masster 0.4.4__py3-none-any.whl → 0.4.6__py3-none-any.whl

masster/sample/h5.py

@@ -11,7 +11,13 @@ from masster.chromatogram import Chromatogram
 from masster.spectrum import Spectrum
 
 
-def _save_sample5(self, filename=None, include_ms1=True, include_scans=True, save_featurexml=False):
+def _save_sample5(
+    self,
+    filename=None,
+    include_ms1=True,
+    include_scans=True,
+    save_featurexml=False,
+):
     """
     Save the instance data to a sample5 HDF5 file with optimized compression.
 
@@ -56,14 +62,16 @@ def _save_sample5(self, filename=None, include_ms1=True, include_scans=True, sav
             return
 
     # synchronize feature_map if it exists
-    if hasattr(self, '_feature_map') and self._feature_map is not None:
+    if hasattr(self, "_feature_map") and self._feature_map is not None:
         self._features_sync()
 
     # if no extension is given, add .sample5
     if not filename.endswith(".sample5"):
         filename += ".sample5"
 
-    self.logger.debug(f"Saving sample to {filename} with optimized LZF+shuffle compression")
+    self.logger.debug(
+        f"Saving sample to {filename} with optimized LZF+shuffle compression",
+    )
 
     # delete existing file if it exists
     if os.path.exists(filename):
@@ -116,12 +124,18 @@ def _save_sample5(self, filename=None, include_ms1=True, include_scans=True, sav
                     except Exception:
                         try:
                             # Try to convert to numeric using numpy
-                            numeric_data = np.array([
-                                float(x)
-                                if x is not None and str(x).replace(".", "").replace("-", "").isdigit()
-                                else np.nan
-                                for x in data
-                            ])
+                            numeric_data = np.array(
+                                [
+                                    float(x)
+                                    if x is not None
+                                    and str(x)
+                                    .replace(".", "")
+                                    .replace("-", "")
+                                    .isdigit()
+                                    else np.nan
+                                    for x in data
+                                ],
+                            )
                             if not np.isnan(numeric_data).all():
                                 scans_group.create_dataset(
                                     col,
@@ -149,7 +163,12 @@ def _save_sample5(self, filename=None, include_ms1=True, include_scans=True, sav
                             )
                             scans_group[col].attrs["dtype"] = "string_repr"
                 else:
-                    scans_group.create_dataset(col, data=data, compression="lzf", shuffle=True)
+                    scans_group.create_dataset(
+                        col,
+                        data=data,
+                        compression="lzf",
+                        shuffle=True,
+                    )
                     scans_group[col].attrs["dtype"] = "native"
             scans_group.attrs["columns"] = list(scans_df.columns)
 
@@ -226,7 +245,12 @@ def _save_sample5(self, filename=None, include_ms1=True, include_scans=True, sav
                     data = features[col].to_list()
                     # convert None to 'None' strings
                     data = ["None" if x is None else x for x in data]
-                    features_group.create_dataset(col, data=data, compression="lzf", shuffle=True)
+                    features_group.create_dataset(
+                        col,
+                        data=data,
+                        compression="lzf",
+                        shuffle=True,
+                    )
                 else:
                     try:
                         data = features[col].to_numpy()
@@ -261,16 +285,18 @@ def _save_sample5(self, filename=None, include_ms1=True, include_scans=True, sav
         feature_map = self._get_feature_map()
         if feature_map is not None:
             # Temporarily set features for save operation
-            old_features = getattr(self, '_oms_features_map', None)
+            old_features = getattr(self, "_oms_features_map", None)
             self._oms_features_map = feature_map
             try:
-                self._save_featureXML(filename=filename.replace(".sample5", ".featureXML"))
+                self._save_featureXML(
+                    filename=filename.replace(".sample5", ".featureXML"),
+                )
             finally:
                 # Restore original features value
                 if old_features is not None:
                     self._oms_features_map = old_features
                 else:
-                    delattr(self, '_oms_features_map')
+                    delattr(self, "_oms_features_map")
         else:
             self.logger.warning("Cannot save featureXML: no feature data available")
 
@@ -309,15 +335,21 @@ def _load_sample5(self, filename: str, map: bool = False):
         # Load metadata
         if "metadata" in f:
             metadata_group = f["metadata"]
-            self.file_path = decode_metadata_attr(metadata_group.attrs.get("file_path", ""))
+            self.file_path = decode_metadata_attr(
+                metadata_group.attrs.get("file_path", ""),
+            )
 
             # Load file_source if it exists, otherwise set it equal to file_path
             if "file_source" in metadata_group.attrs:
-                self.file_source = decode_metadata_attr(metadata_group.attrs.get("file_source", ""))
+                self.file_source = decode_metadata_attr(
+                    metadata_group.attrs.get("file_source", ""),
+                )
             else:
                 self.file_source = self.file_path
 
-            self.file_type = decode_metadata_attr(metadata_group.attrs.get("file_type", ""))
+            self.file_type = decode_metadata_attr(
+                metadata_group.attrs.get("file_type", ""),
+            )
             self.label = decode_metadata_attr(metadata_group.attrs.get("label", ""))
 
             # Load parameters from JSON in metadata
@@ -368,19 +400,23 @@ def _load_sample5(self, filename: str, map: bool = False):
                 # Convert "None" strings and NaN values to proper null values
                 for col in self.scans_df.columns:
                     if self.scans_df[col].dtype == pl.Utf8:  # String columns
-                        self.scans_df = self.scans_df.with_columns([
-                            pl.when(pl.col(col).is_in(["None", "", "null", "NULL"]))
-                            .then(None)
-                            .otherwise(pl.col(col))
-                            .alias(col),
-                        ])
+                        self.scans_df = self.scans_df.with_columns(
+                            [
+                                pl.when(pl.col(col).is_in(["None", "", "null", "NULL"]))
+                                .then(None)
+                                .otherwise(pl.col(col))
+                                .alias(col),
+                            ],
+                        )
                     elif self.scans_df[col].dtype in [
                         pl.Float64,
                         pl.Float32,
                     ]:  # Float columns
-                        self.scans_df = self.scans_df.with_columns([
-                            pl.col(col).fill_nan(None).alias(col),
-                        ])
+                        self.scans_df = self.scans_df.with_columns(
+                            [
+                                pl.col(col).fill_nan(None).alias(col),
+                            ],
+                        )
 
