masster 0.4.0__py3-none-any.whl → 0.4.1__py3-none-any.whl

masster/sample/sample.py

@@ -23,7 +23,7 @@ Classes:
 
 Example Usage:
 ```python
-from master.sample import Sample
+from masster.sample import Sample
 
 sample = Sample(file="example.mzML")
 sample.find_features()
@@ -38,87 +38,86 @@ import sys
 
 import polars as pl
 
-from master._version import get_version
-from master.logger import MasterLogger
+from masster._version import get_version
+from masster.logger import MassterLogger
 
-from master.sample.defaults.sample_def import sample_defaults
-from master.sample.defaults.find_features_def import find_features_defaults
-from master.sample.defaults.find_adducts_def import find_adducts_defaults
-from master.sample.defaults.find_ms2_def import find_ms2_defaults
-from master.sample.defaults.get_spectrum_def import get_spectrum_defaults
+from masster.sample.defaults.sample_def import sample_defaults
+from masster.sample.defaults.find_features_def import find_features_defaults
+from masster.sample.defaults.find_adducts_def import find_adducts_defaults
+from masster.sample.defaults.find_ms2_def import find_ms2_defaults
+from masster.sample.defaults.get_spectrum_def import get_spectrum_defaults
 
 # Sample-specific imports
-from master.sample.h5 import _load_sample5
-from master.sample.h5 import _load_sample5_study
-from master.sample.h5 import _save_sample5
-from master.sample.helpers import _delete_ms2
-from master.sample.helpers import _estimate_memory_usage
-from master.sample.helpers import _get_scan_uids
-from master.sample.helpers import _get_feature_uids
-from master.sample.helpers import _features_sync
-
-# from master.sample.helpers import _parse_adduct_specs
-# from master.sample.helpers import _calculate_adduct_mass_shift
-# from master.sample.helpers import _parse_formula_expression
-# from master.sample.helpers import _calculate_molecular_mass
-# from master.sample.helpers import _parse_legacy_adduct_format
-# from master.sample.helpers import _extract_adduct_probability
-# from master.sample.helpers import _detect_adduct_groups_direct
-# from master.sample.helpers import _check_adduct_relationship
-from master.sample.adducts import _get_adducts
-from master.sample.adducts import find_adducts
-from master.sample.helpers import features_delete
-from master.sample.helpers import features_filter
-from master.sample.helpers import select
-from master.sample.helpers import select_closest_scan
-from master.sample.helpers import get_dda_stats
-from master.sample.helpers import get_feature
-from master.sample.helpers import get_scan
-from master.sample.helpers import get_eic
-from master.sample.helpers import set_source
-from master.sample.helpers import _recreate_feature_map
-from master.sample.helpers import _get_feature_map
-from master.sample.load import _load_featureXML
-from master.sample.load import _load_ms2data
-from master.sample.load import _load_mzML
-from master.sample.load import _load_raw
-from master.sample.load import _load_wiff
-from master.sample.load import chrom_extract
-from master.sample.load import index_file
-from master.sample.load import load
-from master.sample.load import load_noms1
-from master.sample.load import load_study
-from master.sample.load import sanitize
-from master.sample.plot import plot_2d
-from master.sample.plot import plot_2d_oracle
-from master.sample.plot import plot_dda_stats
-from master.sample.plot import plot_chrom
-from master.sample.plot import plot_feature_stats
-from master.sample.plot import plot_ms2_cycle
-from master.sample.plot import plot_ms2_eic
-from master.sample.plot import plot_ms2_q1
-from master.sample.plot import plot_bpc
-from master.sample.plot import plot_tic
-from master.sample.plot import _handle_sample_plot_output
-from master.sample.processing import _clean_features_df
-from master.sample.processing import _features_deisotope
-from master.sample.processing import _get_ztscan_stats
-from master.sample.processing import _spec_to_mat
-from master.sample.processing import analyze_dda
-from master.sample.processing import find_features
-from master.sample.processing import find_ms2
-from master.sample.processing import get_spectrum
-from master.sample.parameters import store_history
-from master.sample.parameters import get_parameters
-from master.sample.parameters import update_parameters
-from master.sample.parameters import get_parameters_property
-from master.sample.parameters import set_parameters_property
-from master.sample.save import _save_featureXML
-from master.sample.save import export_chrom
