def load():
"""
Loads the Grunfeld data and returns a Dataset class.
Returns
-------
Dataset instance:
See DATASET_PROPOSAL.txt for more information.
Notes
-----
raw_data has the firm variable expanded to dummy variables for each
firm (ie., there is no reference dummy)
"""
filepath = dirname(abspath(__file__))
data = recfromtxt(open(filepath + '/grunfeld.csv', 'rb'),
delimiter=",",
names=True,
dtype="f8,f8,f8,a17,f8")
names = list(data.dtype.names)
endog = array(data[names[0]], dtype=float)
endog_name = names[0]
exog = data[list(names[1:])]
exog_name = list(names[1:])
dataset = Dataset(data=data,
names=names,
endog=endog,
exog=exog,
endog_name=endog_name,
exog_name=exog_name)
raw_data = categorical(data, col='firm', drop=True)
dataset.raw_data = raw_data
return dataset
def load():
"""
Loads the Grunfeld data and returns a Dataset class.
Returns
-------
Dataset instance:
See DATASET_PROPOSAL.txt for more information.
Notes
-----
raw_data has the firm variable expanded to dummy variables for each
firm (ie., there is no reference dummy)
"""
filepath = dirname(abspath(__file__))
data = recfromtxt(open(filepath + '/grunfeld.csv','rb'), delimiter=",",
names=True, dtype="f8,f8,f8,a17,f8")
names = list(data.dtype.names)
endog = array(data[names[0]], dtype=float)
endog_name = names[0]
exog = data[list(names[1:])]
exog_name = list(names[1:])
dataset = Dataset(data=data, names=names, endog=endog, exog=exog,
endog_name=endog_name, exog_name=exog_name)
raw_data = categorical(data, col='firm', drop=True)
dataset.raw_data = raw_data
return dataset
def load():
"""
Load the strikes data and return a Dataset class instance.
Returns
-------
Dataset instance:
See DATASET_PROPOSAL.txt for more information.
"""
filepath = dirname(abspath(__file__))
##### EDIT THE FOLLOWING TO POINT TO DatasetName.csv #####
data = recfromtxt(open(filepath + '/strikes.csv', 'rb'),
delimiter=",",
names=True,
dtype=float)
names = list(data.dtype.names)
##### SET THE INDEX #####
endog = array(data[names[0]], dtype=float)
endog_name = names[0]
##### SET THE INDEX #####
exog = column_stack(data[i] for i in names[1:]).astype(float)
exog_name = names[1:]
dataset = Dataset(data=data,
names=names,
endog=endog,
exog=exog,
endog_name=endog_name,
exog_name=exog_name)
return dataset
def load():
"""
Load the Longley data and return a Dataset class.
Returns
-------
Dataset instance
See DATASET_PROPOSAL.txt for more information.
"""
filepath = dirname(abspath(__file__))
data = recfromtxt(open(filepath + '/longley.csv', "rb"),
delimiter=",",
names=True,
dtype=float,
usecols=(1, 2, 3, 4, 5, 6, 7))
names = list(data.dtype.names)
endog = array(data[names[0]], dtype=float)
endog_name = names[0]
exog = column_stack(data[i] for i in names[1:]).astype(float)
exog_name = names[1:]
dataset = Dataset(data=data,
names=names,
endog=endog,
exog=exog,
endog_name=endog_name,
exog_name=exog_name)
return dataset
def load():
"""Load the credit card data and returns a Dataset class.
Returns
-------
Dataset instance:
See DATASET_PROPOSAL.txt for more information.
"""
filepath = dirname(abspath(__file__))
data = recfromtxt(open(filepath + '/ccard.csv', 'rb'),
delimiter=",",
names=True,
dtype=float)
names = list(data.dtype.names)
endog = array(data[names[0]], dtype=float)
endog_name = names[0]
exog = column_stack(data[i] \
for i in names[1:]).astype(float)
exog_name = names[1:]
dataset = Dataset(data=data,
names=names,
endog=endog,
exog=exog,
endog_name=endog_name,
exog_name=exog_name)
return dataset
def load():
"""
Load the Spector dataset and returns a Dataset class instance.
