def test_ctor_dict(self):
itema = self.panel['ItemA']
itemb = self.panel['ItemB']
d = {'A' : itema, 'B' : itemb[5:]}
d2 = {'A' : itema._series, 'B' : itemb[5:]._series}
d3 = {'A' : DataFrame(itema._series),
'B' : DataFrame(itemb[5:]._series)}
wp = WidePanel.from_dict(d)
wp2 = WidePanel.from_dict(d2) # nested Dict
wp3 = WidePanel.from_dict(d3)
self.assert_(wp.major_axis.equals(self.panel.major_axis))
assert_panel_equal(wp, wp2)
# intersect
wp = WidePanel.from_dict(d, intersect=True)
self.assert_(wp.major_axis.equals(itemb.index[5:]))
# use constructor
assert_panel_equal(WidePanel(d), WidePanel.from_dict(d))
assert_panel_equal(WidePanel(d2), WidePanel.from_dict(d2))
assert_panel_equal(WidePanel(d3), WidePanel.from_dict(d3))
# cast
result = WidePanel(d, dtype=int)
expected = WidePanel(dict((k, v.astype(int)) for k, v in d.iteritems()))
def test_from_dict(self):
itema = self.panel['ItemA']
itemb = self.panel['ItemB']
d = {'A' : itema, 'B' : itemb[5:]}
d2 = {'A' : itema._series, 'B' : itemb[5:]._series}
d3 = {'A' : DataFrame(itema._series),
'B' : DataFrame(itemb[5:]._series)}
wp = WidePanel.from_dict(d)
wp2 = WidePanel.from_dict(d2) # nested Dict
wp3 = WidePanel.from_dict(d3)
self.assert_(wp.major_axis.equals(self.panel.major_axis))
assert_panel_equal(wp, wp2)
# intersect
wp = WidePanel.from_dict(d, intersect=True)
self.assert_(wp.major_axis.equals(itemb.index[5:]))
def _filter_data(self):
"""
"""
data = self._x_orig
cat_mapping = {}
if isinstance(data, LongPanel):
data = data.to_wide()
else:
if isinstance(data, WidePanel):
data = data.copy()
if not isinstance(data, SparseWidePanel):
data, cat_mapping = self._convert_x(data)
if not isinstance(data, WidePanel):
data = WidePanel.from_dict(data, intersect=True)
x_names = data.items
if self._weights is not None:
data['__weights__'] = self._weights
# Filter x's without y (so we can make a prediction)
filtered = data.to_long()
# Filter all data together using to_long
# convert to DataFrame
y = self._y_orig
if isinstance(y, Series):
y = y.unstack()
data['__y__'] = y
data_long = data.to_long()
x_filt = filtered.filter(x_names)
if self._weights:
weights_filt = filtered.ix[:, ['__weights__']]
else:
weights_filt = None
x = data_long.filter(x_names)
y = data_long.ix[:, ['__y__']]
if self._weights:
weights = data_long.ix[:, ['__weights__']]
else:
weights = None
return x, x_filt, y, weights, weights_filt, cat_mapping
