masster 0.3.17__py3-none-any.whl → 0.3.19__py3-none-any.whl

masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.3.17"
+__version__ = "0.3.19"
 
 
 def get_version():

masster/sample/h5.py

@@ -900,7 +900,7 @@ def _load_sample5(self, filename: str, map: bool = True):
 def _load_sample5_study(self, filename: str, map: bool = True):
     """
     Optimized variant of _load_sample5 for study loading that skips reading ms1_df.
-    
+
     This is used when adding samples to studies where ms1_df data is not needed,
     improving loading throughput by skipping the potentially large ms1_df dataset.
 

masster/sample/helpers.py

@@ -176,7 +176,7 @@ def _get_feature_uids(self, features=None, verbose=True):
                 if not isinstance(features, pd.DataFrame):
                     if verbose:
                         self.logger.error(
-                            "Invalid input type. Expected None, list, polars DataFrame, or pandas DataFrame."
+                            "Invalid input type. Expected None, list, polars DataFrame, or pandas DataFrame.",
                         )
                     return []
 
@@ -298,7 +298,7 @@ def get_eic(self, mz, mz_tol=None):
     """
     # Use default mz_tol from sample parameters if not provided
     if mz_tol is None:
-        if hasattr(self, 'parameters') and hasattr(self.parameters, 'eic_mz_tol'):
+        if hasattr(self, "parameters") and hasattr(self.parameters, "eic_mz_tol"):
             mz_tol = self.parameters.eic_mz_tol
         else:
             mz_tol = 0.01  # fallback default
@@ -323,11 +323,7 @@ def get_eic(self, mz, mz_tol=None):
             return None
 
         # Aggregate intensities per retention time. Use sum in case multiple points per rt.
-        chrom = (
-            matches.group_by("rt")
-            .agg([pl.col("inty").sum().alias("inty")])
-            .sort("rt")
-        )
+        chrom = matches.group_by("rt").agg([pl.col("inty").sum().alias("inty")]).sort("rt")
 
         # Attach to Sample
         self.chrom_df = chrom

masster/sample/load.py

@@ -119,7 +119,7 @@ def load_study(
 ):
     """
     Optimized load method for study use that skips loading ms1_df for better performance.
-    
+
     This method is identical to load() but uses _load_sample5_study() for .sample5 files,
     which skips reading the potentially large ms1_df dataset to improve throughput when
     adding samples to studies.
@@ -983,7 +983,7 @@ def index_file(self):
             self.set_source(self.file_source.replace(".sample5", ".mzml"))
         else:
             raise FileNotFoundError(
-                f"File {self.file_source} not found. Did the path change? Consider running source()."
+                f"File {self.file_source} not found. Did the path change? Consider running source().",
             )
         self.index_file()
     else:

masster/sample/plot.py

@@ -87,9 +87,10 @@ def _is_notebook_environment():
         # Check if marimo is in modules
         if "marimo" in sys.modules:
             return True
-            
+
         # Check for marimo in the call stack or environment
         import inspect
+
         frame = inspect.currentframe()
         try:
             while frame:

masster/study/export.py

@@ -445,7 +445,7 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
     mtd_lines.append("MTD\tsmall_molecule-quantification_unit\t[MS, MS:1001844, MS1 feature area, ]")
     mtd_lines.append("MTD\tsmall_molecule_feature-quantification_unit\t[MS, MS:1001844, MS1 feature area, ]")
     mtd_lines.append(
-        "MTD\tsmall_molecule-identification_reliability\t[MS, MS:1002955, hr-ms compound identification confidence level, ]"
+        "MTD\tsmall_molecule-identification_reliability\t[MS, MS:1002955, hr-ms compound identification confidence level, ]",
     )
     mtd_lines.append("MTD\tid_confidence_measure[1]\t[MS, MS:1002888, small molecule confidence measure, ]")
     mtd_lines.append("")
@@ -499,8 +499,16 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
     # Use the matrix as-is since it already has the correct sample columns
     # The matrix columns are sample names, which is what we want for the assay columns
 
-    # round to int
-    abundance_matrix = abundance_matrix.round(0)
+    # round to int - handle both Polars and Pandas DataFrames
+    if hasattr(abundance_matrix, 'with_columns'):
+        # Polars DataFrame
+        numeric_cols = [col for col in abundance_matrix.columns if abundance_matrix[col].dtype.is_numeric()]
+        abundance_matrix = abundance_matrix.with_columns([
+            abundance_matrix[col].round(0) for col in numeric_cols
+        ])
+    else:
+        # Pandas DataFrame
+        abundance_matrix = abundance_matrix.round(0)
 
