def webuse(data, baseurl='https://www.stata-press.com/data/r11/', as_df=True):
"""
Download and return an example dataset from Stata.
Parameters
----------
data : str
Name of dataset to fetch.
baseurl : str
The base URL to the stata datasets.
as_df : bool
Deprecated. Always returns a DataFrame
Returns
-------
dta : DataFrame
A DataFrame containing the Stata dataset.
Examples
--------
>>> dta = webuse('auto')
Notes
-----
Make sure baseurl has trailing forward slash. Doesn't do any
error checking in response URLs.
"""
url = urljoin(baseurl, data+'.dta')
return read_stata(url)
def webuse(data, baseurl='https://www.stata-press.com/data/r11/', as_df=True):
"""
Download and return an example dataset from Stata.
Parameters
----------
data : str
Name of dataset to fetch.
baseurl : str
The base URL to the stata datasets.
as_df : bool
Deprecated. Always returns a DataFrame
Returns
-------
dta : DataFrame
A DataFrame containing the Stata dataset.
Examples
--------
>>> dta = webuse('auto')
Notes
-----
Make sure baseurl has trailing forward slash. Doesn't do any
error checking in response URLs.
"""
url = urljoin(baseurl, data+'.dta')
return read_stata(url)
def webuse(data, baseurl='http://www.stata-press.com/data/r11/', as_df=True):
"""
Parameters
----------
data : str
Name of dataset to fetch.
baseurl : str
The base URL to the stata datasets.
as_df : bool
If True, returns a `pandas.DataFrame`
Returns
-------
dta : Record Array
A record array containing the Stata dataset.
Examples
--------
>>> dta = webuse('auto')
Notes
-----
Make sure baseurl has trailing forward slash. Doesn't do any
error checking in response URLs.
"""
# lazy imports
from statsmodels.iolib import genfromdta
url = urljoin(baseurl, data+'.dta')
dta = urlopen(url)
dta = StringIO(dta.read()) # make it truly file-like
if as_df: # could make this faster if we don't process dta twice?
return DataFrame.from_records(genfromdta(dta))
else:
return genfromdta(dta)