                 # update all columns with schema types
                 for col in self.scans_df.columns:
@@ -398,7 +434,9 @@ def _load_sample5(self, filename: str, map: bool = False):
                                     if self.scans_df[col].dtype == pl.Utf8:
                                         # String data - convert to integer
                                         self.scans_df = self.scans_df.with_columns(
-                                            pl.col(col).str.to_integer().cast(eval(dtype_str)),
+                                            pl.col(col)
+                                            .str.to_integer()
+                                            .cast(eval(dtype_str)),
                                         )
                                     elif self.scans_df[col].dtype in [
                                         pl.Float64,
@@ -418,7 +456,9 @@ def _load_sample5(self, filename: str, map: bool = False):
                                     if self.scans_df[col].dtype == pl.Utf8:
                                         # String data - convert to float
                                         self.scans_df = self.scans_df.with_columns(
-                                            pl.col(col).str.to_decimal().cast(eval(dtype_str)),
+                                            pl.col(col)
+                                            .str.to_decimal()
+                                            .cast(eval(dtype_str)),
                                         )
                                     else:
                                         # Try direct casting
@@ -442,7 +482,9 @@ def _load_sample5(self, filename: str, map: bool = False):
                                             self.scans_df = self.scans_df.with_columns(
                                                 pl.col(col)
                                                 .map_elements(
-                                                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
+                                                    lambda x: x.decode("utf-8")
+                                                    if isinstance(x, bytes)
+                                                    else str(x),
                                                     return_dtype=pl.Utf8,
                                                 )
                                                 .cast(target_dtype),
@@ -451,7 +493,9 @@ def _load_sample5(self, filename: str, map: bool = False):
                                             self.scans_df = self.scans_df.with_columns(
                                                 pl.col(col)
                                                 .map_elements(
-                                                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
+                                                    lambda x: x.decode("utf-8")
+                                                    if isinstance(x, bytes)
+                                                    else str(x),
                                                     return_dtype=pl.Utf8,
                                                 )
                                                 .str.to_integer()
@@ -461,7 +505,9 @@ def _load_sample5(self, filename: str, map: bool = False):
                                             self.scans_df = self.scans_df.with_columns(
                                                 pl.col(col)
                                                 .map_elements(
-                                                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
+                                                    lambda x: x.decode("utf-8")
+                                                    if isinstance(x, bytes)
+                                                    else str(x),
                                                     return_dtype=pl.Utf8,
                                                 )
                                                 .str.to_decimal()
@@ -490,7 +536,9 @@ def _load_sample5(self, filename: str, map: bool = False):
             if "scans_df" in schema and "columns" in schema["scans_df"]:
                 schema_column_order = list(schema["scans_df"]["columns"].keys())
                 # Only reorder columns that exist in both schema and DataFrame
-                existing_columns = [col for col in schema_column_order if col in self.scans_df.columns]
+                existing_columns = [
+                    col for col in schema_column_order if col in self.scans_df.columns
+                ]
                 if existing_columns:
                     self.scans_df = self.scans_df.select(existing_columns)
 
@@ -617,23 +665,29 @@ def _load_sample5(self, filename: str, map: bool = False):
                         if k in schema.get("features_df", {}).get("columns", {})
                         and schema["features_df"]["columns"][k]["dtype"] == "pl.Object"
                     }
-                    regular_columns = {k: v for k, v in data.items() if k not in object_columns}
+                    regular_columns = {
+                        k: v for k, v in data.items() if k not in object_columns
+                    }
 
                     # Create DataFrame with regular columns first
                     if regular_columns:
                         self.features_df = pl.DataFrame(regular_columns)
                         # Add Object columns one by one
                         for col, values in object_columns.items():
-                            self.features_df = self.features_df.with_columns([
-                                pl.Series(col, values, dtype=pl.Object),
-                            ])
+                            self.features_df = self.features_df.with_columns(
+                                [
+                                    pl.Series(col, values, dtype=pl.Object),
+                                ],
+                            )
                     else:
                         # Only Object columns
                         self.features_df = pl.DataFrame()
                         for col, values in object_columns.items():
-                            self.features_df = self.features_df.with_columns([
-                                pl.Series(col, values, dtype=pl.Object),
-                            ])
+                            self.features_df = self.features_df.with_columns(
+                                [
+                                    pl.Series(col, values, dtype=pl.Object),
+                                ],
+                            )
 
