masster 0.5.1__py3-none-any.whl → 0.5.3__py3-none-any.whl

masster/study/plot.py

@@ -1385,6 +1385,7 @@ def plot_rt_correction(
     """
     Plot RT correction per sample: (rt - rt_original) vs rt overlaid for selected samples.
 
+    Only features with filled==False are used for the RT correction plot.
     This uses the same color mapping as `plot_bpc` so curves for the same samples match.
     """
     from bokeh.plotting import figure, show, output_file
@@ -1447,29 +1448,35 @@ def plot_rt_correction(
         if sample_feats.is_empty():
             continue
 
-        # Convert to pandas for easy numeric handling
-        try:
-            df = sample_feats.to_pandas()
-        except Exception:
-            continue
+        # Filter to only use features with filled==False
+        if "filled" in sample_feats.columns:
+            sample_feats = sample_feats.filter(~pl.col("filled"))
+            if sample_feats.is_empty():
+                continue
 
-        # Need both rt and rt_original
-        if "rt" not in df.columns or "rt_original" not in df.columns:
+        # Stay in Polars - much faster than pandas conversion!
+        if "rt" not in sample_feats.columns or "rt_original" not in sample_feats.columns:
             continue
 
-        # Drop NA and ensure numeric arrays
-        df = df.dropna(subset=["rt", "rt_original"]).copy()
-        if df.empty:
-            continue
+        # Filter nulls and add delta column in Polars
+        sample_feats = (
+            sample_feats
+            .filter(
+                pl.col("rt").is_not_null() &
+                pl.col("rt_original").is_not_null()
+            )
+            .with_columns([
+                (pl.col("rt") - pl.col("rt_original")).alias("delta")
+            ])
+            .sort("rt")
+        )
 
-        rt = _np.asarray(df["rt"], dtype=float)
-        rt_orig = _np.asarray(df["rt_original"], dtype=float)
-        delta = rt - rt_orig
+        if sample_feats.is_empty():
+            continue
 
-        # sort by rt
-        idx = _np.argsort(rt)
-        rt = rt[idx]
-        delta = delta[idx]
+        # Extract arrays directly from Polars
+        rt = sample_feats["rt"].to_numpy()
+        delta = sample_feats["delta"].to_numpy()
 
         sample_name = str(uid)
         if samples_info is not None:
@@ -1759,21 +1766,26 @@ def plot_consensus_stats(
     import polars as pl
     import numpy as np
 
-    # Check if consensus_df exists and has data
-    if self.consensus_df is None or self.consensus_df.is_empty():
-        self.logger.error("No consensus data available. Run merge/find_consensus first.")
+    # Get the consensus statistics data using the new helper method
+    data_df = self.get_consensus_stats()
+    
+    if data_df is None or data_df.is_empty():
+        self.logger.error("No consensus statistics data available.")
         return
 
-    # Get all columns and their data types - work with original dataframe
-    data_df = self.consensus_df.clone()
+    # Remove consensus_uid column for plotting (keep only numeric columns)
+    if "consensus_uid" in data_df.columns:
+        data_df_clean = data_df.drop("consensus_uid")
+    else:
+        data_df_clean = data_df
 
-    # Define specific columns to plot in the exact order requested
+    # Define specific columns to plot in the exact order requested (excluding consensus_uid)
     desired_columns = [
         "rt", 
         "rt_delta_mean", 
         "mz", 
-        "mz_range",  # mz_max-mz_min (will be calculated)
-        "log10_inty_mean",  # log10(inty_mean) (will be calculated)
+        "mz_range",  # mz_max-mz_min
+        "log10_inty_mean",  # log10(inty_mean)
         "number_samples", 
         "number_ms2", 
         "charge_mean", 
@@ -1783,20 +1795,13 @@ def plot_consensus_stats(
         "chrom_prominence_scaled_mean"
     ]
     
-    # Calculate derived columns if they don't exist
-    if "mz_range" not in data_df.columns and "mz_max" in data_df.columns and "mz_min" in data_df.columns:
-        data_df = data_df.with_columns((pl.col("mz_max") - pl.col("mz_min")).alias("mz_range"))
-    
-    if "log10_inty_mean" not in data_df.columns and "inty_mean" in data_df.columns:
-        data_df = data_df.with_columns(pl.col("inty_mean").log10().alias("log10_inty_mean"))
-    
     # Filter to only include columns that exist in the dataframe, preserving order
-    numeric_columns = [col for col in desired_columns if col in data_df.columns]
+    numeric_columns = [col for col in desired_columns if col in data_df_clean.columns]
     
     # Check if the numeric columns are actually numeric
     final_numeric_columns = []
     for col in numeric_columns:
-        dtype = data_df[col].dtype
+        dtype = data_df_clean[col].dtype
         if dtype in [pl.Int8, pl.Int16, pl.Int32, pl.Int64, 
                     pl.UInt8, pl.UInt16, pl.UInt32, pl.UInt64,
                     pl.Float32, pl.Float64]:
@@ -1805,13 +1810,13 @@ def plot_consensus_stats(
     numeric_columns = final_numeric_columns
 
     if len(numeric_columns) == 0:
-        self.logger.error(f"None of the requested consensus statistics columns were found or are numeric. Available columns: {list(data_df.columns)}")
+        self.logger.error(f"None of the requested consensus statistics columns were found or are numeric. Available columns: {list(data_df_clean.columns)}")
         return
 
     self.logger.debug(f"Creating distribution plots for {len(numeric_columns)} specific consensus columns: {numeric_columns}")
 
-    # Work directly with Polars - no conversion to pandas needed
-    data_df_clean = data_df.select(numeric_columns)
+    # Select only the numeric columns for plotting
+    data_df_clean = data_df_clean.select(numeric_columns)
 
     # Check if all numeric columns are empty
     all_columns_empty = True