Minor message fixes

machine_learning_hep/analysis/do_systematics.py

@@ -128,7 +128,7 @@ def __init__(self, path_database_analysis: str, typean: str, var: str):
         elif binning := self.cfg(f'observables.{var}.bins_fix'):
             bins_tmp = bin_array(*binning)
         else:
-            self.logger.error('no binning specified for %s, using defaults', var)
+            self.logger.error('No binning specified for %s, using defaults', var)
             bins_tmp = bin_array(10, 0., 1.)
         binning_obs_rec = bins_tmp
         self.n_bins_obs_rec = len(binning_obs_rec) - 1
@@ -151,7 +151,7 @@ def __init__(self, path_database_analysis: str, typean: str, var: str):
         elif binning := self.cfg(f'observables.{var}.bins_fix'):
             bins_tmp = bin_array(*binning)
         else:
-            self.logger.error('no binning specified for %s, using defaults', var)
+            self.logger.error('No binning specified for %s, using defaults', var)
             bins_tmp = bin_array(10, 0., 1.)
         binning_obs_gen = bins_tmp
         self.n_bins_obs_gen = len(binning_obs_gen) - 1

machine_learning_hep/data/data_run3/database_ml_parameters_D0Jet_pp.yml

@@ -11,7 +11,7 @@
 #    You should have received a copy of the GNU General Public License    #
 #   along with this program. if not, see <https://www.gnu.org/licenses/>. #
 
-D0jet_pp:
+D0Jet_pp:
   doml: true
   mass: 1.864
   sel_reco_unp: "fPt > 1."

machine_learning_hep/globalfitter.py

@@ -230,7 +230,7 @@ def update_check_signal_fit(self):
         return ""
 
     def derive_yields(self):
-        self.logger.info("calculate signal, backgroud, S/B, significance")
+        self.logger.info("Calculate signal, backgroud, S/B, significance")
         self.mean_fit = self.sig_fit_func.GetParameter(1)
         self.mean_err_fit = self.sig_fit_func.GetParError(1)
         # Could be negative together with the integral pre-factor
@@ -393,7 +393,7 @@ def fit(self):
         self.logger.info("Initial parameters for signal fit are")
         print(f"mean = {self.mean}\nsigma = {self.sigma}")
 
-        self.logger.debug("fit background (just side bands)")
+        self.logger.debug("Fit background (just side bands)")
         self.histo_to_fit.Fit(self.bkg_sideband_fit_func, ("R,%s,+,0" % (self.fit_options)))
 
         # Prepare a function to store the signal parameters which will finally be extracted
@@ -413,7 +413,7 @@ def fit(self):
         self.sig_fit_func.SetParameter(1, self.mean)
         self.sig_fit_func.SetParameter(2, self.sigma)
 
-        self.logger.info("fit all (signal + background)")
+        self.logger.info("Fit all (signal + background)")
         self.tot_fit_func.SetLineColor(4)
         parmin = Double()
         parmax = Double()

machine_learning_hep/multiprocesser.py

@@ -204,7 +204,7 @@ def multi_histomass(self):
         for indexp, _ in enumerate(self.process_listsample):
             if self.p_useperiod[indexp] == 1:
                 self.process_listsample[indexp].process_histomass()
-        self.logger.debug('merging all')
+        self.logger.debug('Merging all')
         with tempfile.TemporaryDirectory() as tmp_merged_dir:
             mergerootfiles(self.lper_filemass, self.filemass_mergedall, tmp_merged_dir)
 

machine_learning_hep/optimiser.py

@@ -215,7 +215,7 @@ def __init__(self, data_param, case, typean, model_config, binmin,
         self.f_mltest_applied = f"{self.dirmlout}/testsample_{self.s_suffix}_mldecision.pkl"
         self.df_mltest_applied = None
 