                 # update all columns with schema types (skip Object columns)
                 for col in self.features_df.columns:
@@ -650,16 +704,25 @@ def _load_sample5(self, filename: str, map: bool = False):
                                     # Convert to numeric first, handling different input types
                                     if self.features_df[col].dtype == pl.Utf8:
                                         # String data - convert to integer
-                                        self.features_df = self.features_df.with_columns(
-                                            pl.col(col).str.to_integer().cast(eval(dtype_str)),
+                                        self.features_df = (
+                                            self.features_df.with_columns(
+                                                pl.col(col)
+                                                .str.to_integer()
+                                                .cast(eval(dtype_str)),
+                                            )
                                         )
                                     elif self.features_df[col].dtype in [
                                         pl.Float64,
                                         pl.Float32,
                                     ]:
                                         # Float data - cast to integer with null handling for NaN values
-                                        self.features_df = self.features_df.with_columns(
-                                            pl.col(col).cast(eval(dtype_str), strict=False),
+                                        self.features_df = (
+                                            self.features_df.with_columns(
+                                                pl.col(col).cast(
+                                                    eval(dtype_str),
+                                                    strict=False,
+                                                ),
+                                            )
                                         )
                                     else:
                                         # Handle special cases and try direct casting for other types
@@ -670,50 +733,70 @@ def _load_sample5(self, filename: str, map: bool = False):
                                         if "Binary" in str(current_dtype):
                                             # Convert binary to string first, then to target type
                                             if target_dtype == pl.Utf8:
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col)
-                                                    .map_elements(
-                                                        lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                        return_dtype=pl.Utf8,
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col)
+                                                        .map_elements(
+                                                            lambda x: x.decode("utf-8")
+                                                            if isinstance(x, bytes)
+                                                            else str(x),
+                                                            return_dtype=pl.Utf8,
+                                                        )
+                                                        .cast(target_dtype),
                                                     )
-                                                    .cast(target_dtype),
                                                 )
                                             elif "Int" in str(target_dtype):
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col)
-                                                    .map_elements(
-                                                        lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                        return_dtype=pl.Utf8,
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col)
+                                                        .map_elements(
+                                                            lambda x: x.decode("utf-8")
+                                                            if isinstance(x, bytes)
+                                                            else str(x),
+                                                            return_dtype=pl.Utf8,
+                                                        )
+                                                        .str.to_integer()
+                                                        .cast(target_dtype),
                                                     )
-                                                    .str.to_integer()
-                                                    .cast(target_dtype),
                                                 )
                                             elif "Float" in str(target_dtype):
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col)
-                                                    .map_elements(
-                                                        lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                        return_dtype=pl.Utf8,
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col)
+                                                        .map_elements(
+                                                            lambda x: x.decode("utf-8")
+                                                            if isinstance(x, bytes)
+                                                            else str(x),
+                                                            return_dtype=pl.Utf8,
+                                                        )
+                                                        .str.to_decimal()
+                                                        .cast(target_dtype),
                                                     )
-                                                    .str.to_decimal()
-                                                    .cast(target_dtype),
                                                 )
                                             else:
                                                 # Try direct casting
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col).cast(target_dtype),
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col).cast(target_dtype),
+                                                    )
                                                 )
                                         else:
                                             # Try direct casting for non-binary types
-                                            self.features_df = self.features_df.with_columns(
-                                                pl.col(col).cast(target_dtype),
+                                            self.features_df = (
+                                                self.features_df.with_columns(
+                                                    pl.col(col).cast(target_dtype),
+                                                )
                                             )
                                 elif "Float" in dtype_str:
                                     # Convert to float, handling different input types
                                     if self.features_df[col].dtype == pl.Utf8:
                                         # String data - convert to float
-                                        self.features_df = self.features_df.with_columns(
-                                            pl.col(col).str.to_decimal().cast(eval(dtype_str)),
+                                        self.features_df = (
+                                            self.features_df.with_columns(
+                                                pl.col(col)
+                                                .str.to_decimal()
+                                                .cast(eval(dtype_str)),
+                                            )
                                         )
                                     else:
                                         # Handle special cases and try direct casting for other types
@@ -724,43 +807,59 @@ def _load_sample5(self, filename: str, map: bool = False):
                                         if "Binary" in str(current_dtype):
                                             # Convert binary to string first, then to target type
                                             if target_dtype == pl.Utf8:
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col)
-                                                    .map_elements(
-                                                        lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                        return_dtype=pl.Utf8,
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col)
+                                                        .map_elements(
+                                                            lambda x: x.decode("utf-8")
+                                                            if isinstance(x, bytes)
+                                                            else str(x),
+                                                            return_dtype=pl.Utf8,
+                                                        )
+                                                        .cast(target_dtype),
                                                     )
-                                                    .cast(target_dtype),
                                                 )
                                             elif "Int" in str(target_dtype):
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col)
-                                                    .map_elements(
-                                                        lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                        return_dtype=pl.Utf8,
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col)
+                                                        .map_elements(
+                                                            lambda x: x.decode("utf-8")
+                                                            if isinstance(x, bytes)
+                                                            else str(x),
+                                                            return_dtype=pl.Utf8,
+                                                        )
+                                                        .str.to_integer()
+                                                        .cast(target_dtype),
                                                     )
-                                                    .str.to_integer()
-                                                    .cast(target_dtype),
                                                 )
                                             elif "Float" in str(target_dtype):
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col)
-                                                    .map_elements(
-                                                        lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                        return_dtype=pl.Utf8,
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col)
+                                                        .map_elements(
+                                                            lambda x: x.decode("utf-8")
+                                                            if isinstance(x, bytes)
+                                                            else str(x),
+                                                            return_dtype=pl.Utf8,
+                                                        )
+                                                        .str.to_decimal()
+                                                        .cast(target_dtype),
                                                     )
-                                                    .str.to_decimal()
-                                                    .cast(target_dtype),
                                                 )
                                             else:
                                                 # Try direct casting
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col).cast(target_dtype),
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col).cast(target_dtype),
+                                                    )
                                                 )
                                         else:
                                             # Try direct casting for non-binary types
-                                            self.features_df = self.features_df.with_columns(
-                                                pl.col(col).cast(target_dtype),
+                                            self.features_df = (
+                                                self.features_df.with_columns(
+                                                    pl.col(col).cast(target_dtype),
+                                                )
                                             )
                                 elif "Utf8" in dtype_str:
                                     # Ensure it's string type
@@ -776,43 +875,59 @@ def _load_sample5(self, filename: str, map: bool = False):
                                     if "Binary" in str(current_dtype):
                                         # Convert binary to string first, then to target type
                                         if target_dtype == pl.Utf8:
-                                            self.features_df = self.features_df.with_columns(
-                                                pl.col(col)
-                                                .map_elements(
-                                                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                    return_dtype=pl.Utf8,
+                                            self.features_df = (
+                                                self.features_df.with_columns(
+                                                    pl.col(col)
+                                                    .map_elements(
+                                                        lambda x: x.decode("utf-8")
+                                                        if isinstance(x, bytes)
+                                                        else str(x),
+                                                        return_dtype=pl.Utf8,
+                                                    )
+                                                    .cast(target_dtype),
                                                 )
-                                                .cast(target_dtype),
                                             )
                                         elif "Int" in str(target_dtype):
-                                            self.features_df = self.features_df.with_columns(
-                                                pl.col(col)
-                                                .map_elements(
-                                                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                    return_dtype=pl.Utf8,
+                                            self.features_df = (
+                                                self.features_df.with_columns(
+                                                    pl.col(col)
+                                                    .map_elements(
+                                                        lambda x: x.decode("utf-8")
+                                                        if isinstance(x, bytes)
+                                                        else str(x),
+                                                        return_dtype=pl.Utf8,
+                                                    )
+                                                    .str.to_integer()
+                                                    .cast(target_dtype),
                                                 )
-                                                .str.to_integer()
-                                                .cast(target_dtype),
                                             )
                                         elif "Float" in str(target_dtype):
-                                            self.features_df = self.features_df.with_columns(
-                                                pl.col(col)
-                                                .map_elements(
-                                                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                    return_dtype=pl.Utf8,
+                                            self.features_df = (
+                                                self.features_df.with_columns(
+                                                    pl.col(col)
+                                                    .map_elements(
+                                                        lambda x: x.decode("utf-8")
+                                                        if isinstance(x, bytes)
+                                                        else str(x),
+                                                        return_dtype=pl.Utf8,
+                                                    )
+                                                    .str.to_decimal()
+                                                    .cast(target_dtype),
                                                 )
-                                                .str.to_decimal()
-                                                .cast(target_dtype),
                                             )
                                         else:
                                             # Try direct casting
-                                            self.features_df = self.features_df.with_columns(
-                                                pl.col(col).cast(target_dtype),
+                                            self.features_df = (
+                                                self.features_df.with_columns(
+                                                    pl.col(col).cast(target_dtype),
+                                                )
                                             )
                                     else:
                                         # Try direct casting for non-binary types
-                                        self.features_df = self.features_df.with_columns(
-                                            pl.col(col).cast(target_dtype),
+                                        self.features_df = (
+                                            self.features_df.with_columns(
+                                                pl.col(col).cast(target_dtype),
+                                            )
                                         )
                         except Exception as e:
                             self.logger.warning(
@@ -827,23 +942,31 @@ def _load_sample5(self, filename: str, map: bool = False):
                 # This ensures "None" strings introduced by failed conversions are properly handled
                 for col in self.features_df.columns:
                     if self.features_df[col].dtype == pl.Utf8:  # String columns
-                        self.features_df = self.features_df.with_columns([
-                            pl.when(pl.col(col).is_in(["None", "", "null", "NULL"]))
-                            .then(None)
-                            .otherwise(pl.col(col))
-                            .alias(col),
-                        ])
+                        self.features_df = self.features_df.with_columns(
+                            [
+                                pl.when(pl.col(col).is_in(["None", "", "null", "NULL"]))
+                                .then(None)
+                                .otherwise(pl.col(col))
+                                .alias(col),
+                            ],
+                        )
                     # Float columns
                     elif self.features_df[col].dtype in [pl.Float64, pl.Float32]:
-                        self.features_df = self.features_df.with_columns([
-                            pl.col(col).fill_nan(None).alias(col),
-                        ])
+                        self.features_df = self.features_df.with_columns(
+                            [
+                                pl.col(col).fill_nan(None).alias(col),
+                            ],
+                        )
 
