masster 0.4.17__tar.gz → 0.4.19__tar.gz

{masster-0.4.17 → masster-0.4.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: masster
-Version: 0.4.17
+Version: 0.4.19
 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-0.4.17 → masster-0.4.19}/pyproject.toml

@@ -1,7 +1,7 @@
 
 [project]
 name = "masster"
-version = "0.4.17"
+version = "0.4.19"
 description = "Mass spectrometry data analysis package"
 authors = [
     { name = "Zamboni Lab" }

{masster-0.4.17 → masster-0.4.19}/src/masster/_version.py

@@ -1,7 +1,7 @@
 from __future__ import annotations
 
 
-__version__ = "0.4.17"
+__version__ = "0.4.19"
 
 
 def get_version():

{masster-0.4.17 → masster-0.4.19}/src/masster/study/defaults/merge_def.py

@@ -1,7 +1,7 @@
 """Parameter class for Study merge method."""
 
 from dataclasses import dataclass, field
-from typing import Any
+from typing import Any, Optional
 
 
 @dataclass
@@ -25,25 +25,28 @@ class merge_defaults:
         link_ms2 (bool): Whether to link MS2 spectra to consensus features. Default is True.
     """
 
-    method: str = "quality"
-    min_samples: int = 10
+    method: str = "qt"
+    min_samples: int = 2
     rt_tol: float = 5.0
     mz_tol: float = 0.01
-    chunk_size: int = 300
+    chunk_size: int = 500
     nr_partitions: int = 1000
-    min_rel_cc_size: float = 0.2
+    min_rel_cc_size: float = 0.1
     max_pairwise_log_fc: float = -1.0
     max_nr_conflicts: int = 0
     link_ms2: bool = True
     
+    # Parallel processing parameters
+    threads: Optional[int] = None
+    
     # KD-Strict specific parameters
     optimize_rt_tol: bool = False
-    rt_tol_range: tuple = (0.8, 2.0)  
-    rt_tol_steps: int = 5
-    secondary_merge_rt_tol: float = 0.5
+    rt_tol_range: tuple = (0.5, 4.0)  
+    rt_tol_steps: int = 7
+    secondary_merge_rt_tol: float = 1.0
     secondary_merge_mz_tol: float = 0.005
     min_sample_overlap: float = 0.8
-    max_rt_spread: float = None  # Will default to 2x rt_tol
+    max_rt_spread: float = 2.0  # Will default to 2x rt_tol
     min_coherence: float = 0.0
 
     _param_metadata: dict[str, dict[str, Any]] = field(
@@ -53,7 +56,8 @@ class merge_defaults:
                 "description": "Merge method (algorithm) to use",
                 "default": "quality",
                 "allowed_values": ["sensitivity", "qt", "nowarp", "chunked", "quality", 
-                                 "kd", "kd-nowarp", "kd_nowarp", "kd-strict", "kd_strict"],
+                                 "kd", "kd-nowarp", "kd_nowarp", "kd-strict", "kd_strict",
+                                 "kd_chunked", "kd-chunked", "qt_chunked", "qt-chunked"],
             },
             "min_samples": {
                 "dtype": int,
@@ -114,6 +118,14 @@ class merge_defaults:
                 "description": "Whether to link MS2 spectra to consensus features",
                 "default": True,
             },
+            # Parallel processing parameters
+            "threads": {
+                "dtype": [int, type(None)],
+                "description": "Number of parallel threads/processes for chunked methods (None=original sequential)",
+                "default": None,
+                "min_value": 1,
+                "max_value": 32,
+            },
             # KD-Strict specific parameters
             "optimize_rt_tol": {
                 "dtype": bool,
@@ -216,7 +228,37 @@ class merge_defaults:
         metadata = self._param_metadata[param_name]
         expected_dtype = metadata["dtype"]
 
-        # Type checking
+        # Handle Optional types (list of types including None)
+        if isinstance(expected_dtype, list):
+            # Check if value matches any of the allowed types
+            valid_type = False
+            for dtype in expected_dtype:
+                if dtype is type(None) and value is None:
+                    return True  # None is explicitly allowed
+                elif dtype is int and isinstance(value, int):
+                    valid_type = True
+                    break
+                elif dtype is float and isinstance(value, (int, float)):
+                    valid_type = True
+                    break
+                elif dtype is bool and isinstance(value, bool):
+                    valid_type = True
+                    break
+                elif dtype is str and isinstance(value, str):
+                    valid_type = True
+                    break
+            
+            if not valid_type:
+                return False
+            
+            # For None values, skip further validation
+            if value is None:
+                return True
+            
+            # Use the first non-None type for range validation
+            expected_dtype = next((dt for dt in expected_dtype if dt is not type(None)), expected_dtype[0])
+
+        # Type checking for non-Optional types
         if expected_dtype is int:
             if not isinstance(value, int):
                 try: