From d0822726b8008f8d961e92187f87e03b25f87d6d Mon Sep 17 00:00:00 2001
From: PengnanZ <57605178+PengnanZ@users.noreply.github.com>
Date: Fri, 25 Feb 2022 15:22:56 -0500
Subject: [PATCH] Add files via upload
---
.../Censusdata_tutorial.ipynb | 541 ++++++++++++++++++
censusdata_package_tutorial/Help_Functions.py | 29 +
censusdata_package_tutorial/README.md | 3 +
3 files changed, 573 insertions(+)
create mode 100644 censusdata_package_tutorial/Censusdata_tutorial.ipynb
create mode 100644 censusdata_package_tutorial/Help_Functions.py
create mode 100644 censusdata_package_tutorial/README.md
diff --git a/censusdata_package_tutorial/Censusdata_tutorial.ipynb b/censusdata_package_tutorial/Censusdata_tutorial.ipynb
new file mode 100644
index 0000000..1d52b95
--- /dev/null
+++ b/censusdata_package_tutorial/Censusdata_tutorial.ipynb
@@ -0,0 +1,541 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "id": "7a42b048",
+ "metadata": {},
+ "source": [
+ "# U.S. Census Data Tutorial"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "319735dc",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "#!pip install censusdata"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "7baf9942",
+ "metadata": {},
+ "source": [
+ "If censusdata package was not in your enviroment, make sure to uncommond above line to pip it.\n",
+ "\n",
+ "Reference of the [CensusData library](https://jtleider.github.io/censusdata/index.html)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "id": "83acab08",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "import re\n",
+ "import numpy as np\n",
+ "import censusdata"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "04dc2a46",
+ "metadata": {},
+ "source": [
+ "### Main Methods\n",
+ "[CensusData API Documentation](https://jtleider.github.io/censusdata/api.html)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 2,
+ "id": "333e3815",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "# Search for ACS 2015-2019 5-year estimate variables where the concept \n",
+ "# includes the text 'population'.\n",
+ "sample = censusdata.search('acs5', 2019, 'concept', \n",
+ " lambda value: re.search('population', value, re.IGNORECASE))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "cb0b1ea5",
+ "metadata": {},
+ "source": [
+ "**Parameters:**\t\n",
+ "* src (str) – Census data source: ```‘acs1’``` for **ACS 1-year estimates**, ```‘acs5’``` for **ACS 5-year estimates**, ```‘acs3’``` for **ACS 3-year estimates**, ```‘acsse’``` for **ACS 1-year supplemental estimates**, ```‘sf1’``` for **SF1 data**.\n",
+ "* year (int) – Year of data.\n",
+ "* field (str) – Field in which to search.\n",
+ "* criterion (str or function) – Search criterion. Either string to search for, or a function which will be passed the value of field and return True if a match and False otherwise.\n",
+ "* tabletype (str, optional) – Type of table from which variables are drawn (only applicable to ACS data). Options are ```‘detail’``` (detail tables), ```‘subject’``` (subject tables), ```‘profile’``` (data profile tables), ```‘cprofile’``` (comparison profile tables).\n",
+ "\n",
+ "**Returns:**\t\n",
+ "List of 3-tuples containing variable names, concepts, and labels matching the search criterion.\n",
+ "\n",
+ "**Return type:**\t\n",
+ "list"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 3,
+ "id": "4984d1b7",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "10765\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(len(sample))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "ede1fed8",
+ "metadata": {},
+ "source": [
+ "This would be the sample amount we get based on what we use to search. In this case, there are 10765 samples which are ACS 5-year estimates for 2019 include the text 'population'."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 5,
+ "id": "dbffaeca",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "('B01003_001E', 'TOTAL POPULATION', 'Estimate!!Total')\n"
+ ]
+ }
+ ],
+ "source": [
+ "print(sample[0])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "07ae53a2",
+ "metadata": {},
+ "source": [
+ "Let's use the first sample file as an example. Based on the result from above, the first sample is called: 'B01003_001E', which is a total population table under the parent table B01003. "
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "a97df25b",
+ "metadata": {},
+ "source": [
+ "After you know the parent table you're interested in you can use the ```printtable``` function to get a clean readout of all the subtables in order to check if there are other subtables we might interested about."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 6,
+ "id": "fe3d19e4",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Variable | Table | Label | Type \n",
+ "-------------------------------------------------------------------------------------------------------------------\n",
+ "B01003_001E | TOTAL POPULATION | !! Estimate Total | int \n",
+ "-------------------------------------------------------------------------------------------------------------------\n"
+ ]
+ }
+ ],
+ "source": [