-from master.sample.save import export_dda_stats
-from master.sample.save import export_features
-from master.sample.save import export_mgf
-from master.sample.save import save
+from masster.sample.h5 import _load_sample5
+from masster.sample.h5 import _load_sample5_study
+from masster.sample.h5 import _save_sample5
+from masster.sample.helpers import _delete_ms2
+from masster.sample.helpers import _estimate_memory_usage
+from masster.sample.helpers import _get_scan_uids
+from masster.sample.helpers import _get_feature_uids
+from masster.sample.helpers import _features_sync
+#from masster.sample.helpers import _parse_adduct_specs
+#from masster.sample.helpers import _calculate_adduct_mass_shift
+#from masster.sample.helpers import _parse_formula_expression
+#from masster.sample.helpers import _calculate_molecular_mass
+#from masster.sample.helpers import _parse_legacy_adduct_format
+#from masster.sample.helpers import _extract_adduct_probability
+#from masster.sample.helpers import _detect_adduct_groups_direct
+#from masster.sample.helpers import _check_adduct_relationship
+from masster.sample.adducts import _get_adducts
+from masster.sample.adducts import find_adducts
+from masster.sample.helpers import features_delete
+from masster.sample.helpers import features_filter
+from masster.sample.helpers import select
+from masster.sample.helpers import select_closest_scan
+from masster.sample.helpers import get_dda_stats
+from masster.sample.helpers import get_feature
+from masster.sample.helpers import get_scan
+from masster.sample.helpers import get_eic
+from masster.sample.helpers import set_source
+from masster.sample.helpers import _recreate_feature_map
+from masster.sample.helpers import _get_feature_map
+from masster.sample.load import _load_featureXML
+from masster.sample.load import _load_ms2data
+from masster.sample.load import _load_mzML
+from masster.sample.load import _load_raw
+from masster.sample.load import _load_wiff
+from masster.sample.load import chrom_extract
+from masster.sample.load import index_file
+from masster.sample.load import load
+from masster.sample.load import load_noms1
+from masster.sample.load import load_study
+from masster.sample.load import sanitize
+from masster.sample.plot import plot_2d
+from masster.sample.plot import plot_2d_oracle
+from masster.sample.plot import plot_dda_stats
+from masster.sample.plot import plot_chrom
+from masster.sample.plot import plot_feature_stats
+from masster.sample.plot import plot_ms2_cycle
+from masster.sample.plot import plot_ms2_eic
+from masster.sample.plot import plot_ms2_q1
+from masster.sample.plot import plot_bpc
+from masster.sample.plot import plot_tic
+from masster.sample.plot import _handle_sample_plot_output
+from masster.sample.processing import _clean_features_df
+from masster.sample.processing import _features_deisotope
+from masster.sample.processing import _get_ztscan_stats
+from masster.sample.processing import _spec_to_mat
+from masster.sample.processing import analyze_dda
+from masster.sample.processing import find_features
+from masster.sample.processing import find_ms2
+from masster.sample.processing import get_spectrum
+from masster.sample.parameters import store_history
+from masster.sample.parameters import get_parameters
+from masster.sample.parameters import update_parameters
+from masster.sample.parameters import get_parameters_property
+from masster.sample.parameters import set_parameters_property
+from masster.sample.save import _save_featureXML
+from masster.sample.save import export_chrom
+from masster.sample.save import export_dda_stats
+from masster.sample.save import export_features
+from masster.sample.save import export_mgf
+from masster.sample.save import save
 
 
 class Sample:
@@ -180,7 +179,7 @@ class Sample:
         self.log_sink = params.log_sink
 
         # Initialize independent logger
-        self.logger = MasterLogger(
+        self.logger = MassterLogger(
             instance_type="sample",
             level=params.log_level.upper(),
             label=params.log_label if params.log_label else "",
@@ -299,12 +298,7 @@ class Sample:
     find_ms2_defaults = find_ms2_defaults
     get_spectrum_defaults = get_spectrum_defaults
 
-    def logger_update(
-        self,
-        level: str | None = None,
-        label: str | None = None,
-        sink: str | None = None,
-    ):
+    def logger_update(self, level: str | None = None, label: str | None = None, sink: str | None = None):
         """Update the logging configuration for this Sample instance.
