masster 0.4.13__tar.gz → 0.4.14__tar.gz

{masster-0.4.13 → masster-0.4.14}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.4.13
+Version: 0.4.14
 Summary: Mass spectrometry data analysis package
 Project-URL: homepage, https://github.com/zamboni-lab/masster
 Project-URL: repository, https://github.com/zamboni-lab/masster

{masster-0.4.13 → masster-0.4.14}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.4.13"
+version = "0.4.14"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }

{masster-0.4.13 → masster-0.4.14}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.4.13"
+__version__ = "0.4.14"
 
 
 def get_version():

{masster-0.4.13 → masster-0.4.14}/src/masster/sample/sample.py

@@ -299,6 +299,47 @@ class Sample:
     find_ms2_defaults = find_ms2_defaults
     get_spectrum_defaults = get_spectrum_defaults
 
+    def __dir__(self):
+        """
+        Custom __dir__ implementation to hide internal methods starting with '_' 
+        and backward compatibility aliases from tab completion and dir() calls, 
+        while keeping them accessible to class methods.
+        
+        Returns:
+            list: List of public attribute and method names (excluding internal and deprecated methods)
+        """
+        # Define backward compatibility aliases to hide
+        backward_compatibility_aliases = {
+            'load_study',           # deprecated alias for load_noms1
+            'filter_features',      # alias for filter (deprecated naming)
+            'select_features',      # alias for select (deprecated naming)
+            'features_filter',      # confusing duplicate of filter
+            'features_select',      # confusing duplicate of select
+            'merge_defaults',       # alias for find_features_defaults (confusing)
+        }
+        
+        # Get all attributes from the class
+        all_attrs = set()
+        
+        # Add attributes from the class and all its bases
+        for cls in self.__class__.__mro__:
+            all_attrs.update(cls.__dict__.keys())
+        
+        # Add instance attributes
+        all_attrs.update(self.__dict__.keys())
+        
+        # Filter out attributes starting with '_' (but keep special methods like __init__, __str__, etc.)
+        # Also filter out backward compatibility aliases
+        public_attrs = [
+            attr for attr in all_attrs 
+            if not attr.startswith('_') or attr.startswith('__') and attr.endswith('__')
+        ]
+        
+        # Remove backward compatibility aliases from the public attributes
+        public_attrs = [attr for attr in public_attrs if attr not in backward_compatibility_aliases]
+        
+        return sorted(public_attrs)
+
     def logger_update(
         self,
         level: str | None = None,

{masster-0.4.13 → masster-0.4.14}/src/masster/study/processing.py

@@ -290,6 +290,85 @@ def merge(self, **kwargs):
     # Complete merge process
     self._finalize_merge(link_ms2, min_samples)
 
