Merge branch 'verbosity_fixes_dec2024' into 'master'

corilo · corilo · commit 581da35bae9d · 2024-12-17T16:08:30.000Z
Verbosity fixes dec2024

See merge request mass-spectrometry/corems!146
diff --git a/corems/__init__.py b/corems/__init__.py
@@ -21,19 +21,22 @@
 
 
 
-def timeit(method):
-    def timed(*args, **kw):
-        ts = time.time()
-        result = method(*args, **kw)
-        te = time.time()
-        if "log_time" in kw:
-            name = kw.get("log_name", method.__name__.upper())
-            kw["log_time"][name] = int((te - ts) * 1000)
-        else:
-            print("%r  %2.2f ms" % (method.__name__, (te - ts) * 1000))
-        return result
-
-    return timed
+def timeit(print_time=True):
+    def decorator(method):
+        def timed(*args, **kw):
+            # Extract print_time from kwargs if provided
+            local_print_time = kw.pop('print_time', print_time)
+            ts = time.time()
+            result = method(*args, **kw)
+            te = time.time()
+            if "log_time" in kw:
+                name = kw.get("log_name", method.__name__.upper())
+                kw["log_time"][name] = int((te - ts) * 1000)
+            elif local_print_time:
+                print("%r  %2.2f ms" % (method.__name__, (te - ts) * 1000))
+            return result
+        return timed
+    return decorator
 
 
 class SuppressPrints:
diff --git a/corems/encapsulation/factory/parameters.py b/corems/encapsulation/factory/parameters.py
@@ -13,6 +13,12 @@
 )
 from corems.encapsulation.factory.processingSetting import DataInputSetting
 
+def hush_output():
+    """Toggle all the verbose_processing flags to False on the MSParameters, GCMSParameters and LCMSParameters classes"""
+    MSParameters.molecular_search.verbose_processing = False
+    MSParameters.mass_spectrum.verbose_processing = False
+    GCMSParameters.gc_ms.verbose_processing = False
+    LCMSParameters.lc_ms.verbose_processing = False
 
 def reset_ms_parameters():
     """Reset the MSParameter class to the default values"""
diff --git a/corems/encapsulation/factory/processingSetting.py b/corems/encapsulation/factory/processingSetting.py
@@ -816,7 +816,10 @@ class MolecularFormulaSearchSettings:
         m/z error average. Default is 0.0.
     used_atom_valences : dict, optional
         Dictionary of atoms and valences. Default is {'C': 4, '13C': 4, 'H': 1, 'O': 2, '18O': 2, 'N': 3, 'S': 2, '34S': 2, 'P': 3, 'Cl': 1, '37Cl': 1, 'Br': 1, 'Na': 1, 'F': 1, 'K': 0}.
+    verbose_processing: bool, optional
+        If True, print verbose processing information. Default is True.
     """
+    verbose_processing: bool = True    
 
     use_isotopologue_filter: bool = False
 
diff --git a/corems/mass_spectrum/calc/Calibration.py b/corems/mass_spectrum/calc/Calibration.py
@@ -65,7 +65,7 @@ def __init__(self, mass_spectrum, ref_masslist, mzsegment=None):
 
         # define reference mass list - bruker .ref format
         self.ref_mass_list_path = ref_masslist
-        if self.mass_spectrum.percentile_assigned()[0] != 0:
+        if self.mass_spectrum.percentile_assigned(mute_output=True)[0] != 0:
             warnings.warn(
                 "Warning: calibrating spectra which have already been assigned may yield erroneous results"
             )
@@ -77,10 +77,6 @@ def __init__(self, mass_spectrum, ref_masslist, mzsegment=None):
                 "MS Obj loaded - " + str(len(mass_spectrum.mspeaks)) + " peaks found."
             )
 
-            print(
-                "MS Obj loaded - " + str(len(mass_spectrum.mspeaks)) + " peaks found."
-            )
-
     def load_ref_mass_list(self):
         """Load reference mass list (Bruker format)
 
