Skip to content

chore: move LMDB imports into methods for performance #945

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
njzjz wants to merge 3 commits into
base: master
Choose a base branch
from
Draft

chore: move LMDB imports into methods for performance #945

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
a83abdf
chore: move LMDB imports into methods for performance
njzjz Feb 27, 2026
876a866
Update format.py
njzjz Feb 27, 2026
dc22e44
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Feb 27, 2026
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
18 changes: 13 additions & 5 deletions dpdata/lmdb/format.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,15 +2,10 @@

import os

import lmdb
import msgpack
import msgpack_numpy as m
import numpy as np

from dpdata.format import Format

m.patch()


class LMDBError(Exception):
"""Base class for LMDB errors."""
Expand Down Expand Up @@ -63,6 +58,11 @@ class LMDBFormat(Format):
>>> loaded_multi_systems = dpdata.MultiSystems.from_file("my_multi_system_db.lmdb", fmt="lmdb")
"""

def __init__(self, *args, **kwargs) -> None:
import msgpack_numpy as m

m.patch()

def to_multi_systems(
self, formulas, directory, map_size=1000000000, frame_idx_fmt="012d", **kwargs
):
Expand All @@ -86,6 +86,9 @@ def to_multi_systems(
tuple
(self, formula) to be used by to_system
"""
import lmdb
import msgpack

self._frame_idx_fmt = frame_idx_fmt
self._global_frame_idx = 0
self._system_info = []
Expand All @@ -105,6 +108,8 @@ def to_multi_systems(
self._txn = None

def _dump_to_txn(self, data, txn, formula, dtypes):
import msgpack

from dpdata.data_type import Axis

nframes = data["coords"].shape[0]
Expand Down Expand Up @@ -209,6 +214,9 @@ def from_multi_systems(self, file_name, map_size=1000000000, **kwargs):
dict
data dictionary for each system
"""
import lmdb
import msgpack

from dpdata.data_type import Axis, DataType
from dpdata.system import LabeledSystem, System

Expand Down