notebook.community

Edit and run

${t\bar{t}H\left(b\bar{b}\right)}$ scikit-learn BDT for classification of ${t\bar{t}H}$ and ${t\bar{t}b\bar{b}}$ events

For each signal region, information from the output of the reconstruction BDT is combined with kinematic variables for input to classification BDTs, with ${t\bar{t}H \left(H\to b\bar{b}\right)}$ as signal and ${t\bar{t}}$ as background. There is one BDT trained for events with exactly 5 jets or at least 6 jets.





In [1]:



    


import datetime
import graphviz
import matplotlib.pyplot as plt
%matplotlib inline
import numpy as np
plt.rcParams["figure.figsize"] = (17, 10)
import pandas as pd
import seaborn as sns
sns.set(context = "paper", font = "monospace")
import sklearn.datasets
from sklearn.preprocessing import MinMaxScaler
import sklearn.tree
import sqlite3
import warnings
warnings.filterwarnings("ignore")
pd.set_option("display.max_rows", 500)
pd.set_option("display.max_columns", 500)

read





In [2]:



    


df = pd.read_csv("ttHbb_data.csv")

df.head()



    


















    
Out[2]:











  
    

      
      dRbb_avg_Sort4
      dRbb_MaxPt_Sort4
      dEtajj_MaxdEta
      Mbb_MindR_Sort4
      Mjj_MindR
      nHiggsbb30_Sort4
      HT_jets
      dRlepbb_MindR_Sort4
      Aplanarity_jets
      H1_all
      TTHReco_best_TTHReco
      TTHReco_best_Higgs_mass
      TTHReco_best_Higgsbleptop_mass
      TTHReco_best_bbHiggs_dR
      TTHReco_withH_best_Higgsttbar_dR
      TTHReco_best_Higgsleptop_dR
      TTHReco_best_b1Higgsbhadtop_dR
      LHD_Discriminant
      target
    

  
  
    

      0
      0.265696
      0.325133
      0.311509
      0.017415
      0.023733
      0.333333
      0.029321
      0.335150
      0.025005
      0.836903
      0.000000
      0.000000
      0.000000
      0.000000
      0.000000
      0.000000
      0.000000
      0.000000
      1
    

    

      1
      0.412821
      0.174657
      0.276681
      0.051575
      0.062728
      0.333333
      0.151450
      0.509171
      0.062811
      0.548197
      0.595407
      0.079543
      0.162228
      0.348091
      0.400588
      0.441174
      0.262685
      0.728361
      1
    

    

      2
      0.346333
      0.386509
      0.081872
      0.031549
      0.025527
      0.000000
      0.112252
      0.224414
      0.152014
      0.738440
      0.663737
      0.082487
      0.102262
      0.640163
      0.398795
      0.477156
      0.555918
      0.712721
      1
    

    

      3
      0.427364
      0.106369
      0.369438
      0.070832
      0.084710
      0.500000
      0.058080
      0.375719
      0.111577
      0.508818
      0.000000
      0.000000
      0.000000
      0.000000
      0.000000
      0.000000
      0.000000
      0.000000
      1
    

    

      4
      0.384440
      0.218341
      0.438701
      0.054052
      0.069121
      0.500000
      0.167710
      0.218126
      0.671929
      0.169410
      0.874208
      0.029553
      0.058182
      0.377938
      0.374169
      0.397906
      0.505010
      0.815084
      1

features and targets





In [3]:



    


features = list(df.columns[:-1])

X = df[features]
y = df["target"]



    











In [4]:



    


classifier = sklearn.tree.DecisionTreeClassifier(min_samples_split = 20, random_state = 99, max_depth = 5)
classifier.fit(X, y)



    


















    
Out[4]:








DecisionTreeClassifier(class_weight=None, criterion='gini', max_depth=5,
            max_features=None, max_leaf_nodes=None,
            min_impurity_split=1e-07, min_samples_leaf=1,
            min_samples_split=20, min_weight_fraction_leaf=0.0,
            presort=False, random_state=99, splitter='best')

















In [5]:



    


graph = graphviz.Source(
    sklearn.tree.export_graphviz(
        classifier,
        out_file           = None,
        feature_names      = list(df[features].columns.values),
        filled             = True,
        rounded            = True,
        special_characters = True
    )
)
graph



