def load_pandas():
"""
Load the China smoking/lung cancer data and return a Dataset class.
Returns
-------
Dataset instance:
See DATASET_PROPOSAL.txt for more information.
"""
raw_data = du.load_csv(__file__, 'china_smoking.csv')
data = raw_data.set_index('Location')
dset = du.Dataset(data=data,
title="Smoking and lung cancer in Chinese regions")
dset.raw_data = raw_data
return dset
def _get_data():
data = du.load_csv(__file__, 'star98.csv')
names = [
"NABOVE", "NBELOW", "LOWINC", "PERASIAN", "PERBLACK", "PERHISP",
"PERMINTE", "AVYRSEXP", "AVSALK", "PERSPENK", "PTRATIO", "PCTAF",
"PCTCHRT", "PCTYRRND", "PERMINTE_AVYRSEXP", "PERMINTE_AVSAL",
"AVYRSEXP_AVSAL", "PERSPEN_PTRATIO", "PERSPEN_PCTAF", "PTRATIO_PCTAF",
"PERMINTE_AVYRSEXP_AVSAL", "PERSPEN_PTRATIO_PCTAF"
]
data.columns = names
nabove = data['NABOVE'].copy()
nbelow = data['NBELOW'].copy()
data['NABOVE'] = nbelow # successes
data['NBELOW'] = nabove - nbelow # now failures
return data
def _get_data():
return du.load_csv(__file__, 'modechoice.csv', sep=';', convert_float=True)
def _get_data():
data = du.load_csv(__file__, 'longley.csv')
data = data.iloc[:, [1, 2, 3, 4, 5, 6, 7]].astype(float)
return data
def _get_data():
data = du.load_csv(__file__, 'copper.csv')
data = data.iloc[:, 1:7]
return data.astype(float)
def _get_data():
data = du.load_csv(__file__, 'cpunish.csv')
data = data.iloc[:, 1:8].astype(float)
return data
def _get_data():
data = du.load_csv(__file__, 'scotvote.csv')
data = data.iloc[:, 1:9]
return data.astype(float)
def _get_data():
return du.load_csv(__file__, 'sunspots.csv').astype(float)
def _get_data():
return du.load_csv(__file__, 'randhie.csv')
def _get_data():
return du.load_csv(__file__, 'statecrime.csv')
def _get_data():
data = du.load_csv(__file__, 'spector.csv', sep=r'\s')
data = du.strip_column_names(data)
data = data.iloc[:, [1, 2, 3, 4]]
return data.astype(float)
def _get_data():
return du.load_csv(__file__, 'DatasetName.csv')
def _get_data():
return du.load_csv(__file__, 'fertility.csv')
def _get_data():
return du.load_csv(__file__, 'co2.csv')
def _get_data():
return du.load_csv(__file__, 'heart.csv')
def _get_data():
return du.load_csv(__file__, 'engel.csv')
def _get_data():
return du.load_csv(__file__, 'strikes.csv').astype(float)
def _get_data():
data = du.load_csv(__file__, 'anes96.csv', sep=r'\s')
data = du.strip_column_names(data)
data['logpopul'] = log(data['popul'] + .1)
return data.astype(float)
def _get_data():
data = du.load_csv(__file__, 'grunfeld.csv')
return data
def _get_data():
return du.load_csv(__file__, 'fair.csv', convert_float=True)
def _get_data():
data = du.load_csv(__file__, 'committee.csv')
data = data.iloc[:, 1:7].astype(float)
return data