                 # Ensure column order matches schema order
                 if "features_df" in schema and "columns" in schema["features_df"]:
                     schema_column_order = list(schema["features_df"]["columns"].keys())
                     # Only reorder columns that exist in both schema and DataFrame
-                    existing_columns = [col for col in schema_column_order if col in self.features_df.columns]
+                    existing_columns = [
+                        col
+                        for col in schema_column_order
+                        if col in self.features_df.columns
+                    ]
                     if existing_columns:
                         self.features_df = self.features_df.select(existing_columns)
 
@@ -873,13 +996,17 @@ def _load_sample5(self, filename: str, map: bool = False):
                             dtype_str = schema_columns[col]["dtype"]
                             try:
                                 if "Int" in dtype_str:
-                                    self.ms1_df = self.ms1_df.with_columns([
-                                        pl.col(col).cast(pl.Int64, strict=False),
-                                    ])
+                                    self.ms1_df = self.ms1_df.with_columns(
+                                        [
+                                            pl.col(col).cast(pl.Int64, strict=False),
+                                        ],
+                                    )
                                 elif "Float" in dtype_str:
-                                    self.ms1_df = self.ms1_df.with_columns([
-                                        pl.col(col).cast(pl.Float64, strict=False),
-                                    ])
+                                    self.ms1_df = self.ms1_df.with_columns(
+                                        [
+                                            pl.col(col).cast(pl.Float64, strict=False),
+                                        ],
+                                    )
                             except Exception as e:
                                 self.logger.warning(
                                     f"Failed to apply schema type {dtype_str} to column {col}: {e}",
@@ -948,15 +1075,21 @@ def _load_sample5_study(self, filename: str, map: bool = False):
         # Load metadata
         if "metadata" in f:
             metadata_group = f["metadata"]
-            self.file_path = decode_metadata_attr(metadata_group.attrs.get("file_path", ""))
+            self.file_path = decode_metadata_attr(
+                metadata_group.attrs.get("file_path", ""),
+            )
 
             # Load file_source if it exists, otherwise set it equal to file_path
             if "file_source" in metadata_group.attrs:
-                self.file_source = decode_metadata_attr(metadata_group.attrs.get("file_source", ""))
+                self.file_source = decode_metadata_attr(
+                    metadata_group.attrs.get("file_source", ""),
+                )
             else:
                 self.file_source = self.file_path
 
-            self.file_type = decode_metadata_attr(metadata_group.attrs.get("file_type", ""))
+            self.file_type = decode_metadata_attr(
+                metadata_group.attrs.get("file_type", ""),
+            )
             self.label = decode_metadata_attr(metadata_group.attrs.get("label", ""))
 
             # Load parameters from JSON in metadata
@@ -1007,19 +1140,23 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                 # Convert "None" strings and NaN values to proper null values
                 for col in self.scans_df.columns:
                     if self.scans_df[col].dtype == pl.Utf8:  # String columns
-                        self.scans_df = self.scans_df.with_columns([
-                            pl.when(pl.col(col).is_in(["None", "", "null", "NULL"]))
-                            .then(None)
-                            .otherwise(pl.col(col))
-                            .alias(col),
-                        ])
+                        self.scans_df = self.scans_df.with_columns(
+                            [
+                                pl.when(pl.col(col).is_in(["None", "", "null", "NULL"]))
+                                .then(None)
+                                .otherwise(pl.col(col))
+                                .alias(col),
+                            ],
+                        )
                     elif self.scans_df[col].dtype in [
                         pl.Float64,
                         pl.Float32,
                     ]:  # Float columns
-                        self.scans_df = self.scans_df.with_columns([
-                            pl.col(col).fill_nan(None).alias(col),
-                        ])
+                        self.scans_df = self.scans_df.with_columns(
+                            [
+                                pl.col(col).fill_nan(None).alias(col),
+                            ],
+                        )
 
