masster 0.5.22__py3-none-any.whl → 0.5.24__py3-none-any.whl

masster/study/save.py

@@ -48,11 +48,7 @@ def save(self, filename=None, add_timestamp=True, compress=False):
     # Log file size information for performance monitoring
     if hasattr(self, "features_df") and not self.features_df.is_empty():
         feature_count = len(self.features_df)
-        sample_count = (
-            len(self.samples_df)
-            if hasattr(self, "samples_df") and not self.samples_df.is_empty()
-            else 0
-        )
+        sample_count = len(self.samples_df) if hasattr(self, "samples_df") and not self.samples_df.is_empty() else 0
         self.logger.debug(
             f"Saving study with {sample_count} samples and {feature_count} features to {filename}",
         )
@@ -60,14 +56,17 @@ def save(self, filename=None, add_timestamp=True, compress=False):
     # Use compressed mode for large datasets
     if compress:
         from masster.study.h5 import _save_study5_compressed
+
         _save_study5_compressed(self, filename)
     else:
         from masster.study.h5 import _save_study5
+
         _save_study5(self, filename)
 
     if self.consensus_map is not None:
         # save the features as a separate file
         from masster.study.save import _save_consensusXML
+
         _save_consensusXML(self, filename=filename.replace(".study5", ".consensusXML"))
     self.filename = filename
 
@@ -160,14 +159,15 @@ def _save_consensusXML(self, filename: str):
     if self.consensus_df is None or self.consensus_df.is_empty():
         self.logger.error("No consensus features found.")
         return
-        
+
     # Build consensus map from consensus_df with proper consensus_id values
     import pyopenms as oms
+
     consensus_map = oms.ConsensusMap()
-    
+
     # Set up file descriptions for all samples
     file_descriptions = consensus_map.getColumnHeaders()
-    if hasattr(self, 'samples_df') and not self.samples_df.is_empty():
+    if hasattr(self, "samples_df") and not self.samples_df.is_empty():
         for i, sample_row in enumerate(self.samples_df.iter_rows(named=True)):
             file_description = file_descriptions.get(i, oms.ColumnHeader())
             file_description.filename = sample_row.get("sample_name", f"sample_{i}")
@@ -175,17 +175,17 @@ def _save_consensusXML(self, filename: str):
             file_description.unique_id = i + 1
             file_descriptions[i] = file_description
         consensus_map.setColumnHeaders(file_descriptions)
-    
+
     # Add consensus features to the map (simplified version without individual features)
     for consensus_row in self.consensus_df.iter_rows(named=True):
         consensus_feature = oms.ConsensusFeature()
-        
+
         # Set basic properties
         consensus_feature.setRT(float(consensus_row.get("rt", 0.0)))
         consensus_feature.setMZ(float(consensus_row.get("mz", 0.0)))
         consensus_feature.setIntensity(float(consensus_row.get("inty_mean", 0.0)))
         consensus_feature.setQuality(float(consensus_row.get("quality", 1.0)))
-        
+
         # Set the unique consensus_id as the unique ID
         consensus_id_str = consensus_row.get("consensus_id", "")
         if consensus_id_str and len(consensus_id_str) == 16:
@@ -199,9 +199,9 @@ def _save_consensusXML(self, filename: str):
         else:
             # Fallback to consensus_uid
             consensus_feature.setUniqueId(consensus_row.get("consensus_uid", 0))
-        
+
         consensus_map.push_back(consensus_feature)
-    
+
     # Save the consensus map
     fh = oms.ConsensusXMLFile()
     fh.store(filename, consensus_map)
@@ -215,4 +215,5 @@ def save_consensus(self, **kwargs):
         self.logger.error("No consensus map found.")
         return
     from masster.study.save import _save_consensusXML
+
     _save_consensusXML(self, **kwargs)

masster/study/study.py

@@ -80,7 +80,8 @@ from masster.study.load import add
 from masster.study.load import add_sample
 from masster.study.load import fill
 from masster.study.load import load
-#from masster.study.load import _load_features
+
+# from masster.study.load import _load_features
 from masster.study.h5 import _load_ms1
 from masster.study.h5 import _load_study5
 from masster.study.h5 import _save_study5
@@ -215,13 +216,13 @@ class Study:
         """
         # ===== PARAMETER INITIALIZATION =====
         auto_load_filename = self._init_parameters(filename, kwargs)
-        
+
         # ===== DATA STRUCTURES INITIALIZATION =====
         self._init_data_structures()
-        
+
         # ===== LOGGER INITIALIZATION =====
         self._init_logger()
-        
+
         # ===== AUTO-LOAD FILE IF PROVIDED =====
         if auto_load_filename is not None:
             self.load(filename=auto_load_filename)
@@ -266,11 +267,7 @@ class Study:
         # Set instance attributes (ensure proper string values for logger)
         self.folder = params.folder
         self.label = params.label
-        self.polarity = (
-            params.polarity
-            if params.polarity in ["positive", "negative", "pos", "neg"]
-            else "positive"
-        )
+        self.polarity = params.polarity if params.polarity in ["positive", "negative", "pos", "neg"] else "positive"
         self.log_level = params.log_level.upper() if params.log_level else "INFO"
         self.log_label = params.log_label + " | " if params.log_label else ""
         self.log_sink = params.log_sink
@@ -278,7 +275,7 @@ class Study:
         # Create folder if it doesn't exist
         if self.folder is not None and not os.path.exists(self.folder):
             os.makedirs(self.folder)
-            
+
         return auto_load_filename
 
