publicdata/j40-cejst-2
1
0
Fork 0
mirror of https://github.com/DOI-DO/j40-cejst-2.git synced 2025-08-21 04:21:41 -07:00
Code Issues Projects Releases Packages Wiki Activity Actions

"CalEnviroScreen for the US" example score (#204)

Browse source
This commit is contained in:
Lucas Merrill Brown 2021-06-22 17:09:53 -07:00 • committed by GitHub
commit f542d0e675
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
5 changed files with 365 additions and 1093 deletions
Download patch file Download diff file Expand all files Collapse all files

114
score/ipython/ejscreen_etl.ipynb
View file

@ -2,7 +2,7 @@
"cells": [
{
"cell_type": "code",
"execution_count": 1,
"execution_count": null,
"id": "20aa3891",
"metadata": {},
"outputs": [],
@ -21,21 +21,15 @@
},
{
"cell_type": "code",
"execution_count": 3,
"execution_count": null,
"id": "67a58c24",
"metadata": {},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"c:\\opt\\justice40-tool\\score\\venv\\lib\\site-packages\\urllib3\\connectionpool.py:1013: InsecureRequestWarning: Unverified HTTPS request is being made to host 'gaftp.epa.gov'. Adding certificate verification is strongly advised. See: https://urllib3.readthedocs.io/en/latest/advanced-usage.html#ssl-warnings\n",
" warnings.warn(\n"
]
}
],
"outputs": [],
"source": [
"download = requests.get(\"https://gaftp.epa.gov/EJSCREEN/2020/EJSCREEN_2020_StatePctile.csv.zip\", verify=False)\n",
"download = requests.get(\n",
" \"https://gaftp.epa.gov/EJSCREEN/2020/EJSCREEN_2020_StatePctile.csv.zip\",\n",
" verify=False,\n",
")\n",
"file_contents = download.content\n",
"zip_file_path = data_path / \"tmp\"\n",
"zip_file = open(zip_file_path / \"downloaded.zip\", \"wb\")\n",
@ -45,7 +39,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": null,
"id": "cc3fb9ec",
"metadata": {},
"outputs": [],
@ -57,101 +51,33 @@
},
{
"cell_type": "code",
"execution_count": 5,
"execution_count": null,
"id": "b25738bb",
"metadata": {
"scrolled": true
},
"outputs": [],
"source": [
"df = pd.read_csv(ejscreen_csv, dtype={'ID': 'string'}, low_memory=False)"
"df = pd.read_csv(ejscreen_csv, dtype={\"ID\": \"string\"}, low_memory=False)"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "e6994f2d",
"metadata": {},
"outputs": [],
"source": [
"df = df[[\"ID\", \"ACSTOTPOP\", \"LESSHSPCT\", \"LOWINCPCT\"]]"
]
},
{
"cell_type": "code",
"execution_count": 7,
"execution_count": null,
"id": "9fa2077a",
"metadata": {},
"outputs": [],
"source": [
"# write nationwide csv\n",
"df.to_csv(csv_path / f\"usa.csv\", index = False)"
"df.to_csv(csv_path / f\"usa.csv\", index=False)"
]
},
{
"cell_type": "code",
"execution_count": 8,
"execution_count": null,
"id": "5e5cc12a",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Generating data01 csv\n",
"Generating data02 csv\n",
"Generating data04 csv\n",
"Generating data05 csv\n",
"Generating data06 csv\n",
"Generating data08 csv\n",
"Generating data09 csv\n",
"Generating data10 csv\n",
"Generating data11 csv\n",
"Generating data12 csv\n",
"Generating data13 csv\n",
"Generating data15 csv\n",
"Generating data16 csv\n",
"Generating data17 csv\n",
"Generating data18 csv\n",
"Generating data19 csv\n",
"Generating data20 csv\n",
"Generating data21 csv\n",
"Generating data22 csv\n",
"Generating data23 csv\n",
"Generating data24 csv\n",
"Generating data25 csv\n",
"Generating data26 csv\n",
"Generating data27 csv\n",
"Generating data28 csv\n",
"Generating data29 csv\n",
"Generating data30 csv\n",
"Generating data31 csv\n",
"Generating data32 csv\n",
"Generating data33 csv\n",
"Generating data34 csv\n",
"Generating data35 csv\n",
"Generating data36 csv\n",
"Generating data37 csv\n",
"Generating data38 csv\n",
"Generating data39 csv\n",
"Generating data40 csv\n",
"Generating data41 csv\n",
"Generating data42 csv\n",
"Generating data44 csv\n",
"Generating data45 csv\n",
"Generating data46 csv\n",
"Generating data47 csv\n",
"Generating data48 csv\n",
"Generating data49 csv\n",
"Generating data50 csv\n",
"Generating data51 csv\n",
"Generating data53 csv\n",
"Generating data54 csv\n",
"Generating data55 csv\n",
"Generating data56 csv\n"
]
}
],
"outputs": [],
"source": [
"# write per state csvs\n",
"with open(fips_csv_path) as csv_file:\n",
@ -166,16 +92,8 @@
" print(f\"Generating data{fips} csv\")\n",
" df1 = df[df.ID.str[:2] == fips]\n",
" # we need to name the file data01.csv for ogr2ogr csv merge to work\n",
" df1.to_csv(csv_path / f\"data{fips}.csv\", index = False)"
" df1.to_csv(csv_path / f\"data{fips}.csv\", index=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "2674fb20",
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
@ -194,7 +112,7 @@
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.0"
"version": "3.7.1"
}
},
"nbformat": 4,