+ "censusdata.printtable(censusdata.censustable('acs5', 2019, 'B01003'))"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "60ac12ee",
+ "metadata": {},
+ "source": [
+ "### Data download"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "d74c7914",
+ "metadata": {},
+ "source": [
+ "If you want download data based on some state, county etc. Start at **step 1**, if not start at **step 3**.\n",
+ "\n",
+ "**Step 1** If you want to download the data for some States, you need to find the geography code for it. And function ```geographies``` is build for that"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "501fec9c",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Summary level: 040, state:26\n"
+ ]
+ }
+ ],
+ "source": [
+ "states = censusdata.geographies(censusdata.censusgeo([('state', '*')]), 'acs5', 2019)\n",
+ "print(states['Michigan'])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "6de55a1a",
+ "metadata": {},
+ "source": [
+ "**Step 2** Also if you want it be county level you need do almost the same thing but by adding county after state. For example:"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "bb5ad44b",
+ "metadata": {},
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "Summary level: 050, state:26> county:163\n"
+ ]
+ }
+ ],
+ "source": [
+ "counties = censusdata.geographies(censusdata.censusgeo([('state', '26'), ('county', '*')]), 'acs5', 2019)\n",
+ "print(counties['Wayne County, Michigan'])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "e610da56",
+ "metadata": {},
+ "source": [
+ "**Step 3** Now, is time to download what you want. Example based on Michigan, Wayne County. If you don't have state and county code, leave that as ```'*'```."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 7,
+ "id": "d7dac8c6",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "data = censusdata.download('acs5', 2019, censusdata.censusgeo([('state', '26'),\n",
+ " ('county', '163'),\n",
+ " ('block group', '*')]),\n",
+ " ['B01003_001E'])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "d19c7015",
+ "metadata": {},
+ "source": [
+ "And this is the length of the data we get."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 8,
+ "id": "44f953f0",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "1822"
+ ]
+ },
+ "execution_count": 8,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "len(data)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "57c5df9b",
+ "metadata": {},
+ "source": [
+ "### Extra (data formating, slice)\n",
+ "\n",
+ "This part are some extra step if you need, such as change the column name by using pandas, and slice it based on Census Tract by using ```census_cut``` in ```Help_Functions```."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 9,
+ "id": "1af89c80",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "column_name = ['TOTAL POPULATION']\n",
+ "data.columns = column_name"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 10,
+ "id": "02d0bfed",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "new_indices = []\n",
+ "for index in data.index.tolist():\n",
+ " new_indices.append(index)\n",
+ "\n",
+ "data.index = new_indices"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 11,
+ "id": "9a537ede",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>TOTAL POPULATION</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Block Group 0, Census Tract 9901, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:990100> block group:0</th>\n",
+ " <td>0</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Block Group 3, Census Tract 5104, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:510400> block group:3</th>\n",
+ " <td>238</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Block Group 5, Census Tract 5528, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:552800> block group:5</th>\n",
+ " <td>1546</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Block Group 3, Census Tract 5014, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:501400> block group:3</th>\n",
+ " <td>757</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Block Group 2, Census Tract 5044, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:504400> block group:2</th>\n",
+ " <td>427</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " TOTAL POPULATION\n",
+ "Block Group 0, Census Tract 9901, Wayne County,... 0\n",
+ "Block Group 3, Census Tract 5104, Wayne County,... 238\n",
+ "Block Group 5, Census Tract 5528, Wayne County,... 1546\n",
+ "Block Group 3, Census Tract 5014, Wayne County,... 757\n",
+ "Block Group 2, Census Tract 5044, Wayne County,... 427"
+ ]
+ },
+ "execution_count": 11,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "data.head()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "54f9165e",
+ "metadata": {},
+ "source": [
+ "### ```census_cut``` usage"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 12,
+ "id": "6f39eed2",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from Help_Functions import census_cut\n",
+ "import re"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "id": "229c79aa",
+ "metadata": {},
+ "source": [
