adding housing CSV to score

This commit is contained in:
lucasmbrown-usds 2021-06-23 12:26:45 -07:00
commit 678ab8c081
3 changed files with 165 additions and 12 deletions

View file

@ -7,11 +7,13 @@
"metadata": {},
"outputs": [],
"source": [
"# Before running this notebook, you must run the following notebooks:\n",
"# Before running this notebook, you must run the following notebooks (in any order):\n",
"# 1. `ejscreen_etl.ipynb`\n",
"# 2. `census_etl.ipynb`\n",
"# 3. `housing_and_transportation_etl.ipynb`\n",
"\n",
"import collections\n",
"import functools\n",
"from pathlib import Path\n",
"import pandas as pd\n",
"import csv\n",
@ -74,6 +76,25 @@
"census_df.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "144bdde2",
"metadata": {},
"outputs": [],
"source": [
"# Load housing and transportation data\n",
"housing_and_transportation_index_csv = (\n",
" data_path / \"dataset\" / \"housing_and_transportation_index\" / \"usa.csv\"\n",
")\n",
"housing_and_transportation_df = pd.read_csv(\n",
" housing_and_transportation_index_csv,\n",
" dtype={GEOID_FIELD_NAME: \"string\"},\n",
" low_memory=False,\n",
")\n",
"housing_and_transportation_df.head()"
]
},
{
"cell_type": "code",
"execution_count": null,
@ -81,11 +102,14 @@
"metadata": {},
"outputs": [],
"source": [
"# Join the two datasets\n",
"df = ejscreen_df.merge(\n",
" census_df,\n",
" how=\"left\",\n",
" on=GEOID_FIELD_NAME,\n",
"# Join all the data sources that use census block groups\n",
"dfs = [ejscreen_df, census_df, housing_and_transportation_df]\n",
"\n",
"df = functools.reduce(\n",
" lambda left, right: pd.merge(\n",
" left=left, right=right, on=GEOID_FIELD_NAME, how=\"outer\"\n",
" ),\n",
" dfs,\n",
")\n",
"\n",
"df.head()"
@ -195,6 +219,11 @@
" renamed_field=\"Unemployed Civilians (percent)\",\n",
" bucket=BUCKET_SOCIOECONOMIC,\n",
" ),\n",
" DataSet(\n",
" input_field=\"ht_ami\",\n",
" renamed_field=\"Housing + Transportation Costs % Income for the Regional Typical Household\",\n",
" bucket=BUCKET_SOCIOECONOMIC,\n",
" ),\n",
"]"
]
},