diff --git a/machine_learning_hep/data/data_run3/database_ml_parameters_D0Jet_pp.yml b/machine_learning_hep/data/data_run3/database_ml_parameters_D0Jet_pp.yml index fc7acb2f03..e95455c809 100644 --- a/machine_learning_hep/data/data_run3/database_ml_parameters_D0Jet_pp.yml +++ b/machine_learning_hep/data/data_run3/database_ml_parameters_D0Jet_pp.yml @@ -27,26 +27,17 @@ D0Jet_pp: var_binning: fPt dofullevtmerge: false - # obsolete, to be removed - # var_cand: fCandidateSelFlag - # # var_swap: fIsCandidateSwapped bitmap_sel: var_name: fFlagMcMatchRec - var_name_gen: fFlagMcMatchGen - var_name_origgen: fOriginMcGen - var_name_origrec: fOriginMcRec - var_isstd: isstd + # var_name_gen: fFlagMcMatchGen # unused + # var_name_origgen: fOriginMcGen # unused + # var_name_origrec: fOriginMcRec # unused var_ismcsignal: ismcsignal - var_ismcprompt: ismcprompt - var_ismcfd: ismcfd var_ismcbkg: ismcbkg - var_ismcrefl: ismcrefl - isstd: [[1], []] ismcsignal: [[0], []] ismcprompt: [[0], [1]] ismcfd: [[1], [0]] ismcbkg: [[], [1]] - ismcrefl: [[1], [1]] # probably missing from tree creator #region dfs dfs: @@ -360,13 +351,7 @@ D0Jet_pp: #region analysis analysis: - anahptspectrum: "D0Kpi" #D0Kpi, DplusKpipi, DstarD0pi, DsKKpi, LctopKpi, LcK0Sp # used in analysis/analyzerdhadrons_mult.py - fd_method: "Nb" #fc, Nb - cctype: "pp" - inputfonllpred: data/fonll/D0DplusDstarPredictions_13TeV_y05_all_300416_BDShapeCorrected.root # used in machine_learning_hep/hf_pt_spectrum.py - dir_general_plots: /data2/jklein/data/analysis_plots - - jet_obs: &jet_default + jet_obs: sel_an_binmin: [1, 2, 3, 4, 5, 6, 7, 8, 10, 12, 16, 24] # hadron pt bins (sel_an_binmin bins) sel_an_binmax: [2, 3, 4, 5, 6, 7, 8, 10, 12, 16, 24, 48] # hadron pt bins (sel_an_binmin bins) # FIXME: move the last edge in sel_an_binmin bins_ptjet: [5, 7, 15, 30, 50, 70] # systematics, TODO: split rec and gen binning @@ -375,9 +360,9 @@ D0Jet_pp: counter_read_data: fReadCountsWithTVXAndZVertexAndSel8 counter_read_mc: fReadCountsWithTVXAndZVertexAndSelMC counter_tvx: fReadCountsWithTVX - xsection_inel: 59.4 # (mb) cross-section of minimum-bias events # used # systematics + xsection_inel: 59.4 # (mb) cross-section of minimum-bias events # systematics lumi_scale_mc: 408 # charm enhancement factor in MC to scale the MC luminosity - branching_ratio: 3.947e-2 # used + branching_ratio: 3.947e-2 observables: zg: @@ -710,8 +695,8 @@ D0Jet_pp: index_match: fIndexArrayD0CMCPJETOS_hf correction_method: run3 - unfolding_iterations: 8 # used, maximum iteration - unfolding_iterations_sel: 5 # used, selected iteration # systematics + unfolding_iterations: 8 # maximum iteration + unfolding_iterations_sel: 5 # selected iteration # systematics unfolding_prior_flatness: 0. # ranges from 0. (no flatness) to 1. (flat) closure: @@ -725,48 +710,17 @@ D0Jet_pp: fd_root: "/data2/vkucera/powheg/trees_powheg_fd_central.root" # systematics fd_parquet: "/data2/jklein/powheg/trees_powheg_fd_central.parquet" # systematics - # obsolete? - proc_type: Jets # used - useperiod: [1] #list of periods # used - # usejetptbinned_deff: false - # doeff_resp: true #efficiency correction for the response matrix - # unmatched_gen: true + proc_type: Jets + useperiod: [1] #list of periods latexnamehadron: "D^{0}" - # latexnamedecay: "K^{#minus} #pi^{#plus}" - var_binning2: pt_jet - # var_binning2_gen: pt_gen_jet - latexbin2var: "#it{p}_{T}^{jet ch}" - # sel_binmin2_reco: [5, 7, 15, 30] # rec jet pt bins (sel_binmin2_reco bins) - # sel_binmax2_reco: [7, 15, 30, 50] # rec jet pt bins (sel_binmin2_reco bins) - # sel_binmin2_gen: [5, 7, 15, 30] # rec