def stack_sparse_frame(frame):
"""
Only makes sense when fill_value is NaN
"""
lengths = [s.sp_index.npoints for _, s in frame.iteritems()]
nobs = sum(lengths)
# this is pretty fast
minor_labels = np.repeat(np.arange(len(frame.columns)), lengths)
inds_to_concat = []
vals_to_concat = []
for _, series in frame.iteritems():
if not np.isnan(series.fill_value):
raise Exception('This routine assumes NaN fill value')
int_index = series.sp_index.to_int_index()
inds_to_concat.append(int_index.indices)
vals_to_concat.append(series.sp_values)
major_labels = np.concatenate(inds_to_concat)
stacked_values = np.concatenate(vals_to_concat)
index = MultiIndex(levels=[frame.index, frame.columns],
labels=[major_labels, minor_labels])
lp = LongPanel(stacked_values.reshape((nobs, 1)), index=index,
columns=['foo'])
return lp.sortlevel(level=0)
def stack_sparse_frame(frame):
"""
Only makes sense when fill_value is NaN
"""
lengths = [s.sp_index.npoints for _, s in frame.iteritems()]
nobs = sum(lengths)
# this is pretty fast
minor_labels = np.repeat(np.arange(len(frame.columns)), lengths)
inds_to_concat = []
vals_to_concat = []
for _, series in frame.iteritems():
if not np.isnan(series.fill_value):
raise Exception('This routine assumes NaN fill value')
int_index = series.sp_index.to_int_index()
inds_to_concat.append(int_index.indices)
vals_to_concat.append(series.sp_values)
major_labels = np.concatenate(inds_to_concat)
stacked_values = np.concatenate(vals_to_concat)
index = MultiIndex(levels=[frame.index, frame.columns],
labels=[major_labels, minor_labels])
lp = LongPanel(stacked_values.reshape((nobs, 1)),
index=index,
columns=['foo'])
return lp.sortlevel(level=0)
def to_long(self, filter_observations=True):
"""
Convert SparsePanel to (dense) LongPanel
Returns
-------
lp : LongPanel
"""
if not filter_observations:
raise Exception('filter_observations=False not supported for '
'SparsePanel.to_long')
I, N, K = self.shape
counts = np.zeros(N * K, dtype=int)
d_values = {}
d_indexer = {}
for item in self.items:
frame = self[item]
values, major, minor = _stack_sparse_info(frame)
# values are stacked column-major
indexer = minor * N + major
counts.put(indexer, counts.take(indexer) + 1) # cuteness
d_values[item] = values
d_indexer[item] = indexer
# have full set of observations for each item
mask = counts == I
# for each item, take mask values at index locations for those sparse
# values, and use that to select values
values = np.column_stack([d_values[item][mask.take(d_indexer[item])]
for item in self.items])
inds, = mask.nonzero()
# still column major
major_labels = inds % N
minor_labels = inds // N
index = MultiIndex(levels=[self.major_axis, self.minor_axis],
labels=[major_labels, minor_labels])
lp = LongPanel(values, index=index, columns=self.items)
return lp.sortlevel(level=0)