                 # update all columns with schema types
                 for col in self.scans_df.columns:
@@ -1037,7 +1174,9 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                                     if self.scans_df[col].dtype == pl.Utf8:
                                         # String data - convert to integer
                                         self.scans_df = self.scans_df.with_columns(
-                                            pl.col(col).str.to_integer().cast(eval(dtype_str)),
+                                            pl.col(col)
+                                            .str.to_integer()
+                                            .cast(eval(dtype_str)),
                                         )
                                     elif self.scans_df[col].dtype in [
                                         pl.Float64,
@@ -1057,7 +1196,9 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                                     if self.scans_df[col].dtype == pl.Utf8:
                                         # String data - convert to float
                                         self.scans_df = self.scans_df.with_columns(
-                                            pl.col(col).str.to_decimal().cast(eval(dtype_str)),
+                                            pl.col(col)
+                                            .str.to_decimal()
+                                            .cast(eval(dtype_str)),
                                         )
                                     else:
                                         # Try direct casting
@@ -1081,7 +1222,9 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                                             self.scans_df = self.scans_df.with_columns(
                                                 pl.col(col)
                                                 .map_elements(
-                                                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
+                                                    lambda x: x.decode("utf-8")
+                                                    if isinstance(x, bytes)
+                                                    else str(x),
                                                     return_dtype=pl.Utf8,
                                                 )
                                                 .cast(target_dtype),
@@ -1090,7 +1233,9 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                                             self.scans_df = self.scans_df.with_columns(
                                                 pl.col(col)
                                                 .map_elements(
-                                                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
+                                                    lambda x: x.decode("utf-8")
+                                                    if isinstance(x, bytes)
+                                                    else str(x),
                                                     return_dtype=pl.Utf8,
                                                 )
                                                 .str.to_integer()
@@ -1100,7 +1245,9 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                                             self.scans_df = self.scans_df.with_columns(
                                                 pl.col(col)
                                                 .map_elements(
-                                                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
+                                                    lambda x: x.decode("utf-8")
+                                                    if isinstance(x, bytes)
+                                                    else str(x),
                                                     return_dtype=pl.Utf8,
                                                 )
                                                 .str.to_decimal()
@@ -1129,7 +1276,9 @@ def _load_sample5_study(self, filename: str, map: bool = False):
             if "scans_df" in schema and "columns" in schema["scans_df"]:
                 schema_column_order = list(schema["scans_df"]["columns"].keys())
                 # Only reorder columns that exist in both schema and DataFrame
-                existing_columns = [col for col in schema_column_order if col in self.scans_df.columns]
+                existing_columns = [
+                    col for col in schema_column_order if col in self.scans_df.columns
+                ]
                 if existing_columns:
                     self.scans_df = self.scans_df.select(existing_columns)
 
@@ -1208,12 +1357,18 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                                             spectrum_list = []
                                             for spec_data in json.loads(item):
                                                 if spec_data is not None:
-                                                    spectrum = Spectrum.from_json(spec_data)
+                                                    spectrum = Spectrum.from_json(
+                                                        spec_data,
+                                                    )
                                                     spectrum_list.append(spectrum)
                                                 else:
                                                     spectrum_list.append(None)
                                             reconstructed_data.append(spectrum_list)
-                                        except (json.JSONDecodeError, ValueError, TypeError):
+                                        except (
+                                            json.JSONDecodeError,
+                                            ValueError,
+                                            TypeError,
+                                        ):
                                             reconstructed_data.append(None)
 
                                 data[col] = reconstructed_data
@@ -1229,10 +1384,13 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                 # Separate Object columns from regular columns to avoid astuple issues
                 object_columns = {}
                 regular_columns = {}
-                
+
                 for col, values in data.items():
                     if col in schema.get("features_df", {}).get("columns", {}):
-                        if "Object" in schema["features_df"]["columns"][col].get("dtype", ""):
+                        if "Object" in schema["features_df"]["columns"][col].get(
+                            "dtype",
+                            "",
+                        ):
                             object_columns[col] = values
                         else:
                             regular_columns[col] = values
@@ -1245,38 +1403,48 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                 else:
                     # If no regular columns, create empty DataFrame
                     self.features_df = pl.DataFrame()
-                
+
                 # Add Object columns one by one
                 for col, values in object_columns.items():
                     if not self.features_df.is_empty():
                         self.features_df = self.features_df.with_columns(
-                            pl.Series(col, values, dtype=pl.Object).alias(col)
+                            pl.Series(col, values, dtype=pl.Object).alias(col),
                         )
                     else:
                         # Create DataFrame with just this Object column
-                        self.features_df = pl.DataFrame({col: values}, schema={col: pl.Object})
+                        self.features_df = pl.DataFrame(
+                            {col: values},
+                            schema={col: pl.Object},
+                        )
 
                 # Convert "None" strings and NaN values to proper null values for regular columns first
                 for col in self.features_df.columns:
                     # Skip Object columns - they're already properly reconstructed
                     if col in schema.get("features_df", {}).get("columns", {}):
-                        if "Object" in schema["features_df"]["columns"][col].get("dtype", ""):
+                        if "Object" in schema["features_df"]["columns"][col].get(
+                            "dtype",
+                            "",
+                        ):
                             continue
 
                     if self.features_df[col].dtype == pl.Utf8:  # String columns
-                        self.features_df = self.features_df.with_columns([
-                            pl.when(pl.col(col).is_in(["None", "", "null", "NULL"]))
-                            .then(None)
-                            .otherwise(pl.col(col))
-                            .alias(col),
-                        ])
+                        self.features_df = self.features_df.with_columns(
+                            [
+                                pl.when(pl.col(col).is_in(["None", "", "null", "NULL"]))
+                                .then(None)
+                                .otherwise(pl.col(col))
+                                .alias(col),
+                            ],
+                        )
                     elif self.features_df[col].dtype in [
                         pl.Float64,
                         pl.Float32,
                     ]:  # Float columns
-                        self.features_df = self.features_df.with_columns([
-                            pl.col(col).fill_nan(None).alias(col),
-                        ])
+                        self.features_df = self.features_df.with_columns(
+                            [
+                                pl.col(col).fill_nan(None).alias(col),
+                            ],
+                        )
 