-        self.logger.info('training variables: %s', training_var)
+        self.logger.info('Training variables: %s', training_var)
 
     def create_suffix(self):
         string_selection = createstringselection(self.v_bin, self.p_binmin, self.p_binmax)
@@ -249,7 +249,7 @@ def prepare_data_mc_mcgen(self):
 
 
     def preparesample(self): # pylint: disable=too-many-branches
-        self.logger.info("Prepare Sample")
+        self.logger.info("Prepare sample")
 
         filename_train = \
                 os.path.join(self.dirmlout, f"df_train_{self.p_binmin}_{self.p_binmax}.pkl")

machine_learning_hep/processer.py

@@ -328,7 +328,7 @@ def dfmerge(dfl, dfr, **kwargs):
             try:
                 return pd.merge(dfl, dfr, **kwargs)
             except Exception as e:
-                self.logger.error('merging failed: %s', str(e))
+                self.logger.error('Merging failed: %s', str(e))
                 dfl.info()
                 dfr.info()
                 raise e
@@ -339,20 +339,20 @@ def dfuse(df_spec):
                     (level in ('mc', 'gen', 'det') and self.mcordata == 'mc') or
                     (level in ('data') and self.mcordata == 'data'))
 
-        self.logger.info('unpacking: %s', self.l_root[file_index])
+        self.logger.info('Unpacking: %s', self.l_root[file_index])
         dfs = {}
         self.logger.debug(' -> reading')
         with uproot.open(self.l_root[file_index]) as rfile:
             df_processed = set()
             keys = rfile.keys(recursive=False, filter_name='DF_*')
-            self.logger.info('found %d dataframes, reading %s', len(keys), max_no_keys or "all")
+            self.logger.info('Found %d dataframes, reading %s', len(keys), max_no_keys or "all")
             for (idx, key) in enumerate(keys[:max_no_keys]):
                 if not (df_key := re.match('^DF_(\\d+);', key)):
                     continue
                 if (df_no := int(df_key.group(1))) in df_processed:
-                    self.logger.warning('multiple versions of DF %d', df_no)
+                    self.logger.warning('Multiple versions of DF %d', df_no)
                     continue
-                self.logger.debug('processing DF %d - %d / %d', df_no, idx, len(keys))
+                self.logger.debug('Processing DF %d - %d / %d', df_no, idx, len(keys))
                 df_processed.add(df_no)
                 rdir = rfile[key]
 
@@ -410,19 +410,19 @@ def dfuse(df_spec):
                 out = m_spec.get('out', base)
                 if all([dfuse(self.df_read[base]), dfuse(self.df_read[ref])]):
                     if (on := m_spec.get('use', None)) is not None:
-                        self.logger.info('merging %s with %s on %s into %s', base, ref, on, out)
+                        self.logger.info('Merging %s with %s on %s into %s', base, ref, on, out)
                         if not isinstance(on, list) or 'df' not in on:
                             on = ['df', on]
                         dfs[out] = dfmerge(dfs[base], dfs[ref], on=on)
                     elif (on := m_spec.get('left_on', None)) is not None:
-                        self.logger.info('merging %s with %s on %s into %s', base, ref, on, out)
+                        self.logger.info('Merging %s with %s on %s into %s', base, ref, on, out)
                         if not is_numeric_dtype(dfs[base][on]):
-                            self.logger.info('exploding dataframe %s on variable %s', base, on)
+                            self.logger.info('Exploding dataframe %s on variable %s', base, on)
                             dfs[base] = dfs[base].explode(on)
                         dfs[out] = dfmerge(dfs[base], dfs[ref], left_on=['df', on], right_index=True)
                     else:
                         var = self.df_read[ref]['index']
-                        self.logger.info('merging %s with %s on %s (default) into %s', base, ref, var, out)
+                        self.logger.info('Merging %s with %s on %s (default) into %s', base, ref, var, out)
                         dfs[out] = dfmerge(dfs[base], dfs[ref], left_on=['df', var], right_index=True)
                     if 'extra' in m_spec:
                         self.logger.debug(' %s -> extra', out)
@@ -432,7 +432,7 @@ def dfuse(df_spec):
         if self.df_write:
             for df_name, df_spec in self.df_write.items():
                 if dfuse(df_spec):
-                    self.logger.info('writing %s to %s', df_name, df_spec['file'])
+                    self.logger.info('Writing %s to %s', df_name, df_spec['file'])
                     src = df_spec.get('source', df_name)
                     dfo = dfquery(dfs[src], df_spec.get('filter', None))
                     path = os.path.join(self.d_pkl, self.l_path[file_index], df_spec['file'])
@@ -530,7 +530,7 @@ def process_applymodel_par(self):
         self.parallelizer(self.applymodel, arguments, self.p_chunksizeskim)
 
