generate_logs_from_classifiers.py

def generate_logs_from_classifiers(classifiers):
  log_cols=["Classifier", "Accuracy", "Log Loss"]
  log = pd.DataFrame(columns=log_cols)

  for clf in classifiers:
      name = clf.__class__.__name__
      print('Processing {} classifier'.format(name))

      clf.fit(X_train, y_train)
      train_predictions = clf.predict(X_test)
      train_predictions_proba = clf.predict_proba(X_test)

      acc = accuracy_score(y_test, train_predictions)
      ll = log_loss(y_test, train_predictions_proba)

      log_entry = pd.DataFrame([[name, acc*100, ll]], columns=log_cols)
      log = log.append(log_entry)
  
  visualize_log(log)

  return log

def visualize_log(log):
  sns.set_color_codes("muted")
  sns.barplot(x='Accuracy', y='Classifier', data=log, color="b")

  plt.xlabel('Accuracy %')
  plt.title('Classifier Accuracy')
  plt.show()

  sns.set_color_codes("muted")
  sns.barplot(x='Log Loss', y='Classifier', data=log, color="g")

  plt.xlabel('Log Loss')
  plt.title('Classifier Log Loss')
  plt.show()