def _get_dt_format():
"""
Return the datetime format that should be used in the outputs
"""
config = util.get_configuration()
format = config['Output']['DateAndTimeFormat']
return format
def __init__(self, year=None, key=None):
"""
Initialize a new ACS object
Parameters
----------
year : None or int, default None
The last year to retrieve data from. For example, if
year=2015, retrieve data from 2011-2015.
If None, use the year specified in the configuration file.
key : None or str, default None
A key used to make requests for the data. If None, use the
key specified in the configuration file.
"""
# retrieve default values from configuration
if year is None or key is None:
config = util.get_configuration()
if year is None:
year = config['Census'].getint('Year')
if key is None:
key = config['Census']['Key']
self.year = year
self.key = key
def _save_processed(self, df):
# convert Timestamp column to str
_config = util.get_configuration()
_dt_format = _config['Output']['DateAndTimeFormat']
df['INCIDENT_DATE'] = df['INCIDENT_DATE'].dt.strftime(_dt_format)
df.to_csv(self.processed_path, index=False)
def __init__(self, year=None):
"""
Initialize a TIGER object
Parameters
----------
year : None or int
Year to retrieve geographies from. If None, use the
year present in the configuration file.
"""
if year is None:
config = util.get_configuration()
year = config['Census'].getint('Year')
self.year = year
def _download(url, out):
"""
Download a file, no checks
Parameters
----------
url : str
out : str or Path
"""
ua = util.get_configuration()['Downloads']['UserAgent']
subprocess.run([
'http',
'--ignore-stdin',
'--check-status',
'--timeout=2.0',
'--print=',
'--output', str(out),
'--download',
url,
'User-Agent:' + ua,
], check=True)
def _query(self, variables, geography='us', inside=None):
"""
Query the ACS API and returns the result as a list of lists
Parameters
----------
variables : list of str
A list of variable names to query for.
The list must not contain more than 50 elements.
Example:
["B01001_002E", "B01001_026E"]
geography : str, default 'us'
The unit to retrieve statistics from. For example, if you
want to retrieve statistics for census tracts, set
geography='tract'.
A complete list of geographies can be found here (look at
the leftmost column):
https://api.census.gov/data/2016/acs/acs5/examples.html
inside : str, default None
Restricts the search inside a specified area. For example,
if you only want results inside the state of Alabama, you
can set inside to:
'state:01'
If you want to nest deeper, you can specify the needed
geographies in order. For example:
'state:01 county:001'
Will filter the results to Autauga County, Alabama.
Returns
-------
list of lists
The first list contains the variable names while the others
carry the requested values.
"""
# API limit
assert len(variables) <= 50
# generate query params
params = {
'get': ','.join(variables),
'for': '{}:*'.format(geography),
}
if inside is not None:
params['in'] = inside
if self.key != '':
params['key'] = self.key
# generate headers
ua = util.get_configuration()['Downloads']['UserAgent']
headers = {'User-Agent': ua}
# generate query url
query_url = f'https://api.census.gov/data/{self.year}/acs/acs5'
r = requests.get(query_url, params=params, headers=headers)
r.raise_for_status()
o = r.json()
return o