adding more contexts

Please see if this is a correct way of adding a new feature/context in user model. Do I need to take unique values of additional feature (location in this case):

`#user encoder

class UserModel(tf.keras.Model):

def init(self):
super().init()

self.user_embedding = tf.keras.Sequential([
    tf.keras.layers.StringLookup(
        vocabulary=unique_user_ids, mask_token=None),
    tf.keras.layers.Embedding(len(unique_user_ids) + 1, 32),
])
self.timestamp_embedding = tf.keras.Sequential([
    tf.keras.layers.Discretization(timestamp_buckets.tolist()),
    tf.keras.layers.Embedding(len(timestamp_buckets) + 1, 32),
])
self.normalized_timestamp = tf.keras.layers.Normalization(
    axis=None
)

self.normalized_timestamp.adapt(timestamps)

self.loc_embedding =  tf.keras.Sequential([
    tf.keras.layers.StringLookup(
        vocabulary=unique_loc, mask_token=None),
    tf.keras.layers.Embedding(len(unique_loc) + 1, 32),
])

def call(self, inputs):
# Take the input dictionary, pass it through each input layer,
# and concatenate the result.
return tf.concat([
self.user_embedding(inputs["user_id"]),
self.loc_embedding(inputs["location"]),
self.timestamp_embedding(inputs["comment_date"]),
tf.reshape(self.normalized_timestamp(inputs["comment_date"]), (-1, 1)),
], axis=1)`

Start with the UserModel class and the StringLookup, Embedding, Discretization, and Normalization layers shown in the issue. Check the TensorFlow Recommenders and TensorFlow documentation for adding location as context; the work is done when the approach and vocabulary requirements are validated for this model.