def main():
pd.set_option('display.expand_frame_repr', False)
pd.set_option('display.precision', 2)
#to download we must identify the tables containing the variables interest to us.
#use ACS documentation, in particular Table Shells (https://www.census.gov/programs-surveys/acs/technical-documentation/summary-file-documentation.html)
#can use cenusdata.search to find given text patterns. We can limit the output to the relevenant variables
censusdata.search('acs5', 2015, 'label', 'unemploy')[160:170]
censusdata.search('acs5', 2015, 'concept', 'education')[730:790]
#using censusdata.printtable to show vars in table
censusdata.printtable(censusdata.censustable('acs5', 2015, 'B23025'))
censusdata.printtable(censusdata.censustable('acs5', 2015, 'B15003'))
#after getting relevant variables, we need to identify the geographies.
#we are going to get block groups in Cook County IL
#1. look for FIPS code
#2. find identifiers for all counties within IL to find Cook
#1
#print(censusdata.geographies(censusdata.censusgeo([('state','*')]), 'acs5', 2015)) #IL is 17
#2
#print(censusdata.geographies(censusdata.censusgeo([('state','17'), ('county', '*')]), 'acs5', 2015)) #cook is 031
#once we have identified variables and geos of interest,
#we can download the data using censusdata.download. compute variables for the percent unemployed and the percent w no hs degree
cook_cnty = censusdata.download('acs5', 2015, censusdata.censusgeo([('state','17'), ('county','031'), ('block group','*')]), ['B23025_003E', 'B23025_005E', 'B15003_001E', 'B15003_002E', 'B15003_003E','B15003_004E', 'B15003_005E', 'B15003_006E', 'B15003_007E', 'B15003_008E','B15003_009E', 'B15003_010E', 'B15003_011E', 'B15003_012E', 'B15003_013E','B15003_014E', 'B15003_015E', 'B15003_016E'])
cook_cnty['percent_unemployed'] = cook_cnty.B23025_005E / cook_cnty.B23025_003E * 100
cook_cnty['percent_nohs'] = (cook_cnty.B15003_002E + cook_cnty.B15003_003E + cook_cnty.B15003_004E + cook_cnty.B15003_005E + cook_cnty.B15003_006E + cook_cnty.B15003_007E + cook_cnty.B15003_008E + cook_cnty.B15003_009E + cook_cnty.B15003_010E + cook_cnty.B15003_011E + cook_cnty.B15003_012E + cook_cnty.B15003_013E + cook_cnty.B15003_014E + cook_cnty.B15003_015E + cook_cnty.B15003_016E) / cook_cnty.B15003_001E * 100
cook_cnty = cook_cnty[['percent_unemployed', 'percent_nohs']]
print(cook_cnty.describe())
#to show the 30 block groups in cook w highest rate of unemployment and the percent w no hs degree
print(cook_cnty.sort_values('percent_unemployed', ascending=False).head(30))
#show correlation
print(cook_cnty.corr())
censusdata.exportcsv('cook_data.csv', cook_cnty)
def test_printtable(self):
testtable = censusdata.censustable('acs5', 2015, 'B19013')
printedtable = io.StringIO()
sys.stdout = printedtable
censusdata.printtable(testtable)
sys.stdout = sys.__stdout__
self.assertEqual(
printedtable.getvalue(),
textwrap.dedent('''\
Variable | Table | Label | Type
-------------------------------------------------------------------------------------------------------------------
B19013_001E | MEDIAN HOUSEHOLD INCOME IN THE | !! Estimate Median household income in the past 12 month | int
-------------------------------------------------------------------------------------------------------------------
'''))
printedtable.close()
printedtable = io.StringIO()
sys.stdout = printedtable
censusdata.printtable(testtable, moe=True)
sys.stdout = sys.__stdout__
self.assertEqual(
printedtable.getvalue(),
textwrap.dedent('''\