jet pt bins (sel_binmin2_reco bins) - # sel_binmax2_gen: [7, 15, 30, 50] # rec jet pt bins (sel_binmin2_reco bins) - # var_binningshape: zg_jet - # var_binningshape_gen: zg_gen_jet - # var_shape_latex: "shape" - # sel_binminshape_reco: [-0.1,0.1,0.2,0.3,0.4] - # sel_binmaxshape_reco: [0.1,0.2,0.3,0.4,0.5] - # sel_binminshape_gen: [-0.1,0.1,0.2,0.3,0.4] - # sel_binmaxshape_gen: [0.1,0.2,0.3,0.4,0.5] - # sel_closure_frac: 0.2 - # triggerbit: INT7 - #jetsel_gen: "abs(y_cand) < 0.8 and abs(z_vtx_gen) < 10 and abs(eta_jet) < 0.5" - #jetsel_sim: "abs(y_cand) < 0.8 and abs(eta_jet) < 0.5" # jet selection in simulations - #jetsel_reco: "abs(y_cand) < 0.8 and abs(z_vtx_reco) < 10 and abs(eta_jet) < 0.5" - #jetsel_gen_matched_reco: "abs(eta_gen_jet) < 5.0" - # jetsel_gen: "abs(y_cand) < 0.5 and abs(z_vtx_gen) < 10 and abs(eta_jet) < 0.5" - # jetsel_sim: "abs(y_cand) < 0.5 and abs(eta_jet) < 0.5" # jet selection in simulations - # jetsel_reco: "abs(y_cand) < 0.5 and abs(z_vtx_reco) < 10 and abs(eta_jet) < 0.5" - # jetsel_gen_matched_reco: "abs(y_cand) < 0.5 and abs(z_vtx_gen) < 10 and abs(eta_gen_jet) < 0.5" evtsel: null # fIsEventReject==0 triggersel: data: "trigger_hasbit_INT7==1" mc: null data: &data_out_default - runselection: [null] #FIXME # used but useless results: ["/home/${USER}/mlhep/d0jet/jet_obs/default/default/data/results"] #list of periods resultsallp: "/home/${USER}/mlhep/d0jet/jet_obs/default/default/data/results_all" mc: &mc_out_default - runselection: [null] #FIXME # used but useless results: ["/home/${USER}/mlhep/d0jet/jet_obs/default/default/mc/results"] #list of periods resultsallp: "/home/${USER}/mlhep/d0jet/jet_obs/default/default/mc/results_all" data_proc: # alternative processor output used as the analyzer input @@ -774,74 +728,8 @@ D0Jet_pp: mc_proc: # alternative processor output used as the analyzer input <<: *mc_out_default - # simple fitter START # used in cplusutilities/mass_fitter.C - # sgnfunc: [0,0,0,0,0,0,0,0,0,0,0,0] # kGaus=0, k2Gaus=1, k2GausSigmaRatioPar=2 (sel_an_binmin bins) - # bkgfunc: [0,0,0,0,0,0,0,0,0,0,0,0] # kExpo=0, kLin=1, kPol2=2, kNoBk=3, kPow=4, kPowEx=5 (sel_an_binmin bins) - # masspeak: 1.864 - # massmin: [1.66,1.66,1.66,1.66,1.66,1.66,1.66,1.66,1.66,1.66,1.66,1.66] # sel_an_binmin bins, fit region of the invariant mass distribution [GeV/c^2] - # massmax: [2.06,2.06,2.06,2.06,2.06,2.06,2.06,2.06,2.06,2.06,2.06,2.06] # sel_an_binmin bins, fit region of the invariant mass distribution [GeV/c^2] - # rebin: [6,6,6,6,6,6,6,6,6,6,6,6] # sel_an_binmin bins - # fix_mean: [false, false, false, false, false, false, false, false, false, false, false, false] # sel_an_binmin bins - # masspeaksec: 1.864 - - # obsolete (uses Ali... fitter) - # If SetArraySigma true: sigma_initial is taken from sigmaarray; false: sigma_initial is taken from MC - # If SetFixGaussianSigma true: sigma fixed to sigma_initial - # SetFixGaussianSigma: [false, false, false, false, false, false, false, false, false, false, false, false] # sel_an_binmin bins - # SetFixGaussianSigma: [true, true, true, true, true, true, true, true, true, true, true, true] # sel_an_binmin bins - # SetArraySigma: [false, false, false, false, false, false, false, false, false, false, false, false] # sel_an_binmin bins - # sigmaarray: [0.01,0.01,0.01,0.01,0.01,0.01,0.01,0.01,0.01,0.01,0.01,0.01] # initial sigma (sel_an_binmin bins) - - # fix_sigmasec: [true, true, true, true, true, true, true, true, true, true, true, true] # sel_an_binmin bins - # sigmaarraysec: [0.007497,0.01,0.01,0.01,0.01,0.01,0.01,0.01,0.01,0.01,0.01,0.01] # sel_an_binmin bins - # use_reflections: true - # simple fitter END - - # signal_sigma: 2.0 - # sigma_scale: 0.9545 - # sideband_sigma_1_left: 4 - # sideband_sigma_2_left: 9 - # sideband_sigma_1_right: 4 - # sideband_sigma_2_right: 9 - # sidebandleftonly: false - - # niterunfolding: 15 - # niterunfoldingchosen: 4 - - # doprior: false - # domodeldep: false - # path_modeldep: /home/nzardosh/PYTHIA_Sim/PYTHIA8_Simulations/Plots/D0_Substructure_Simulations_Output.root - - # replace with fd_root... - # powheg_path_nonprompt: /data/POWHEG/trees_powheg_fd_central.root - # powheg_path_prompt: /data/POWHEG/trees_powheg_pr_central.root - # powheg_prompt_variations_path: /data/POWHEG/trees_powheg_pr_ - # powheg_prompt_variations: ["F1_R05","F05_R1","F2_R1","F1_R2","F2_R2","F05_R05","Mhigh","Mlow"] - - # pythia8_prompt_variations_path: /data/PYTHIA8/trees_pythia8_pr_ - # pythia8_prompt_variations: ["default", "charm_lo"] #["default","colour0soft"] - # pythia8_prompt_variations_legend: ["PYTHIA 8 (Monash)", "PYTHIA 8 charm LO"] # ["PYTHIA 8 (Monash)","PYTHIA 8 SoftQCD, mode 0"] - variations_db: database_variations_D0Jet_pp_jet_obs.yml # Additional cuts applied before mass histogram is filled use_cuts: True # systematics cuts: ["mlBkgScore < 0.02", "mlBkgScore < 0.02", "mlBkgScore < 0.02", "mlBkgScore < 0.05", "mlBkgScore < 0.06", "mlBkgScore < 0.08", "mlBkgScore < 0.08", "mlBkgScore < 0.10", "mlBkgScore < 0.10", "mlBkgScore < 0.20", "mlBkgScore < 0.25", "mlBkgScore < 0.30"] # (sel_an_binmin bins) systematics FIXME: Update for new model. - - systematics: # used in machine_learning_hep/analysis/systematics.py - probvariation: - useperiod: [0, 0, 1] #period from where to define prob cuts - ncutvar: 10 #number of looser and tighter variations - maxperccutvar: 0.25 #max diff in efficiency for loosest/tightest var - cutvarminrange: [0.80, 0.80, 0.6, 0.3, 0.3] #Min starting point for scan - cutvarmaxrange: [0.98, 0.95, 0.95, 0.95, 0.95] #Max starting point for scan - fixedmean: True #Fix mean cutvar histo to central fit - fixedsigma: True #Fix sigma cutvar histo to central fit - mcptshape: - #FONLL / generated LHC19h4c1 - weights: [1.000000] - #From SetPtWeightsFromFONLL13overLHC17c3a12 in AliPhysics - #weights: [1.429770] - weights_min_pt: 0 - weights_max_pt: 40 - weights_bins: 400 diff --git a/machine_learning_hep/data/data_run3/database_ml_parameters_LcJet_pp.yml b/machine_learning_hep/data/data_run3/database_ml_parameters_LcJet_pp.yml index 814c890aca..70ecf03702 100644 --- a/machine_learning_hep/data/data_run3/database_ml_parameters_LcJet_pp.yml +++ b/machine_learning_hep/data/data_run3/database_ml_parameters_LcJet_pp.yml @@ -25,25 +25,18 @@ LcJet_pp: sel_skim_binmax: [2, 3, 4, 5, 6, 7, 8, 10, 12, 24] # skimming pt bins (sel_skim_binmin bins) var_binning: fPt dofullevtmerge: false - var_cand: fCandidateSelFlag - # var_swap: fIsCandidateSwapped + bitmap_sel: var_name: fFlagMcMatchRec - var_name_gen: fFlagMcMatchGen - var_name_origgen: fOriginMcGen - var_name_origrec: fOriginMcRec - var_isstd: isstd + # var_name_gen: fFlagMcMatchGen # unused + # var_name_origgen: fOriginMcGen # unused + # var_name_origrec: fOriginMcRec # unused var_ismcsignal: ismcsignal - var_ismcprompt: ismcprompt - var_ismcfd: ismcfd var_ismcbkg: ismcbkg - var_ismcrefl: ismcrefl - isstd: [[1], []] ismcsignal: [[1], []] ismcprompt: [[0], []] ismcfd: [[1], []] ismcbkg: [[], [1]] - ismcrefl: [[1], [1]] # probably missing from tree creator #region dfs dfs: @@ -337,14 +330,7 @@ LcJet_pp: #region analysis analysis: - anahptspectrum: "LctopKpi" #D0Kpi, DplusKpipi, DstarD0pi, DsKKpi, LctopKpi, LcK0Sp - fd_method: "Nb" #fc, Nb - cctype: "pp" - sigmamb: 57.8e-3 #NB: multiplied by 1e12 before giving to HFPtSpectrum! - inputfonllpred: data/fonll/DmesonLcPredictions_13TeV_y05_FFptDepLHCb_BRpythia8_PDG2020.root - dir_general_plots: "/data2/${USER}/data/analysis_plots" - - jet_obs: &jet_default + jet_obs: sel_an_binmin: [2, 3, 4, 5, 6, 7, 8, 10, 12, 16] # hadron pt bins (sel_an_binmin bins) sel_an_binmax: [3, 4, 5, 6, 7, 8, 10, 12, 16, 24] # hadron pt bins (sel_an_binmin bins) bins_ptjet: [2, 5, 7, 10, 15, 30] # systematics, TODO: split rec and gen binning @@ -353,9 +339,9 @@ LcJet_pp: counter_read_data: fReadCountsWithTVXAndZVertexAndSel8 counter_read_mc: fReadCountsWithTVXAndZVertexAndSelMC counter_tvx: fReadCountsWithTVX - xsection_inel: 59.4 # (mb) cross-section of minimum-bias events # used # systematics + xsection_inel: 59.4 # (mb) cross-section of minimum-bias events # systematics lumi_scale_mc: 408 # charm enhancement factor in MC to scale the MC luminosity - branching_ratio: 6.24e-2 # used + branching_ratio: 6.24e-2 observables: zg: @@ -474,8 +460,8 @@ LcJet_pp: extra_cols: ["mlBkgScore"] correction_method: run3 - unfolding_iterations: 8 # used, maximum iteration - unfolding_iterations_sel: 5 # used, selected iteration # systematics + unfolding_iterations: 8 # maximum iteration + unfolding_iterations_sel: 5 # selected iteration # systematics unfolding_prior_flatness: 0. # ranges from 0. (no flatness) to 1. (flat) fd_folding_method: 3d @@ -484,45 +470,15 @@ LcJet_pp: proc_type: Jets useperiod: [1] #list of periods - usejetptbinned_deff: false - doeff_resp: true #efficiency correction for the response matrix - unmatched_gen: true latexnamehadron: "#Lambda_{c}^{#plus}" - latexnamedecay: "pK#pi" - var_binning2: pt_jet - var_binning2_gen: pt_gen_jet - latexbin2var: "#it{p}_{T}^{jet ch}" - sel_binmin2_reco: [7.0, 15.0, 30.0] # rec jet pt bins (sel_binmin2_reco bins) - sel_binmax2_reco: [15.0, 30.0, 50.0] # rec jet pt bins (sel_binmin2_reco bins) - sel_binmin2_gen: [7.0, 15.0, 30.0] # gen jet pt bins (sel_binmin2_gen bins) - sel_binmax2_gen: [15.0, 30.0, 50.0] # gen jet pt bins (sel_binmin2_gen bins) - var_binningshape: zg_jet - var_binningshape_gen: zg_gen_jet - var_shape_latex: "#it{z}_{g}" - sel_binminshape_reco: [-0.1, 0.1, 0.2, 0.3, 0.4] - sel_binmaxshape_reco: [0.1, 0.2, 0.3, 0.4, 0.5] - sel_binminshape_gen: [-0.1, 0.1, 0.2, 0.3, 0.4] - sel_binmaxshape_gen: [0.1, 0.2, 0.3, 0.4, 0.5] - sel_closure_frac: 0.2 - triggerbit: INT7 - #jetsel_gen: "abs(y_cand) < 0.8 and abs(z_vtx_gen) < 10 and abs(eta_jet) < 0.5" - #jetsel_sim: "abs(y_cand) < 0.8 and abs(eta_jet) < 0.5" # jet selection in simulations - #jetsel_reco: "abs(y_cand) < 0.8 and abs(z_vtx_reco) < 10 and abs(eta_jet) < 0.5" - #jetsel_gen_matched_reco: "abs(eta_gen_jet) < 5.0" - jetsel_gen: "abs(y_cand) < 0.5 and abs(z_vtx_gen) < 10 and abs(eta_jet) < 0.5" - jetsel_sim: "abs(y_cand) < 0.5 and abs(eta_jet) < 0.5" # jet selection in simulations - jetsel_reco: "abs(y_cand) < 0.5 and abs(z_vtx_reco) < 10 and abs(eta_jet) < 0.5" - jetsel_gen_matched_reco: "abs(y_cand) < 0.5 and abs(z_vtx_gen) < 10 and abs(eta_gen_jet) < 0.5" evtsel: fIsEventReject==0 triggersel: data: "trigger_hasbit_INT7==1" mc: null data: &data_out_default - runselection: [null] #FIXME results: ["/home/${USER}/mlhep/lcjet/jet_obs/default/default/data/results"] #list of periods resultsallp: "/home/${USER}/mlhep/lcjet/jet_obs/default/default/data/results_all" mc: &mc_out_default - runselection: [null, null] #FIXME results: ["/home/${USER}/mlhep/lcjet/jet_obs/default/default/mc/results"] #list of periods resultsallp: "/home/${USER}/mlhep/lcjet/jet_obs/default/default/mc/results_all" data_proc: # alternative processor output used as the analyzer input @@ -530,73 +486,8 @@ LcJet_pp: mc_proc: # alternative processor output used as the analyzer input <<: *mc_out_default - # simple fitter START - sgnfunc: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0] # kGaus=0, k2Gaus=1, k2GausSigmaRatioPar=2 (sel_an_binmin bins) - bkgfunc: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0] # kExpo=0, kLin=1, kPol2=2, kNoBk=3, kPow=4, kPowEx=5 (sel_an_binmin bins) - masspeak: 2.286 - massmin: [1.66, 1.66, 1.66, 1.66, 1.66, 1.66, 1.66, 1.66, 1.66, 1.66, 1.66, 1.66] # sel_an_binmin bins, fit region of the invariant mass distribution [GeV/c^2] - massmax: [2.06, 2.06, 2.06, 2.06, 2.06, 2.06, 2.06, 2.06, 2.06, 2.06, 2.06, 2.06] # sel_an_binmin bins, fit region of the invariant mass distribution [GeV/c^2] - rebin: [6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6] # sel_an_binmin bins - fix_mean: [false, false, false, false, false, false, false, false, false, false, false, false] # sel_an_binmin bins - masspeaksec: 2.286 - - # If SetArraySigma true: sigma_initial is taken from sigmaarray; false: sigma_initial is taken from MC - # If SetFixGaussianSigma true: sigma fixed to sigma_initial - # SetFixGaussianSigma: [false, false, false, false, false, false, false, false, false, false, false, false] # sel_an_binmin bins - SetFixGaussianSigma: [true, true, true, true, true, true, true, true, true, true, true] # sel_an_binmin bins - SetArraySigma: [false, false, false, false, false, false, false, false, false, false, false, false] # sel_an_binmin bins - sigmaarray: [0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01] # initial sigma (sel_an_binmin bins) - - fix_sigmasec: [true, true, true, true, true, true, true, true, true, true] # sel_an_binmin bins - sigmaarraysec: [0.007497, 0.007497, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01, 0.01] # sel_an_binmin bins - use_reflections: true - # simple fitter END - - signal_sigma: 2.0 - sigma_scale: 0.9545 - sideband_sigma_1_left: 4 - sideband_sigma_2_left: 9 - sideband_sigma_1_right: 4 - sideband_sigma_2_right: 9 - sidebandleftonly: false - - niterunfolding: 15 - niterunfoldingchosen: 4 - - doprior: false - domodeldep: false - path_modeldep: /home/nzardosh/PYTHIA_Sim/PYTHIA8_Simulations/Plots/D0_Substructure_Simulations_Output.root - - powheg_path_nonprompt: /data/POWHEG/trees_powheg_fd_central.root - - powheg_path_prompt: /data/POWHEG/trees_powheg_pr_central.root - powheg_prompt_variations_path: /data/POWHEG/trees_powheg_pr_ - powheg_prompt_variations: ["F1_R05", "F05_R1", "F2_R1", "F1_R2", "F2_R2", "F05_R05", "Mhigh", "Mlow"] - - pythia8_prompt_variations_path: /data/PYTHIA8/trees_pythia8_pr_ - pythia8_prompt_variations: ["default", "charm_lo"] #["default","colour0soft"] - pythia8_prompt_variations_legend: ["PYTHIA 8 (Monash)", "PYTHIA 8 charm LO"] # ["PYTHIA 8 (Monash)","PYTHIA 8 SoftQCD, mode 0"] - variations_db: database_variations_LcJet_pp_jet_obs.yml # Additional cuts applied before mass histogram is filled use_cuts: True cuts: ["mlBkgScore < 0.03", "mlBkgScore < 0.04", "mlBkgScore < 0.07", "mlBkgScore < 0.09", "mlBkgScore < 0.11", "mlBkgScore < 0.15", "mlBkgScore < 0.18", "mlBkgScore < 0.25", "mlBkgScore < 0.35", "mlBkgScore < 0.35"] # (sel_an_binmin bins) systematics FIXME: Update for new model. - - systematics: # used in machine_learning_hep/analysis/systematics.py - probvariation: - useperiod: [0, 0, 1] #period from where to define prob cuts - ncutvar: 10 #number of looser and tighter variations - maxperccutvar: 0.25 #max diff in efficiency for loosest/tightest var - cutvarminrange: [0.80, 0.80, 0.6, 0.3, 0.3] #Min starting point for scan - cutvarmaxrange: [0.98, 0.95, 0.95, 0.95, 0.95] #Max starting point for scan - fixedmean: True #Fix mean cutvar histo to central fit - fixedsigma: True #Fix sigma cutvar histo to central fit - mcptshape: - #FONLL / generated LHC19h4c1 - weights: [1.000000] - #From SetPtWeightsFromFONLL13overLHC17c3a12 in AliPhysics - #weights: [1.429770] - weights_min_pt: 0 - weights_max_pt: 40 - weights_bins: 400 diff --git a/machine_learning_hep/multiprocesser.py b/machine_learning_hep/multiprocesser.py index cfe999c2d5..c73a6b49ec 100755 --- a/machine_learning_hep/multiprocesser.py +++ b/machine_learning_hep/multiprocesser.py @@ -110,8 +110,6 @@ def __init__(self, case, proc_class, datap, typean, run_param, mcordata): self.f_evt_mergedallp = os.path.join(self.d_pklevt_mergedallp, self.n_evt) self.f_evtorig_mergedallp = os.path.join(self.d_pklevt_mergedallp, self.n_evtorig) - self.lper_runlistrigger = datap["analysis"][self.typean][self.mcordata]["runselection"] - self.lper_mcreweights = None if self.mcordata == "mc": self.lper_mcreweights = [os.path.join(direc, self.n_mcreweights) for direc in self.dlper_mcreweights] @@ -140,7 +138,6 @@ def __init__(self, case, proc_class, datap, typean, run_param, mcordata): self.dlper_reco_modappmerged[indexp], self.d_results[indexp], self.typean, - self.lper_runlistrigger[indexp], self.dlper_mcreweights[indexp], ) self.process_listsample.append(myprocess) diff --git a/machine_learning_hep/optimiser.py b/machine_learning_hep/optimiser.py index 062621bb50..f3fe0bdff7 100644 --- a/machine_learning_hep/optimiser.py +++ b/machine_learning_hep/optimiser.py @@ -34,7 +34,6 @@ from sklearn.preprocessing import label_binarize from sklearn.utils import shuffle -# from machine_learning_hep.root import write_tree import machine_learning_hep.mlperformance as mlhep_plot import machine_learning_hep.optimization as optz from machine_learning_hep.correlations import ( @@ -124,19 +123,12 @@ def __init__(self, data_param, case, typean, model_config, binmin, binmax, multb self.v_all = data_param["variables"]["var_all"] self.v_train = training_var self.v_selected = data_param["variables"].get("var_selected", None) - # if self.v_selected: - # self.v_selected = self.v_selected[index] self.v_bound = data_param["variables"]["var_boundaries"] self.v_class = data_param["variables"]["var_class"] self.v_invmass = data_param["variables"]["var_inv_mass"] self.v_cuts = data_param["variables"].get("var_cuts", []) self.v_corrx = data_param["variables"]["var_correlation"][0] self.v_corry = data_param["variables"]["var_correlation"][1] - self.v_isstd = data_param["bitmap_sel"]["var_isstd"] - self.v_ismcsignal = data_param["bitmap_sel"]["var_ismcsignal"] - self.v_ismcprompt = data_param["bitmap_sel"]["var_ismcprompt"] - self.v_ismcfd = data_param["bitmap_sel"]["var_ismcfd"] - self.v_ismcbkg = data_param["bitmap_sel"]["var_ismcbkg"] # parameters self.p_case = case self.p_typean = typean @@ -415,7 +407,6 @@ def loadmodels(self): self.logger.info("Read and use models from disk. Remove them if you don't want to use them") self.p_trainedmod = clfs self.p_class = clfs - return def do_train(self): if self.step_done("training"): @@ -446,8 +437,6 @@ def do_test(self): self.p_mltype, self.p_classname, self.p_trainedmod, self.df_mltest, self.v_train, self.p_class_labels ) write_df(self.df_mltest_applied, self.f_mltest_applied) - # df_ml_test_to_root = self.dirmlout+"/testsample_%s_mldecision.root" % (self.s_suffix) - # write_tree(df_ml_test_to_root, self.n_treetest, self.df_mltest_applied) def do_apply(self): self.prepare_data_mc_mcgen() @@ -845,11 +834,6 @@ def do_significance(self): transform=fig_signif.gca().transAxes, fontsize=30, ) - # signif_array_tot = [sig * sqrt(self.p_nevttot) for sig in signif_array] - # signif_err_array_tot = [sig_err * sqrt(self.p_nevttot) for sig_err in signif_err_array] - # plt.figure(fig_signif.number) - # plt.errorbar(x_axis, signif_array_tot, yerr=signif_err_array_tot, - # label=f'{name}_Tot', elinewidth=2.5, linewidth=5.0) plt.figure(fig_signif_pevt.number) plt.legend(loc="lower left", fontsize=25) plt.savefig(f"{self.dirmlplot}/Significance_PerEvent_{self.s_suffix}.png", bbox_inches="tight") diff --git a/machine_learning_hep/processer.py b/machine_learning_hep/processer.py index 7072ac3eef..acaa18a558 100644 --- a/machine_learning_hep/processer.py +++ b/machine_learning_hep/processer.py @@ -80,7 +80,6 @@ def __init__( d_pkl_decmerged, d_results, typean, - runlisttrigger, d_mcreweights, ): self.doml = datap["doml"] @@ -112,8 +111,6 @@ def __init__( self.p_rd_merge = p_rd_merge self.period = p_period - # self.i_period = i_period - # self.select_period = datap["multi"][mcordata]["select_period"] self.select_jobs = datap["multi"][mcordata].get("select_jobs", None) if self.select_jobs: self.select_jobs = [f"{job}/" for job in self.select_jobs[i_period]] @@ -129,15 +126,11 @@ def __init__( # parameter names self.p_maxprocess = p_maxprocess - # self.indexsample = None self.p_dofullevtmerge = datap["dofullevtmerge"] # namefile root self.n_root = datap["files_names"]["namefile_unmerged_tree"] # namefiles pkl - # def nget(d : dict, k : list, dd = None): - # return nget(d.get(k.pop(0), {}), k, dd) if len(k) > 1 else d.get(k.pop(0), dd) - # nget(datap, ['dfs', 'write', 'jetsubdet', 'file']) self.n_reco = datap["files_names"]["namefile_reco"] self.n_evt = datap["files_names"]["namefile_evt"] self.n_collcnt = datap["files_names"]["namefile_collcnt"] @@ -155,26 +148,13 @@ def __init__( self.s_reco_skim = datap["sel_reco_skim"] self.s_gen_skim = datap["sel_gen_skim"] - # bitmap - # self.b_mcrefl = datap["bitmap_sel"].get("ismcrefl", None) - # variables name self.v_train = datap["variables"]["var_training"] self.v_bitvar = datap["bitmap_sel"]["var_name"] # used in hadrons - # self.v_bitvar_gen = datap["bitmap_sel"]["var_name_gen"] - # self.v_bitvar_origgen = datap["bitmap_sel"]["var_name_origgen"] - # self.v_bitvar_origrec = datap["bitmap_sel"]["var_name_origrec"] - # self.v_candtype = datap["var_cand"] - # self.v_swap = datap.get("var_swap", None) - # self.v_isstd = datap["bitmap_sel"]["var_isstd"] - self.v_ismcsignal = datap["bitmap_sel"]["var_ismcsignal"] - # self.v_ismcprompt = datap["bitmap_sel"]["var_ismcprompt"] - # self.v_ismcfd = datap["bitmap_sel"]["var_ismcfd"] + self.v_ismcsignal = datap["bitmap_sel"]["var_ismcsignal"] # used in hadrons self.v_ismcbkg = datap["bitmap_sel"]["var_ismcbkg"] # used in hadrons - self.v_ismcrefl = datap["bitmap_sel"]["var_ismcrefl"] # used in hadrons self.v_var_binning = datap["var_binning"] self.v_invmass = datap["variables"].get("var_inv_mass", "inv_mass") - # self.v_rapy = datap["variables"].get("var_y", "y_cand") # list of files names if os.path.isdir(self.d_root): @@ -195,7 +175,6 @@ def __init__( self.l_bccnt = createlist(self.d_pkl, self.l_path, self.n_bccnt) self.l_histomass = createlist(self.d_results, self.l_path, self.n_filemass) self.l_histoeff = createlist(self.d_results, self.l_path, self.n_fileeff) - # self.l_historesp = createlist(self.d_results, self.l_path, self.n_fileresp) if