mirror of
https://github.com/DOI-DO/j40-cejst-2.git
synced 2025-07-29 19:21:16 -07:00
Adding persistent poverty tracts (#738)
* persistent poverty working * fixing left-padding * running black and adding persistent poverty to comp tool * fixing bug * running black and fixing linter * fixing linter * fixing linter error
This commit is contained in:
Lucas Merrill Brown
GitHub
parent
d1ced6d584
commit
b1a4d26be8
15 changed files with 518 additions and 201 deletions
|
|
@ -101,17 +101,25 @@
|
|||
"outputs": [],
|
||||
"source": [
|
||||
"geocorr_urban_rural_map = pd.read_csv(\n",
|
||||
" os.path.join(GEOCORR_DATA_DIR, 'geocorr2014_2125804280.csv'),\n",
|
||||
" encoding = \"ISO-8859-1\",\n",
|
||||
" os.path.join(GEOCORR_DATA_DIR, \"geocorr2014_2125804280.csv\"),\n",
|
||||
" encoding=\"ISO-8859-1\",\n",
|
||||
" skiprows=[1],\n",
|
||||
" dtype='str',\n",
|
||||
" dtype=\"str\",\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"geocorr_urban_rural_map['pop10'] = pd.to_numeric(geocorr_urban_rural_map['pop10'])\n",
|
||||
"geocorr_urban_rural_map['afact'] = pd.to_numeric(geocorr_urban_rural_map['afact'])\n",
|
||||
"geocorr_urban_rural_map[\"pop10\"] = pd.to_numeric(\n",
|
||||
" geocorr_urban_rural_map[\"pop10\"]\n",
|
||||
")\n",
|
||||
"geocorr_urban_rural_map[\"afact\"] = pd.to_numeric(\n",
|
||||
" geocorr_urban_rural_map[\"afact\"]\n",
|
||||
")\n",
|
||||
"\n",
|
||||
"geocorr_urban_rural_map[GEOID_TRACT_FIELD_NAME] = geocorr_urban_rural_map['county'] + geocorr_urban_rural_map['tract'] # + geocorr_urban_rural_map['bg']\n",
|
||||
"geocorr_urban_rural_map[GEOID_TRACT_FIELD_NAME] = geocorr_urban_rural_map[GEOID_TRACT_FIELD_NAME].str.replace('.', '', regex=False)"
|
||||
"geocorr_urban_rural_map[GEOID_TRACT_FIELD_NAME] = (\n",
|
||||
" geocorr_urban_rural_map[\"county\"] + geocorr_urban_rural_map[\"tract\"]\n",
|
||||
") # + geocorr_urban_rural_map['bg']\n",
|
||||
"geocorr_urban_rural_map[GEOID_TRACT_FIELD_NAME] = geocorr_urban_rural_map[\n",
|
||||
" GEOID_TRACT_FIELD_NAME\n",
|
||||
"].str.replace(\".\", \"\", regex=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -139,15 +147,9 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"geocorr_urban_rural_map = geocorr_urban_rural_map[[\n",
|
||||
" GEOID_TRACT_FIELD_NAME,\n",
|
||||
" 'ur',\n",
|
||||
" 'ua',\n",
|
||||
" 'cntyname',\n",
|
||||
" 'uaname',\n",
|
||||
" 'pop10',\n",
|
||||
" 'afact'\n",
|
||||
"]]"
|
||||
"geocorr_urban_rural_map = geocorr_urban_rural_map[\n",
|
||||
" [GEOID_TRACT_FIELD_NAME, \"ur\", \"ua\", \"cntyname\", \"uaname\", \"pop10\", \"afact\"]\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -165,7 +167,9 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"geocorr_urban_rural_map.groupby([GEOID_TRACT_FIELD_NAME, 'ur', 'ua'], dropna=False).size().sort_values(ascending=False)"
|
||||
"geocorr_urban_rural_map.groupby(\n",
|
||||
" [GEOID_TRACT_FIELD_NAME, \"ur\", \"ua\"], dropna=False\n",
|
||||
").size().sort_values(ascending=False)"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -175,7 +179,9 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"geocorr_urban_rural_map.loc[geocorr_urban_rural_map[GEOID_TRACT_FIELD_NAME] == '36117020302']"
|
||||
"geocorr_urban_rural_map.loc[\n",
|
||||
" geocorr_urban_rural_map[GEOID_TRACT_FIELD_NAME] == \"36117020302\"\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -185,8 +191,12 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"total_geo_population = geocorr_urban_rural_map.groupby(GEOID_TRACT_FIELD_NAME).agg({'pop10': np.sum}).reset_index()\n",
|
||||
"total_geo_population.rename(columns={'pop10': 'total_population'}, inplace=True)\n",
|
||||
"total_geo_population = (\n",
|
||||
" geocorr_urban_rural_map.groupby(GEOID_TRACT_FIELD_NAME)\n",
|
||||
" .agg({\"pop10\": np.sum})\n",
|
||||
" .reset_index()\n",
