VSB Power Line Blog - Get the distribution of the target data

target_distribution.py

splot = sns.countplot(x='target', data=metadata_train)
# https://github.com/mwaskom/seaborn/issues/1582
for ind, p in enumerate(splot.patches):
  percent = np.round((metadata_train[metadata_train['target']==ind].shape[0]/metadata_train['target'].shape[0])*100, 2)
  splot.annotate(str(metadata_train[metadata_train['target']==ind].shape[0]) + f" ({percent}%)", 
                 (p.get_x()+p.get_width()/2, p.get_height()))
plt.title("Distribution of target classes")
plt.show()