def update_histogram(
self,
created: Optional[bitmap] = None,
updated: Optional[bitmap] = None,
deleted: Optional[bitmap] = None,
) -> None:
"Update the histogram index"
created = bitmap.asbitmap(created)
updated = bitmap.asbitmap(updated)
deleted = bitmap.asbitmap(deleted)
# if deleted:
# self._tdigest_is_valid = False
if deleted or updated:
to_remove = updated | deleted
for i, bm in enumerate(self.bitmaps):
self.bitmaps[i] = bm - to_remove
if created or updated:
to_add = created | updated
ids = np.array(to_add, np.int64)
values = self.column.loc[to_add]
bins = np.digitize(values, self.bins) # type: ignore
counts = np.bincount(bins)
for i in np.nonzero(counts)[0]:
bm = self.bitmaps[i]
selection = bins == i # boolean mask of values in bin i
bm.update(ids[selection]) # add them to the bitmap
def _process_created(ret: Dict[str, Any]) -> None:
b = dialog.bag
if not created:
return
if how == "outer":
return _process_created_outer(ret)
# if first_key not in created: return
first_ids = created.get(first_key, None)
second_ids = created.get(second_key, None)
only_1st, common, only_2nd = inter_slice(first_ids, second_ids)
assert isinstance(join_table, Table)
if first_ids is not None:
new_size = _len(first_ids)
if (
isinstance(first_ids, slice)
and join_table.is_identity
and (
join_table.last_id + 1 == first_ids.start or join_table.last_id == 0
)
):
# the nice case (no gaps)
join_table.resize(new_size)
else: # there are gaps ...we have to keep trace of existing ids
join_table.resize(new_size, index=bitmap.asbitmap(first_ids))
if b.get("existing_ids", None) is None:
b["existing_ids"] = bitmap.asbitmap(join_table.index)
else:
b["existing_ids"] = bitmap.union(
b["existing_ids"], bitmap.asbitmap(first_ids)
)
join_table.loc[_fix(first_ids), first_cols] = first.loc[
_fix(first_ids), first.columns
]
if not _void(common):
join_table.loc[_fix(common), second_cols] = second.loc[
_fix(common), second.columns
]
# first matching: older orphans on the second table with new orphans on the first
only_1st_bm = bitmap.asbitmap(only_1st)
paired = b["second_orphans"] & only_1st_bm
if paired:
join_table.loc[paired, second_cols] = second.loc[paired, second.columns]
b["second_orphans"] = b["second_orphans"] - paired
only_1st_bm -= paired
b["first_orphans"] = bitmap.union(b["first_orphans"], only_1st_bm)
# 2nd matching: older orphans on the first table with new orphans on the second
only_2nd_bm = bitmap.asbitmap(only_2nd)
paired = b["first_orphans"] & only_2nd_bm
if paired:
join_table.loc[paired, second_cols] = second.loc[paired, second.columns]
b["first_orphans"] = b["first_orphans"] - paired
only_2nd_bm -= paired
b["second_orphans"] = bitmap.union(b["second_orphans"], only_2nd_bm)
def resize(self,
newsize: int,
index: Optional[Union[bitmap, List[int]]] = None) -> None:
# NB: newsize means how many active rows the table must contain
if index is not None:
index = bitmap.asbitmap(index)
newsize_ = index.max() + 1 if index else 0
if newsize < newsize_:
logger.warning(f"Wrong newsize={newsize}, fixed to {newsize_}")
newsize = newsize_
assert newsize is not None
delta = newsize - len(self.index)
# if delta < 0:
# return
newsize = self.last_id + delta + 1
crt_index = bitmap(self._index)
self._resize_rows(newsize, index)
del_index = crt_index - self._index
if del_index:
self.add_deleted(del_index)
if delta < 0:
return
self._storagegroup.attrs[metadata.ATTR_NROWS] = newsize
assert newsize is not None
for column in self._columns:
col = cast(Column, column)
col._resize(newsize)
def restricted_range_query(
self, lower: float, upper: float, only_locs: Any, approximate: bool = APPROX
) -> bitmap:
"""
Return the bitmap of only_locs rows in range [`lower`, `upper`[
"""
if lower > upper:
lower, upper = upper, lower
only_locs = bitmap.asbitmap(only_locs)
pos_lo, pos_up = np.digitize([lower, upper], self.bins) # type: ignore
union = bitmap.union(
*[(bm & only_locs) for bm in self.bitmaps[pos_lo + 1 : pos_up]]
)
if not approximate:
detail = bitmap()
ids = np.array(self.bitmaps[pos_lo] & only_locs, np.int64)
values = self.column.loc[ids]
if pos_lo == pos_up:
selected = ids[(lower <= values) & (values < upper)]
detail.update(selected)
else:
selected = ids[lower <= values]
detail.update(selected)
ids = np.array(self.bitmaps[pos_up] & only_locs, np.int64)
values = self.column.loc[ids]
selected = ids[values < upper]
detail.update(selected)
union.update(detail)
return union
def restricted_query(
self,
operator_: Callable[[Any, Any], int],
limit: Any,
only_locs: Any,
approximate: bool = APPROX,
) -> bitmap: # blocking...
