After training a model, I want to plot the accuracy, validation accuracy, etc. In Seaborn, this is what I tried to do:
df_model_history = pd.DataFrame(
np.array([
history.history['accuracy'],
history.history['val_accuracy']
]).T,
columns=['Accuracy', 'Validation Accuracy']
)
df_model_history.index.name = 'Epochs'
That creates a data frame that looks like this:
| Epochs | Accuracy | Validation Accuracy |
|---|---|---|
| 0 | 0.769296 | 0.766673 |
| 1 | 0.858553 | 0.894064 |
| 2 | 0.915641 | 0.901508 |
| 3 | 0.936782 | 0.892285 |
And when I want to plot, I do this:
sns.set(rc={'figure.figsize':(11.7,8.27)})
sns.lineplot(
x='Epochs',
y='Accuracy',
data=df_model_history
)
However, this only plots a single variable in the figure, but I wanted both 'accuracy' and 'val_accuracy' in the same figure. Also, compared to Matplotlib, I have a lot more steps in Seaborn to plot the same output, so I was wondering if I'm doing it incorrectly.