+def _perform_adduct_grouping(self, rt_tol, mz_tol):
+    """Perform adduct grouping on consensus features."""
+    # Add adduct grouping and adduct_of assignment
+    if len(self.consensus_df) > 0:
+        # Get relevant columns for grouping
+        consensus_data = []
+        for row in self.consensus_df.iter_rows(named=True):
+            consensus_data.append(
+                {
+                    "consensus_uid": row["consensus_uid"],
+                    "rt": row["rt"],
+                    "adduct_mass_neutral_top": row.get("adduct_mass_neutral_top"),
+                    "adduct_top": row.get("adduct_top"),
+                    "inty_mean": row.get("inty_mean", 0),
+                },
+            )
+
+        # Use optimized adduct grouping
+        adduct_group_list, adduct_of_list = _optimized_adduct_grouping(
+            self, consensus_data, rt_tol, mz_tol
+        )
+
+        # Add the new columns to consensus_df
+        self.consensus_df = self.consensus_df.with_columns(
+            [
+                pl.Series("adduct_group", adduct_group_list, dtype=pl.Int64),
+                pl.Series("adduct_of", adduct_of_list, dtype=pl.Int64),
+            ],
+        )
+
+def _finalize_merge(self, link_ms2, min_samples):
+    """Complete the merge process with final calculations and cleanup."""
+    # Validate min_samples parameter
+    if min_samples is None:
+        min_samples = 1
+    if min_samples < 1:
+        min_samples = int(min_samples * len(self.samples_df))
+
+    # Validate that min_samples doesn't exceed the number of samples
+    if min_samples > len(self.samples_df):
+        self.logger.warning(
+            f"min_samples ({min_samples}) exceeds the number of samples ({len(self.samples_df)}). "
+            f"Setting min_samples to {len(self.samples_df)}.",
+        )
+        min_samples = len(self.samples_df)
+
+    # Filter out consensus features with less than min_samples features
+    l1 = len(self.consensus_df)
+    self.consensus_df = self.consensus_df.filter(
+        pl.col("number_samples") >= min_samples,
+    )
+    self.logger.debug(
+        f"Filtered {l1 - len(self.consensus_df)} consensus features with less than {min_samples} samples.",
+    )
+    
+    # Filter out consensus mapping with less than min_samples features
+    self.consensus_mapping_df = self.consensus_mapping_df.filter(
+        pl.col("consensus_uid").is_in(self.consensus_df["consensus_uid"].to_list()),
+    )
+
+    # Calculate the completeness of the consensus map
+    if len(self.consensus_df) > 0 and len(self.samples_df) > 0:
+        c = (
+            len(self.consensus_mapping_df)
+            / len(self.consensus_df)
+            / len(self.samples_df)
+        )
+        self.logger.info(
+            f"Merging completed. Consensus features: {len(self.consensus_df)}. Completeness: {c:.2f}.",
+        )
+    else:
+        self.logger.warning(
+            f"Merging completed with empty result. Consensus features: {len(self.consensus_df)}. "
+            f"This may be due to min_samples ({min_samples}) being too high for the available data.",
+        )
+    
+    if link_ms2:
+        self.find_ms2()
+
 def _reset_consensus_data(self):
     """Reset consensus-related DataFrames at the start of merge."""
     self.consensus_df = pl.DataFrame()
@@ -605,7 +684,6 @@ def _extract_consensus_features(self, consensus_map, min_samples):
             total_count = sum(adduct_counts.values())
             for adduct, count in adduct_counts.items():
                 percentage = (count / total_count) * 100 if total_count > 0 else 0
-                mass = adduct_masses.get(adduct, None)
                 # Store as list with [name, num, %] format for the adducts column
                 adduct_values.append(
                     [
@@ -872,56 +950,6 @@ def _extract_consensus_features(self, consensus_map, min_samples):
 
     self.consensus_map = consensus_map
 
-    # Add adduct grouping and adduct_of assignment
-    if len(self.consensus_df) > 0:
-        # Get rt_tol and mz_tol from kwargs or use defaults from merge_defaults
-        adduct_rt_tol = rt_tol  # Use the same rt_tol from merge parameters
-        adduct_mz_tol = mz_tol  # Use the same mz_tol from merge parameters
-
-        # Get relevant columns for grouping
-        consensus_data = []
-        for row in self.consensus_df.iter_rows(named=True):
-            consensus_data.append(
-                {
-                    "consensus_uid": row["consensus_uid"],
-                    "rt": row["rt"],
-                    "adduct_mass_neutral_top": row.get("adduct_mass_neutral_top"),
-                    "adduct_top": row.get("adduct_top"),
-                    "inty_mean": row.get("inty_mean", 0),
-                },
-            )
-
-        # Use optimized adduct grouping
-        adduct_group_list, adduct_of_list = _optimized_adduct_grouping(
-            self, consensus_data, adduct_rt_tol, adduct_mz_tol
-        )
-
-        # Add the new columns to consensus_df
-        self.consensus_df = self.consensus_df.with_columns(
-            [
-                pl.Series("adduct_group", adduct_group_list, dtype=pl.Int64),
-                pl.Series("adduct_of", adduct_of_list, dtype=pl.Int64),
-            ],
-        )
-
-    # calculate the completeness of the consensus map
-    if len(self.consensus_df) > 0 and len(self.samples_df) > 0:
-        c = (
-            len(self.consensus_mapping_df)
-            / len(self.consensus_df)
-            / len(self.samples_df)
-        )
-        self.logger.info(
-            f"Merging completed. Consensus features: {len(self.consensus_df)}. Completeness: {c:.2f}.",
-        )
-    else:
-        self.logger.warning(
-            f"Merging completed with empty result. Consensus features: {len(self.consensus_df)}. "
-            f"This may be due to min_samples ({min_samples}) being too high for the available data.",
-        )
-    if link_ms2:
-        self.find_ms2()
-
 
 def _optimized_feature_lookup(study_obj, features_df):
     """