+ "For example, we want the data for some areas based on Census Tracts are 5303, 5304, 5316, 5317"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 13,
+ "id": "58749d91",
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "Tracts = ['Census Tract 5303', 'Census Tract 5304','Census Tract 5316', 'Census Tract 5317']"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 14,
+ "id": "336301fe",
+ "metadata": {},
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "<div>\n",
+ "<style scoped>\n",
+ " .dataframe tbody tr th:only-of-type {\n",
+ " vertical-align: middle;\n",
+ " }\n",
+ "\n",
+ " .dataframe tbody tr th {\n",
+ " vertical-align: top;\n",
+ " }\n",
+ "\n",
+ " .dataframe thead th {\n",
+ " text-align: right;\n",
+ " }\n",
+ "</style>\n",
+ "<table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: right;\">\n",
+ " <th></th>\n",
+ " <th>TOTAL POPULATION</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <th>Block Group 2, Census Tract 5304, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:530400> block group:2</th>\n",
+ " <td>647</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Block Group 1, Census Tract 5304, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:530400> block group:1</th>\n",
+ " <td>398</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Block Group 3, Census Tract 5303, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:530300> block group:3</th>\n",
+ " <td>702</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Block Group 1, Census Tract 5303, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:530300> block group:1</th>\n",
+ " <td>281</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Block Group 2, Census Tract 5317, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:531700> block group:2</th>\n",
+ " <td>905</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Block Group 1, Census Tract 5317, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:531700> block group:1</th>\n",
+ " <td>648</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Block Group 2, Census Tract 5316, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:531600> block group:2</th>\n",
+ " <td>1094</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Block Group 1, Census Tract 5316, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:531600> block group:1</th>\n",
+ " <td>761</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <th>Block Group 2, Census Tract 5303, Wayne County, Michigan: Summary level: 150, state:26> county:163> tract:530300> block group:2</th>\n",
+ " <td>329</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table>\n",
+ "</div>"
+ ],
+ "text/plain": [
+ " TOTAL POPULATION\n",
+ "Block Group 2, Census Tract 5304, Wayne County,... 647\n",
+ "Block Group 1, Census Tract 5304, Wayne County,... 398\n",
+ "Block Group 3, Census Tract 5303, Wayne County,... 702\n",
+ "Block Group 1, Census Tract 5303, Wayne County,... 281\n",
+ "Block Group 2, Census Tract 5317, Wayne County,... 905\n",
+ "Block Group 1, Census Tract 5317, Wayne County,... 648\n",
+ "Block Group 2, Census Tract 5316, Wayne County,... 1094\n",
+ "Block Group 1, Census Tract 5316, Wayne County,... 761\n",
+ "Block Group 2, Census Tract 5303, Wayne County,... 329"
+ ]
+ },
+ "execution_count": 14,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "df = census_cut(Tracts, data)\n",
+ "df"
+ ]
+ }
+ ],
+ "metadata": {
+ "kernelspec": {
+ "display_name": "Python 3",
+ "language": "python",
+ "name": "python3"
+ },
+ "language_info": {
+ "codemirror_mode": {
+ "name": "ipython",
+ "version": 3
+ },
+ "file_extension": ".py",
+ "mimetype": "text/x-python",
+ "name": "python",
+ "nbconvert_exporter": "python",
+ "pygments_lexer": "ipython3",
+ "version": "3.8.8"
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/censusdata_package_tutorial/Help_Functions.py b/censusdata_package_tutorial/Help_Functions.py
new file mode 100644
index 0000000..baefe39
--- /dev/null
+++ b/censusdata_package_tutorial/Help_Functions.py
@@ -0,0 +1,29 @@
+# +
+import pandas as pd
+import numpy as np
+import re
+
+def census_cut(tracts, data):
+ '''
+ This function is use to cut based on Census Tract for data download by using censusdata package.
+
+ Parameters:
+ tracts: A list of string which are the Census Tract. Such as 'Census Tract 0000'.
+ data: Data download by using censusdata package.
+ Return:
+ result: A new set of data which only include the data based on Census Track.
+ '''
+ mask = []
+ for i in range(len(data.index)):
+ string = str(data.index[i])
+ check = True
+ for tract in tracts:
+ match = re.search(tract, string)
+ if match:
+ mask.append(True)
+ check = False
+ if check:
+ mask.append(False)
+ len(mask), len(data.index)
+ result = data[mask]
+ return result
diff --git a/censusdata_package_tutorial/README.md b/censusdata_package_tutorial/README.md
new file mode 100644
index 0000000..8a32031
--- /dev/null
+++ b/censusdata_package_tutorial/README.md
@@ -0,0 +1,3 @@
+# Censusdata_tutorial
+
+This is the Tutorial for how to use censusdata package. There also include an extra ```Help_Functions.py``` file which has a help function use for help slice the data download by using cens
--
GitLab