     def _init_data_structures(self):
@@ -316,11 +313,11 @@ class Study:
                 "num_ms2": pl.Int64,
             },
         )
-        
+
         # Feature-related data structures
         self.features_maps = []
         self.features_df = pl.DataFrame()
-        
+
         # Consensus-related data structures
         self.consensus_ms2 = pl.DataFrame()
         self.consensus_df = pl.DataFrame()
@@ -330,7 +327,7 @@ class Study:
 
         # Library and identification data structures
         self.lib_df = pl.DataFrame()  # populated by lib_load
-        self.id_df = pl.DataFrame()   # populated by identify
+        self.id_df = pl.DataFrame()  # populated by identify
 
     def _init_logger(self):
         """Initialize the logger for this Study instance."""
@@ -352,24 +349,24 @@ class Study:
     _load_ms1 = _load_ms1
     _load_study5 = _load_study5
     _save_study5 = _save_study5
-    
+
     # === Sample Management ===
     add = add
     add_sample = add_sample
-    
+
     # === Core Processing Operations ===
     align = align
-    merge = merge   
-    
+    merge = merge
+
     find_ms2 = find_ms2
     find_iso = find_iso
     reset_iso = reset_iso
     iso_reset = reset_iso
     integrate = integrate
-    
+
     fill = fill
-    #_estimate_rt_original_for_filled_feature = _estimate_rt_original_for_filled_feature
-    
+    # _estimate_rt_original_for_filled_feature = _estimate_rt_original_for_filled_feature
+
     # === Data Retrieval and Access ===
     get_consensus = get_consensus
     get_chrom = get_chrom
@@ -382,11 +379,11 @@ class Study:
     get_sample_stats = get_sample_stats
     get_consensus_stats = get_consensus_stats
     _get_adducts = _get_adducts
-    
+
     # === Data Selection and Filtering ===
     samples_select = samples_select
     samples_delete = samples_delete
-    
+
     features_select = features_select
     features_filter = features_filter
     features_delete = features_delete
@@ -397,22 +394,22 @@ class Study:
     # === Sample Metadata and Styling ===
     set_samples_source = set_samples_source
     set_samples_color = set_samples_color
-       
+
     samples_name_replace = sample_name_replace
     samples_name_reset = sample_name_reset
-    
+
     # Backward compatibility aliases for renamed methods
     set_folder = set_study_folder
-    set_source = set_samples_source  
-    #sample_color = set_samples_color
-    #get_sample = get_samples
-    #load_features = _load_features
+    set_source = set_samples_source
+    # sample_color = set_samples_color
+    # get_sample = get_samples
+    # load_features = _load_features
     store_history = update_history
-    
+
     # === Data Compression and Storage ===
     compress = compress
     decompress = decompress
-    
+
     # === Reset Operations ===
     consensus_reset = consensus_reset
     fill_reset = fill_reset
@@ -435,27 +432,29 @@ class Study:
 
     # === Analysis Operations ===
     analyze_umap = analyze_umap
-    
+
     # === Export Operations ===
     export_mgf = export_mgf
     export_mztab = export_mztab
     export_xlsx = export_xlsx
     export_parquet = export_parquet
-    
+
     # === Identification and Library Matching ===
     lib_load = lib_load
-    
+
     def lib_to_consensus(self, **kwargs):
         """Create consensus features from library entries."""
         from masster.study.id import lib_to_consensus as _lib_to_consensus
+
         return _lib_to_consensus(self, **kwargs)
+
     identify = identify
     get_id = get_id
     id_reset = id_reset
     reset_id = id_reset
     lib_reset = lib_reset
     reset_lib = lib_reset
-    
+
     # === Oracle Import Operations ===
     import_oracle = import_oracle
 
@@ -465,12 +464,12 @@ class Study:
     update_parameters = update_parameters
     get_parameters_property = get_parameters_property
     set_parameters_property = set_parameters_property
-    
+
     # === Private/Internal Methods ===
     _get_consensus_uids = _get_consensus_uids
     _get_features_uids = _get_features_uids
     _get_samples_uids = _get_samples_uids
-    
+
     # === Default Parameters ===
     study_defaults = study_defaults
     align_defaults = align_defaults
@@ -506,10 +505,7 @@ class Study:
 
