Merge pull request #441 from pepkit/dev

Release v0.35.5

.gitignore

@@ -79,4 +79,9 @@ peppy.egg-info/
 env/
 .env
 venv/
-.venv/
+.venv/
+
+# swap files
+.swp
+.swo
+.swn

README.md

@@ -12,3 +12,4 @@ Links to complete documentation:
 * Complete documentation and API for the `peppy` python package is at [peppy.databio.org](https://peppy.databio.org).
 * Reference documentation for standard **PEP** format is at [pep.databio.org](https://pep.databio.org/).
 * Example PEPs for testing `peppy` are in the [example_peps repository](https://github.com/pepkit/example_peps).
+* The package [on PyPI](https://pypi.org/project/peppy/).

docs/changelog.md

@@ -2,6 +2,11 @@
 
 This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html) and [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) format.
 
+## [0.35.5] -- 2023-03-27
+### Fixed
+- A [bug](https://github.com/pepkit/peppy/issues/435) with custom sample ids
+- Improved performance for large tables dramatically
+
 ## [0.35.4] -- 2023-01-17
 ### Fixed
 - Fixed disabling rich progress on small datasets bug

peppy/_version.py

@@ -1 +1 @@
-__version__ = "0.35.4"
+__version__ = "0.35.5"

peppy/project.py

@@ -635,26 +635,23 @@ def _all_values_in_the_list_are_the_same(list_of_values: List) -> bool:
         return all(value == list_of_values[0] for value in list_of_values)
 
     def _get_duplicated_sample_ids(self, sample_names_list: List) -> set:
-        return set(
-            [
-                sample_id
-                for sample_id in track(
-                    sample_names_list,
-                    description="Detecting duplicate sample names",
-                    disable=not (self.is_sample_table_large and self.progressbar),
-                    console=Console(file=sys.stderr),
-                )
-                if sample_names_list.count(sample_id) > 1
-            ]
-        )
+        duplicated_ids = set()
+        seen = set()
+
+        for sample_id in sample_names_list:
+            if sample_id in seen:
+                duplicated_ids.add(sample_id)
+            else:
+                seen.add(sample_id)
+
+        return duplicated_ids
 
     @staticmethod
     def _get_merged_attributes(
         sample_attributes: List[str], duplicated_samples: List[Sample]
     ) -> dict:
         merged_attributes = {}
         for attr in sample_attributes:
-
             attribute_values = []
             for sample in duplicated_samples:
                 attribute_value_for_sample = getattr(sample, attr, "")
@@ -836,7 +833,9 @@ def attr_derive(self, attrs=None):
                     _LOGGER.debug("'{}' has been derived".format(attr))
                     continue
                 _LOGGER.debug(
-                    "Deriving '{}' attribute for '{}'".format(attr, sample.sample_name)
+                    "Deriving '{}' attribute for '{}'".format(
+                        attr, sample[self.st_index]
+                    )
                 )
 
                 # Set {atr}_key, so the original source can also be retrieved

peppy/sample.py

@@ -39,7 +39,6 @@ class Sample(PathExAttMap):
     """
 
     def __init__(self, series, prj=None):
-
         super(Sample, self).__init__()
 
         data = OrderedDict(series)

requirements/requirements-all.txt

@@ -1,5 +1,4 @@
 attmap>=0.13.2
-logmuse>=0.2
 pandas>=0.24.2
 pyyaml
 rich>=10.3.0

setup.py

@@ -16,6 +16,7 @@
 # Additional keyword arguments for setup().
 extra = {"install_requires": DEPENDENCIES}
 
+
 # Additional files to include with package
 def get_static(name, condition=None):
     static = [

tests/test_Project.py

@@ -485,7 +485,6 @@ def test_get_sample_nonexistent(self, example_pep_cfg_path):
         """Verify that sample getting returns ValueError if not sample found"""
         p = Project(cfg=example_pep_cfg_path)
         with pytest.raises(ValueError):
-
             p.get_sample(sample_name="kdkdkdk")