In [1]:

    

import pandas as pd


    

In [75]:

    

c = pd.read_csv('resources/classification.csv')


    

In [83]:

    

tp = len(c[(c['true'] == c['pred']) & (c['true'] == 1)])
fp = len(c[(c['true'] == 0) & (c['pred'] == 1)])
fn = len(c[(c['true'] == 1) & (c['pred'] == 0)])
tn = len(c[(c['true'] == c['pred']) & (c['true'] == 0)])


    

In [84]:

    

print("Total: {}".format(len(c)))
print("Total: {}".format((tp + fp + fn + tn)))
print("{} {} {} {}".format(tp, fp, fn, tn))


    

    




Total: 200
Total: 200
43 34 59 64

In [31]:

    

from sklearn.metrics import accuracy_score
from sklearn.metrics import precision_score
from sklearn.metrics import recall_score
from sklearn.metrics import f1_score

ac = accuracy_score(c['true'], c['pred'])
ps = precision_score(c['true'], c['pred'])
rs = recall_score(c['true'], c['pred'])
f1 = f1_score(c['true'], c['pred'])

print("{} {} {} {}".format(ac, ps, rs, f1))


    

    




0.535 0.558441558442 0.421568627451 0.480446927374

In [33]:

    

s = pd.read_csv('resources/scores.csv')
s.head()


    

    
Out[33]:







  

    

      

      
true
      
score_logreg
      
score_svm
      
score_knn
      
score_tree
    
  
  

    

      
0
      
0
      
0.683832
      
0.145976
      
0.787063
      
0.500000
    
    

      
1
      
1
      
0.801966
      
0.239511
      
1.000000
      
0.833333
    
    

      
2
      
0
      
0.382315
      
-0.245701
      
0.000000
      
0.000000
    
    

      
3
      
1
      
0.506797
      
-0.137058
      
0.000000
      
0.105263
    
    

      
4
      
1
      
0.488781
      
-0.154148
      
0.000000
      
0.105263
    
  

In [39]:

    

from sklearn.metrics import roc_auc_score

lr = roc_auc_score(s['true'], s['score_logreg'])
svm = roc_auc_score(s['true'], s['score_svm'])
knn = roc_auc_score(s['true'], s['score_knn'])
tree = roc_auc_score(s['true'], s['score_tree'])

print("{} {} {} {}".format(lr, svm, knn, tree))


    

    




0.71918767507 0.708683473389 0.635154061625 0.691926770708

In [73]:

    

from sklearn.metrics import precision_recall_curve

#lr = precision_recall_curve(s['true'], s['score_logreg'])

lr_prec, lr_recall, lr_thres = precision_recall_curve(s['true'], s['score_logreg'])
lr_df = pd.DataFrame([lr_prec, lr_recall, lr_thres]).transpose()
lr_df.columns = ['precision', 'recall', 'thresholds']

svm_prec, svm_recall, svm_thres = precision_recall_curve(s['true'], s['score_svm'])
svm_df = pd.DataFrame([svm_prec, svm_recall, svm_thres]).transpose()
svm_df.columns = ['precision', 'recall', 'thresholds']

knn_prec, knn_recall, knn_thres = precision_recall_curve(s['true'], s['score_knn'])
knn_df = pd.DataFrame([knn_prec, knn_recall, knn_thres]).transpose()
knn_df.columns = ['precision', 'recall', 'thresholds']

t_prec, t_recall, t_thres = precision_recall_curve(s['true'], s['score_tree'])
t_df = pd.DataFrame([t_prec, t_recall, t_thres]).transpose()
t_df.columns = ['precision', 'recall', 'thresholds']

print("LR   max precision: {}".format(lr_df[lr_df['recall'] >= 0.70]['precision'].describe()['max']))
print("Svm  max precision: {}".format(svm_df[svm_df['recall'] >= 0.70]['precision'].describe()['max']))
print("Knn  max precision: {}".format(knn_df[knn_df['recall'] >= 0.70]['precision'].describe()['max']))
print("Tree max precision: {}".format(t_df[t_df['recall'] >= 0.70]['precision'].describe()['max']))


    

    




LR   max precision: 0.63025210084
Svm  max precision: 0.622807017544
Knn  max precision: 0.606557377049
Tree max precision: 0.651785714286