     # Use actual number of samples from the abundance matrix
     n_assays = len(abundance_matrix.columns)
@@ -570,9 +578,14 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
         ]
         # Add abundance values for each assay
         consensus_uid = row["consensus_uid"]
-        if consensus_uid in abundance_matrix.index:
-            abundance_values = abundance_matrix.loc[consensus_uid].tolist()
-            sml_row += [str(val) if pd.notna(val) else "null" for val in abundance_values]
+        # Check if consensus_uid exists in the abundance_matrix (Polars)
+        filtered_matrix = abundance_matrix.filter(pl.col("consensus_uid") == consensus_uid)
+        if filtered_matrix.height > 0:
+            # Get the first (and should be only) matching row
+            abundance_row = filtered_matrix.row(0, named=True)
+            # Extract values excluding the consensus_uid column
+            abundance_values = [abundance_row[col] for col in abundance_matrix.columns if col != "consensus_uid"]
+            sml_row += [str(val) if val is not None else "null" for val in abundance_values]
         else:
             sml_row += ["null"] * n_assays
         sml_row += ["null", "null"]
@@ -615,11 +628,15 @@ def export_mztab(self, filename: str = None, include_mgf=True, **kwargs) -> None
             str(row.get("retention_time_in_seconds_start", "null")),
             str(row.get("retention_time_in_seconds_end", "null")),
         ]
-        # Add abundance values for each assay - same as SML
+        # Add abundance values for each assay - same as SML (Polars)
         consensus_uid = row["consensus_uid"]
-        if consensus_uid in abundance_matrix.index:
-            abundance_values = abundance_matrix.loc[consensus_uid].tolist()
-            smf_row += [str(val) if pd.notna(val) else "null" for val in abundance_values]
+        filtered_matrix = abundance_matrix.filter(pl.col("consensus_uid") == consensus_uid)
+        if filtered_matrix.height > 0:
+            # Get the first (and should be only) matching row
+            abundance_row = filtered_matrix.row(0, named=True)
+            # Extract values excluding the consensus_uid column
+            abundance_values = [abundance_row[col] for col in abundance_matrix.columns if col != "consensus_uid"]
+            smf_row += [str(val) if val is not None else "null" for val in abundance_values]
         else:
             smf_row += ["null"] * n_assays
         smf_lines.append("\t".join(smf_row))

masster/study/h5.py

@@ -94,7 +94,7 @@ def _save_dataframe_optimized(df, group, schema, df_name, logger, chunk_size=100
                 numeric_cols.append(col)
 
         logger.debug(
-            f"Saving {df_name}: {total_rows} rows, {len(numeric_cols)} numeric, {len(string_cols)} string, {len(object_cols)} object columns"
+            f"Saving {df_name}: {total_rows} rows, {len(numeric_cols)} numeric, {len(string_cols)} string, {len(object_cols)} object columns",
         )
 
         # Process numeric columns in batch (most efficient)
@@ -277,7 +277,7 @@ def _save_object_columns_optimized(group, df, object_cols, logger, chunk_size):
                             results[chunk_start] = chunk_result
                         except Exception as e:
                             logger.warning(
-                                f"Failed to serialize chunk starting at {chunk_start} for column '{col}': {e}"
+                                f"Failed to serialize chunk starting at {chunk_start} for column '{col}': {e}",
                             )
                             # Fallback to simple string conversion for this chunk
                             chunk = data_list[chunk_start : chunk_start + chunk_size]
@@ -435,7 +435,7 @@ def _save_dataframe_column_legacy(group, col: str, data, dtype: str, logger, com
             group.create_dataset(col, data=data_as_str, compression=compression)
         else:
             logger.warning(
-                f"Unexpectedly, column '{col}' has dtype '{dtype}'. Implement serialization for this column."
+                f"Unexpectedly, column '{col}' has dtype '{dtype}'. Implement serialization for this column.",
             )
     elif dtype == "string":
         # Handle string columns
@@ -698,17 +698,17 @@ def _load_dataframe_from_group(group, schema: dict, df_name: str, logger, object
     # Get available columns from HDF5 file
     hdf5_columns = list(group.keys())
     logger.debug(f"HDF5 columns available: {hdf5_columns}")
-    
+
     # Handle column name migrations for backward compatibility first
     if df_name == "samples_df":
         # Migrate old column names to new names
         column_migrations = {
             "size": "num_features",
-            "file_source": "sample_source", 
+            "file_source": "sample_source",
             "ms1": "num_ms1",
-            "ms2": "num_ms2"
+            "ms2": "num_ms2",
         }
-        
+
         # Create a mapping of what's actually available after migrations
         effective_columns = hdf5_columns.copy()
         for old_name, new_name in column_migrations.items():
@@ -720,14 +720,14 @@ def _load_dataframe_from_group(group, schema: dict, df_name: str, logger, object
     # First pass: load all existing columns (including migrated ones)
     for col in schema_columns or []:
         source_col = col
-        
+
         # Check if we need to load from a migrated column name
         if df_name == "samples_df":
             column_migrations = {
                 "size": "num_features",
-                "file_source": "sample_source", 
+                "file_source": "sample_source",
                 "ms1": "num_ms1",
-                "ms2": "num_ms2"
+                "ms2": "num_ms2",
             }
             # Reverse lookup - find old name for new name
             reverse_migrations = {v: k for k, v in column_migrations.items()}
@@ -736,7 +736,7 @@ def _load_dataframe_from_group(group, schema: dict, df_name: str, logger, object
                 if old_name in group:
                     source_col = old_name
                     logger.info(f"Loading '{col}' from old column name '{old_name}'")
-        
+
         if source_col not in group:
             missing_columns.append(col)
             continue
@@ -829,12 +829,12 @@ def _load_dataframe_from_group(group, schema: dict, df_name: str, logger, object
     if df_name == "samples_df":
         column_migrations = {
             "size": "num_features",
-            "file_source": "sample_source", 
+            "file_source": "sample_source",
             "ms1": "num_ms1",
-            "ms2": "num_ms2"
+            "ms2": "num_ms2",
         }
         migrated_old_names = set(column_migrations.keys())
-    
+
     extra_columns = [col for col in hdf5_columns if col not in (schema_columns or []) and col not in migrated_old_names]
 
