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 2021-08-24 15:40:54 -05:00 committed by GitHub
commit 65ceb7900f
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
23 changed files with 557 additions and 153 deletions

View file

@ -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
}
}