From e188d8045275dbdb83062d94affd323e64346613 Mon Sep 17 00:00:00 2001 From: Wout Bittremieux Date: Wed, 24 Jul 2024 09:39:05 +0200 Subject: [PATCH] Report number of batches in the dataset Useful for timing estimates in the progress bar. --- depthcharge/data/spectrum_datasets.py | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/depthcharge/data/spectrum_datasets.py b/depthcharge/data/spectrum_datasets.py index 1944ea9..05038eb 100644 --- a/depthcharge/data/spectrum_datasets.py +++ b/depthcharge/data/spectrum_datasets.py @@ -4,6 +4,7 @@ import copy import logging +import math import uuid from collections.abc import Generator, Iterable from os import PathLike @@ -178,6 +179,10 @@ def __del__(self) -> None: if self._tmpdir is not None: self._tmpdir.cleanup() + def __len__(self) -> int: + """The number of batches in the dataset.""" + return math.ceil(self.n_spectra / self.batch_size) + @property def n_spectra(self) -> int: """The number of spectra in the Lance dataset."""