    


















    
Out[5]:













Tree


0

HT_jets ≤ 0.0938
gini = 0.4995
samples = 22795
value = [11743, 11052]


1

LHD_Discriminant ≤ 0.765
gini = 0.4239
samples = 8883
value = [6174, 2709]


0->1


True


30

dRbb_avg_Sort4 ≤ 0.5026
gini = 0.4801
samples = 13912
value = [5569, 8343]


0->30


False


2

dRbb_avg_Sort4 ≤ 0.4929
gini = 0.3984
samples = 7892
value = [5725, 2167]


1->2




17

dEtajj_MaxdEta ≤ 0.5966
gini = 0.4956
samples = 991
value = [449, 542]


1->17




3

HT_jets ≤ 0.0559
gini = 0.4405
samples = 5191
value = [3491, 1700]


2->3




10

dEtajj_MaxdEta ≤ 0.4184
gini = 0.286
samples = 2701
value = [2234, 467]


2->10




4

H1_all ≤ 0.6972
gini = 0.3434
samples = 2216
value = [1728, 488]


3->4




7

H1_all ≤ 0.3079
gini = 0.4828
samples = 2975
value = [1763, 1212]


3->7




5

gini = 0.3109
samples = 1797
value = [1451, 346]


4->5




6

gini = 0.4481
samples = 419
value = [277, 142]


4->6




8

gini = 0.4562
samples = 1540
value = [998, 542]


7->8




9

gini = 0.4978
samples = 1435
value = [765, 670]


7->9




11

dEtajj_MaxdEta ≤ 0.287
gini = 0.4604
samples = 128
value = [82, 46]


10->11




14

HT_jets ≤ 0.0612
gini = 0.2737
samples = 2573
value = [2152, 421]


10->14




12

gini = 0.0
samples = 3
value = [0, 3]


11->12




13

gini = 0.4513
samples = 125
value = [82, 43]


11->13




15

gini = 0.2183
samples = 1291
value = [1130, 161]


14->15




16

gini = 0.3234
samples = 1282
value = [1022, 260]


14->16




18

LHD_Discriminant ≤ 0.9071
gini = 0.484
samples = 838
value = [344, 494]


17->18




25

dRlepbb_MindR_Sort4 ≤ 0.6003
gini = 0.4306
samples = 153
value = [105, 48]


17->25




19

LHD_Discriminant ≤ 0.772
gini = 0.4955
samples = 694
value = [314, 380]


18->19




22

TTHReco_best_Higgsbleptop_mass ≤ 0.1115
gini = 0.3299
samples = 144
value = [30, 114]


18->22




20

gini = 0.0
samples = 17
value = [0, 17]


19->20




21

gini = 0.4974
samples = 677
value = [314, 363]


19->21




23

gini = 0.2778
samples = 132
value = [22, 110]


22->23




24

gini = 0.4444
samples = 12
value = [8, 4]


22->24




26

Mbb_MindR_Sort4 ≤ 0.0127
gini = 0.4123
samples = 148
value = [105, 43]


25->26




29

gini = 0.0
samples = 5
value = [0, 5]


25->29




27

gini = 0.0
samples = 5
value = [0, 5]


26->27




28

gini = 0.3902
samples = 143
value = [105, 38]


26->28




31

LHD_Discriminant ≤ 0.7618
gini = 0.4461
samples = 10136
value = [3404, 6732]


30->31




46

HT_jets ≤ 0.191
gini = 0.4892
samples = 3776
value = [2165, 1611]


30->46




32

HT_jets ≤ 0.1472
gini = 0.4722
samples = 7398
value = [2827, 4571]


31->32




39

dEtajj_MaxdEta ≤ 0.5161
gini = 0.3327
samples = 2738
value = [577, 2161]


31->39




33

Aplanarity_jets ≤ 0.2967
gini = 0.4988
samples = 3278
value = [1560, 1718]


32->33




36

HT_jets ≤ 0.284
gini = 0.4259
samples = 4120
value = [1267, 2853]


32->36




34

gini = 0.4998
samples = 2727
value = [1390, 1337]


33->34




35

gini = 0.4267
samples = 551
value = [170, 381]