         # Get all currently loaded modules that are part of the study package
         for module_name in sys.modules:
-            if (
-                module_name.startswith(study_module_prefix)
-                and module_name != current_module
-            ):
+            if module_name.startswith(study_module_prefix) and module_name != current_module:
                 study_modules.append(module_name)
 
         # Add core masster modules
@@ -524,20 +520,14 @@ class Study:
         sample_modules = []
         sample_module_prefix = f"{base_modname}.sample."
         for module_name in sys.modules:
-            if (
-                module_name.startswith(sample_module_prefix)
-                and module_name != current_module
-            ):
+            if module_name.startswith(sample_module_prefix) and module_name != current_module:
                 sample_modules.append(module_name)
 
         # Add lib submodules
         lib_modules = []
         lib_module_prefix = f"{base_modname}.lib."
         for module_name in sys.modules:
-            if (
-                module_name.startswith(lib_module_prefix)
-                and module_name != current_module
-            ):
+            if module_name.startswith(lib_module_prefix) and module_name != current_module:
                 lib_modules.append(module_name)
 
         all_modules_to_reload = core_modules + sample_modules + study_modules + lib_modules
@@ -565,73 +555,66 @@ class Study:
             self.logger.debug("Module reload completed")
         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, 
+        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
-            '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
+            "add_folder",  # alias for add
+            "find_consensus",  # alias for merge
+            "integrate_chrom",  # alias for integrate
+            "fill_chrom",  # alias for fill
+            "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
             # Backward compatibility for renamed methods
-            'set_folder',           # alias for set_study_folder
-            'set_source',           # alias for set_samples_source
-            'sample_color',         # alias for set_samples_color
-            'get_sample',           # alias for get_samples
-            'load_features',        # alias for _load_features
-            'store_history',        # alias for update_history
-            'sample_color_reset',   # alias for set_samples_color(by=None)
-            'reset_sample_color',   # alias for sample_color_reset
+            "set_folder",  # alias for set_study_folder
+            "set_source",  # alias for set_samples_source
+            "sample_color",  # alias for set_samples_color
+            "get_sample",  # alias for get_samples
+            "load_features",  # alias for _load_features
+            "store_history",  # alias for update_history
+            "sample_color_reset",  # alias for set_samples_color(by=None)
+            "reset_sample_color",  # alias for sample_color_reset
         }
-        
+
         # Get all attributes from the class
         all_attrs: set[str] = 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('__')
+            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):
         """
         Return a short summary string with number of samples and consensus features.
         """
-        samples = (
-            len(self.samples_df)
-            if (self.samples_df is not None and not self.samples_df.is_empty())
-            else 0
-        )
+        samples = len(self.samples_df) if (self.samples_df is not None and not self.samples_df.is_empty()) else 0
         consensus = (
-            len(self.consensus_df)
-            if (self.consensus_df is not None and not self.consensus_df.is_empty())
-            else 0
+            len(self.consensus_df) if (self.consensus_df is not None and not self.consensus_df.is_empty()) else 0
         )
         return f"{samples} samples, {consensus} consensus"
 
@@ -699,8 +682,7 @@ class Study:
             max_samples = 0
 
         # Count only features where 'filled' == False
-        if (self.features_df is not None and not self.features_df.is_empty() and 
-            "filled" in self.features_df.columns):
+        if self.features_df is not None and not self.features_df.is_empty() and "filled" in self.features_df.columns:
             unfilled_features_count = self.features_df.filter(
                 ~self.features_df["filled"],
             ).height
@@ -708,8 +690,12 @@ class Study:
             unfilled_features_count = 0
 
         # Calculate features in consensus vs not in consensus (only for unfilled features)
-        if (self.features_df is not None and not self.features_df.is_empty() and 
-            self.consensus_mapping_df is not None and not self.consensus_mapping_df.is_empty()):
+        if (
+            self.features_df is not None
+            and not self.features_df.is_empty()
+            and self.consensus_mapping_df is not None
+            and not self.consensus_mapping_df.is_empty()
+        ):
             # Get unfilled features only
             unfilled_features = (
                 self.features_df.filter(~self.features_df["filled"])
@@ -730,17 +716,13 @@ class Study:
                     unfilled_features = unfilled_features.with_columns(
                         pl.col("feature_uid").cast(pl.Int64),
                     )
-                    consensus_feature_uids = [
-                        int(uid) for uid in consensus_feature_uids
-                    ]
+                    consensus_feature_uids = [int(uid) for uid in consensus_feature_uids]
                 except Exception:
                     # If casting fails, ensure both are strings
                     unfilled_features = unfilled_features.with_columns(
                         pl.col("feature_uid").cast(pl.Utf8),
                     )
-                    consensus_feature_uids = [
-                        str(uid) for uid in consensus_feature_uids
-                    ]
+                    consensus_feature_uids = [str(uid) for uid in consensus_feature_uids]
 
