def webuse(data, baseurl='http://www.stata-press.com/data/r11/'):
"""
Parameters
----------
data : str
Name of dataset to fetch.
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
import pandas
from scikits.statsmodels.iolib import genfromdta
from urllib2 import urlopen
from urlparse import urljoin
from StringIO import StringIO
url = urljoin(baseurl, data+'.dta')
dta = urlopen(url)
dta = StringIO(dta.read()) # make it truly file-like
return genfromdta(dta)
def open_mortality():
# load file
try:
import scikits.statsmodels.iolib as pd
except:
import scikits.statsmodels.lib.io as pd
mortality = pandas.DataFrame(pd.genfromdta('/home/j/Project/Mortality/GBD Envelopes/04. Lifetables/02. MORTMatch/cluster/results/compiled/iso3_lt_mean_uncertainty.dta'))
# keep desired variables
mortality = mortality.ix[:,0:7]
mortality.columns = ['area', 'sex', 'year_start', 'age_start', 'lower_ci', 'upper_ci', 'value']
# add input data
mortality = mortality[((mortality['year_start']==1990)|(mortality['year_start']==2005)|(mortality['year_start']==2010))]
return mortality
def open_mortality():
# load file
try:
import scikits.statsmodels.iolib as pd
except:
import scikits.statsmodels.lib.io as pd
mortality = pandas.DataFrame(
pd.genfromdta(
'/home/j/Project/Mortality/GBD Envelopes/04. Lifetables/02. MORTMatch/cluster/results/compiled/iso3_lt_mean_uncertainty.dta'
))
# keep desired variables
mortality = mortality.ix[:, 0:7]
mortality.columns = [
'area', 'sex', 'year_start', 'age_start', 'lower_ci', 'upper_ci',
'value'
]
# add input data
mortality = mortality[((mortality['year_start'] == 1990) |
(mortality['year_start'] == 2005) |
(mortality['year_start'] == 2010))]
return mortality