33->35




37

gini = 0.4459
samples = 3231
value = [1084, 2147]


36->37




38

gini = 0.327
samples = 889
value = [183, 706]


36->38




40

HT_jets ≤ 0.1588
gini = 0.2888
samples = 1777
value = [311, 1466]


39->40




43

HT_jets ≤ 0.2091
gini = 0.4004
samples = 961
value = [266, 695]


39->43




41

gini = 0.3491
samples = 972
value = [219, 753]


40->41




42

gini = 0.2024
samples = 805
value = [92, 713]


40->42




44

gini = 0.4398
samples = 637
value = [208, 429]


43->44




45

gini = 0.2939
samples = 324
value = [58, 266]


43->45




47

LHD_Discriminant ≤ 0.7961
gini = 0.4612
samples = 2506
value = [1602, 904]


46->47




54

LHD_Discriminant ≤ 0.728
gini = 0.4936
samples = 1270
value = [563, 707]


46->54




48

dEtajj_MaxdEta ≤ 0.5976
gini = 0.4428
samples = 2270
value = [1519, 751]


47->48




51

Mbb_MindR_Sort4 ≤ 0.1091
gini = 0.456
samples = 236
value = [83, 153]


47->51




49

gini = 0.4889
samples = 778
value = [447, 331]


48->49




50

gini = 0.4045
samples = 1492
value = [1072, 420]


48->50




52

gini = 0.494
samples = 137
value = [61, 76]


51->52




53

gini = 0.3457
samples = 99
value = [22, 77]


51->53




55

dRbb_avg_Sort4 ≤ 0.6057
gini = 0.4994
samples = 1070
value = [516, 554]


54->55




58

Mbb_MindR_Sort4 ≤ 0.028
gini = 0.3596
samples = 200
value = [47, 153]


54->58




56

gini = 0.4895
samples = 739
value = [316, 423]


55->56




57

gini = 0.4783
samples = 331
value = [200, 131]


55->57




59

gini = 0.0
samples = 3
value = [3, 0]


58->59




60

gini = 0.3469
samples = 197
value = [44, 153]


58->60

accuracy





In [6]:



    


y_predictions = classifier.predict(X)
y_predictions



    


















    
Out[6]:








array([0, 1, 0, ..., 0, 0, 0])

















In [7]:



    


sklearn.metrics.accuracy_score(y, y_predictions)



    


















    
Out[7]:








0.68335161219565699

















In [8]:



    


_df = pd.DataFrame()
_df["variable"]   = X.columns.values
_df["importance"] = classifier.feature_importances_

_df.index = _df["variable"].values
del _df["variable"]

_df = _df.sort_values(by = "importance", ascending = False)
_df



    


















    
Out[8]:











  
    

      
      importance
    

  
  
    

      HT_jets
      0.580307
    

    

      dRbb_avg_Sort4
      0.190065
    

    

      LHD_Discriminant
      0.154543
    

    

      dEtajj_MaxdEta
      0.030467
    

    

      Aplanarity_jets
      0.017219
    

    

      H1_all
      0.015864
    

    

      Mbb_MindR_Sort4
      0.006724
    

    

      TTHReco_best_Higgsbleptop_mass
      0.002552
    

    

      dRlepbb_MindR_Sort4
      0.002259
    

    

      Mjj_MindR
      0.000000
    

    

      nHiggsbb30_Sort4
      0.000000
    

    

      dRbb_MaxPt_Sort4
      0.000000
    

    

      TTHReco_best_TTHReco
      0.000000
    

    

      TTHReco_best_Higgs_mass
      0.000000
    

    

      TTHReco_best_bbHiggs_dR
      0.000000
    

    

      TTHReco_withH_best_Higgsttbar_dR
      0.000000
    

    

      TTHReco_best_Higgsleptop_dR
      0.000000
    

    

      TTHReco_best_b1Higgsbhadtop_dR
      0.000000
    

  




















In [9]:



    


plt.rcParams["figure.figsize"] = (17, 10)

_df.sort_values(by = "importance", ascending = True).plot(kind = "barh", legend = "False");



    


















    
























In [ ]:

Content source: wdbm/abstraction

Similar notebooks:

notebook.community | gallery | about