 
         Args:
@@ -329,20 +323,20 @@ class Sample:
 
     def _reload(self):
         """
-        Reloads all master modules to pick up any changes to their source code,
+        Reloads all masster modules to pick up any changes to their source code,
         and updates the instance's class reference to the newly reloaded class version.
         This ensures that the instance uses the latest implementation without restarting the interpreter.
         """
         # Reset logger configuration flags to allow proper reconfiguration after reload
         try:
-            import master.logger as logger_module
+            import masster.logger as logger_module
 
             if hasattr(logger_module, "_SAMPLE_LOGGER_CONFIGURED"):
                 logger_module._SAMPLE_LOGGER_CONFIGURED = False
         except Exception:
             pass
 
-        # Get the base module name (master)
+        # Get the base module name (masster)
         base_modname = self.__class__.__module__.split(".")[0]
         current_module = self.__class__.__module__
 
@@ -352,13 +346,10 @@ class Sample:
 
         # Get all currently loaded modules that are part of the sample package
         for module_name in sys.modules:
-            if (
-                module_name.startswith(sample_module_prefix)
-                and module_name != current_module
-            ):
+            if module_name.startswith(sample_module_prefix) and module_name != current_module:
                 sample_modules.append(module_name)
 
-        # Add core master modules
+        # Add core masster modules
         core_modules = [
             f"{base_modname}._version",
             f"{base_modname}.chromatogram",
@@ -370,10 +361,7 @@ class Sample:
         study_modules = []
         study_module_prefix = f"{base_modname}.study."
         for module_name in sys.modules:
-            if (
-                module_name.startswith(study_module_prefix)
-                and module_name != current_module
-            ):
+            if module_name.startswith(study_module_prefix) and module_name != current_module:
                 study_modules.append(module_name)
 
         """ # Add parameters submodules
@@ -384,9 +372,7 @@ class Sample:
                 parameters_modules.append(module_name)
         """
 
-        all_modules_to_reload = (
-            core_modules + sample_modules + study_modules
-        )  # + parameters_modules
+        all_modules_to_reload = core_modules + sample_modules + study_modules  # + parameters_modules
 
         # Reload all discovered modules
         for full_module_name in all_modules_to_reload:
@@ -415,6 +401,7 @@ class Sample:
     def get_version(self):
         return get_version()
 
+
     def info(self):
         # show the key attributes of the object
         str = f"File: {os.path.basename(self.file_path)}\n"
@@ -437,9 +424,9 @@ class Sample:
 
     def __str__(self):
         if self.features_df is None:
-            str = f"master Sample, source: {os.path.basename(self.file_path)}, features: 0"
+            str = f"masster Sample, source: {os.path.basename(self.file_path)}, features: 0"
         else:
-            str = f"master Sample, source: {os.path.basename(self.file_path)}, features: {len(self.features_df)}"
+            str = f"masster Sample, source: {os.path.basename(self.file_path)}, features: {len(self.features_df)}"
         return str
 
 

masster/sample/sample5_schema.json

@@ -1,95 +1,95 @@
 {
   "features_df": {
     "columns": {
-      "adduct": {
-        "dtype": "pl.Utf8"
-      },
-      "adduct_charge": {
-        "dtype": "pl.Int64"
-      },
-      "adduct_group": {
+      "feature_uid": {
         "dtype": "pl.Int64"
       },
-      "adduct_mass_neutral": {
-        "dtype": "pl.Float64"
-      },
-      "adduct_mass_shift": {
-        "dtype": "pl.Float64"
+      "feature_id": {
+        "dtype": "pl.Utf8"
       },
-      "charge": {
+      "sample_uid": {
         "dtype": "pl.Int32"
       },
-      "chrom": {
-        "dtype": "pl.Object"
