visualize_results_news.py

# Plot accuracy curves:
with sns.color_palette("Accent", n_colors=8):
    plt.figure(figsize=(8,6))
    sns.lineplot(data=np.asarray(m_h.history['acc']))
    sns.lineplot(data=np.asarray(m_h.history['val_acc']))
    plt.xlabel("Epochs")
    plt.ylabel("Accuracy")
    plt.title("Accuracy for Media Bias Classification") # change title here
    plt.legend(labels=['training', 'validation'],loc='lower right')
    plt.text(330,0.755,'val Ac = ' + str(round(accuracy_score(y_test,model.predict_classes(X_test)),2))) 
    plt.savefig('outlets_bias_acc.svg',format='svg') # edit file title here

# Plot confusion matrix:
plt.figure(figsize=(4, 3))
sns.heatmap(confusion_matrix(y_test,model.predict_classes(X_test)),\
annot=True,linewidths=2, cmap="YlGnBu",fmt="g", \
xticklabels=['Right','Left'],\ 
yticklabels=['Right','Left']) # Or change labels to ['outlet1','outlet2','outlet3','outlet4'] for outlet classifier
plt.autoscale()
plt.savefig('confusion_matrix_outlet_bias_bal.png',format='PNG',bbox_inches = "tight") # edit file title here


# Plot loss curves:
with sns.color_palette("Accent", n_colors=8):
    plt.figure(figsize=(8,6))
    sns.lineplot(data=np.asarray(m_h.history['loss']))
    sns.lineplot(data=np.asarray(m_h.history['loss']))
    plt.xlabel("Epochs")
    plt.ylabel("Loss")
    plt.title("Loss functions for Media Bias Classification") #change title here
    plt.legend(labels=['training', 'validation'])
    plt.savefig('outlets_bias_loss.svg',format='SVG') # edit file title here