fix

Author: Luigi Dello Stritto

machine_learning_hep/analysis/analyzerdhadrons.py

@@ -338,7 +338,8 @@ def fit(self):
                             pdf_bkg = roo_ws.pdf(self.p_pdfnames["pdf_bkg"])
                             if pdf_bkg:
                                 self.fit_func_bkg[level][ipt] = pdf_bkg.asTF(roo_ws.var(var_m))
-                            self.fit_range[level][ipt] = (roo_ws.var(var_m).getMin('fit'), roo_ws.var(var_m).getMax('fit'))
+                            self.fit_range[level][ipt] = (roo_ws.var(var_m).getMin('fit'), \
+                                                          roo_ws.var(var_m).getMax('fit'))
                         else:
                             self.logger.error('RooFit failed for %s bin %d', level, ipt)
 
@@ -535,4 +536,4 @@ def makenormyields(self):  # pylint: disable=import-outside-toplevel, too-many-b
             fileoutcrosstot.cd()
             hcross.Write()
         histonorm.Write()
-        fileoutcrosstot.Close()
+        fileoutcrosstot.Close()

machine_learning_hep/analysis/analyzerdhadrons_mult.py

@@ -370,7 +370,8 @@ def fit(self):
                                 pdf_bkg = roo_ws.pdf(self.p_pdfnames["pdf_bkg"])
                                 if pdf_bkg:
                                     self.fit_func_bkg[level][ipt] = pdf_bkg.asTF(roo_ws.var(var_m))
-                                self.fit_range[level][ipt] = (roo_ws.var(var_m).getMin('fit'), roo_ws.var(var_m).getMax('fit'))
+                                self.fit_range[level][ipt] = (roo_ws.var(var_m).getMin('fit'), \
+                                                              roo_ws.var(var_m).getMax('fit'))
                             else:
                                 self.logger.error('RooFit failed for %s bin %d', level, ipt)
 
@@ -639,7 +640,7 @@ def makenormyields(self): # pylint: disable=import-outside-toplevel, too-many-br
             # pylint: disable=logging-not-lazy
             self.logger.warning("Number of events %d for mult bin %d" % (norm, imult))
 
-            if self.p_fprompt_from_mb: 
+            if self.p_fprompt_from_mb:
                 if imult == 0:
                     fileoutcrossmb = "%s/finalcross%s%smult0.root" % \
                                         (self.d_resultsallpdata, self.case, self.typean)
@@ -746,4 +747,4 @@ def plotternormyields(self):
         cCrossvsvar1.SaveAs("%s/CorrectedYieldsNorm%s%sVs%s.eps" % (self.d_resultsallpdata,
                                                                     self.case, self.typean,
                                                                     self.v_var_binning))
-        fileoutcrosstot.Close()
+        fileoutcrosstot.Close()

machine_learning_hep/fitting/roofitter.py

@@ -233,4 +233,4 @@ def add_text_info_perf(text_info, sig, sig_err, bkg, bkg_err, s_over_b, s_over_b
     text_info.AddText(f"S(3#sigma) = {sig:.0f} #pm {sig_err:.0f}")
     text_info.AddText(f"B(3#sigma) = {bkg:.0f} #pm {bkg_err:.0f}")
     text_info.AddText(f"S/B(3#sigma) = {s_over_b:.3f} #pm {s_over_b_err:.3f}")
-    text_info.AddText(f"Signif(3#sigma) = {signif:.1f} #pm {signif_err:.1f}")
+    text_info.AddText(f"Signif(3#sigma) = {signif:.1f} #pm {signif_err:.1f}")

machine_learning_hep/models.py

@@ -17,6 +17,7 @@
             load and save ML models
             obtain control plots
 """
+# pylint: disable=too-many-branches
 from os.path import exists
 import pickle
 import pandas as pd
@@ -155,7 +156,7 @@ def apply(ml_type, names_, trainedmodels_, test_set_, mylistvariables_, labels_=
                 test_set_[f"y_test_prediction{name}"]=0
                 test_set_[f"y_test_prob{name}"]=0
             return test_set_
-        elif ml_type == "MultiClassification":
+        else:
             for name in names_:
                 for pred, lab in enumerate(labels_):
                     safe_lab = lab.replace('-', '_')

machine_learning_hep/processer.py

@@ -425,7 +425,8 @@ def dfuse(df_spec):
                         dfs[out] = dfmerge(dfs[base], dfs[ref], left_on=['df', on], right_index=True)
                         dfs[out].index.name = 'MergedIndex'
                         dfs[out] = dfs[out].reset_index()
-                        dfs[out] = dfs[out].sort_values('fMultZeqNTracksPV', ascending=False).drop_duplicates('MergedIndex')
+                        sorted_df = dfs[out].sort_values('fMultZeqNTracksPV', ascending=False)
+                        dfs[out] = sorted_df.drop_duplicates('MergedIndex')
                         dfs[out] = dfs[out].sort_values('MergedIndex', ascending=True)
                     else:
                         var = self.df_read[ref]['index']

machine_learning_hep/processerdhadrons.py

@@ -233,4 +233,4 @@ def process_efficiency_single(self, index):
         h_sel_pr.Write()
         h_gen_fd.Write()
         h_presel_fd.Write()
-        h_sel_fd.Write()
+        h_sel_fd.Write()

machine_learning_hep/processerdhadrons_mult.py

@@ -385,4 +385,4 @@ def process_efficiency(self):
         arguments = [(i,) for i in range(len(self.l_root))]
         self.parallelizer(self.process_efficiency_single, arguments, self.p_chunksizeunp)
         tmp_merged = f"/data/tmp/hadd/{self.case}_{self.typean}/histoeff_{self.period}/{get_timestamp_string()}/"
-        mergerootfiles(self.l_histoeff, self.n_fileeff, tmp_merged)
+        mergerootfiles(self.l_histoeff, self.n_fileeff, tmp_merged)