{ "cells": [ { "cell_type": "code", "execution_count": 8, "metadata": {}, "outputs": [], "source": [ "import sys\n", "import os\n", "import getpass\n", "user = getpass.getuser()\n", "DVUTILS_LOCAL_CLONE_PATH = f\"/Users/{user}/Documents/GitHub/dvutils\"\n", "sys.path.insert(0, DVUTILS_LOCAL_CLONE_PATH)\n", "from utils_io import *\n", "\n", "CENSUS_UTILS_PATH = f\"/Users/{user}/Documents/GitHub/hess_application/data_processing/6 - affh\"\n", "sys.path.insert(0, CENSUS_UTILS_PATH)\n", "import census\n", "\n", "import pandas as pd\n", "import geopandas as gpd" ] }, { "attachments": {}, "cell_type": "markdown", "metadata": {}, "source": [ "## Pull Census Data" ] }, { "cell_type": "code", "execution_count": 10, "metadata": {}, "outputs": [], "source": [ "census_api = getpass.getpass()" ] }, { "cell_type": "code", "execution_count": 34, "metadata": {}, "outputs": [], "source": [ "lep_df = census.pull_acs_5_year_est_data(\n", " census_api_key=census_api,\n", " acs_year=2021,\n", " tbl_prof_type=\"Detailed\",\n", " table_id=\"C16001\",\n", ")" ] }, { "cell_type": "code", "execution_count": 35, "metadata": {}, "outputs": [], "source": [ "# Rename columns to human-readable\n", "cols = {\n", " \"C16001_001E\": \"pop_5_years_over\",\n", " \"C16001_002E\": \"pop_english_only\",\n", " \"C16001_003E\": \"spanish_speaking_total\",\n", " \"C16001_004E\": \"spanish_english_vw\",\n", " \"C16001_005E\": \"spanish_english_lvw\",\n", " \"C16001_006E\": \"french_speaking_total\",\n", " \"C16001_007E\": \"french_english_vw\",\n", " \"C16001_008E\": \"french_english_lvw\",\n", " \"C16001_009E\": \"german_speaking_total\",\n", " \"C16001_010E\": \"german_english_vw\",\n", " \"C16001_011E\": \"german_english_lvw\",\n", " \"C16001_012E\": \"russian_speaking_total\",\n", " \"C16001_013E\": \"russian_english_vw\",\n", " \"C16001_014E\": \"russian_english_lvw\",\n", " \"C16001_015E\": \"other_indo_speaking_total\",\n", " \"C16001_016E\": \"other_indo_english_vw\",\n", " \"C16001_017E\": \"other_indo_english_lvw\",\n", " \"C16001_018E\": \"korean_speaking_total\",\n", " \"C16001_019E\": \"korean_english_vw\",\n", " \"C16001_020E\": \"korean_english_lvw\",\n", " \"C16001_021E\": \"chinese_speaking_total\",\n", " \"C16001_022E\": \"chinese_english_vw\",\n", " \"C16001_023E\": \"chinese_english_lvw\",\n", " \"C16001_024E\": \"vietnamese_speaking_total\",\n", " \"C16001_025E\": \"vietnamese_english_vw\",\n", " \"C16001_026E\": \"vietnamese_english_lvw\",\n", " \"C16001_027E\": \"tagalog_speaking_total\",\n", " \"C16001_028E\": \"tagalog_english_vw\",\n", " \"C16001_029E\": \"tagalog_english_lvw\",\n", " \"C16001_030E\": \"other_asian_speaking_total\",\n", " \"C16001_031E\": \"other_asian_english_vw\",\n", " \"C16001_032E\": \"other_asian_english_lvw\",\n", " \"C16001_033E\": \"arabic_speaking_total\",\n", " \"C16001_034E\": \"arabic_english_vw\",\n", " \"C16001_035E\": \"arabic_english_lvw\",\n", " \"C16001_036E\": \"other_unspec_speaking_total\",\n", " \"C16001_037E\": \"other_unspec_english_vw\",\n", " \"C16001_038E\": \"other_unspec_english_lvw\",\n", "}\n", "lep_df.rename(columns=cols, inplace=True)" ] }, { "cell_type": "code", "execution_count": 39, "metadata": {}, "outputs": [ { "data": { "text/html": [ "
\n", " | language_group | \n", "total_population | \n", "
---|---|---|
0 | \n", "pop_5_years_over | \n", "7322155 | \n", "
1 | \n", "pop_english_only | \n", "4200802 | \n", "
2 | \n", "spanish_english_lvw | \n", "463480 | \n", "
8 | \n", "chinese_english_lvw | \n", "297553 | \n", "
9 | \n", "vietnamese_english_lvw | \n", "103317 | \n", "
6 | \n", "other_indo_english_lvw | \n", "81386 | \n", "
10 | \n", "tagalog_english_lvw | \n", "80000 | \n", "
11 | \n", "other_asian_english_lvw | \n", "61642 | \n", "
7 | \n", "korean_english_lvw | \n", "27806 | \n", "
5 | \n", "russian_english_lvw | \n", "24751 | \n", "
13 | \n", "other_unspec_english_lvw | \n", "15123 | \n", "
12 | \n", "arabic_english_lvw | \n", "10003 | \n", "
3 | \n", "french_english_lvw | \n", "5488 | \n", "
4 | \n", "german_english_lvw | \n", "2759 | \n", "