SoFunction
Updated on 2024-11-15

Python implementation of plotting KS curves

python implementation of KS curve, related to the use of the method please refer to the previous blog - R language implementation of KS curve

The code is as follows:

####################### PlotKS ##########################
def PlotKS(preds, labels, n, asc):
  
  # preds is score: asc=1
  # preds is prob: asc=0
  
  pred = preds # Projected
  bad = labels # Take 1 for bad, 0 for good #
  ksds = DataFrame({'bad': bad, 'pred': pred})
  ksds['good'] = 1 - 
  
  if asc == 1:
    ksds1 = ksds.sort_values(by=['pred', 'bad'], ascending=[True, True])
  elif asc == 0:
    ksds1 = ksds.sort_values(by=['pred', 'bad'], ascending=[False, True])
   = range(len())
  ksds1['cumsum_good1'] = 1.0*()/sum()
  ksds1['cumsum_bad1'] = 1.0*()/sum()
  
  if asc == 1:
    ksds2 = ksds.sort_values(by=['pred', 'bad'], ascending=[True, False])
  elif asc == 0:
    ksds2 = ksds.sort_values(by=['pred', 'bad'], ascending=[False, False])
   = range(len())
  ksds2['cumsum_good2'] = 1.0*()/sum()
  ksds2['cumsum_bad2'] = 1.0*()/sum()
  
  # ksds1 ksds2 -> average
  ksds = ksds1[['cumsum_good1', 'cumsum_bad1']]
  ksds['cumsum_good2'] = ksds2['cumsum_good2']
  ksds['cumsum_bad2'] = ksds2['cumsum_bad2']
  ksds['cumsum_good'] = (ksds['cumsum_good1'] + ksds['cumsum_good2'])/2
  ksds['cumsum_bad'] = (ksds['cumsum_bad1'] + ksds['cumsum_bad2'])/2
  
  # ks
  ksds['ks'] = ksds['cumsum_bad'] - ksds['cumsum_good']
  ksds['tile0'] = range(1, len() + 1)
  ksds['tile'] = 1.0*ksds['tile0']/len(ksds['tile0'])
  
  qe = list((0, 1, 1.0/n))
  (1)
  qe = qe[1:]
  
  ks_index = Series()
  ks_index = ks_index.quantile(q = qe)
  ks_index = (ks_index).astype(int)
  ks_index = list(ks_index)
  
  ksds = [ks_index]
  ksds = ksds[['tile', 'cumsum_good', 'cumsum_bad', 'ks']]
  ksds0 = ([[0, 0, 0, 0]])
  ksds = ([ksds0, ksds], axis=0)
  ksds = DataFrame(ksds, columns=['tile', 'cumsum_good', 'cumsum_bad', 'ks'])
  
  ks_value = ()
  ks_pop = [()]
  print ('ks_value is ' + str((ks_value, 4)) + ' at pop = ' + str((ks_pop, 4)))
  
  # chart
  (, ksds.cumsum_good, label='cum_good',
             color='blue', linestyle='-', linewidth=2)
             
  (, ksds.cumsum_bad, label='cum_bad',
            color='red', linestyle='-', linewidth=2)
            
  (, , label='ks',
          color='green', linestyle='-', linewidth=2)
            
  (ks_pop, color='gray', linestyle='--')
  (ks_value, color='green', linestyle='--')
  ([(), 'cumsum_good'], color='blue', linestyle='--')
  ([(),'cumsum_bad'], color='red', linestyle='--')
  ('KS=%s ' %(ks_value, 4) + 
        'at Pop=%s' %(ks_pop, 4), fontsize=15)
  

  return ksds
####################### over ##########################

The result is as follows:

This is the whole content of this article.