masster 0.5.11__tar.gz → 0.5.12__tar.gz

{masster-0.5.11 → masster-0.5.12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.5.11
+Version: 0.5.12
 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-0.5.11 → masster-0.5.12}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.5.11"
+version = "0.5.12"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }

{masster-0.5.11 → masster-0.5.12}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.5.11"
+__version__ = "0.5.12"
 
 
 def get_version():

{masster-0.5.11 → masster-0.5.12}/src/masster/study/h5.py

@@ -874,8 +874,47 @@ def _create_dataframe_with_objects(data: dict, object_columns: list) -> pl.DataF
 
     # Create DataFrame with regular columns first
     if regular_data:
-        df = pl.DataFrame(regular_data)
-        # print(f"DEBUG: Created DataFrame with regular columns, shape: {df.shape}")
+        # Final safety check: convert any remaining numpy object arrays to Python lists
+        # and handle numpy scalars within lists
+        safe_regular_data = {}
+        import numpy as np
+        
+        def convert_numpy_scalars(value):
+            """Convert numpy scalars to Python native types recursively."""
+            if isinstance(value, np.generic):
+                return value.item()  # Convert numpy scalar to Python scalar
+            elif isinstance(value, list):
+                return [convert_numpy_scalars(item) for item in value]
+            else:
+                return value
+        
+        for k, v in regular_data.items():
+            if hasattr(v, 'dtype') and str(v.dtype) == 'object':
+                # Convert numpy object array to Python list
+                safe_regular_data[k] = [convert_numpy_scalars(item) for item in (v.tolist() if hasattr(v, 'tolist') else list(v))]
+            elif isinstance(v, list):
+                # Handle lists that might contain numpy scalars
+                safe_regular_data[k] = [convert_numpy_scalars(item) for item in v]
+            else:
+                safe_regular_data[k] = convert_numpy_scalars(v)
+        
+        # Create DataFrame with proper error handling
+        try:
+            df = pl.DataFrame(safe_regular_data)
+        except Exception as e:
+            # If direct creation fails, try creating column by column to identify and handle problematic columns
+            df = pl.DataFrame()
+            for k, v in safe_regular_data.items():
+                try:
+                    df = df.with_columns([pl.Series(k, v)])
+                except Exception:
+                    # Skip problematic columns or convert them to string as a fallback
+                    try:
+                        df = df.with_columns([pl.Series(k, [str(item) for item in v])])
+                    except Exception:
+                        # Last resort: skip the column entirely
+                        continue
+        
         # Add Object columns one by one
         for col, values in object_data.items():
             # print(f"DEBUG: Adding object column '{col}', type: {type(values)}, length: {len(values) if values is not None else 'None'}")

{masster-0.5.11 → masster-0.5.12}/src/masster/study/merge.py

@@ -2255,15 +2255,13 @@ def _perform_adduct_grouping(study, rt_tol, mz_tol):
                 {
                     "consensus_uid": row["consensus_uid"],
                     "rt": row["rt"],
-                    "mz": row["mz"],  # Add missing mz field
+                    "mz": row["mz"],
                     "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
-        #study.logger.info(f"About to call adduct grouping for {len(consensus_data)} consensus features")
         adduct_group_list, adduct_of_list = __merge_adduct_grouping(
             study, consensus_data, rt_tol/3, mz_tol
         )
@@ -2718,8 +2716,6 @@ def __identify_adduct_by_mass_shift(study, rt_tol, cached_adducts_df=None):
         study.logger.debug("No consensus features for adduct identification by mass shift")
         return
     
-    study.logger.info(f"Identifying coeluting adducts by mass shifts in {len(study.consensus_df)} consensus features...")
-    
     # Get adducts DataFrame if not provided
     if cached_adducts_df is None or cached_adducts_df.is_empty():
         try:
@@ -3025,8 +3021,7 @@ def __identify_adduct_by_mass_shift(study, rt_tol, cached_adducts_df=None):
             pl.Series("adduct_mass_neutral_top", new_adduct_mass_neutral_top),
             pl.Series("adduct_mass_shift_top", new_adduct_mass_shift_top)
         ])
-        
-        study.logger.info(f"Updated adduct assignments for {updated_count} consensus features based on mass shifts")
+        study.logger.success(f"Adduct information updated for {updated_count} consensus features.")
     else:
         study.logger.debug("No consensus features updated based on mass shift analysis")
 
@@ -3395,7 +3390,7 @@ def __merge_adduct_grouping(study, consensus_data, rt_tol, mz_tol):
             adduct_of_list = [0] * len(consensus_data)
             return adduct_group_list, adduct_of_list
             
-        study.logger.info(f"Built local intensity matrix: {len(intensity_matrix_pd)} features x {len(intensity_matrix_pd.columns)} samples")
+        study.logger.debug(f"Built local intensity matrix: {len(intensity_matrix_pd)} features x {len(intensity_matrix_pd.columns)} samples")
         
     except Exception as e:
         study.logger.warning(f"Could not build local intensity matrix: {e}. Creating single-feature groups.")
@@ -3405,7 +3400,7 @@ def __merge_adduct_grouping(study, consensus_data, rt_tol, mz_tol):
     
     # Step 2: Get adduct pairs with likelihood information and build hash map for fast lookup  
     adduct_pairs_with_likelihood = _get_adduct_deltas_with_likelihood(study)
-    study.logger.info(f"Using {len(adduct_pairs_with_likelihood)} adduct pairs with likelihood scoring")
+    study.logger.debug(f"Using {len(adduct_pairs_with_likelihood)} adduct pairs with likelihood scoring")
     
     # Build hash map for O(1) mass shift lookup
     mass_shift_map = {}  # rounded_delta -> [(likelihood, adduct1, adduct2), ...]

{masster-0.5.11 → masster-0.5.12}/uv.lock

@@ -1420,7 +1420,7 @@ wheels = [
 
 [[package]]
 name = "masster"
-version = "0.5.11"
+version = "0.5.12"
 source = { editable = "." }
 dependencies = [
     { name = "alpharaw" },