Variable | Table | Label | Type
-------------------------------------------------------------------------------------------------------------------
B19013_001E | MEDIAN HOUSEHOLD INCOME IN THE | !! Estimate Median household income in the past 12 month | int
-------------------------------------------------------------------------------------------------------------------
'''))
printedtable.close()
def test_censustable_sf1(self):
expected = OrderedDict()
expected['P002001'] = {
'label': 'Total',
'concept': 'URBAN AND RURAL',
'predicateType': 'int'
}
expected['P002002'] = {
'label': 'Total!!Urban',
'concept': 'URBAN AND RURAL',
'predicateType': 'int'
}
expected['P002003'] = {
'label': 'Total!!Urban!!Inside urbanized areas',
'concept': 'URBAN AND RURAL',
'predicateType': 'int'
}
expected['P002004'] = {
'label': 'Total!!Urban!!Inside urban clusters',
'concept': 'URBAN AND RURAL',
'predicateType': 'int'
}
expected['P002005'] = {
'label': 'Total!!Rural',
'concept': 'URBAN AND RURAL',
'predicateType': 'int'
}
expected['P002006'] = {
'label': 'Total!!Not defined for this file',
'concept': 'URBAN AND RURAL',
'predicateType': 'int'
}
self.assertEqual(censusdata.censustable('sf1', 2010, 'P002'), expected)
def fetch_variables_and_labels(table, survey=survey, year=year):
results = censusdata.censustable(survey, year, table)
result_variables = []
result_labels = []
for (value, info) in results.items():
result_variables.append(value)
result_labels.append(re.sub(r".*[!!]", '', info['label']))
return (result_variables, result_labels)
def get_census_demo():
variables = [
i for tid in table_ids.keys()
for i in censusdata.censustable('acs5', 2015, tid)
]
data_dict = {}
for tid in table_ids.keys():
for (elt, v) in censusdata.censustable('acs5', 2015, tid).items():
data_dict[elt] = v['concept'] + ' | ' + v['label']
county_data = censusdata.download(
'acs5', 2015, censusdata.censusgeo([('state', '*'), ('county', '*')]),
variables)
def get_fips(county):
# concat state and county fips from string
state_fips = county.split('state:')[1].split('>')[0]
county_fips = county.split('> county:')[1]
return state_fips + county_fips
def get_county_names(county):
# extract county names from string
return str(county).split(':')[0]
county_data['county_name'] = [
get_county_names(str(x)) for x in county_data.index
]
county_data['county_id'] = [
get_fips(str(x)) if x else 'NaN' for x in county_data.index
]
county_data = county_data.reset_index(drop=True).set_index('county_id')
county_data.to_csv('./data/groomed_data/county_census.csv', index=False)
with open('./data/groomed_data/county_census_data_dict.json', 'w') as f:
f.write(json.dumps(data_dict))
return county_data
def test_censustable_acs5_2017_detail(self):
expected = OrderedDict()
expected['B23025_001E'] = {
'label': 'Estimate!!Total',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
expected['B23025_002E'] = {
'label': 'Estimate!!Total!!In labor force',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
expected['B23025_003E'] = {
'label': 'Estimate!!Total!!In labor force!!Civilian labor force',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
expected['B23025_004E'] = {
'label':
'Estimate!!Total!!In labor force!!Civilian labor force!!Employed',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
expected['B23025_005E'] = {
'label':
'Estimate!!Total!!In labor force!!Civilian labor force!!Unemployed',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
expected['B23025_006E'] = {
