masster 0.4.22__py3-none-any.whl → 0.5.1__py3-none-any.whl

masster/study/load.py

@@ -213,18 +213,19 @@ def load(self, filename=None):
             return
 
     # self.logger.info(f"Loading study from {filename}")
-    self._load_study5(filename)
+    from masster.study.h5 import _load_study5
+    _load_study5(self, filename)
     
     # After loading the study, check if we have consensus features before loading consensus XML
-    if (self.consensus_df is not None and not self.consensus_df.is_empty()):
-        consensus_xml_path = filename.replace(".study5", ".consensusXML")
-        if os.path.exists(consensus_xml_path):
-            self._load_consensusXML(filename=consensus_xml_path)
+    #if (self.consensus_df is not None and not self.consensus_df.is_empty()):
+    #    consensus_xml_path = filename.replace(".study5", ".consensusXML")
+    #    if os.path.exists(consensus_xml_path):
+    #        self._load_consensusXML(filename=consensus_xml_path)
             # self.logger.info(f"Automatically loaded consensus from {consensus_xml_path}")
-        else:
-            self.logger.warning(f"No consensus XML file found at {consensus_xml_path}")
-    else:
-        self.logger.debug("No consensus features found, skipping consensusXML loading")
+    #    else:
+    #        self.logger.warning(f"No consensus XML file found at {consensus_xml_path}")
+    #else:
+    #    self.logger.debug("No consensus features found, skipping consensusXML loading")
     
     self.filename = filename
 
@@ -260,9 +261,14 @@ def _fill_chrom_single_impl(
     min_number_abs = 1
     if isinstance(min_samples_rel, float) and min_samples_rel > 0:
         min_number_rel = int(min_samples_rel * len(self.samples_df))
-    if isinstance(min_samples_abs, int) and min_samples_abs > 0:
-        min_number_abs = int(min_samples_abs)
+    if isinstance(min_samples_abs, int) and min_samples_abs >= 0:
+        min_number_abs = int(min_samples_abs) if min_samples_abs > 0 else 0
     min_number = max(min_number_rel, min_number_abs)
+    
+    # Special case: if min_samples_abs is explicitly 0, allow 0-sample features (like library features)
+    if isinstance(min_samples_abs, int) and min_samples_abs == 0:
+        min_number = 0
+        
     self.logger.debug(f"Threshold for gap filling: number_samples>={min_number}")
 
     if min_number > 0:
@@ -276,7 +282,7 @@ def _fill_chrom_single_impl(
         )
     self.logger.debug("Identifying missing features...")
     # Instead of building full chromatogram matrix, identify missing consensus/sample combinations directly
-    missing_combinations = self._get_missing_consensus_sample_combinations(uids)
+    missing_combinations = _get_missing_consensus_sample_combinations(self,uids)
     if not missing_combinations:
         self.logger.info("No missing features found to fill.")
         return
@@ -559,7 +565,7 @@ def fill_single(self, **kwargs):
     # end of parameter initialization
 
     # Store parameters in the Study object
-    self.store_history(["fill_single"], params.to_dict())
+    self.update_history(["fill_single"], params.to_dict())
     self.logger.debug("Parameters stored to fill_single")
 
     # Call the original fill_chrom_single function with extracted parameters
@@ -753,10 +759,14 @@ def _fill_chrom_impl(
     min_number_abs = 1
     if isinstance(min_samples_rel, float) and min_samples_rel > 0:
         min_number_rel = int(min_samples_rel * len(self.samples_df))
-    if isinstance(min_samples_abs, int) and min_samples_abs > 0:
-        min_number_abs = int(min_samples_abs)
+    if isinstance(min_samples_abs, int) and min_samples_abs >= 0:
+        min_number_abs = int(min_samples_abs) if min_samples_abs > 0 else 0
     min_number = max(min_number_rel, min_number_abs)
 