                 # update all columns with schema types
                 for col in self.features_df.columns:
@@ -1293,16 +1461,25 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                                     # Convert to numeric first, handling different input types
                                     if self.features_df[col].dtype == pl.Utf8:
                                         # String data - convert to integer
-                                        self.features_df = self.features_df.with_columns(
-                                            pl.col(col).str.to_integer().cast(eval(dtype_str)),
+                                        self.features_df = (
+                                            self.features_df.with_columns(
+                                                pl.col(col)
+                                                .str.to_integer()
+                                                .cast(eval(dtype_str)),
+                                            )
                                         )
                                     elif self.features_df[col].dtype in [
                                         pl.Float64,
                                         pl.Float32,
                                     ]:
                                         # Float data - cast to integer with null handling for NaN values
-                                        self.features_df = self.features_df.with_columns(
-                                            pl.col(col).cast(eval(dtype_str), strict=False),
+                                        self.features_df = (
+                                            self.features_df.with_columns(
+                                                pl.col(col).cast(
+                                                    eval(dtype_str),
+                                                    strict=False,
+                                                ),
+                                            )
                                         )
                                     else:
                                         # Handle special cases and try direct casting for other types
@@ -1313,50 +1490,70 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                                         if "Binary" in str(current_dtype):
                                             # Convert binary to string first, then to target type
                                             if target_dtype == pl.Utf8:
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col)
-                                                    .map_elements(
-                                                        lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                        return_dtype=pl.Utf8,
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col)
+                                                        .map_elements(
+                                                            lambda x: x.decode("utf-8")
+                                                            if isinstance(x, bytes)
+                                                            else str(x),
+                                                            return_dtype=pl.Utf8,
+                                                        )
+                                                        .cast(target_dtype),
                                                     )
-                                                    .cast(target_dtype),
                                                 )
                                             elif "Int" in str(target_dtype):
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col)
-                                                    .map_elements(
-                                                        lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                        return_dtype=pl.Utf8,
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col)
+                                                        .map_elements(
+                                                            lambda x: x.decode("utf-8")
+                                                            if isinstance(x, bytes)
+                                                            else str(x),
+                                                            return_dtype=pl.Utf8,
+                                                        )
+                                                        .str.to_integer()
+                                                        .cast(target_dtype),
                                                     )
-                                                    .str.to_integer()
-                                                    .cast(target_dtype),
                                                 )
                                             elif "Float" in str(target_dtype):
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col)
-                                                    .map_elements(
-                                                        lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                        return_dtype=pl.Utf8,
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col)
+                                                        .map_elements(
+                                                            lambda x: x.decode("utf-8")
+                                                            if isinstance(x, bytes)
+                                                            else str(x),
+                                                            return_dtype=pl.Utf8,
+                                                        )
+                                                        .str.to_decimal()
+                                                        .cast(target_dtype),
                                                     )
-                                                    .str.to_decimal()
-                                                    .cast(target_dtype),
                                                 )
                                             else:
                                                 # Try direct casting
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col).cast(target_dtype),
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col).cast(target_dtype),
+                                                    )
                                                 )
                                         else:
                                             # Try direct casting for non-binary types
-                                            self.features_df = self.features_df.with_columns(
-                                                pl.col(col).cast(target_dtype),
+                                            self.features_df = (
+                                                self.features_df.with_columns(
+                                                    pl.col(col).cast(target_dtype),
+                                                )
                                             )
                                 elif "Float" in dtype_str:
                                     # Convert to float, handling different input types
                                     if self.features_df[col].dtype == pl.Utf8:
                                         # String data - convert to float
-                                        self.features_df = self.features_df.with_columns(
-                                            pl.col(col).str.to_decimal().cast(eval(dtype_str)),
+                                        self.features_df = (
+                                            self.features_df.with_columns(
+                                                pl.col(col)
+                                                .str.to_decimal()
+                                                .cast(eval(dtype_str)),
+                                            )
                                         )
                                     else:
                                         # Handle special cases and try direct casting for other types
@@ -1367,43 +1564,59 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                                         if "Binary" in str(current_dtype):
                                             # Convert binary to string first, then to target type
                                             if target_dtype == pl.Utf8:
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col)
-                                                    .map_elements(
-                                                        lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                        return_dtype=pl.Utf8,
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col)
+                                                        .map_elements(
+                                                            lambda x: x.decode("utf-8")
+                                                            if isinstance(x, bytes)
+                                                            else str(x),
+                                                            return_dtype=pl.Utf8,
+                                                        )
+                                                        .cast(target_dtype),
                                                     )
-                                                    .cast(target_dtype),
                                                 )
                                             elif "Int" in str(target_dtype):
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col)
-                                                    .map_elements(
-                                                        lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                        return_dtype=pl.Utf8,
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col)
+                                                        .map_elements(
+                                                            lambda x: x.decode("utf-8")
+                                                            if isinstance(x, bytes)
+                                                            else str(x),
+                                                            return_dtype=pl.Utf8,
+                                                        )
+                                                        .str.to_integer()
+                                                        .cast(target_dtype),
                                                     )
-                                                    .str.to_integer()
-                                                    .cast(target_dtype),
                                                 )
                                             elif "Float" in str(target_dtype):
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col)
-                                                    .map_elements(
-                                                        lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                        return_dtype=pl.Utf8,
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col)
+                                                        .map_elements(
+                                                            lambda x: x.decode("utf-8")
+                                                            if isinstance(x, bytes)
+                                                            else str(x),
+                                                            return_dtype=pl.Utf8,
+                                                        )
+                                                        .str.to_decimal()
+                                                        .cast(target_dtype),
                                                     )
-                                                    .str.to_decimal()
-                                                    .cast(target_dtype),
                                                 )
                                             else:
                                                 # Try direct casting
-                                                self.features_df = self.features_df.with_columns(
-                                                    pl.col(col).cast(target_dtype),
+                                                self.features_df = (
+                                                    self.features_df.with_columns(
+                                                        pl.col(col).cast(target_dtype),
+                                                    )
                                                 )
                                         else:
                                             # Try direct casting for non-binary types
-                                            self.features_df = self.features_df.with_columns(
-                                                pl.col(col).cast(target_dtype),
+                                            self.features_df = (
+                                                self.features_df.with_columns(
+                                                    pl.col(col).cast(target_dtype),
+                                                )
                                             )
                                 elif "Utf8" in dtype_str:
                                     # Ensure it's string type
@@ -1419,43 +1632,59 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                                     if "Binary" in str(current_dtype):
                                         # Convert binary to string first, then to target type
                                         if target_dtype == pl.Utf8:
-                                            self.features_df = self.features_df.with_columns(
-                                                pl.col(col)
-                                                .map_elements(
-                                                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                    return_dtype=pl.Utf8,
+                                            self.features_df = (
+                                                self.features_df.with_columns(
+                                                    pl.col(col)
+                                                    .map_elements(
+                                                        lambda x: x.decode("utf-8")
+                                                        if isinstance(x, bytes)
+                                                        else str(x),
+                                                        return_dtype=pl.Utf8,
+                                                    )
+                                                    .cast(target_dtype),
                                                 )
-                                                .cast(target_dtype),
                                             )
                                         elif "Int" in str(target_dtype):
-                                            self.features_df = self.features_df.with_columns(
-                                                pl.col(col)
-                                                .map_elements(
-                                                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                    return_dtype=pl.Utf8,
+                                            self.features_df = (
+                                                self.features_df.with_columns(
+                                                    pl.col(col)
+                                                    .map_elements(
+                                                        lambda x: x.decode("utf-8")
+                                                        if isinstance(x, bytes)
+                                                        else str(x),
+                                                        return_dtype=pl.Utf8,
+                                                    )
+                                                    .str.to_integer()
+                                                    .cast(target_dtype),
                                                 )
-                                                .str.to_integer()
-                                                .cast(target_dtype),
                                             )
                                         elif "Float" in str(target_dtype):
-                                            self.features_df = self.features_df.with_columns(
-                                                pl.col(col)
-                                                .map_elements(
-                                                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
-                                                    return_dtype=pl.Utf8,
+                                            self.features_df = (
+                                                self.features_df.with_columns(
+                                                    pl.col(col)
+                                                    .map_elements(
+                                                        lambda x: x.decode("utf-8")
+                                                        if isinstance(x, bytes)
+                                                        else str(x),
+                                                        return_dtype=pl.Utf8,
+                                                    )
+                                                    .str.to_decimal()
+                                                    .cast(target_dtype),
                                                 )
-                                                .str.to_decimal()
-                                                .cast(target_dtype),
                                             )
                                         else:
                                             # Try direct casting
-                                            self.features_df = self.features_df.with_columns(
-                                                pl.col(col).cast(target_dtype),
+                                            self.features_df = (
+                                                self.features_df.with_columns(
+                                                    pl.col(col).cast(target_dtype),
+                                                )
                                             )
                                     else:
                                         # Try direct casting for non-binary types
-                                        self.features_df = self.features_df.with_columns(
-                                            pl.col(col).cast(target_dtype),
+                                        self.features_df = (
+                                            self.features_df.with_columns(
+                                                pl.col(col).cast(target_dtype),
+                                            )
                                         )
                         except Exception as e:
                             self.logger.warning(
@@ -1470,23 +1699,31 @@ def _load_sample5_study(self, filename: str, map: bool = False):
                 # This ensures "None" strings introduced by failed conversions are properly handled
                 for col in self.features_df.columns:
                     if self.features_df[col].dtype == pl.Utf8:  # String columns
-                        self.features_df = self.features_df.with_columns([
-                            pl.when(pl.col(col).is_in(["None", "", "null", "NULL"]))
-                            .then(None)
-                            .otherwise(pl.col(col))
-                            .alias(col),
-                        ])
+                        self.features_df = self.features_df.with_columns(
+                            [
+                                pl.when(pl.col(col).is_in(["None", "", "null", "NULL"]))
+                                .then(None)
+                                .otherwise(pl.col(col))
+                                .alias(col),
+                            ],
+                        )
                     # Float columns
                     elif self.features_df[col].dtype in [pl.Float64, pl.Float32]:
-                        self.features_df = self.features_df.with_columns([
-                            pl.col(col).fill_nan(None).alias(col),
-                        ])
+                        self.features_df = self.features_df.with_columns(
+                            [
+                                pl.col(col).fill_nan(None).alias(col),
+                            ],
+                        )
 