'label': 'Estimate!!Total!!In labor force!!Armed Forces',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
expected['B23025_007E'] = {
'label': 'Estimate!!Total!!Not in labor force',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
self.assertEqual(censusdata.censustable('acs5', 2017, 'B23025'),
expected)
def _parse_table_str(self, table_str):
"""Return table_id from table str"""
if isinstance(table_str, dict):
return table_str
base_table_id = self.tables_dict[table_str]
tables_dict = censusdata.censustable(self.survey, self.year,
base_table_id)
final_table_dict = {}
for table_id, table_dict in tables_dict.items():
table_label = table_dict["concept"] + "!!" + table_dict["label"]
table_id_moe = table_id.replace("E", "M")
table_label_moe = "MOE!!" + table_label
final_table_dict.update({
table_id: table_label,
table_id_moe: table_label_moe
})
return final_table_dict
def test_censustable_acsse(self):
for year in range(2014, 2015 + 1):
censusdata.censustable('acsse', year, 'K201601')
for year in range(2016, 2018 + 1):
censusdata.censustable('acsse', year, 'K201601')
censusdata.censustable('acsse', 2019, 'K201601')
def test_censustable_acs5_2019_detail(self):
expected = OrderedDict()
expected['B23025_001E'] = {
'label': 'Estimate!!Total:',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
expected['B23025_002E'] = {
'label': 'Estimate!!Total:!!In labor force:',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
expected['B23025_003E'] = {
'label':
'Estimate!!Total:!!In labor force:!!Civilian labor force:',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
expected['B23025_004E'] = {
'label':
'Estimate!!Total:!!In labor force:!!Civilian labor force:!!Employed',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
expected['B23025_005E'] = {
'label':
'Estimate!!Total:!!In labor force:!!Civilian labor force:!!Unemployed',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
expected['B23025_006E'] = {
'label': 'Estimate!!Total:!!In labor force:!!Armed Forces',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
expected['B23025_007E'] = {
'label': 'Estimate!!Total:!!Not in labor force',
'concept':
'EMPLOYMENT STATUS FOR THE POPULATION 16 YEARS AND OVER',
'predicateType': 'int'
}
self.assertEqual(censusdata.censustable('acs5', 2019, 'B23025'),
expected)
expected = OrderedDict()
expected['C15010_001E'] = {
'label': 'Estimate!!Total:',
'concept':
"FIELD OF BACHELOR'S DEGREE FOR FIRST MAJOR FOR THE POPULATION 25 YEARS AND OVER",
'predicateType': 'int'
}
expected['C15010_002E'] = {
'label': 'Estimate!!Total:!!Science and Engineering',
'concept':
"FIELD OF BACHELOR'S DEGREE FOR FIRST MAJOR FOR THE POPULATION 25 YEARS AND OVER",
'predicateType': 'int'
}
expected['C15010_003E'] = {
'label':
'Estimate!!Total:!!Science and Engineering Related Fields',
'concept':
"FIELD OF BACHELOR'S DEGREE FOR FIRST MAJOR FOR THE POPULATION 25 YEARS AND OVER",
'predicateType': 'int'
}
expected['C15010_004E'] = {
'label': 'Estimate!!Total:!!Business',
'concept':
"FIELD OF BACHELOR'S DEGREE FOR FIRST MAJOR FOR THE POPULATION 25 YEARS AND OVER",
'predicateType': 'int'
}
expected['C15010_005E'] = {
'label': 'Estimate!!Total:!!Education',
'concept':
"FIELD OF BACHELOR'S DEGREE FOR FIRST MAJOR FOR THE POPULATION 25 YEARS AND OVER",
'predicateType': 'int'
}
expected['C15010_006E'] = {
'label': 'Estimate!!Total:!!Arts, Humanities and Other',
'concept':
"FIELD OF BACHELOR'S DEGREE FOR FIRST MAJOR FOR THE POPULATION 25 YEARS AND OVER",
