From c60a6b1699a6bb5c437ed2846f3f718b3a38c098 Mon Sep 17 00:00:00 2001
From: Yannick DAYER <yannick.dayer@idiap.ch>
Date: Wed, 1 May 2024 15:52:33 +0200
Subject: [PATCH] fix(scores): pandas to read score column as float.
When loading a score file, indicate to pandas to interpret the score
column as float (prevent issues when the first elements are empty).
---
src/bob/bio/base/score/load.py | 9 +++++++--
1 file changed, 7 insertions(+), 2 deletions(-)
diff --git a/src/bob/bio/base/score/load.py b/src/bob/bio/base/score/load.py
index 3ce39f3..60b9fe6 100644
--- a/src/bob/bio/base/score/load.py
+++ b/src/bob/bio/base/score/load.py
@@ -9,6 +9,7 @@ import logging
import os
import tarfile
+from collections import defaultdict
from pathlib import Path
import dask.dataframe
@@ -162,7 +163,9 @@ def get_split_dataframe(filename):
:ref:`bob.bio.base.pipeline_simple_advanced_features`)
"""
- df = dask.dataframe.read_csv(filename)
+ df = dask.dataframe.read_csv(
+ filename, dtype=defaultdict(lambda: str, {"score": float})
+ )
genuines = df[df.probe_subject_id == df.bio_ref_subject_id]
impostors = df[df.probe_subject_id != df.bio_ref_subject_id]
@@ -195,7 +198,9 @@ def split_csv_scores(filename, score_column: str = "score"):
:ref:`bob.bio.base.pipeline_simple_advanced_features`)
"""
- df = dask.dataframe.read_csv(filename)
+ df = dask.dataframe.read_csv(
+ filename, dtype=defaultdict(lambda: str, {"score": float})
+ )
genuines = df[df.probe_subject_id == df.bio_ref_subject_id]
impostors = df[df.probe_subject_id != df.bio_ref_subject_id]
--
GitLab