                 # Ensure column order matches schema order
                 if "features_df" in schema and "columns" in schema["features_df"]:
                     schema_column_order = list(schema["features_df"]["columns"].keys())
                     # Only reorder columns that exist in both schema and DataFrame
-                    existing_columns = [col for col in schema_column_order if col in self.features_df.columns]
+                    existing_columns = [
+                        col
+                        for col in schema_column_order
+                        if col in self.features_df.columns
+                    ]
                     if existing_columns:
                         self.features_df = self.features_df.select(existing_columns)
 
@@ -1516,7 +1753,9 @@ def _load_sample5_study(self, filename: str, map: bool = False):
     # set self.label to basename without extension
     if self.label is None or self.label == "":
         self.label = os.path.splitext(os.path.basename(filename))[0]
-    self.logger.info(f"Sample loaded successfully from {filename} (optimized for study)")
+    self.logger.info(
+        f"Sample loaded successfully from {filename} (optimized for study)",
+    )
 
 
 def load_schema(schema_path: str) -> Dict[str, Any]:
@@ -1564,13 +1803,20 @@ def clean_null_values_polars(df: pl.DataFrame) -> pl.DataFrame:
     cleaned_df = df
     for col in df.columns:
         if df[col].dtype == pl.Utf8:  # String columns
-            cleaned_df = cleaned_df.with_columns([
-                pl.when(pl.col(col).is_in(["None", "", "null", "NULL"])).then(None).otherwise(pl.col(col)).alias(col),
-            ])
+            cleaned_df = cleaned_df.with_columns(
+                [
+                    pl.when(pl.col(col).is_in(["None", "", "null", "NULL"]))
+                    .then(None)
+                    .otherwise(pl.col(col))
+                    .alias(col),
+                ],
+            )
         elif df[col].dtype in [pl.Float64, pl.Float32]:  # Float columns
-            cleaned_df = cleaned_df.with_columns([
-                pl.col(col).fill_nan(None).alias(col),
-            ])
+            cleaned_df = cleaned_df.with_columns(
+                [
+                    pl.col(col).fill_nan(None).alias(col),
+                ],
+            )
     return cleaned_df
 
