MLA.py

def compare_algorithms2df(MLA, X_train, X_test, y_train, y_test, sorted_by_measure='accuracy'):
  #show grid with compared results - accuracy, recall, ppv, f1-measure, mcc
  
  MLA_columns = []
  MLA_compare = pd.DataFrame(columns = MLA_columns)


  row_index = 0
  for alg in MLA:

    predicted = alg.fit(X_train, y_train).predict(X_test)
    fp, tp, th = roc_curve(y_test, predicted)
    MLA_name = alg.__class__.__name__
    MLA_compare.loc[row_index,'MLA Name'] = MLA_name
    MLA_compare.loc[row_index, 'MLA Train Accuracy'] = round(alg.score(X_train, y_train), 4)
    MLA_compare.loc[row_index, 'MLA Test Accuracy'] = round(alg.score(X_test, y_test), 4)
    MLA_compare.loc[row_index, 'MLA Precission'] = precision_score(y_test, predicted)
    MLA_compare.loc[row_index, 'MLA Recall'] = recall_score(y_test, predicted)
    MLA_compare.loc[row_index, 'MLA AUC'] = auc(fp, tp)
    row_index+=1
  
  MLA_compare.sort_values(by = ['MLA AUC'], ascending = False, inplace = True)    
  return MLA_compare


def roc_curve_MLA(MLA,X_train, X_test, y_train, y_test):
  index = 1
  for alg in MLA:


      predicted = alg.fit(X_train, y_train).predict(X_test)
      fp, tp, th = roc_curve(y_test, predicted)
      roc_auc_mla = auc(fp, tp)
      MLA_name = alg.__class__.__name__
      plt.plot(fp, tp, lw=2, alpha=0.3, label='ROC %s (AUC = %0.2f)'  % (MLA_name, roc_auc_mla))

      index+=1

  plt.title('ROC Curve comparison')
  plt.legend(bbox_to_anchor=(1.05, 1), loc=2, borderaxespad=0.)
  plt.plot([0,1],[0,1],'r--')
  plt.xlim([0,1])
  plt.ylim([0,1])
  plt.ylabel('True Positive Rate')
  plt.xlabel('False Positive Rate')    
  plt.show()