'predicateType': 'int'
}
self.assertEqual(censusdata.censustable('acs5', 2019, 'C15010'),
expected)
# %%
import censusdata
import pandas as pd
import sqlite3
import ssl
import re
import os
pd.set_option('display.expand_frame_repr', False)
pd.set_option('display.precision', 2)
# %%
# Aggregate Population by Age
censusdata.printtable(censusdata.censustable('acs5', 2018, 'B01001'))
# %%
# Geographies by state>place
censusdata.geographies(censusdata.censusgeo([('state', '12'), ('place', '*')]),
'acs5', 2018)
# %%
# By County
censusdata.geographies(
censusdata.censusgeo([('state', '12'), ('county', '*')]), 'acs5', 2018)
# %%
# By County Subdivision
censusdata.geographies(
censusdata.censusgeo([('state', '12'), ('county', '057'),
('county subdivision', '*')]), 'acs5', 2018)
# %%
key=KEY)
# In[4]:
state_dict_lookup = {v.geo[0][1]: k for k, v in state_dict.items()}
state_dict_lookup
# In[5]:
# allegheny is '003' for testing
county_dict = censusdata.geographies(censusdata.censusgeo([('state', '42'),
('county', '*')]),
'acs5',
2015,
key=KEY)
sex_by_age_table_info_dict = censusdata.censustable('acs5', 2015, 'B01001')
# In[6]:
county_dict_lookup = {
v.geo[1][1]: " ".join(k.split(',')[0].split(' ')[:-1])
for k, v in county_dict.items()
}
county_dict_lookup
# In[7]:
# pennsylvania is 42
# get all county codes from above dictionary and loop through them with this
pa_state_code = '42'
#Creating dictionary mapping for census tract to zipcode
#to be able to map the census data to education data
census_zipcode_relation_filename = 'zcta_tract.csv'
census_zipcode_relation = pd.read_csv(census_zipcode_relation_filename, \
delimiter=',', dtype=str)
ny_tract_to_zipcode = census_zipcode_relation[census_zipcode_relation\
['STATE'] == '36'][['TRACT', 'ZCTA5']]
tract_zipcode = {}
for row in ny_tract_to_zipcode.itertuples():
tract_zipcode[row[1]] = row[2]
#Obtaining 2010 Census median income data for each borough in NYC
censusdata.search('acs5', 2015, 'label', 'median income')
censusdata.censustable('acs5', 2015, 'B06011')
median_income_bronx = censusdata.download('acs5', 2015, \
censusdata.censusgeo([('state', '36'), ('county', '005'), \
('tract', '*')]), ['B06011_001E'])
median_income_kings = censusdata.download('acs5', 2015, \
censusdata.censusgeo([('state', '36'), ('county', '047'), \
('tract', '*')]), ['B06011_001E'])
median_income_ny = censusdata.download('acs5', 2015, \
censusdata.censusgeo([('state', '36'), ('county', '061'), \
('tract', '*')]), ['B06011_001E'])
median_income_queens = censusdata.download('acs5', 2015, \
censusdata.censusgeo([('state', '36'), ('county', '081'), \
('tract', '*')]), ['B06011_001E'])
median_income_richmond = censusdata.download('acs5', 2015, \
censusdata.censusgeo([('state', '36'), ('county', '085'), \
('tract', '*')]), ['B06011_001E'])
def test_censustable_acs3(self):
for year in range(2012, 2013 + 1):
censusdata.censustable('acs3', year, 'B23025')
def test_censustable_acs_subject_full(self):
censusdata.censustable('acs5', 2018, 'S1810')
def genTable(table):
return censusdata.printtable(censusdata.censustable('acs1', 2018, table))
input_drive = 'data/raw'
table_shell = os.path.join(input_drive, 'ACS2017_Table_Shells.xlsx')
xl = pd.ExcelFile(table_shell)
table_shell_df = xl.parse(xl.sheet_names[0])
# variables I've flagged to use
use_vars = table_shell_df[table_shell_df.Use == 1]
print(use_vars[['TableID', 'Stub', 'Use']])
use_vars.to_csv(os.path.join(input_drive, 'ACS_variables.csv'))
