def process_recarray(data, endog_idx=0, exog_idx=None, stack=True, dtype=None):
names = list(data.dtype.names)
if isinstance(endog_idx, (int, long)):
endog = array(data[names[endog_idx]], dtype=dtype)
endog_name = names[endog_idx]
endog_idx = [endog_idx]
else:
endog_name = [names[i] for i in endog_idx]
if stack:
endog = np.column_stack(data[field] for field in endog_name)
else:
endog = data[endog_name]
if exog_idx is None:
exog_name = [names[i] for i in range(len(names))
if i not in endog_idx]
else:
exog_name = [names[i] for i in exog_idx]
if stack:
exog = np.column_stack(data[field] for field in exog_name)
else:
exog = recarray_select(data, exog_name)
if dtype:
endog = endog.astype(dtype)
exog = exog.astype(dtype)
dataset = Dataset(data=data, names=names, endog=endog, exog=exog,
endog_name=endog_name, exog_name=exog_name)
return dataset
def __init__(self):
self.acf = self.results['acvar']
#self.acf = np.concatenate(([1.], self.acf))
self.qstat = self.results['Q1']
self.res1 = acf(self.x, nlags=40, qstat=True, alpha=.05)
res = DataFrame.from_records(self.results)
self.confint_res = recarray_select(self.results, ['acvar_lb','acvar_ub'])
self.confint_res = self.confint_res.view((float, 2))
def test_grangercausality(self):
# some example data
mdata = macrodata.load().data
mdata = recarray_select(mdata, ['realgdp', 'realcons'])
data = mdata.view((float, 2))
data = np.diff(np.log(data), axis=0)
#R: lmtest:grangertest
r_result = [0.243097, 0.7844328, 195, 2] # f_test
gr = grangercausalitytests(data[:, 1::-1], 2, verbose=False)
assert_almost_equal(r_result, gr[2][0]['ssr_ftest'], decimal=7)
assert_almost_equal(gr[2][0]['params_ftest'], gr[2][0]['ssr_ftest'], decimal=7)
def setup_class(self):
#SAS case
self.endog = dta3['Relief']
self.groups = dta3['Brand']
self.alpha = 0.05
self.setup_class_()
#super(self, self).setup_class_()
#CheckTuckeyHSD.setup_class_()
self.meandiff2 = sas_['mean']
self.confint2 = recarray_select(sas_, ['lower','upper']).view(float).reshape((3,2))
self.reject2 = sas_['sig'] == asbytes('***')
def setup_class(self):
#SAS case
self.endog = dta3['Relief']
self.groups = dta3['Brand']
self.alpha = 0.05
self.setup_class_()
#super(self, self).setup_class_()
#CheckTuckeyHSD.setup_class_()
self.meandiff2 = sas_['mean']
self.confint2 = recarray_select(
sas_, ['lower', 'upper']).view(float).reshape((3, 2))
self.reject2 = sas_['sig'] == asbytes('***')
def add_lag(x, col=None, lags=1, drop=False, insert=True):
"""
Returns an array with lags included given an array.
Parameters
----------
x : array
An array or NumPy ndarray subclass. Can be either a 1d or 2d array with
observations in columns.
col : 'string', int, or None
If data is a structured array or a recarray, `col` can be a string
that is the name of the column containing the variable. Or `col` can
be an int of the zero-based column index. If it's a 1d array `col`
can be None.
lags : int
The number of lags desired.
drop : bool
Whether to keep the contemporaneous variable for the data.
insert : bool or int
If True, inserts the lagged values after `col`. If False, appends
the data. If int inserts the lags at int.
Returns
-------
array : ndarray
Array with lags
Examples
--------
>>> import statsmodels.api as sm
>>> data = sm.datasets.macrodata.load(as_pandas=False)
>>> data = data.data[['year','quarter','realgdp','cpi']]
>>> data = sm.tsa.add_lag(data, 'realgdp', lags=2)
Notes
-----
Trims the array both forward and backward, so that the array returned
so that the length of the returned array is len(`X`) - lags. The lags are
returned in increasing order, ie., t-1,t-2,...,t-lags
"""
lags = int_like(lags, 'lags')
drop = bool_like(drop, 'drop')
if x.dtype.names:
names = x.dtype.names
if not col and np.squeeze(x).ndim > 1:
raise IndexError("col is None and the input array is not 1d")
elif len(names) == 1:
col = names[0]
if isinstance(col, int):
col = x.dtype.names[col]
contemp = x[col]
# make names for lags
tmp_names = [col + '_' + 'L(%i)' % i for i in range(1, lags + 1)]
ndlags = lagmat(contemp, maxlag=lags, trim='Both')
# get index for return
if insert is True:
ins_idx = list(names).index(col) + 1
elif insert is False:
ins_idx = len(names) + 1
else: # insert is an int
if insert > len(names):
import warnings
warnings.warn(
"insert > number of variables, inserting at the"
" last position", ValueWarning)
ins_idx = insert
first_names = list(names[:ins_idx])
last_names = list(names[ins_idx:])
if drop:
if col in first_names:
first_names.pop(first_names.index(col))
else:
last_names.pop(last_names.index(col))
if first_names: # only do this if x is not "empty"
# Workaround to avoid NumPy FutureWarning
_x = recarray_select(x, first_names)
first_arr = nprf.append_fields(_x[lags:],
tmp_names,
ndlags.T,
usemask=False)
else:
first_arr = np.zeros(len(x) - lags,
dtype=lzip(tmp_names,
(x[col].dtype, ) * lags))
for i, name in enumerate(tmp_names):
first_arr[name] = ndlags[:, i]
if last_names:
return nprf.append_fields(first_arr,
last_names,
[x[name][lags:] for name in last_names],
usemask=False)
else: # lags for last variable
return first_arr
else: # we have an ndarray
if x.ndim == 1: # make 2d if 1d
x = x[:, None]
if col is None:
col = 0
# handle negative index
if col < 0:
col = x.shape[1] + col
contemp = x[:, col]
if insert is True:
ins_idx = col + 1
elif insert is False:
ins_idx = x.shape[1]
else:
if insert < 0: # handle negative index
insert = x.shape[1] + insert + 1
if insert > x.shape[1]:
insert = x.shape[1]
import warnings
warnings.warn(
"insert > number of variables, inserting at the"
" last position", ValueWarning)
ins_idx = insert
ndlags = lagmat(contemp, lags, trim='Both')
first_cols = lrange(ins_idx)
last_cols = lrange(ins_idx, x.shape[1])
if drop:
if col in first_cols:
first_cols.pop(first_cols.index(col))
else:
last_cols.pop(last_cols.index(col))
return np.column_stack((x[lags:, first_cols], ndlags, x[lags:,
last_cols]))
def add_lag(x, col=None, lags=1, drop=False, insert=True):
"""
Returns an array with lags included given an array.