"""
Returns the subset of only_locs matching the query.
"""
only_locs = bitmap.asbitmap(only_locs)
assert self.bins is not None
pos = np.digitize(limit, self.bins)
detail = bitmap()
if not approximate:
ids = np.array(self.bitmaps[pos] & only_locs, np.int64)
values = self.column.loc[ids]
selected = ids[operator_(values, limit)]
detail.update(selected)
if operator_ in (operator.lt, operator.le):
for bm in self.bitmaps[:pos]:
detail.update(bm & only_locs)
else:
for bm in self.bitmaps[pos + 1 :]:
detail.update(bm & only_locs)
return detail
def restricted_range_query(self,
lower,
upper,
only_locs,
approximate=APPROX):
"""
Return the bitmap of only_locs rows in range [`lower`, `upper`[
"""
if lower > upper:
lower, upper = upper, lower
only_locs = bitmap.asbitmap(only_locs)
pos = np.digitize([lower, upper], self.bins)
detail = bitmap()
if not approximate:
ids = np.array(self.bitmaps[pos[0]] & only_locs, np.int64)
values = self.column.loc[ids]
if pos[0] == pos[1]:
selected = ids[(lower <= values) & (values < upper)]
else:
selected = ids[lower <= values]
detail.update(selected)
ids = np.array(self.bitmaps[pos[1]] & only_locs, np.int64)
values = self.column.loc[ids]
selected = ids[values < upper]
detail.update(selected)
for bm in self.bitmaps[pos[0] + 1:pos[1]]:
detail.update(bm & only_locs)
return detail
def update_histogram(self, created, updated=(), deleted=()):
"Update the histogram index"
created = bitmap.asbitmap(created)
updated = bitmap.asbitmap(updated)
deleted = bitmap.asbitmap(deleted)
# if deleted:
# self._tdigest_is_valid = False
if deleted or updated:
to_remove = updated | deleted
for bm in self.bitmaps:
bm -= to_remove
if created or updated:
to_add = created | updated
ids = np.array(to_add, np.int64)
values = self.column.loc[to_add]
#self._tdigest.batch_update(values)
bins = np.digitize(values, self.bins)
counts = np.bincount(bins)
for i in np.nonzero(counts)[0]:
bm = self.bitmaps[i]
selection = (bins == i) # boolean mask of values in bin i
bm.update(ids[selection]) # add them to the bitmap
def _allocate(self,
count: int,
index: Optional[Union[bitmap, List[int]]] = None) -> bitmap:
start = self.last_id + 1
index = (bitmap(range(start, start + count))
if index is None else bitmap.asbitmap(index))
newsize = max(index.max(), self.last_id) + 1
self.add_created(index)
self._storagegroup.attrs[metadata.ATTR_NROWS] = newsize
for column in self._columns:
col = cast(Column, column)
col._resize(newsize)
self._resize_rows(newsize, index)
return index
def __getitem__(self, key):
index, col_key, _ = self.parse_key(key)
if isinstance(index, integer_types):
row = self._table.row(index)
if col_key != slice(None):
return row[col_key]
return row
if isinstance(index, slice) and index.step in (None, 1):
from .table_sliced import TableSlicedView
return TableSlicedView(self._table, index, col_key)
elif isinstance(index, Iterable):
from .table_selected import TableSelectedView
selection = bitmap.asbitmap(self._table.index[index])
return TableSelectedView(self._table, selection, col_key,
self._table.name)
raise ValueError('getitem not implemented for index "%s"', index)
def restricted_query(self,
operator_,
limit,
only_locs,
approximate=APPROX): # blocking...
"""
Returns the subset of only_locs matching the query.
"""
only_locs = bitmap.asbitmap(only_locs)
pos = np.digitize(limit, self.bins)
detail = bitmap()
if not approximate:
ids = np.array(self.bitmaps[pos] & only_locs, np.int64)
values = self.column.loc[ids]
selected = ids[operator_(values, limit)]
detail.update(selected)
if operator_ in (operator.lt, operator.le):
for bm in self.bitmaps[:pos]:
detail.update(bm & only_locs)
else:
for bm in self.bitmaps[pos + 1:]:
detail.update(bm & only_locs)
return detail