self.mcordata == "mc": self.l_gen = createlist(self.d_pkl, self.l_path, self.n_gen) @@ -345,12 +324,6 @@ def __init__( else None ) - # self.triggerbit = datap["analysis"][self.typean]["triggerbit"] - self.runlistrigger = runlisttrigger - - # if os.path.exists(self.d_root) is False: - # self.logger.warning("ROOT tree folder is not there. Is it intentional?") - # Analysis cuts (loaded in self.process_histomass) self.analysis_cuts = None # Flag if they should be used @@ -372,7 +345,6 @@ def dfread(rdir, trees, cols, idx_name=None): if not isinstance(trees, list): trees = [trees] cols = [cols] - # if all(type(var) is str for var in vars): vars = [vars] df = None for tree, col in zip([rdir[name] for name in trees], cols): try: @@ -694,7 +666,6 @@ def apply_cut_for_ipt(df_full, ipt: int): def process_histomass(self): self.logger.debug("Doing masshisto %s %s", self.mcordata, self.period) - self.logger.debug("Using run selection for mass histo %s %s %s", self.runlistrigger, "for period", self.period) if self.doml is True: self.logger.debug("Doing ml analysis") elif self.do_custom_analysis_cuts: @@ -713,7 +684,6 @@ def process_histomass(self): def process_efficiency(self): print("Doing efficiencies", self.mcordata, self.period) - print("Using run selection for eff histo", self.runlistrigger, "for period", self.period) if self.doml is True: print("Doing ml analysis") elif self.do_custom_analysis_cuts: diff --git a/machine_learning_hep/processer_jet.py b/machine_learning_hep/processer_jet.py index 58ea87211b..06cb274d16 100644 --- a/machine_learning_hep/processer_jet.py +++ b/machine_learning_hep/processer_jet.py @@ -50,7 +50,6 @@ def __init__( d_pkl_decmerged, d_results, typean, - runlisttrigger, d_mcreweights, ): super().__init__( @@ -74,7 +73,6 @@ def __init__( d_pkl_decmerged, d_results, typean, - runlisttrigger, d_mcreweights, ) self.logger.info("initialized processer for HF jets") diff --git a/machine_learning_hep/processerdhadrons.py b/machine_learning_hep/processerdhadrons.py index a46e90ee37..5d7e8818b9 100755 --- a/machine_learning_hep/processerdhadrons.py +++ b/machine_learning_hep/processerdhadrons.py @@ -58,7 +58,6 @@ def __init__( d_pkl_decmerged, d_results, typean, - runlisttrigger, d_mcreweights, ): super().__init__( @@ -82,7 +81,6 @@ def __init__( d_pkl_decmerged, d_results, typean, - runlisttrigger, d_mcreweights, ) diff --git a/machine_learning_hep/processerdhadrons_mult.py b/machine_learning_hep/processerdhadrons_mult.py index c0d060a9c0..958bd2858e 100755 --- a/machine_learning_hep/processerdhadrons_mult.py +++ b/machine_learning_hep/processerdhadrons_mult.py @@ -67,7 +67,6 @@ def __init__( d_pkl_decmerged, d_results, typean, - runlisttrigger, d_mcreweights, ): super().__init__( @@ -91,7 +90,6 @@ def __init__( d_pkl_decmerged, d_results, typean, - runlisttrigger, d_mcreweights, ) diff --git a/machine_learning_hep/steer_analysis.py b/machine_learning_hep/steer_analysis.py index 6958a2461e..b062acbde2 100644 --- a/machine_learning_hep/steer_analysis.py +++ b/machine_learning_hep/steer_analysis.py @@ -276,9 +276,6 @@ def mlhepmod(name): elif proc_type == "Dhadrons_mult": proc_class = mlhepmod("processerdhadrons_mult").ProcesserDhadrons_mult ana_class = mlhepmod("analysis.analyzerdhadrons_mult").AnalyzerDhadrons_mult - elif proc_type == "Dhadrons_jet": - proc_class = mlhepmod("processerdhadrons_jet").ProcesserDhadrons_jet - ana_class = mlhepmod("analysis.analyzer_jet").AnalyzerJet elif proc_type == "Jets": proc_class = mlhepmod("processer_jet").ProcesserJets ana_class = mlhepmod("analysis.analyzer_jets").AnalyzerJets