Returns
-------
Dataset instance:
See DATASET_PROPOSAL.txt for more information.
"""
filepath = dirname(abspath(__file__))
##### EDIT THE FOLLOWING TO POINT TO DatasetName.csv #####
data = recfromtxt(open(filepath + '/spector.csv', "rb"),
delimiter=" ",
names=True,
dtype=float,
usecols=(1, 2, 3, 4))
names = list(data.dtype.names)
endog = array(data[names[3]], dtype=float)
endog_name = names[3]
exog = column_stack(data[i] for i in names[:3]).astype(float)
exog_name = names[:3]
dataset = Dataset(data=data,
names=names,
endog=endog,
exog=exog,
endog_name=endog_name,
exog_name=exog_name)
return dataset
def load():
"""
Loads the RAND HIE data and returns a Dataset class.
----------
endog - structured array of response variable, mdvis
exog - strucutured array of design
Returns
Load instance:
a class of the data with array attrbutes 'endog' and 'exog'
"""
filepath = dirname(abspath(__file__))
##### EDIT THE FOLLOWING TO POINT TO DatasetName.csv #####
data = recfromtxt(open(filepath + '/randhie.csv', "rb"),
delimiter=",",
names=True,
dtype=float)
names = list(data.dtype.names)
endog = array(data[names[0]]).astype(float)
endog_name = names[0]
exog = data[list(names[1:])]
exog_name = names[1:]
dataset = Dataset(data=data,
names=names,
endog=endog,
exog=exog,
endog_name=endog_name,
exog_name=exog_name)
return dataset
def load():
"""
Load the US macro data and return a Dataset class.
Returns
-------
Dataset instance:
See DATASET_PROPOSAL.txt for more information.
Notes
-----
The macrodata Dataset instance does not contain endog and exog attributes.
"""
filepath = dirname(abspath(__file__))
data = recfromtxt(open(filepath + '/macrodata.csv', 'rb'),
delimiter=",",
names=True,
dtype=float)
names = data.dtype.names
dataset = Dataset(data=data, names=names)
return dataset
def load():
"""
Load the star98 data and returns a Dataset class instance.
Returns
-------
Load instance:
a class of the data with array attrbutes 'endog' and 'exog'
"""
filepath = dirname(abspath(__file__))
##### EDIT THE FOLLOWING TO POINT TO DatasetName.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 = recfromtxt(open(filepath + '/star98.csv', "rb"),
delimiter=",",
names=names,
skip_header=1,
dtype=float)
names = list(data.dtype.names)
# endog = (successes, failures)
NABOVE = array(data[names[1]]).astype(float) # successes
NBELOW = array(data[names[0]]).astype(float) \
- array(data[names[1]]).astype(float) # now its failures
endog = column_stack((NABOVE, NBELOW))
endog_name = names[:2]
exog = column_stack(data[i] for i in names[2:]).astype(float)
exog_name = names[2:]
dataset = Dataset(data=data,
names=names,
endog=endog,
exog=exog,
endog_name=endog_name,
exog_name=exog_name)
return dataset
def load():
"""
Load the yearly sunspot data and returns a data class.
Returns
--------
Dataset instance:
See DATASET_PROPOSAL.txt for more information.
Notes
-----
This dataset only contains data for one variable, so the attributes
data, raw_data, and endog are all the same variable. There is no exog
attribute defined.
"""
filepath = dirname(abspath(__file__))
data = recfromtxt(open(filepath + '/sunspots.csv', 'rb'), delimiter=",",
names=True, dtype=float, usecols=(1))
names = list(data.dtype.names)
endog = array(data[names[0]], dtype=float)
endog_name = names
dataset = Dataset(data=data, names=names, endog=endog,
endog_name=endog_name)
return dataset