From f0ee7b727ba6538a3480d54b5a47adae57fceff9 Mon Sep 17 00:00:00 2001
From: Robrecht Cannoodt <rcannood@gmail.com>
Date: Fri, 8 Nov 2024 17:52:35 +0100
Subject: [PATCH] Fix reporting (#914)

* fix extract component

* add to par

* fix par

* add more checks

* simplify

* use pd function

* fix function

* fix function

* update changelog
---
 CHANGELOG.md                             |  4 ++++
 src/utils/extract_uns_metadata/script.py | 11 ++++++-----
 2 files changed, 10 insertions(+), 5 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 276eb63a8..3213323e2 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -28,6 +28,10 @@
 
 - Update `dataset_id` for `tenx_visium`, `zenodo_spatial`, `zenodo_spatial_slidetags` datasets and use `mouse_brain_coronal` as a test resource in the `spatially_variable_genes` task (PR #908).
 
+## Bug fixes
+
+- Fix extracting metadata from anndata files in the `extract_metadata` component (PR #914).
+
 # openproblems v2.0.0
 
 A major update to the OpenProblems framework, switching from a Python-based framework to a Viash + Nextflow-based framework. This update features the same concepts as the previous version, but with a new implementation that is more flexible, scalable, and maintainable.
diff --git a/src/utils/extract_uns_metadata/script.py b/src/utils/extract_uns_metadata/script.py
index 5d759b60a..ac5e93f13 100644
--- a/src/utils/extract_uns_metadata/script.py
+++ b/src/utils/extract_uns_metadata/script.py
@@ -11,6 +11,7 @@
   'input': 'resources_test/common/pancreas/dataset.h5ad',
   'schema': 'src/datasets/api/file_raw.yaml',
   'output': 'output/meta.yaml',
+  'uns_length_cutoff': 100
 }
 ## VIASH END
 
@@ -36,13 +37,13 @@
 ## Helper functions for extracting the dataset metadata in uns                                    ##
 ####################################################################################################
 def is_atomic(obj):
-  return isinstance(obj, str) or isinstance(obj, int) or isinstance(obj, bool) or isinstance(obj, float)
+  return pd.api.types.is_scalar(obj)
 
 def to_atomic(obj):
-  if isinstance(obj, np.float64):
-    return float(obj)
-  elif isinstance(obj, np.int64):
+  if isinstance(obj, (np.int32,np.int64)):
     return int(obj)
+  elif isinstance(obj, (np.float32,np.float64)):
+    return float(obj)
   elif isinstance(obj, np.bool_):
     return bool(obj)
   elif isinstance(obj, np.str_):
@@ -50,7 +51,7 @@ def to_atomic(obj):
   return obj
 
 def is_list_of_atomics(obj):
-  if not isinstance(obj, (list,pd.core.series.Series,np.ndarray)):
+  if not isinstance(obj, (list, pd.core.series.Series, np.ndarray)):
     return False
   return all(is_atomic(elem) for elem in obj)