masster 0.3.13__py3-none-any.whl → 0.3.15__py3-none-any.whl

masster/study/load.py

@@ -71,11 +71,8 @@ def add(
 
         # Build search pattern
         if any(char in folder for char in ["*", "?", "[", "]"]):
-            # If folder already contains glob patterns, modify the extension
-            if folder.endswith("*.sample5"):
-                pattern = folder.replace("*.sample5", f"*{ext}")
-            else:
-                pattern = os.path.join(search_folder, "**", f"*{ext}")
+            # If folder already contains glob patterns, use it as-is
+            pattern = folder
         else:
             pattern = os.path.join(search_folder, "**", f"*{ext}")
 
@@ -187,7 +184,9 @@ def add_sample(self, file, type=None, reset=False, adducts=None):
         sample_type = "qc"
     if "blank" in sample_name.lower():
         sample_type = "blank"
-    map_id_value = str(ddaobj.features.getUniqueId())
+    
+    # Use the index of the feature map in self.features_maps as map_id
+    map_id_value = len(self.features_maps) - 1
 
     # Determine the final sample path based on file type
     if file.endswith(".sample5"):
@@ -222,28 +221,39 @@ def add_sample(self, file, type=None, reset=False, adducts=None):
         ms1_count = int(ddaobj.scans_df.filter(pl.col("ms_level") == 1).height)
         ms2_count = int(ddaobj.scans_df.filter(pl.col("ms_level") == 2).height)
 
+    # Calculate next sequence number
+    next_sequence = len(self.samples_df) + 1 if not self.samples_df.is_empty() else 1
+
     new_sample = pl.DataFrame(
         {
             "sample_uid": [int(len(self.samples_df) + 1)],
             "sample_name": [sample_name],
             "sample_path": [final_sample_path],  # Use the determined path
             "sample_type": [sample_type],
-            "size": [int(ddaobj.features.size())],
             "map_id": [map_id_value],
-            "file_source": [getattr(ddaobj, "file_source", file)],
-            "ms1": [ms1_count],
-            "ms2": [ms2_count],
+            "sample_source": [getattr(ddaobj, "file_source", file)],
+            "sample_color": [None],  # Will be set by set_sample_color below
+            "sample_group": [""],  # Default empty string
+            "sample_batch": [1],  # Default batch 1
+            "sample_sequence": [next_sequence],  # Increasing sequence number
+            "num_features": [int(ddaobj.features.size())],
+            "num_ms1": [ms1_count],
+            "num_ms2": [ms2_count],
         },
         schema={
             "sample_uid": pl.Int64,
             "sample_name": pl.Utf8,
             "sample_path": pl.Utf8,
             "sample_type": pl.Utf8,
-            "size": pl.Int64,
-            "map_id": pl.Utf8,
-            "file_source": pl.Utf8,
-            "ms1": pl.Int64,
-            "ms2": pl.Int64,
+            "map_id": pl.Int64,
+            "sample_source": pl.Utf8,
+            "sample_color": pl.Utf8,
+            "sample_group": pl.Utf8,
+            "sample_batch": pl.Int64,
+            "sample_sequence": pl.Int64,
+            "num_features": pl.Int64,
+            "num_ms1": pl.Int64,
+            "num_ms2": pl.Int64,
         },
     )
     self.samples_df = pl.concat([self.samples_df, new_sample])
@@ -309,6 +319,9 @@ def add_sample(self, file, type=None, reset=False, adducts=None):
     # Ensure features_df column order matches schema
     self._ensure_features_df_schema_order()
     
+    # Auto-assign colors when new sample is added (reset all colors using turbo colormap based on UID)
+    self.sample_color_reset()
+    
     self.logger.debug(
         f"Added sample {sample_name} with {ddaobj.features.size()} features to the study.",
     )