Identifying variables

When combined, the identifying variables provide a unique key for each encounter. While this may come in handy in many situations, fortunately, pandas DataFrames already uniquely assign an integer to each row, so we can remove the ID variables:

id_cols = [
    'HOSPCODE','PATCODE'
]

X_train.drop(id_cols, axis=1, inplace=True)
X_test.drop(id_cols, axis=1, inplace=True)