-      },
-      "chrom_area": {
+      "mz": {
         "dtype": "pl.Float64"
       },
-      "chrom_coherence": {
+      "rt": {
         "dtype": "pl.Float64"
       },
-      "chrom_height_scaled": {
+      "rt_original": {
         "dtype": "pl.Float64"
       },
-      "chrom_prominence": {
+      "rt_start": {
         "dtype": "pl.Float64"
       },
-      "chrom_prominence_scaled": {
+      "rt_end": {
         "dtype": "pl.Float64"
       },
-      "feature_id": {
-        "dtype": "pl.Utf8"
+      "rt_delta": {
+        "dtype": "pl.Float64"
       },
-      "feature_uid": {
-        "dtype": "pl.Int64"
+      "mz_start": {
+        "dtype": "pl.Float64"
       },
-      "filled": {
-        "dtype": "pl.Boolean"
+      "mz_end": {
+        "dtype": "pl.Float64"
       },
       "inty": {
         "dtype": "pl.Float64"
       },
+      "quality": {
+        "dtype": "pl.Float64"
+      },
+      "charge": {
+        "dtype": "pl.Int32"
+      },
       "iso": {
         "dtype": "pl.Int64"
       },
       "iso_of": {
         "dtype": "pl.Int64"
       },
-      "ms2_scans": {
-        "dtype": "pl.Object"
+      "adduct": {
+        "dtype": "pl.Utf8"
       },
-      "ms2_specs": {
-        "dtype": "pl.Object"
+      "adduct_charge": {
+        "dtype": "pl.Int64"
       },
-      "mz": {
+      "adduct_mass_shift": {
         "dtype": "pl.Float64"
       },
-      "mz_end": {
+      "adduct_mass_neutral": {
         "dtype": "pl.Float64"
       },
-      "mz_start": {
-        "dtype": "pl.Float64"
+      "adduct_group": {
+        "dtype": "pl.Int64"
       },
-      "quality": {
-        "dtype": "pl.Float64"
+      "chrom": {
+        "dtype": "pl.Object"
       },
-      "rt": {
+      "filled": {
+        "dtype": "pl.Boolean"
+      },
+      "chrom_area": {
         "dtype": "pl.Float64"
       },
-      "rt_delta": {
+      "chrom_coherence": {
         "dtype": "pl.Float64"
       },
-      "rt_end": {
+      "chrom_prominence": {
         "dtype": "pl.Float64"
       },
-      "rt_original": {
+      "chrom_prominence_scaled": {
         "dtype": "pl.Float64"
       },
-      "rt_start": {
+      "chrom_height_scaled": {
         "dtype": "pl.Float64"
       },
-      "sample_uid": {
-        "dtype": "pl.Int32"
+      "ms2_scans": {
+        "dtype": "pl.Object"
+      },
+      "ms2_specs": {
+        "dtype": "pl.Object"
       }
     }
   },

masster/sample/save.py

@@ -67,7 +67,7 @@ import pyopenms as oms
 from tqdm import tqdm
 
 # Parameters removed - using hardcoded defaults
-from master.spectrum import combine_peaks
+from masster.spectrum import combine_peaks
 
 
 def save(self, filename=None):
@@ -139,13 +139,9 @@ def export_features(self, filename="features.csv"):
         clean_df = clean_df.with_columns(
             (pl.col("ms2_scans").is_not_null()).alias("has_ms2"),
         )
-    clean_df = self.features_df.select(
-        [
-            col
-            for col in self.features_df.columns
-            if self.features_df[col].dtype not in (pl.List, pl.Object)
-        ],
-    )
+    clean_df = self.features_df.select([
+        col for col in self.features_df.columns if self.features_df[col].dtype not in (pl.List, pl.Object)
+    ])
     if filename.lower().endswith((".xls", ".xlsx")):
         clean_df.to_pandas().to_excel(filename, index=False)
         self.logger.info(f"Features exported to {filename} (Excel format)")
@@ -279,10 +275,7 @@ def export_mgf(
             if spect.ms_level > 1 and hasattr(spect, "energy"):
                 f.write(f"ENERGY={spect.energy}\n")
         # Use list comprehension for better performance
-        peak_lines = [
-            f"{mz_val:.5f} {inty_val:.0f}\n"
-            for mz_val, inty_val in zip(spect.mz, spect.inty, strict=False)
-        ]
+        peak_lines = [f"{mz_val:.5f} {inty_val:.0f}\n" for mz_val, inty_val in zip(spect.mz, spect.inty, strict=False)]
         f.writelines(peak_lines)
         f.write("END IONS\n\n")
 
@@ -294,8 +287,7 @@ def export_mgf(
 