+    # Special case: if min_samples_abs is explicitly 0, allow 0-sample features (like library features)
+    if isinstance(min_samples_abs, int) and min_samples_abs == 0:
+        min_number = 0
+
     self.logger.debug(f"Threshold for gap filling: number_samples>={min_number}")
 
     if min_number > 0:
@@ -769,7 +779,7 @@ def _fill_chrom_impl(
 
     # Get missing consensus/sample combinations using the optimized method
     self.logger.debug("Identifying missing features...")
-    missing_combinations = self._get_missing_consensus_sample_combinations(uids)
+    missing_combinations = _get_missing_consensus_sample_combinations(self, uids)
 
     if not missing_combinations or len(missing_combinations) == 0:
         self.logger.info("No missing features found to fill.")
@@ -845,7 +855,7 @@ def _fill_chrom_impl(
         future_to_sample = {}
         for sample_info in samples_to_process:
             future = executor.submit(
-                self._process_sample_for_parallel_fill,
+                _process_sample_for_parallel_fill, self,
                 sample_info,
                 consensus_info,
                 uids,
@@ -979,7 +989,7 @@ def fill(self, **kwargs):
     # end of parameter initialization
 
     # Store parameters in the Study object
-    self.store_history(["fill"], params.to_dict())
+    self.update_history(["fill"], params.to_dict())
     self.logger.debug("Parameters stored to fill")
 
     # Call the original fill_chrom function with extracted parameters
@@ -1115,7 +1125,7 @@ def _get_missing_consensus_sample_combinations(self, uids):
         return missing_combinations
 
 
-def sanitize(self):
+def _sanitize(self):
     """
     Sanitize features DataFrame to ensure all complex objects are properly typed.
     Convert serialized objects back to their proper types (Chromatogram, Spectrum).
@@ -1209,7 +1219,7 @@ def sanitize(self):
         self.logger.error(f"Failed to recreate sanitized DataFrame: {e}")
 
 
-def load_features(self):
+def _load_features(self):
     """
     Load features by reconstructing FeatureMaps from the processed features_df data.
 
@@ -1630,7 +1640,7 @@ def _add_sample_optimized(
     # - No _ensure_features_df_schema_order()
     # - No complex column alignment
     # - No type casting loops
-    # - No sample_color_reset()
+    # - No set_samples_color(by=None) call needed
 
     self.logger.debug(
         f"Added sample {sample_name} with {ddaobj._oms_features_map.size()} features (optimized)",
@@ -1914,42 +1924,6 @@ def _add_sample_standard(
 
 def _sample_color_reset_optimized(self):
     """
-    Optimized version of sample_color_reset that caches colormap initialization.
+    Optimized version of sample color reset using set_samples_color.
     """
-    if self.samples_df is None or len(self.samples_df) == 0:
-        self.logger.warning("No samples found in study.")
-        return
-
-    # Cache the colormap if not already cached
-    if not hasattr(self, "_cached_colormap"):
-        try:
-            from cmap import Colormap
-
-            self._cached_colormap = Colormap("turbo")
-        except ImportError:
-            self.logger.warning("cmap package not available, using default colors")
-            return
-
-    cm = self._cached_colormap
-    n_samples = len(self.samples_df)
-
-    # Pre-allocate colors list for better performance
-    colors = [None] * n_samples
-
-    # Vectorized color generation
-    for i in range(n_samples):
-        normalized_value = 0.1 + ((i + 0.5) / n_samples) * 0.8
-        color_rgba = cm(normalized_value)
-
-        if len(color_rgba) >= 3:
-            r, g, b = color_rgba[:3]
-            if max(color_rgba[:3]) <= 1.0:
-                r, g, b = int(r * 255), int(g * 255), int(b * 255)
-            colors[i] = f"#{r:02x}{g:02x}{b:02x}"
-
-    # Update the sample_color column efficiently
-    self.samples_df = self.samples_df.with_columns(
-        pl.Series("sample_color", colors).alias("sample_color"),
-    )
-
-    self.logger.debug(f"Reset sample colors (cached) for {n_samples} samples")
+    return self.set_samples_color(by=None)