@@ -228,7 +224,7 @@ def find_calibration_points(
             cal_peaks_mz = list(tmpdf.values)
             cal_refs_mz = list(tmpdf.index)
         elif calibration_ref_match_method == "merged":
-            warnings.warn("Using experimental new reference mass list merging")
+            #warnings.warn("Using experimental new reference mass list merging")
             # This is a new approach (August 2024) which uses Pandas 'merged_asof' to find the peaks closest in m/z between
             # reference and measured masses. This is a quicker way to match, and seems to get more matches.
             # It may not work as well when the data are far from correc initial mass
diff --git a/corems/mass_spectrum/calc/MassErrorPrediction.py b/corems/mass_spectrum/calc/MassErrorPrediction.py
@@ -90,12 +90,12 @@ def get_results(self):
 
     def calc_error_dist(self):
         """Calculate the error distribution."""
+        verbose = self.mass_spectrum_obj.parameters.mass_spectrum.verbose_processing
         results_list = []
 
         indexes_without_results = list(range(len(self.mass_spectrum_obj)))
         # loop trough mass spectrum
-
-        for peak_obj_idx, peak_obj in enumerate(tqdm(self.mass_spectrum_obj)):
+        for peak_obj_idx, peak_obj in enumerate(tqdm(self.mass_spectrum_obj), disable=not verbose):
             # access ms peaks triplets ( peak_obj_idx -1, peak_obj_idx, and peak_obj_idx + 1)
             # check lower and upper boundaries to not excesses mass spectrum range
 
diff --git a/corems/mass_spectrum/calc/MassSpectrumCalc.py b/corems/mass_spectrum/calc/MassSpectrumCalc.py
@@ -38,13 +38,16 @@ class MassSpecCalc(PeakPicking, NoiseThresholdCalc):
         Calculate the weight average molecular weight
     """
 
-    def percentile_assigned(self, report_error: bool = False):
+    def percentile_assigned(self, report_error: bool = False, mute_output: bool = False):
         """Percentage of peaks which are assigned
 
         Parameters
         -----------
         report_error: bool, optional
             Report the error of the assigned peaks. Default is False.
+        mute_output: bool, optional
+            Override the verbose setting. Default is False.
+            If True, the function will silence results
         """
         verbose = self.parameters.mass_spectrum.verbose_processing
         assign_abun = 0
@@ -68,15 +71,15 @@ def percentile_assigned(self, report_error: bool = False):
         total_relative_abundance = (assign_abun / (not_assign_abun + assign_abun)) * 100
         if report_error:
             rms_error = sqrt(mean(array(error) ** 2))
-            if verbose:
+            if verbose and not mute_output:
                 print(
                     "%i assigned peaks and %i unassigned peaks, total  = %.2f %%, relative abundance = %.2f %%, RMS error (best candidate) (ppm) = %.3f"
                     % (i, j, total_percent, total_relative_abundance, rms_error)
                 )
             return i, j, total_percent, total_relative_abundance, rms_error
 
         else:
-            if verbose:
+            if verbose and not mute_output:
                 print(
                     "%i assigned peaks and %i unassigned peaks , total  = %.2f %%, relative abundance = %.2f %%"
                     % (
diff --git a/corems/molecular_id/factory/MolecularLookupTable.py b/corems/molecular_id/factory/MolecularLookupTable.py
@@ -364,14 +364,17 @@ def add_carbonsHydrogens(self, settings, existing_classes_objs):
                     self.sql_db.session.execute(insert_query)
                 self.sql_db.session.commit()
 
-    @timeit
-    def runworker(self, molecular_search_settings):
+    @timeit(print_time=True)
+    def runworker(self, molecular_search_settings, **kwargs):
         """Run the molecular formula lookup table worker.
 
         Parameters
         ----------
         molecular_search_settings : object
             An object containing user-defined settings.
+        kwargs : dict
+            A dictionary of keyword arguments.
+            Most notably, the print_time argument which is passed to the timeit decorator.
 
         Returns
         -------
@@ -380,6 +383,7 @@ def runworker(self, molecular_search_settings):
 
 
         """
+        verbose = molecular_search_settings.verbose_processing
 
         classes_list, class_to_create, existing_classes_objs = (
             self.check_database_get_class_list(molecular_search_settings)
@@ -412,7 +416,7 @@ def runworker(self, molecular_search_settings):
             self.even_ch_dbe = [obj.dbe for obj in even_ch_obj]
 
             all_results = list()
-            for class_tuple in tqdm(class_to_create):
+            for class_tuple in tqdm(class_to_create, disable = not verbose):
                 results = self.populate_combinations(class_tuple, settings)
                 all_results.extend(results)
                 if settings.db_jobs == 1:
@@ -438,8 +442,8 @@ def runworker(self, molecular_search_settings):
                 ]
                 p = multiprocessing.Pool(settings.db_jobs)
                 for class_list in tqdm(
-                    p.imap_unordered(insert_database_worker, worker_args)
-                ):
+                        p.imap_unordered(insert_database_worker, worker_args), disable= not verbose
+                        ):
                     pass
                 p.close()
                 p.join()
diff --git a/corems/molecular_id/factory/molecularSQL.py b/corems/molecular_id/factory/molecularSQL.py
@@ -473,6 +473,7 @@ def get_dict_by_classes(
         if the number of classes and nominal_m/zs are higher than 999 the query will fail
         Solution: use postgres or split query
         """
+        verbose = molecular_search_settings.verbose_processing
 