Parameters
----------
x : array
An array or NumPy ndarray subclass. Can be either a 1d or 2d array with
observations in columns.
col : 'string', int, or None
If data is a structured array or a recarray, `col` can be a string
that is the name of the column containing the variable. Or `col` can
be an int of the zero-based column index. If it's a 1d array `col`
can be None.
lags : int
The number of lags desired.
drop : bool
Whether to keep the contemporaneous variable for the data.
insert : bool or int
If True, inserts the lagged values after `col`. If False, appends
the data. If int inserts the lags at int.
Returns
-------
array : ndarray
Array with lags
Examples
--------
>>> import statsmodels.api as sm
>>> data = sm.datasets.macrodata.load(as_pandas=False)
>>> data = data.data[['year','quarter','realgdp','cpi']]
>>> data = sm.tsa.add_lag(data, 'realgdp', lags=2)
Notes
-----
Trims the array both forward and backward, so that the array returned
so that the length of the returned array is len(`X`) - lags. The lags are
returned in increasing order, ie., t-1,t-2,...,t-lags
"""
if x.dtype.names:
names = x.dtype.names
if not col and np.squeeze(x).ndim > 1:
raise IndexError("col is None and the input array is not 1d")
elif len(names) == 1:
col = names[0]
if isinstance(col, (int, long)):
col = x.dtype.names[col]
if not PY3:
# TODO: Get rid of this kludge. See GH # 3658
names = [bytes(name)
if isinstance(name, unicode) # noqa:F821
else name for name in names]
# Fail loudly if there is a non-ascii name.
x.dtype.names = names
if isinstance(col, unicode): # noqa:F821
col = bytes(col)
contemp = x[col]
# make names for lags
tmp_names = [col + '_'+'L(%i)' % i for i in range(1, lags+1)]
ndlags = lagmat(contemp, maxlag=lags, trim='Both')
# get index for return
if insert is True:
ins_idx = list(names).index(col) + 1
elif insert is False:
ins_idx = len(names) + 1
else: # insert is an int
if insert > len(names):
import warnings
warnings.warn("insert > number of variables, inserting at the"
" last position", ValueWarning)
ins_idx = insert
first_names = list(names[:ins_idx])
last_names = list(names[ins_idx:])
if drop:
if col in first_names:
first_names.pop(first_names.index(col))
else:
last_names.pop(last_names.index(col))
if first_names: # only do this if x isn't "empty"
# Workaround to avoid NumPy FutureWarning
_x = recarray_select(x, first_names)
first_arr = nprf.append_fields(_x[lags:], tmp_names, ndlags.T,
usemask=False)
else:
first_arr = np.zeros(len(x)-lags, dtype=lzip(tmp_names,
(x[col].dtype,)*lags))
for i,name in enumerate(tmp_names):
first_arr[name] = ndlags[:,i]
if last_names:
return nprf.append_fields(first_arr, last_names,
[x[name][lags:] for name in last_names], usemask=False)
else: # lags for last variable
return first_arr
else: # we have an ndarray
if x.ndim == 1: # make 2d if 1d
x = x[:,None]
if col is None:
col = 0
# handle negative index
if col < 0:
col = x.shape[1] + col
contemp = x[:,col]
if insert is True:
ins_idx = col + 1
elif insert is False:
ins_idx = x.shape[1]
else:
if insert < 0: # handle negative index
insert = x.shape[1] + insert + 1
if insert > x.shape[1]:
insert = x.shape[1]
import warnings
warnings.warn("insert > number of variables, inserting at the"
" last position", ValueWarning)
ins_idx = insert
ndlags = lagmat(contemp, lags, trim='Both')
first_cols = lrange(ins_idx)
last_cols = lrange(ins_idx,x.shape[1])
if drop:
if col in first_cols:
first_cols.pop(first_cols.index(col))
else:
last_cols.pop(last_cols.index(col))
return np.column_stack((x[lags:,first_cols],ndlags,
x[lags:,last_cols]))