     for col in extra_columns:
@@ -974,7 +974,7 @@ def _save_study5_compressed(self, filename=None):
 
             pbar.update(1)
             pbar.set_description(
-                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {getattr(self, 'log_label', '')}Saving dataframes"
+                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {getattr(self, 'log_label', '')}Saving dataframes",
             )
 
             # Store samples_df - use optimized batch processing
@@ -987,7 +987,7 @@ def _save_study5_compressed(self, filename=None):
             # Store features_df - use fast method that skips chrom and ms2_specs columns
             if self.features_df is not None and not self.features_df.is_empty():
                 self.logger.debug(
-                    f"Fast saving features_df with {len(self.features_df)} rows (skipping chrom and ms2_specs)"
+                    f"Fast saving features_df with {len(self.features_df)} rows (skipping chrom and ms2_specs)",
                 )
                 _save_dataframe_optimized_fast(self.features_df, features_group, schema, "features_df", self.logger)
                 pbar.update(1)
@@ -1066,7 +1066,7 @@ def _save_dataframe_optimized_fast(df, group, schema, df_name, logger, chunk_siz
                 numeric_cols.append(col)
 
         logger.debug(
-            f"Saving {df_name}: {total_rows} rows, {len(numeric_cols)} numeric, {len(string_cols)} string, {len(object_cols)} object columns"
+            f"Saving {df_name}: {total_rows} rows, {len(numeric_cols)} numeric, {len(string_cols)} string, {len(object_cols)} object columns",
         )
 
         # Process numeric columns in batch (most efficient)
@@ -1184,7 +1184,7 @@ def _save_study5(self, filename=None):
 
             pbar.update(1)
             pbar.set_description(
-                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {getattr(self, 'log_label', '')}Saving dataframes"
+                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {getattr(self, 'log_label', '')}Saving dataframes",
             )
 
             # Store samples_df - use optimized batch processing
@@ -1309,7 +1309,7 @@ def _load_study5(self, filename=None):
         ) as pbar:
             # Load metadata
             pbar.set_description(
-                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading metadata"
+                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading metadata",
             )
             if "metadata" in f:
                 metadata = f["metadata"]
@@ -1371,7 +1371,7 @@ def _load_study5(self, filename=None):
 
             # Load samples_df
             pbar.set_description(
-                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading samples"
+                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading samples",
             )
             if "samples" in f and len(f["samples"].keys()) > 0:
                 self.samples_df = _load_dataframe_from_group(f["samples"], schema, "samples_df", self.logger)
@@ -1411,7 +1411,7 @@ def _load_study5(self, filename=None):
             pbar.update(1)
             # Load samples_df
             pbar.set_description(
-                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading samples"
+                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading samples",
             )
             if "samples" in f and len(f["samples"].keys()) > 0:
                 self.samples_df = _load_dataframe_from_group(f["samples"], schema, "samples_df", self.logger)
@@ -1452,12 +1452,16 @@ def _load_study5(self, filename=None):
 
