",
|
||||
" Index(\n",
|
||||
" method_name=\"Score F\",\n",
|
||||
" priority_communities_field=\"Score F (communities)\",\n",
|
||||
" other_census_tract_fields_to_keep=[],\n",
|
||||
" ),\n",
|
||||
" Index(\n",
|
||||
" method_name=\"Score F (socioeconomic only)\",\n",
|
||||
" priority_communities_field=\"Meets socioeconomic criteria\",\n",
|
||||
" other_census_tract_fields_to_keep=[],\n",
|
||||
" ),\n",
|
||||
" Index(\n",
|
||||
" method_name=\"Score F (burden only)\",\n",
|
||||
" priority_communities_field=\"Meets burden criteria\",\n",
|
||||
" other_census_tract_fields_to_keep=[],\n",
|
||||
" ),\n",
|
||||
" Index(\n",
|
||||
" method_name=\"Score A\",\n",
|
||||
" priority_communities_field=\"Score A (top 25th percentile)\",\n",
|
||||
" other_census_tract_fields_to_keep=[],\n",
|
||||
|
|
@ -253,21 +268,21 @@
|
|||
" priority_communities_field=\"Score D (top 25th percentile)\",\n",
|
||||
" other_census_tract_fields_to_keep=[],\n",
|
||||
" ),\n",
|
||||
" Index(\n",
|
||||
" method_name=\"Score D (30th percentile)\",\n",
|
||||
" priority_communities_field=\"Score D (top 30th percentile)\",\n",
|
||||
" other_census_tract_fields_to_keep=[],\n",
|
||||
" ),\n",
|
||||
" Index(\n",
|
||||
" method_name=\"Score D (35th percentile)\",\n",
|
||||
" priority_communities_field=\"Score D (top 35th percentile)\",\n",
|
||||
" other_census_tract_fields_to_keep=[],\n",
|
||||
" ),\n",
|
||||
" Index(\n",
|
||||
" method_name=\"Score D (40th percentile)\",\n",
|
||||
" priority_communities_field=\"Score D (top 40th percentile)\",\n",
|
||||
" other_census_tract_fields_to_keep=[],\n",
|
||||
" ),\n",
|
||||
"# Index(\n",
|
||||
"# method_name=\"Score D (30th percentile)\",\n",
|
||||
"# priority_communities_field=\"Score D (top 30th percentile)\",\n",
|
||||
"# other_census_tract_fields_to_keep=[],\n",
|
||||
"# ),\n",
|
||||
"# Index(\n",
|
||||
"# method_name=\"Score D (35th percentile)\",\n",
|
||||
"# priority_communities_field=\"Score D (top 35th percentile)\",\n",
|
||||
"# other_census_tract_fields_to_keep=[],\n",
|
||||
"# ),\n",
|
||||
"# Index(\n",
|
||||
"# method_name=\"Score D (40th percentile)\",\n",
|
||||
"# priority_communities_field=\"Score D (top 40th percentile)\",\n",
|
||||
"# other_census_tract_fields_to_keep=[],\n",
|
||||
"# ),\n",
|
||||
" Index(\n",
|
||||
" method_name=\"Poverty\",\n",
|
||||
" priority_communities_field=\"Poverty (Less than 200% of federal poverty line) (top 25th percentile)\",\n",
|
||||
|
|
@ -534,7 +549,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "d7acf80d",
|
||||
"id": "eeb9699d",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -682,7 +697,7 @@
|
|||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "777a4623",
|
||||
"id": "4f44426c",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
|
|
@ -1140,14 +1155,6 @@
|
|||
"\n",
|
||||
"print(file_paths)"
|
||||
]
|
||||
},
|
||||
{
|
||||
"cell_type": "code",
|
||||
"execution_count": null,
|
||||
"id": "e679502a",
|
||||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": []
|
||||
}
|
||||
],
|
||||
"metadata": {
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue