Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
59 changes: 55 additions & 4 deletions src/blosc2/ctable.py
Original file line number Diff line number Diff line change
Expand Up @@ -13923,6 +13923,38 @@ def sort_by(
TypeError
If a column used as a sort key does not support ordering
(e.g. complex numbers).

Examples
--------
Create a small table and materialise a plain sort::

>>> import blosc2
>>> from dataclasses import dataclass
>>> @dataclass
... class Record:
... name: str = blosc2.field(blosc2.string(max_length=8))
... score: int = blosc2.field(blosc2.int64())
... group: int = blosc2.field(blosc2.int64())
>>> t = blosc2.CTable(
... Record,
... new_data=[("a", 30, 1), ("b", 10, 2), ("c", 20, 1), ("d", 40, 2)],
... )
>>> t.sort_by("score")["score"][:].tolist()
[10, 20, 30, 40]

Sorting a filtered table stays lazy until rows are read::

>>> filtered = t.where(t.group == 1)
>>> ranked = filtered.sort_by("score")
>>> print(ranked.base is not None)
True
>>> print(ranked["score"][:].tolist())
[20, 30]

Multiple keys are applied from left to right::

>>> t.sort_by(["group", "score"], ascending=[True, False])["name"][:].tolist()
['a', 'c', 'd', 'b']
"""
if inplace and view:
raise ValueError("inplace=True and view=True are mutually exclusive.")
Expand Down Expand Up @@ -15712,14 +15744,33 @@ def where( # noqa: C901

Examples
--------
Start with a small table::

>>> from dataclasses import dataclass
>>> @dataclass
... class Record:
... name: str = blosc2.field(blosc2.string(max_length=8))
... score: int = blosc2.field(blosc2.int64())
... group: int = blosc2.field(blosc2.int64())
>>> t = blosc2.CTable(
... Record,
... new_data=[("a", 30, 1), ("b", 10, 2), ("c", 20, 1), ("d", 40, 2)],
... )

Filter using a string expression::

view = t.where("value * category >= 150")
slim = t.where("value * category >= 150", columns=["value", "category"])
>>> view = t.where("score > 15")
>>> print(view.base is t, view.nrows)
True 3
>>> slim = t.where("score > 15", columns=["name", "score"])
>>> print(slim.col_names)
['name', 'score']

Filter using column arithmetic::
Compound predicates can use column expressions::

view = t.where((t.value * t.category) >= 150)
>>> selected = t.where((t.group == 1) & (t.score >= 25))
>>> print(selected["name"][:].tolist())
['a']

Blosc2 lazy functions can be used in column expressions::

Expand Down
Loading