{masster-0.4.13 → masster-0.4.14}/src/masster/study/study.py

@@ -119,6 +119,13 @@ from masster.study.processing import align
 from masster.study.processing import merge
 from masster.study.processing import integrate
 from masster.study.processing import find_ms2
+from masster.study.processing import _reset_consensus_data
+from masster.study.processing import _process_merge_parameters
+from masster.study.processing import _validate_merge_inputs
+from masster.study.processing import _perform_feature_grouping
+from masster.study.processing import _extract_consensus_features
+from masster.study.processing import _perform_adduct_grouping
+from masster.study.processing import _finalize_merge
 from masster.study.parameters import store_history
 from masster.study.parameters import get_parameters
 from masster.study.parameters import update_parameters
@@ -490,6 +497,15 @@ class Study:
     _format_adduct_name = _format_adduct_name
     _parse_element_counts = _parse_element_counts
     
+    # === Merge Helper Methods ===
+    _reset_consensus_data = _reset_consensus_data
+    _process_merge_parameters = _process_merge_parameters
+    _validate_merge_inputs = _validate_merge_inputs
+    _perform_feature_grouping = _perform_feature_grouping
+    _extract_consensus_features = _extract_consensus_features
+    _perform_adduct_grouping = _perform_adduct_grouping
+    _finalize_merge = _finalize_merge
+    
     # === Default Parameters ===
     study_defaults = study_defaults
     align_defaults = align_defaults
@@ -587,6 +603,51 @@ class Study:
         except Exception as e:
             self.logger.error(f"Failed to reload current module {current_module}: {e}")
 
+    def __dir__(self):
+        """
+        Custom __dir__ implementation to hide internal methods starting with '_' 
+        and backward compatibility aliases from tab completion and dir() calls, 
+        while keeping them accessible to class methods.
+        
+        Returns:
+            list: List of public attribute and method names (excluding internal and deprecated methods)
+        """
+        # Define backward compatibility aliases to hide
+        backward_compatibility_aliases = {
+            'add_folder',           # alias for add
+            'find_consensus',       # alias for merge  
+            'integrate_chrom',      # alias for integrate
+            'fill_chrom',           # alias for fill
+            'fill_chrom_single',    # alias for fill_single
+            'filter_consensus',     # alias for consensus_filter
+            'select_consensus',     # alias for consensus_select
+            'filter_features',      # alias for features_filter
+            'select_features',      # alias for features_select
+            'consensus_find',       # alias for merge
+        }
+        
+        # Get all attributes from the class
+        all_attrs = set()
+        
+        # Add attributes from the class and all its bases
+        for cls in self.__class__.__mro__:
+            all_attrs.update(cls.__dict__.keys())
+        
+        # Add instance attributes
+        all_attrs.update(self.__dict__.keys())
+        
+        # Filter out attributes starting with '_' (but keep special methods like __init__, __str__, etc.)
+        # Also filter out backward compatibility aliases
+        public_attrs = [
+            attr for attr in all_attrs 
+            if not attr.startswith('_') or attr.startswith('__') and attr.endswith('__')
+        ]
+        
+        # Remove backward compatibility aliases from the public attributes
+        public_attrs = [attr for attr in public_attrs if attr not in backward_compatibility_aliases]
+        
+        return sorted(public_attrs)
+
     def __str__(self):
         """
         Returns a string representation of the study.

{masster-0.4.13 → masster-0.4.14}/uv.lock

@@ -1374,7 +1374,7 @@ wheels = [
 
 [[package]]
 name = "masster"
-version = "0.4.13"
+version = "0.4.14"
 source = { editable = "." }
 dependencies = [
     { name = "alpharaw" },