variables = use_vars.TableID.tolist()
# Use the census data package
# Examples of functionality
censusdata.search('acs5', 2017, 'label', 'unemploy')
# censusdata.search('acs5', 2017, 'concept', 'education')
censusdata.printtable(censusdata.censustable('acs5', 2017, 'B23025'))
censusdata.geographies(censusdata.censusgeo([('state', '*')]), 'acs5', 2017)
censusdata.geographies(
censusdata.censusgeo([('state', '08'), ('county', '*')]), 'acs5', 2017)
# doesn't seem like the C variables work, so remove them
variables = [var for var in variables if 'C' not in var]
variables = [var for var in variables if "B17002" not in var]
# loop through all variables and merge data together
count = 0
for variable in variables:
print(variable)
data = censusdata_pull(variable)
if count == 0:
def test_censustable_acs1_201219_detail(self):
for year in range(2012, 2019 + 1):
censusdata.censustable('acs1', year, 'B23025')
def test_censustable_acs5_2015_detail(self):
censusdata.censustable('acs5', 2015, 'B23025')
def main(verbose=False, data_dir='../data/'):
if verbose:
pd.set_option('display.expand_frame_repr', False)
pd.set_option('display.precision', 2)
print("Available race variables:")
print(censusdata.search('acs5', 2015, 'label', 'race'))
print("Table to download:")
censusdata.printtable(censusdata.censustable('acs5', 2015, 'B02001'))
variables = list(censusdata.censustable('acs5', 2015, 'B02001').keys())
# remove variables for margin of errors
variables = list(filter(lambda x: x[-1] != 'M', variables))
if verbose:
print("Variables:")
print(variables)
illinois_demo = censusdata.download(
'acs5', 2015, censusdata.censusgeo([('state', '17'), ('tract', '*')]),
variables)
illinois_demo.rename(
{
'B02001_001E': 'total',
'B02001_002E': 'white',
'B02001_003E': 'black',
'B02001_004E': 'native',
'B02001_005E': 'asian',
'B02001_006E': 'pacific',
'B02001_007E': 'other',
'B02001_008E': 'two_or_more',
'B02001_009E': 'two_or_more_including_other',
'B02001_010E': 'two_or_more_excluding_other'
},
axis='columns',
inplace=True)
illinois_demo.other = illinois_demo.other + \
illinois_demo['two_or_more_including_other'] + \
illinois_demo['two_or_more_excluding_other']
illinois_demo = illinois_demo[[
'total', 'white', 'black', 'native', 'asian', 'pacific', 'other'
]]
total = illinois_demo.total
illinois_demo.white /= total
illinois_demo.black /= total
illinois_demo.native /= total
illinois_demo.asian /= total
illinois_demo.pacific /= total
illinois_demo.other /= total
illinois_demo['censusgeo'] = illinois_demo.index
illinois_demo.reset_index(level=0, drop=True, inplace=True)
illinois_demo['tract'] = illinois_demo['censusgeo'].apply(
lambda x: x.geo[2][1]).astype(str)
illinois_demo['county'] = illinois_demo['censusgeo'].apply(
lambda x: x.geo[1][1])
illinois_demo['county_name'] = illinois_demo['censusgeo'].apply(
lambda x: x.name.split(',')[1][1:-7])
illinois_demo.drop('censusgeo', axis='columns', inplace=True)
if verbose:
print(illinois_demo.sample(frac=10 / len(illinois_demo)))
print(illinois_demo.describe())
illinois_demo = illinois_demo.loc[illinois_demo.county_name == 'Cook']
illinois_demo.to_csv(data_dir + 'Illinois2015CensusTractsDemographics.csv')
print("Successfully downloaded Illinois demographic data.")
url = "https://github.com/uscensusbureau/citysdk/raw/master/v2/GeoJSON/500k/2015/17/tract.json"
fname = 'Illinois2015CensusTracts.json'
target = data_dir + fname
download_file(url, target)
print("Successfully downloaded Illinois census tract shapefile.")
