In [1]:

    

from IPython.core.display import HTML
import os
def css_styling():
    """Load default custom.css file from ipython profile"""
    base = os.getcwd()
    styles = "<style>\n%s\n</style>" % (open(os.path.join(base,'files/custom.css'),'r').read())
    return HTML(styles)
css_styling()


    

    
Out[1]:

In [4]:

    

import pandas as pd
import numpy as np


    

In [5]:

    

df = pd.read_csv('training.csv')


    

In [7]:

    

df.head(1)


    

    
Out[7]:






  

    

      

      
EventId
      
DER_mass_MMC
      
DER_mass_transverse_met_lep
      
DER_mass_vis
      
DER_pt_h
      
DER_deltaeta_jet_jet
      
DER_mass_jet_jet
      
DER_prodeta_jet_jet
      
DER_deltar_tau_lep
      
DER_pt_tot
      
...
      
PRI_jet_num
      
PRI_jet_leading_pt
      
PRI_jet_leading_eta
      
PRI_jet_leading_phi
      
PRI_jet_subleading_pt
      
PRI_jet_subleading_eta
      
PRI_jet_subleading_phi
      
PRI_jet_all_pt
      
Weight
      
Label
    
  
  

    

      
0
      
100000
      
138.47
      
51.655
      
97.827
      
27.98
      
0.91
      
124.711
      
2.666
      
3.064
      
41.928
      
...
      
2
      
67.435
      
2.15
      
0.444
      
46.062
      
1.24
      
-2.475
      
113.497
      
0.002653
      
s
    
  

1 rows × 33 columns

In [10]:

    

bueno=df['Label'].replace(to_replace=['s','b'],value=[1,0])
df['class_int']= bueno


    

In [13]:

    

df.drop('EventId',axis=1,inplace=True)
df.drop('Label',axis=1,inplace=True)
df.drop('class_int',axis=1,inplace=True)


    

In [29]:

    

X = df.values
Y = bueno


    

In [32]:

    

print(X.shape)
print(Y.shape)


    

    




(250000, 31)
(250000,)

In [33]:

    




    

In [34]:

    

print(X_train.shape)
print(Y_train.shape)


    

    




(12500, 31)
(12500,)

In [45]:

    

from sklearn.ensemble import RandomForestClassifier

clf = RandomForestClassifier(
    max_features=3,
    max_depth=10,
    min_samples_leaf=50,
    n_estimators=5
)
clf.fit(X_train,Y_train)
clf.score(X_test,Y_test)


    

    
Out[45]:





0.93377684210526313