             # Load features_df
             pbar.set_description(
-                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading features"
+                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading features",
             )
             if "features" in f and len(f["features"].keys()) > 0:
                 object_columns = ["chrom", "ms2_scans", "ms2_specs"]
                 self.features_df = _load_dataframe_from_group(
-                    f["features"], schema, "features_df", self.logger, object_columns
+                    f["features"],
+                    schema,
+                    "features_df",
+                    self.logger,
+                    object_columns,
                 )
             else:
                 self.features_df = None
@@ -1465,7 +1469,7 @@ def _load_study5(self, filename=None):
 
             # Load consensus_df
             pbar.set_description(
-                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading consensus"
+                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading consensus",
             )
             if "consensus" in f and len(f["consensus"].keys()) > 0:
                 # Only include adducts in object_columns if it actually exists in the file
@@ -1474,7 +1478,11 @@ def _load_study5(self, filename=None):
                     object_columns.append("adducts")
 
                 self.consensus_df = _load_dataframe_from_group(
-                    f["consensus"], schema, "consensus_df", self.logger, object_columns
+                    f["consensus"],
+                    schema,
+                    "consensus_df",
+                    self.logger,
+                    object_columns,
                 )
 
                 # Backward compatibility: If adducts column doesn't exist, initialize with empty lists
@@ -1507,22 +1515,28 @@ def _load_study5(self, filename=None):
 
             # Load consensus_mapping_df
             pbar.set_description(
-                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading consensus mapping"
+                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading consensus mapping",
             )
             if "consensus_mapping" in f and len(f["consensus_mapping"].keys()) > 0:
                 self.consensus_mapping_df = _load_dataframe_from_group(
-                    f["consensus_mapping"], schema, "consensus_mapping_df", self.logger
+                    f["consensus_mapping"],
+                    schema,
+                    "consensus_mapping_df",
+                    self.logger,
                 )
             else:
                 self.consensus_mapping_df = None
             pbar.update(1)
             # Load consensus_mapping_df
             pbar.set_description(
-                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading consensus mapping"
+                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading consensus mapping",
             )
             if "consensus_mapping" in f and len(f["consensus_mapping"].keys()) > 0:
                 self.consensus_mapping_df = _load_dataframe_from_group(
-                    f["consensus_mapping"], schema, "consensus_mapping_df", self.logger
+                    f["consensus_mapping"],
+                    schema,
+                    "consensus_mapping_df",
+                    self.logger,
                 )
             else:
                 self.consensus_mapping_df = None
@@ -1530,34 +1544,38 @@ def _load_study5(self, filename=None):
 
             # Load consensus_ms2
             pbar.set_description(
-                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading consensus MS2"
+                f"{datetime.now().strftime('%Y-%m-%d %H:%M:%S.%f')[:-3]} | INFO     | {self.log_label}Loading consensus MS2",
             )
             if "consensus_ms2" in f and len(f["consensus_ms2"].keys()) > 0:
                 object_columns = ["spec"]
                 self.consensus_ms2 = _load_dataframe_from_group(
-                    f["consensus_ms2"], schema, "consensus_ms2", self.logger, object_columns
+                    f["consensus_ms2"],
+                    schema,
+                    "consensus_ms2",
+                    self.logger,
+                    object_columns,
                 )
             else:
                 self.consensus_ms2 = None
             pbar.update(1)
 
     # Check and migrate old string-based map_id to integer indices
-    if (self.samples_df is not None and 
-        not self.samples_df.is_empty() and 
-        self.samples_df['map_id'].dtype == pl.Utf8):
+    if self.samples_df is not None and not self.samples_df.is_empty() and self.samples_df["map_id"].dtype == pl.Utf8:
         self.logger.info("Detected old string-based map_id format, migrating to integer indices")
-        
+
         # Convert string-based map_id to integer indices
         sample_count = len(self.samples_df)
         new_map_ids = list(range(sample_count))
-        
+
         self.samples_df = self.samples_df.with_columns(
-            pl.lit(new_map_ids).alias("map_id")
+            pl.lit(new_map_ids).alias("map_id"),
         )
-        
+
         # Ensure the column is Int64 type
         self.samples_df = self.samples_df.cast({"map_id": pl.Int64})
-        
-        self.logger.info(f"Successfully migrated {sample_count} samples to indexed map_id format (0 to {sample_count - 1})")
+
+        self.logger.info(
+            f"Successfully migrated {sample_count} samples to indexed map_id format (0 to {sample_count - 1})",
+        )
 
     self.logger.debug("Study loaded")