def test_censustable_acs5_2016_subject(self):
censusdata.censustable('acs5', 2016, 'S0101_C02')
def test_censustable_acs5_2019_subject(self):
expected = OrderedDict()
expected['S0101_C02_001E'] = {
'label': 'Estimate!!Percent!!Total population',
'concept': 'AGE AND SEX',
'predicateType': 'int'
}
expected['S0101_C02_002E'] = {
'label': 'Estimate!!Percent!!Total population!!AGE!!Under 5 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_003E'] = {
'label': 'Estimate!!Percent!!Total population!!AGE!!5 to 9 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_004E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!10 to 14 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_005E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!15 to 19 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_006E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!20 to 24 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_007E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!25 to 29 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_008E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!30 to 34 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_009E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!35 to 39 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_010E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!40 to 44 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_011E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!45 to 49 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_012E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!50 to 54 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_013E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!55 to 59 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_014E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!60 to 64 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_015E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!65 to 69 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_016E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!70 to 74 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_017E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!75 to 79 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_018E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!80 to 84 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_019E'] = {
'label':
'Estimate!!Percent!!Total population!!AGE!!85 years and over',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_020E'] = {
'label':
'Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!5 to 14 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_021E'] = {
'label':
'Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!15 to 17 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_022E'] = {
'label':
'Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!Under 18 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_023E'] = {
'label':
'Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!18 to 24 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_024E'] = {
'label':
'Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!15 to 44 years',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_025E'] = {
'label':
'Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!16 years and over',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_026E'] = {
'label':
'Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!18 years and over',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_027E'] = {
'label':
'Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!21 years and over',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_028E'] = {
'label':
'Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!60 years and over',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_029E'] = {
'label':
'Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!62 years and over',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_030E'] = {
'label':
'Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!65 years and over',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_031E'] = {
'label':
'Estimate!!Percent!!Total population!!SELECTED AGE CATEGORIES!!75 years and over',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_032E'] = {
'label':
'Estimate!!Percent!!Total population!!SUMMARY INDICATORS!!Median age (years)',
'concept': 'AGE AND SEX',
'predicateType': 'int'
}
expected['S0101_C02_033E'] = {
'label':
'Estimate!!Percent!!Total population!!SUMMARY INDICATORS!!Sex ratio (males per 100 females)',
'concept': 'AGE AND SEX',
'predicateType': 'int'
}
expected['S0101_C02_034E'] = {
'label':
'Estimate!!Percent!!Total population!!SUMMARY INDICATORS!!Age dependency ratio',
'concept': 'AGE AND SEX',
'predicateType': 'int'
}
expected['S0101_C02_035E'] = {
'label':
'Estimate!!Percent!!Total population!!SUMMARY INDICATORS!!Old-age dependency ratio',
'concept': 'AGE AND SEX',
'predicateType': 'int'
}
expected['S0101_C02_036E'] = {
'label':
'Estimate!!Percent!!Total population!!SUMMARY INDICATORS!!Child dependency ratio',
'concept': 'AGE AND SEX',
'predicateType': 'int'
}
expected['S0101_C02_037E'] = {
'label':
'Estimate!!Percent!!Total population!!PERCENT ALLOCATED!!Sex',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
expected['S0101_C02_038E'] = {
'label':
'Estimate!!Percent!!Total population!!PERCENT ALLOCATED!!Age',
'concept': 'AGE AND SEX',
'predicateType': 'float'
}
self.assertEqual(censusdata.censustable('acs5', 2019, 'S0101_C02'),
expected)
import censusdata
pd.set_option('display.expand_frame_repr', False)
pd.set_option('display.precision', 2)
# sample = censusdata.search('acs5', 2015, 'concept', 'transportation')#[160:170]
#
# print(len(sample))
#
# for item in sample:
# print(item)
censusdata.printtable(censusdata.censustable('acs5', 2015, 'B08301'))
#
# states = censusdata.geographies(censusdata.censusgeo([('state', '*')]), 'acs5', 2015)
#
#
# counties = censusdata.geographies(censusdata.censusgeo([('state', '36'), ('county', '*')]), 'acs5', 2015)
#
# #print(counties)
#
# # data = censusdata.download('acs5', 2015,
# # censusdata.censusgeo([('state', '36'), ('county', '081'), ('block group', '*')]),
# # ['B23025_001E', 'B23025_002E', 'B23025_003E', 'B23025_004E', 'B23025_005E',
# # 'B23025_006E', 'B23025_007E'])
#
data = censusdata.download('acs5', 2015,
censusdata.censusgeo([('state', '36'), ('county', '*')]),