 
@@ -1606,7 +1852,12 @@ def cast_column_by_dtype(df: pl.DataFrame, col: str, dtype_str: str) -> pl.DataF
         return df
 
 
-def _cast_to_int(df: pl.DataFrame, col: str, current_dtype: pl.DataType, target_dtype: pl.DataType) -> pl.DataFrame:
+def _cast_to_int(
+    df: pl.DataFrame,
+    col: str,
+    current_dtype: pl.DataType,
+    target_dtype: pl.DataType,
+) -> pl.DataFrame:
     """Helper function to cast column to integer type."""
     if current_dtype == pl.Utf8:
         return df.with_columns(
@@ -1618,7 +1869,12 @@ def _cast_to_int(df: pl.DataFrame, col: str, current_dtype: pl.DataType, target_
         return _cast_with_binary_handling(df, col, current_dtype, target_dtype)
 
 
-def _cast_to_float(df: pl.DataFrame, col: str, current_dtype: pl.DataType, target_dtype: pl.DataType) -> pl.DataFrame:
+def _cast_to_float(
+    df: pl.DataFrame,
+    col: str,
+    current_dtype: pl.DataType,
+    target_dtype: pl.DataType,
+) -> pl.DataFrame:
     """Helper function to cast column to float type."""
     if current_dtype == pl.Utf8:
         return df.with_columns(
@@ -1639,20 +1895,29 @@ def _cast_with_binary_handling(
         if target_dtype == pl.Utf8:
             return df.with_columns(
                 pl.col(col)
-                .map_elements(lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x), return_dtype=pl.Utf8)
+                .map_elements(
+                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
+                    return_dtype=pl.Utf8,
+                )
                 .cast(target_dtype),
             )
         elif "Int" in str(target_dtype):
             return df.with_columns(
                 pl.col(col)
-                .map_elements(lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x), return_dtype=pl.Utf8)
+                .map_elements(
+                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
+                    return_dtype=pl.Utf8,
+                )
                 .str.to_integer()
                 .cast(target_dtype),
             )
         elif "Float" in str(target_dtype):
             return df.with_columns(
                 pl.col(col)
-                .map_elements(lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x), return_dtype=pl.Utf8)
+                .map_elements(
+                    lambda x: x.decode("utf-8") if isinstance(x, bytes) else str(x),
+                    return_dtype=pl.Utf8,
+                )
                 .str.to_decimal()
                 .cast(target_dtype),
             )
@@ -1661,7 +1926,11 @@ def _cast_with_binary_handling(
     return df.with_columns(pl.col(col).cast(target_dtype))
 
 
-def apply_schema_to_dataframe(df: pl.DataFrame, schema: Dict[str, Any], df_name: str) -> pl.DataFrame:
+def apply_schema_to_dataframe(
+    df: pl.DataFrame,
+    schema: Dict[str, Any],
+    df_name: str,
+) -> pl.DataFrame:
     """
     Apply schema type casting to a Polars DataFrame.
 
@@ -1819,7 +2088,9 @@ def _create_dataframe_with_object_columns(
     schema_columns = schema.get(df_name, {}).get("columns", {})
 
     object_columns = {
-        k: v for k, v in data.items() if k in schema_columns and schema_columns[k]["dtype"] == "pl.Object"
+        k: v
+        for k, v in data.items()
+        if k in schema_columns and schema_columns[k]["dtype"] == "pl.Object"
     }
     regular_columns = {k: v for k, v in data.items() if k not in object_columns}
 
@@ -1874,13 +2145,17 @@ def load_ms1_dataframe_from_h5_group(
                 dtype_str = schema_columns[col]["dtype"]
                 try:
                     if "Int" in dtype_str:
-                        ms1_df = ms1_df.with_columns([
-                            pl.col(col).cast(pl.Int64, strict=False),
-                        ])
+                        ms1_df = ms1_df.with_columns(
+                            [
+                                pl.col(col).cast(pl.Int64, strict=False),
+                            ],
+                        )
                     elif "Float" in dtype_str:
-                        ms1_df = ms1_df.with_columns([
-                            pl.col(col).cast(pl.Float64, strict=False),
-                        ])
+                        ms1_df = ms1_df.with_columns(
+                            [
+                                pl.col(col).cast(pl.Float64, strict=False),
+                            ],
+                        )
                 except Exception as e:
                     if logger:
                         logger.warning(
@@ -1891,7 +2166,9 @@ def load_ms1_dataframe_from_h5_group(
     return clean_null_values_polars(ms1_df)
 
 
-def load_parameters_from_metadata(metadata_group: h5py.Group) -> Optional[Dict[str, Any]]:
+def load_parameters_from_metadata(
+    metadata_group: h5py.Group,
+) -> Optional[Dict[str, Any]]:
     """
     Load parameters from HDF5 metadata group.
 
@@ -1938,6 +2215,8 @@ def create_h5_metadata_group(
     metadata_group = f.create_group("metadata")
     metadata_group.attrs["format"] = "master-sample5-1"
     metadata_group.attrs["file_path"] = str(file_path) if file_path is not None else ""
-    metadata_group.attrs["file_source"] = str(file_source) if file_source is not None else ""
+    metadata_group.attrs["file_source"] = (
+        str(file_source) if file_source is not None else ""
+    )
     metadata_group.attrs["file_type"] = str(file_type) if file_type is not None else ""
     metadata_group.attrs["label"] = str(label) if label is not None else ""