     # count how many features have charge < 0
     if (
-        self.features_df.filter(pl.col("charge") < 0).shape[0]
-        - self.features_df.filter(pl.col("charge") > 0).shape[0]
+        self.features_df.filter(pl.col("charge") < 0).shape[0] - self.features_df.filter(pl.col("charge") > 0).shape[0]
         > 0
     ):
         preferred_charge = -1
@@ -396,9 +388,7 @@ def export_mgf(
                                     q1_max=q1_ratio_max,
                                 )
                                 # Get the corresponding scan_uid from the list
-                                current_scan_uid = (
-                                    scan_uids[i] if i < len(scan_uids) else "unknown"
-                                )
+                                current_scan_uid = scan_uids[i] if i < len(scan_uids) else "unknown"
                                 write_ion(
                                     f,
                                     f"fid:{feature_uid}, rt:{rt_str}, mz:{mz_str}, scan_uid:{current_scan_uid}",
@@ -421,12 +411,7 @@ def export_mgf(
                     for scan_uid in ms2_scan_uids:
                         spec = self.get_spectrum(scan_uid)
                         if spec is not None:
-                            spectra_with_energy.append(
-                                (
-                                    scan_uid,
-                                    spec.energy if hasattr(spec, "energy") else 0,
-                                ),
-                            )
+                            spectra_with_energy.append((scan_uid, spec.energy if hasattr(spec, "energy") else 0))
 
                     # Group by energy
                     energy_groups: dict[float, list[int]] = {}
@@ -511,18 +496,14 @@ def export_mgf(
                                 spect = spect.centroid(
                                     tolerance=self.parameters["mz_tol_ms1_da"],
                                     ppm=self.parameters["mz_tol_ms1_ppm"],
-                                    min_points=self.parameters[
-                                        "centroid_min_points_ms1"
-                                    ],
+                                    min_points=self.parameters["centroid_min_points_ms1"],
                                     algo=centroid_algo,
                                 )
                             elif spect.ms_level == 2:
                                 spect = spect.centroid(
                                     tolerance=self.parameters["mz_tol_ms2_da"],
                                     ppm=self.parameters["mz_tol_ms2_ppm"],
-                                    min_points=self.parameters[
-                                        "centroid_min_points_ms2"
-                                    ],
+                                    min_points=self.parameters["centroid_min_points_ms2"],
                                     algo=centroid_algo,
                                 )
                         if deisotope:
@@ -614,9 +595,7 @@ def export_dda_stats(self, filename="stats.csv"):
     ms2_count = len(self.scans_df.filter(pl.col("ms_level") == 2))
     features_count = len(self.features_df) if self.features_df is not None else 0
     features_with_ms2 = (
-        self.features_df.filter(pl.col("ms2_scans").is_not_null()).height
-        if self.features_df is not None
-        else 0
+        self.features_df.filter(pl.col("ms2_scans").is_not_null()).height if self.features_df is not None else 0
     )
 
     # Initialize a dictionary to hold statistics
@@ -631,9 +610,7 @@ def export_dda_stats(self, filename="stats.csv"):
     if "time_cycle" in self.scans_df.columns:
         ms1_df = self.scans_df.filter(pl.col("ms_level") == 1)
         avg_cycle_time = ms1_df["time_cycle"].mean()
-        stats["Average_cycle_time"] = (
-            avg_cycle_time if avg_cycle_time is not None else ""
-        )
+        stats["Average_cycle_time"] = avg_cycle_time if avg_cycle_time is not None else ""
     else:
         stats["Average_cycle_time"] = 0