     def process_mergeforml(self):
-        self.logger.info("doing merging for ml %s %s", self.mcordata, self.period)
+        self.logger.info("Doing merging for ml %s %s", self.mcordata, self.period)
         indices_for_evt = []
         for ipt in range(self.p_nptbins):
             nfiles = len(self.mptfiles_recosk[ipt])

machine_learning_hep/processer_jet.py

@@ -76,7 +76,7 @@ def __init__(self, case, datap, run_param, mcordata, p_maxfiles, # pylint: disab
                     elif binning := self.cfg(f'observables.{v}.bins_fix'):
                         self.binarrays_obs[level][v] = bin_array(*binning)
                     else:
-                        self.logger.error('no binning specified for %s, using defaults', v)
+                        self.logger.error('No binning specified for %s, using defaults', v)
                         self.binarrays_obs[level][v] = bin_array(10, 0., 1.)
 
                     if binning := self.cfg(f'observables.{v}.bins_ptjet'):
@@ -121,7 +121,7 @@ def _verify_variables(self, dfi):
 
 
     def _calculate_variables(self, df, verify=False): # pylint: disable=invalid-name
-        self.logger.info('calculating variables')
+        self.logger.info('Calculating variables')
         if len(df) == 0:
             return df
         df['dr'] = np.sqrt((df.fJetEta - df.fEta)**2 + ((df.fJetPhi - df.fPhi + math.pi) % math.tau - math.pi)**2)
@@ -150,7 +150,7 @@ def _calculate_variables(self, df, verify=False): # pylint: disable=invalid-name
             (lambda ar: np.log(ar.fPtSubLeading * np.sin(ar.fTheta))), axis=1)
         df['lntheta'] = df['fTheta'].apply(lambda x: -np.log(x))
         # df['lntheta'] = np.array(-np.log(df.fTheta))
-        self.logger.debug('done')
+        self.logger.debug('Done')
         if verify:
             self._verify_variables(df)
         return df
@@ -175,7 +175,7 @@ def process_histomass_single(self, index):
             dfcollcnt = read_df(self.l_collcnt[index])
             ser_collcnt = dfcollcnt[self.cfg('cnt_events_read', 'fReadSelectedCounts')]
             collcnt = functools.reduce(lambda x,y: float(x)+float(y), (ar[0] for ar in ser_collcnt))
-            self.logger.info('sampled %g collisions', collcnt)
+            self.logger.info('Sampled %g collisions', collcnt)
             histonorm.SetBinContent(2, collcnt)
             get_axis(histonorm, 0).SetBinLabel(1, 'N_{evt}')
             get_axis(histonorm, 0).SetBinLabel(2, 'N_{coll}')
@@ -225,10 +225,10 @@ def process_histomass_single(self, index):
             self._calculate_variables(df)
 