             # Count unfilled features that are in consensus
             in_consensus_count = unfilled_features.filter(
@@ -749,12 +731,8 @@ class Study:
 
             # Calculate ratios that sum to 100%
             total_unfilled = unfilled_features.height
-            ratio_in_consensus_to_total = (
-                (in_consensus_count / total_unfilled * 100) if total_unfilled > 0 else 0
-            )
-            ratio_not_in_consensus_to_total = (
-                100 - ratio_in_consensus_to_total if total_unfilled > 0 else 0
-            )
+            ratio_in_consensus_to_total = (in_consensus_count / total_unfilled * 100) if total_unfilled > 0 else 0
+            ratio_not_in_consensus_to_total = 100 - ratio_in_consensus_to_total if total_unfilled > 0 else 0
         else:
             ratio_in_consensus_to_total = 0
             ratio_not_in_consensus_to_total = 0
@@ -789,8 +767,7 @@ class Study:
                     )
 
             # Use more efficient counting - count non-null chroms only for features in consensus mapping
-            if (self.consensus_mapping_df is not None and 
-                not self.consensus_mapping_df.is_empty()):
+            if self.consensus_mapping_df is not None and not self.consensus_mapping_df.is_empty():
                 non_null_chroms = (
                     self.features_df.join(
                         self.consensus_mapping_df.select("feature_uid"),
@@ -805,9 +782,7 @@ class Study:
             else:
                 non_null_chroms = 0
             total_possible = samples_df_len * consensus_df_len
-            chrom_completeness = (
-                non_null_chroms / total_possible if total_possible > 0 else 0
-            )
+            chrom_completeness = non_null_chroms / total_possible if total_possible > 0 else 0
         else:
             chrom_completeness = 0
 
@@ -831,19 +806,13 @@ class Study:
                 rt_spread_row = filtered.select(
                     (pl.col("rt_max") - pl.col("rt_min")).mean(),
                 ).row(0)
-                rt_spread = (
-                    float(rt_spread_row[0])
-                    if rt_spread_row and rt_spread_row[0] is not None
-                    else 0.0
-                )
+                rt_spread = float(rt_spread_row[0]) if rt_spread_row and rt_spread_row[0] is not None else 0.0
         else:
             rt_spread = -1.0
 
         # Calculate percentage of consensus features with MS2
         consensus_with_ms2_percentage = (
-            (consensus_with_ms2_count / consensus_df_len * 100)
-            if consensus_df_len > 0
-            else 0
+            (consensus_with_ms2_count / consensus_df_len * 100) if consensus_df_len > 0 else 0
         )
 
         # Total MS2 spectra count
@@ -865,6 +834,7 @@ class Study:
         if consensus_df_len > 0:
             try:
                 from masster.study.merge import _count_tight_clusters
+
                 tight_clusters_count = _count_tight_clusters(self, mz_tol=0.04, rt_tol=0.3)
             except Exception:
                 # If tight clusters calculation fails, just use 0
@@ -874,25 +844,13 @@ class Study:
         consensus_warning = f" {_WARNING_SYMBOL}" if consensus_df_len < 50 else ""
 
         rt_spread_text = "N/A" if rt_spread < 0 else f"{rt_spread:.3f}s"
-        rt_spread_warning = (
-            f" {_WARNING_SYMBOL}"
-            if rt_spread >= 0 and (rt_spread > 5 or rt_spread < 0.1)
-            else ""
-        )
+        rt_spread_warning = f" {_WARNING_SYMBOL}" if rt_spread >= 0 and (rt_spread > 5 or rt_spread < 0.1) else ""
 
         chrom_completeness_pct = chrom_completeness * 100
-        chrom_warning = (
-            f" {_WARNING_SYMBOL}"
-            if chrom_completeness_pct < 10 and chrom_completeness_pct >= 0
-            else ""
-        )
+        chrom_warning = f" {_WARNING_SYMBOL}" if chrom_completeness_pct < 10 and chrom_completeness_pct >= 0 else ""
 
         max_samples_warning = ""
-        if (
-            isinstance(max_samples, (int, float))
-            and samples_df_len > 0
-            and max_samples > 0
-        ):
+        if isinstance(max_samples, (int, float)) and samples_df_len > 0 and max_samples > 0:
             if max_samples < samples_df_len / 3.0:
                 max_samples_warning = f" {_WARNING_SYMBOL}"
             elif max_samples < samples_df_len * 0.8:
@@ -923,5 +881,6 @@ class Study:
 
         print(summary)
 
-if __name__ == "__main__":    
+
+if __name__ == "__main__":
     pass