         def query_normal(class_list, len_adduct):
             """query for normal database
@@ -565,10 +566,7 @@ def nominal_mass_by_ion_type(formula_obj):
 
                 elif ion_type == Labels.adduct_ion and adduct_atom:
                     return int(formula_obj._adduct_mz(ion_charge, adduct_atom))
-
-            for formula_obj, ch_obj, classe_obj in tqdm.tqdm(
-                formulas, desc="Loading molecular formula database"
-            ):
+            for formula_obj, ch_obj, classe_obj in tqdm.tqdm(formulas, desc="Loading molecular formula database", disable = not verbose):
                 nominal_mz = nominal_mass_by_ion_type(formula_obj)
 
                 if self.type != "normal":
diff --git a/corems/molecular_id/search/compoundSearch.py b/corems/molecular_id/search/compoundSearch.py
@@ -127,7 +127,6 @@ def metabolite_detector_score(self, gc_peak, ref_obj, spectral_simi):
 
         return spectral_similarity_scores, ri_score, similarity_score
 
-    # @timeit
     def run(self):
         """Runs the low-resolution mass spectral match."""
         # TODO select the best gcms peak
@@ -148,8 +147,8 @@ def run(self):
         self.gcms_obj.chromatogram_settings.use_deconvolution = (
             original_use_deconvolution
         )
-
-        for gc_peak in tqdm.tqdm(self.gcms_obj):
+        verbose = self.gcms_obj.chromatogram_settings.verbose_processing
+        for gc_peak in tqdm.tqdm(self.gcms_obj, disable = not verbose):
             if not self.calibration:
                 window = self.gcms_obj.molecular_search_settings.ri_search_range
 
diff --git a/corems/molecular_id/search/molecularFormulaSearch.py b/corems/molecular_id/search/molecularFormulaSearch.py
@@ -191,7 +191,10 @@ def get_formulas(nominal_overlay: float = 0.1):
 
     def run_worker_mass_spectrum(self):
         """Run the molecular formula search on the mass spectrum object."""
-        self.run_molecular_formula(self.mass_spectrum_obj.sort_by_abundance())
+        self.run_molecular_formula(
+            self.mass_spectrum_obj.sort_by_abundance(), 
+            print_time=self.mass_spectrum_obj.molecular_search_settings.verbose_processing
+            )
 
     def run_worker_ms_peaks(self, ms_peaks):
         """Run the molecular formula search on the given list of mass spectrum peaks.
@@ -201,7 +204,10 @@ def run_worker_ms_peaks(self, ms_peaks):
         ms_peaks : list of MSPeak
             The list of mass spectrum peaks.
         """
-        self.run_molecular_formula(ms_peaks)
+        self.run_molecular_formula(
+            ms_peaks,
+            print_time=self.mass_spectrum_obj.molecular_search_settings.verbose_processing
+        )
 
     @staticmethod
     def database_to_dict(classe_str_list, nominal_mzs, mf_search_settings, ion_charge):
@@ -262,14 +268,18 @@ def database_to_dict(classe_str_list, nominal_mzs, mf_search_settings, ion_charg
 
         return dict_res
 
-    @timeit
-    def run_molecular_formula(self, ms_peaks):
+    @timeit(print_time=True)
+    def run_molecular_formula(self, ms_peaks, **kwargs):
         """Run the molecular formula search on the given list of mass spectrum peaks.
 
         Parameters
         ----------
         ms_peaks : list of MSPeak
             The list of mass spectrum peaks.
+        **kwargs
+            Additional keyword arguments. 
+            Most notably, print_time, which is a boolean flag to indicate whether to print the time 
+            and passed to the timeit decorator.
         """
         # number_of_process = multiprocessing.cpu_count()
 
@@ -288,14 +298,16 @@ def run_molecular_formula(self, ms_peaks):
         # needs to improve to bin by mass defect instead, faster db creation and faster search execution time
         nominal_mzs = self.mass_spectrum_obj.nominal_mz
 
+        verbose = self.mass_spectrum_obj.molecular_search_settings.verbose_processing
         # reset average error, only relevant is average mass error method is being used
         SearchMolecularFormulaWorker(
             find_isotopologues=self.find_isotopologues
         ).reset_error(self.mass_spectrum_obj)
 
         # check database for all possible molecular formula combinations based on the setting passed to self.mass_spectrum_obj.molecular_search_settings
         classes = MolecularCombinations(self.sql_db).runworker(
-            self.mass_spectrum_obj.molecular_search_settings
+            self.mass_spectrum_obj.molecular_search_settings,
+            print_time=self.mass_spectrum_obj.molecular_search_settings.verbose_processing
         )
 
