def _make_long_index(major_values, minor_values):
major_axis = Index(sorted(set(major_values)))
minor_axis = Index(sorted(set(minor_values)))
major_labels, _ = _tseries.getMergeVec(major_values, major_axis.indexMap)
minor_labels, _ = _tseries.getMergeVec(minor_values, minor_axis.indexMap)
long_index = MultiIndex(levels=[major_axis, minor_axis], labels=[major_labels, minor_labels])
return long_index
def map(self, arg):
"""
Map values of Series using input correspondence (which can be
a dict, Series, or function).
Parameters
----------
arg : function, dict, or Series
Returns
-------
y : Series
same index as caller
"""
if isinstance(arg, (dict, Series)):
if isinstance(arg, dict):
arg = Series(arg)
indexer, mask = _tseries.getMergeVec(self, arg.index.indexMap)
notmask = -mask
new_values = arg.view(np.ndarray).take(indexer)
if notmask.any():
if issubclass(new_values.dtype.type, np.integer):
new_values = new_values.astype(float)
np.putmask(new_values, notmask, np.nan)
newSer = Series(new_values, index=self.index)
return newSer
else:
return Series([arg(x) for x in self], index=self.index)
def _read_panel_table(self, group, where=None):
from pandas.core.common import _asarray_tuplesafe
table = getattr(group, 'table')
# create the selection
sel = Selection(table, where)
sel.select()
fields = table._v_attrs.fields
columns = _maybe_convert(sel.values['column'],
table._v_attrs.columns_kind)
index = _maybe_convert(sel.values['index'],
table._v_attrs.index_kind)
# reconstruct
long_index = MultiIndex.from_arrays([index, columns])
lp = LongPanel(sel.values['values'], index=long_index,
columns=fields)
if lp.consistent:
lp = lp.sortlevel(level=0)
wp = lp.to_wide()
else:
if not self._quiet:
print ('Duplicate entries in table, taking most recently '
'appended')
# need a better algorithm
tuple_index = long_index.get_tuple_index()
index_map = _tseries.map_indices_buf(tuple_index)
unique_tuples = _tseries.fast_unique(tuple_index)
unique_tuples = _asarray_tuplesafe(unique_tuples)
indexer, _ = _tseries.getMergeVec(unique_tuples, index_map)
new_index = long_index.take(indexer)
new_values = lp.values.take(indexer, axis=0)
lp = LongPanel(new_values, index=new_index, columns=lp.columns)
wp = lp.to_wide()
if sel.column_filter:
new_minor = sorted(set(wp.minor_axis) & sel.column_filter)
wp = wp.reindex(minor=new_minor)
return wp
def join_on(self, other, on, axis=1):
other_axis = other.axes[axis]
indexer, mask = _tseries.getMergeVec(on, other_axis.indexMap)
# TODO: deal with length-0 case? or does it fall out?
notmask = -mask
needs_masking = len(on) > 0 and notmask.any()
other_blocks = []
for block in other.blocks:
newb = block.reindex_axis(indexer, notmask, needs_masking, axis=axis)
other_blocks.append(newb)
cons_items = self.items + other.items
consolidated = _consolidate(self.blocks + other_blocks, cons_items)
new_axes = list(self.axes)
new_axes[0] = cons_items
return BlockManager(consolidated, new_axes)
def join_on(self, other, on, axis=1, lsuffix=None, rsuffix=None):
this, other = self._maybe_rename_join(other, lsuffix, rsuffix)
other_axis = other.axes[axis]
indexer, mask = _tseries.getMergeVec(on.astype(object),
other_axis.indexMap)
# TODO: deal with length-0 case? or does it fall out?
notmask = -mask
needs_masking = len(on) > 0 and notmask.any()
other_blocks = []
for block in other.blocks:
newb = block.reindex_axis(indexer, notmask, needs_masking,
axis=axis)
other_blocks.append(newb)
cons_items = this.items + other.items
consolidated = _consolidate(this.blocks + other_blocks, cons_items)
new_axes = list(this.axes)
new_axes[0] = cons_items
return BlockManager(consolidated, new_axes)
def fromarray(cls, values):
values = np.asarray(values, dtype=object)
levels = Index(sorted(set(values)))
labels, _ = _tseries.getMergeVec(values, levels.indexMap)
return Factor(labels, levels=levels)