|
||||
")\n",
|
||||
"total_geo_population.rename(columns={\"pop10\": \"total_population\"}, inplace=True)\n",
|
||||
"total_geo_population.head()"
|
||||
]
|
||||
},
|
||||
|
|
@ -197,8 +207,16 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"geocorr_urban_rural_with_total_pop_map = geocorr_urban_rural_map.groupby([GEOID_TRACT_FIELD_NAME, 'ur']).agg({'pop10': np.sum}).reset_index()\n",
|
||||
"geocorr_urban_rural_with_total_pop_map = geocorr_urban_rural_with_total_pop_map.merge(total_geo_population, how='inner', on=GEOID_TRACT_FIELD_NAME)\n",
|
||||
"geocorr_urban_rural_with_total_pop_map = (\n",
|
||||
" geocorr_urban_rural_map.groupby([GEOID_TRACT_FIELD_NAME, \"ur\"])\n",
|
||||
" .agg({\"pop10\": np.sum})\n",
|
||||
" .reset_index()\n",
|
||||
")\n",
|
||||
"geocorr_urban_rural_with_total_pop_map = (\n",
|
||||
" geocorr_urban_rural_with_total_pop_map.merge(\n",
|
||||
" total_geo_population, how=\"inner\", on=GEOID_TRACT_FIELD_NAME\n",
|
||||
" )\n",
|
||||
")\n",
|
||||
"geocorr_urban_rural_with_total_pop_map.head()"
|
||||
]
|
||||
},
|
||||
|
|
@ -209,7 +227,10 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"geocorr_urban_rural_with_total_pop_map['afact'] = geocorr_urban_rural_with_total_pop_map['pop10'] / geocorr_urban_rural_with_total_pop_map['total_population']"
|
||||
"geocorr_urban_rural_with_total_pop_map[\"afact\"] = (\n",
|
||||
" geocorr_urban_rural_with_total_pop_map[\"pop10\"]\n",
|
||||
" / geocorr_urban_rural_with_total_pop_map[\"total_population\"]\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -229,7 +250,10 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"geocorr_urban_rural_with_total_pop_map.loc[geocorr_urban_rural_with_total_pop_map[GEOID_TRACT_FIELD_NAME] == '01001020200']"
|
||||
"geocorr_urban_rural_with_total_pop_map.loc[\n",
|
||||
" geocorr_urban_rural_with_total_pop_map[GEOID_TRACT_FIELD_NAME]\n",
|
||||
" == \"01001020200\"\n",
|
||||
"]"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -239,12 +263,16 @@
|
|||
"metadata": {},
|
||||
"outputs": [],
|
||||
"source": [
|
||||
"urban_rural_map = geocorr_urban_rural_with_total_pop_map.pivot(index=GEOID_TRACT_FIELD_NAME, columns='ur', values=['pop10', 'afact'])\n",
|
||||
"urban_rural_map.columns = ['_'.join(col).strip() for col in urban_rural_map.columns.values]\n",
|
||||
"urban_rural_map = geocorr_urban_rural_with_total_pop_map.pivot(\n",
|
||||
" index=GEOID_TRACT_FIELD_NAME, columns=\"ur\", values=[\"pop10\", \"afact\"]\n",
|
||||
")\n",
|
||||
"urban_rural_map.columns = [\n",
|
||||
" \"_\".join(col).strip() for col in urban_rural_map.columns.values\n",
|
||||
"]\n",
|
||||
"urban_rural_map.reset_index(inplace=True)\n",
|
||||
"urban_rural_map['urban_heuristic_flag'] = 0\n",
|
||||
"mask = urban_rural_map['afact_U'] >= 0.5\n",
|
||||
"urban_rural_map.loc[mask, 'urban_heuristic_flag'] = 1"
|
||||
"urban_rural_map[\"urban_heuristic_flag\"] = 0\n",
|
||||
"mask = urban_rural_map[\"afact_U\"] >= 0.5\n",
|
||||
"urban_rural_map.loc[mask, \"urban_heuristic_flag\"] = 1"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
@ -256,12 +284,13 @@
|
|||
"source": [
|
||||
"urban_rural_map.rename(\n",
|
||||
" columns={\n",
|
||||
" 'pop10_R': 'population_in_rural_areas',\n",
|
||||
" 'pop10_U': 'population_in_urban_areas',\n",
|
||||
" 'afact_R': 'perc_population_in_rural_areas',\n",
|
||||
" 'afact_U': 'perc_population_in_urban_areas',\n",
|
||||
" }, \n",
|
||||
" inplace=True)"
|
||||
" \"pop10_R\": \"population_in_rural_areas\",\n",
|
||||
" \"pop10_U\": \"population_in_urban_areas\",\n",
|
||||
" \"afact_R\": \"perc_population_in_rural_areas\",\n",
|
||||
" \"afact_U\": \"perc_population_in_urban_areas\",\n",
|
||||
" },\n",
|
||||
" inplace=True,\n",
|
||||
")"
|
||||
]
|
||||
},
|
||||
{
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue