Merge pull request #248 from monarch-initiative/it_to_files

updated tqdm to print files/sec instead of it/sec
monarch-initiative · Sep 13, 2024 · 1e3b011 · 1e3b011
2 parents c5e6996 + 5fc0464
commit 1e3b011
Show file tree

Hide file tree

Showing 6 changed files with 7 additions and 7 deletions.
diff --git a/docs/tutorial.rst b/docs/tutorial.rst
@@ -84,7 +84,7 @@ a :class:`~gpsea.model.Cohort`:
 ...     phenopackets=phenopackets,
 ...     cohort_creator=cohort_creator,
 ... )
-Patients Created: ...
+Individuals Processed: ...
 
 and we will check that there are no Q/C issues:
 

diff --git a/docs/user-guide/input-data.rst b/docs/user-guide/input-data.rst
@@ -80,7 +80,7 @@ loader function:
 
 >>> from gpsea.preprocessing import load_phenopackets
 >>> cohort, qc_results = load_phenopackets(phenopackets, cohort_creator)  # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-Patients Created: ...
+Individuals Processed: ...
 >>> len(cohort)
 19
 

diff --git a/docs/user-guide/predicates/hpo_predicate.rst b/docs/user-guide/predicates/hpo_predicate.rst
@@ -71,7 +71,7 @@ processed into a cohort
 >>> from gpsea.preprocessing import configure_caching_cohort_creator, load_phenopackets
 >>> cohort_creator = configure_caching_cohort_creator(hpo)
 >>> cohort, _ = load_phenopackets(phenopackets, cohort_creator)  # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-Patients Created: ...
+Individuals Processed: ...
 
 
 we can create HPO predicates for testing all 260 HPO terms used in the cohort

diff --git a/docs/user-guide/predicates/variant_predicates.rst b/docs/user-guide/predicates/variant_predicates.rst
@@ -60,7 +60,7 @@ and we will convert the phenopacket into a :class:`~gpsea.model.Cohort`:
 
 >>> from gpsea.preprocessing import load_phenopackets
 >>> cohort, _ = load_phenopackets(phenopackets, cohort_creator)  # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-Patients Created: ...
+Individuals Processed: ...
 
 To demonstrate the predicate API, we will use the variant ``1_8358231_8358231_T_C`` that corresponds 
 to a pathogenic variant `VCV000522858.5 <https://www.ncbi.nlm.nih.gov/clinvar/variation/522858/>`_ 

diff --git a/docs/user-guide/stats.rst b/docs/user-guide/stats.rst
@@ -102,7 +102,7 @@ with the default cohort creator:
 >>> from gpsea.preprocessing import configure_caching_cohort_creator, load_phenopackets
 >>> cohort_creator = configure_caching_cohort_creator(hpo)
 >>> cohort, qc_results = load_phenopackets(phenopackets, cohort_creator)  # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-Patients Created: ...
+Individuals Processed: ...
 >>> qc_results.summarize()  # doctest: +SKIP
 Validated under none policy
 No errors or warnings were found
@@ -344,7 +344,7 @@ which we will use to preprocess the cohort
 
 >>> from gpsea.preprocessing import load_phenopackets
 >>> cohort, _ = load_phenopackets(phenopackets, cohort_creator)  # doctest: +ELLIPSIS, +NORMALIZE_WHITESPACE
-Patients Created: ...
+Individuals Processed: ...
 
 
 resulting in a cohort consisting of 19 individuals

diff --git a/src/gpsea/preprocessing/_config.py b/src/gpsea/preprocessing/_config.py
@@ -455,7 +455,7 @@ def load_phenopackets(
     # Turn phenopackets into a cohort using the cohort creator.
     # Keep track of the progress by wrapping the list of phenopackets
     # with TQDM 😎
-    cohort_iter = tqdm(phenopackets, desc="Patients Created", file=sys.stdout)
+    cohort_iter = tqdm(phenopackets, desc="Individuals Processed", file=sys.stdout, unit="individuals")
     notepad = cohort_creator.prepare_notepad("Phenopackets")
     cohort = cohort_creator.process(cohort_iter, notepad)