         # split the database load to not blowout the memory
@@ -315,22 +327,20 @@ def run():
                     self.mass_spectrum_obj.molecular_search_settings,
                     ion_charge,
                 )
-
-                pbar = tqdm.tqdm(classe_chunk)
-
+                pbar = tqdm.tqdm(classe_chunk, disable = not verbose)
                 for classe_tuple in pbar:
                     # class string is a json serialized dict
                     classe_str = classe_tuple[0]
                     classe_dict = classe_tuple[1]
 
                     if self.mass_spectrum_obj.molecular_search_settings.isProtonated:
                         ion_type = Labels.protonated_de_ion
-
-                        pbar.set_description_str(
-                            desc="Started molecular formula search for class %s, (de)protonated "
-                            % classe_str,
-                            refresh=True,
-                        )
+                        if verbose:
+                            pbar.set_description_str(
+                                desc="Started molecular formula search for class %s, (de)protonated "
+                                % classe_str,
+                                refresh=True,
+                            )
 
                         candidate_formulas = dict_res.get(ion_type).get(classe_str)
 
@@ -344,11 +354,12 @@ def run():
                             )
 
                     if self.mass_spectrum_obj.molecular_search_settings.isRadical:
-                        pbar.set_description_str(
-                            desc="Started molecular formula search for class %s, radical "
-                            % classe_str,
-                            refresh=True,
-                        )
+                        if verbose:
+                            pbar.set_description_str(
+                                desc="Started molecular formula search for class %s, radical "
+                                % classe_str,
+                                refresh=True,
+                            )
 
                         ion_type = Labels.radical_ion
 
@@ -365,11 +376,12 @@ def run():
                     # looks for adduct, used_atom_valences should be 0
                     # this code does not support H exchance by halogen atoms
                     if self.mass_spectrum_obj.molecular_search_settings.isAdduct:
-                        pbar.set_description_str(
-                            desc="Started molecular formula search for class %s, adduct "
-                            % classe_str,
-                            refresh=True,
-                        )
+                        if verbose:
+                            pbar.set_description_str(
+                                desc="Started molecular formula search for class %s, adduct "
+                                % classe_str,
+                                refresh=True,
+                            )
 
                         ion_type = Labels.adduct_ion
                         dict_atoms_formulas = dict_res.get(ion_type)
@@ -904,18 +916,24 @@ def run_untargeted_worker_ms1(self):
         # do molecular formula based on the parameters set for ms1 search
         for peak in self.lcms_obj:
             self.mass_spectrum_obj = peak.mass_spectrum
-            self.run_molecular_formula(peak.mass_spectrum.sort_by_abundance())
+            self.run_molecular_formula(
+                peak.mass_spectrum.sort_by_abundance(),
+                print_time=self.lcms_obj.parameters.lc_ms.verbose_processing
+                )
 
     def run_target_worker_ms1(self):
         """Run targeted molecular formula search on the ms1 mass spectrum."""
         # do molecular formula based on the external molecular reference list
-        pbar = tqdm.tqdm(self.lcms_obj)
+        verbose = self.lcms_obj.parameters.lc_ms.verbose_processing
+        if verbose:
+            pbar = tqdm.tqdm(self.lcms_obj)
 
         for peak in self.lcms_obj:
-            pbar.set_description_str(
-                desc=f"Started molecular formulae search for mass spectrum at RT {peak.retention_time} s",
-                refresh=True,
-            )
+            if verbose:
+                pbar.set_description_str(
+                    desc=f"Started molecular formulae search for mass spectrum at RT {peak.retention_time} s",
+                    refresh=True,
+                )
 
             self.mass_spectrum_obj = peak.mass_spectrum
 
@@ -924,7 +942,7 @@ def run_target_worker_ms1(self):
             candidate_formulas = peak.targeted_molecular_formulas
 
             for i in candidate_formulas:
-                if self.lcms_obj.parameters.lc_ms.verbose_processing:
+                if verbose:
                     print(i)
             if self.mass_spectrum_obj.molecular_search_settings.isProtonated:
                 ion_type = Labels.protonated_de_ion
diff --git a/corems/molecular_id/search/priorityAssignment.py b/corems/molecular_id/search/priorityAssignment.py
diff --git a/requirements.txt b/requirements.txt
diff --git a/support_code/nmdc/lipidomics/lipidomics_workflow.py b/support_code/nmdc/lipidomics/lipidomics_workflow.py
diff --git a/tests/test_setting_settings.py b/tests/test_setting_settings.py