             for obs, spec in self.cfg('observables', {}).items():
-                self.logger.debug('preparing histograms for %s', obs)
+                self.logger.debug('Preparing histograms for %s', obs)
                 var = obs.split('-')
                 if not all(v in df for v in var):
-                    self.logger.error('dataframe does not contain %s', var)
+                    self.logger.error('Dataframe does not contain %s', var)
                     continue
                 h = create_hist(
                     f'h_mass-ptjet-pthf-{obs}',
@@ -347,12 +347,12 @@ def process_efficiency_single(self, index):
                 if '-' in var or self.cfg(f'observables.{var}.arraycols'):
                     continue
                 if self.cfg('closure.use_matched'):
-                    self.logger.info('using matched for truth')
+                    self.logger.info('Using matched for truth')
                     df_mcana, _ = self.split_df(dfmatch[cat], self.cfg('frac_mcana', .2))
                 else:
                     df_mcana, _ = self.split_df(dfgen[cat], self.cfg('frac_mcana', .2))
                 if f := self.cfg('closure.exclude_feeddown_gen'):
-                    self.logger.debug('excluding feeddown gen')
+                    self.logger.debug('Excluding feeddown gen')
                     dfquery(df_mcana, f, inplace=True)
                 fill_hist(h_mctruth[(cat, var)], df_mcana[['fJetPt_gen', 'fPt_gen', f'{var}_gen']])
 

machine_learning_hep/steer_analysis.py

@@ -187,7 +187,7 @@ def do_entire_analysis(data_config: dict, data_param: dict, data_param_overwrite
         exdirs.extend(checkdirs(dirresultsdatatot))
 
     if len(exdirs) > 0:
-        logger.info('existing directories must be deleted')
+        logger.info('Existing directories must be deleted')
         for d in exdirs:
             print(f'rm -rf {d}')
         delete = False

machine_learning_hep/utilities.py

@@ -81,16 +81,16 @@ def openfile(filename, attr):
 
 
 def write_df(dfo, path):
-    logger.debug("writing df to <%s>", path)
+    logger.debug("Writing df to <%s>", path)
     if path.endswith(".parquet"):
         start = time.time()
         dfo.to_parquet(path)
-        logger.debug("written to parquet in %.2f s", time.time() - start)
+        logger.debug("Written to parquet in %.2f s", time.time() - start)
     else:
         start = time.time()
         with openfile(path, "wb") as file:
             pickle.dump(dfo, file, pickle.HIGHEST_PROTOCOL)
-        logger.debug("written to pickle in %.2f s", time.time() - start)
+        logger.debug("Written to pickle in %.2f s", time.time() - start)
 
 
 def read_df(path, **kwargs):
@@ -100,7 +100,7 @@ def read_df(path, **kwargs):
         else:
             df = pickle.load(openfile(path, "rb"))
     except Exception as e:  # pylint: disable=broad-except
-        logger.critical("failed to open file <%s>: %s", path, str(e))
+        logger.critical("Failed to open file <%s>: %s", path, str(e))
         sys.exit()
     return df
 

machine_learning_hep/utilities_files.py

@@ -29,7 +29,7 @@ def list_folders(main_dir: str, filenameinput: str, maxfiles: int, select=None):
     :param select: iterable of substrings that must be contained in folders
     """
     if not os.path.isdir(main_dir):
-        logger.error("input directory <%s> does not exist", main_dir)
+        logger.error("Input directory <%s> does not exist", main_dir)
 
     files = glob.glob(f"{main_dir}/**/{filenameinput}", recursive=True)
     listfolders = [os.path.relpath(os.path.dirname(file), main_dir) for file in files]
@@ -78,7 +78,7 @@ def checkmakedir(mydir: str):
     if os.path.exists(mydir):
         logger.warning("Using existing folder %s", mydir)
         return
-    logger.debug("creating folder %s", mydir)
+    logger.debug("Creating folder %s", mydir)
     os.makedirs(mydir)
 
 
@@ -101,7 +101,7 @@ def delete_dir(path: str):
     try:
         shutil.rmtree(path)
     except OSError:
-        logger.error("Error: Failed to delete directory %s", path)
+        logger.error("Failed to delete directory %s", path)
         return False
     return True