filled=True,
rounded=True,
special_characters=True,
feature_names=labels_features,
class_names=['0', '1'])
# Convert to png
call([
'dot', '-Tpng', (subDir + 'HFCR - ' + key + ' - dtree.dot'), '-o',
(subDir + 'HFCR Decision Trees - ' + key +
' - tree representation.png'), '-Gdpi=600'
])
prd_trn_lst = best_model[0]
prd_tst_lst = best_model[1]
ds.plot_evaluation_results_kfold([0, 1], trn_y_lst, prd_trn_lst,
tst_y_lst, prd_tst_lst)
plt.suptitle('HFCR Decision Trees - ' + key +
' - Performance & Confusion matrix')
plt.savefig(subDir + 'HFCR Decision Trees - ' + key +
' - Performance & Confusion matrix')
if (offset == 1):
break
if (last_accuracy > best_accuracy and best_accuracy != -1):
best_accuracy = last_accuracy
last_accuracy = -1
count += offset
offset -= 1
elif (best_accuracy == -1):
best_accuracy = last_accuracy
count += 1
ds.multiple_line_chart(
n_estimators,
overfit_values[d][f],
ax=axs[k, i],
title=
'Overfitting for max_depth = %d with max_features = %f' %
(d, f),
xlabel='n_estimators',
ylabel='accuracy',
percentage=True)
plt.suptitle('HFCR Overfitting - Random Forests')
plt.savefig(subDir + 'HFCR Overfitting - Random Forests')
print('HFCR Random Forests - Performance & Confusion Matrix')
prd_trn_lst = best_model[0]
prd_tst_lst = best_model[1]
ds.plot_evaluation_results_kfold(pd.unique(y), trn_y_lst, prd_trn_lst,
tst_y_lst, prd_tst_lst)
plt.suptitle('HFCR Random Forests - ' + key +
'- Performance & Confusion Matrix')
plt.savefig(subDir + 'HFCR Random Forests - ' + key +
'- Performance & Confusion Matrix')
print()
plt.close("all")
plt.figure(figsize=(7, 7))
ds.multiple_bar_chart(['Train', 'Test'], best_accuracies, ylabel='Accuracy')
plt.suptitle('HFCR Sampling & Feature Selection')
plt.savefig(graphsDir + 'HFCR Sampling & Feature Selection')