C2W2 exercise 6 preprocessing_fn

Course Q&A Machine Learning Engineering for Production(MLOps) Machine Learning Data Lifecycle in Production
1

I received teh following error from grader:

Failed test case: transformed_data incorrectly defined (showing changed values with respect to correct answer).
Expected:
{},
but got:
{“root[0][‘traffic_volume_xf’]”: {‘new_value’: 1, ‘old_value’: 0}, “root[3][‘traffic_volume_xf’]”: {‘new_value’: 1, ‘old_value’: 0}, “root[4][‘traffic_volume_xf’]”: {‘new_value’: 1, ‘old_value’: 0}}.

I wasn’t sure what mean function to use for this part, the only one I found was tf.reduce_mean:

tf.greater(traffic_volume, tf.reduce_mean(tf.cast(inputs[_VOLUME_KEY], tf.float32))),tf.int64)

Any tips? Thanks.

2

There’s also tft.mean

1 Like
3

Please click my name and message your notebook as an attachment if things don’t get sorted out.

4

Your tip worked, thanks! It would be nice to have this hint in the exercise description :slight_smile:

5

Sure. Informed the staff to add a hint.

6

Hi Team ,Possible to help me what I need to write in this section under preprocessing_fn function

Transform the strings into indices

# hint: use the VOCAB_SIZE and OOV_SIZE to define the top_k and num_oov parameters
for key in _VOCAB_FEATURE_KEYS:
    outputs[_transformed_name(key)] = tft.compute_and_apply_vocabulary(inputs[key]

Use tf.cast to cast the label key to float32

tf.greater(None,None,(tf.cast(inputs[_VOLUME_KEY], tf.float32)))

7

Sorry. I can’t send you any code that’s part of the assignment solution. That said, if you changed the assignment starter code by mistake, refresh the workspace to get a fresh copy of the assignment.

Please see this link.