Trouble with C2W1_Assignment

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

Hello , I have these problems
-compare training and evaluating statistics

  • Grader Error: Grader feedback truncated

Grader feedback was truncated due to size limits. Visit the Discussion Forums to see if your peers are experiencing or have found resolutions for similar errors . If the error isn’t resolved in 24 hours, please reach out to Coursera through our Help Center.

this is the code

START CODE HERE

Generate evaluation dataset statistics

HINT: Remember to use the evaluation dataframe and to pass the stats_options (that you defined before) as an argument

eval_stats = tfdv.generate_statistics_from_dataframe(train_df,stats_options)

Compare evaluation data with training data

HINT: Remember to use both the evaluation and training statistics with the lhs_statistics and rhs_statistics arguments

HINT: Assign the names of ‘EVAL_DATASET’ and ‘TRAIN_DATASET’ to the lhs and rhs protocols

tfdv.visualize_statistics(lhs_statistics=eval_stats, rhs_statistics=train_stats,
lhs_name=‘EVAL_DATASET’, rhs_name=‘TRAIN_DATASET’)
Could someone help me?
Thanks

2

Hi @Alberto_Angarano
Check out these solutions: C2W1 Error during grading
Thank you

3

Dear Isaak I cannot find a solution , what can I do? Many thanks

4

Hi @Alberto_Angarano
Have you tried the partial grading method?

Add into your last cell (add it only in one of the last cells)#grade-up-to-here

5

Hi Isaak I have already done

tfdv.visualize_statistics(lhs_statistics=eval_stats, rhs_statistics=train_stats,
lhs_name=‘EVAL_DATASET’, rhs_name=‘TRAIN_DATASET’)

END CODE HERE

grade-up-to-here

but nothing is changing

I don’t understand why I’m wrong about “detecting anomalies” topic too

eval_stats = tfdv.generate_statistics_from_dataframe(train_df)

anomalies =  tfdv.validate_statistics(eval_stats,schema=schema)


# HINTS: Display input anomalies by using the calculated anomalies
tfdv.display_anomalies(anomalies)

after running cell
calculate_and_display_anomalies(eval_stats, schema=schema)
I can’t find anomalies in the medical_specialty and glimepiride-pioglitazone
as described in text , but

‘encounter_id’ New column New column (column in data but not in schema)
|‘patient_nbr’|New column|New column (column in data but not in schema)|

I don’t know why… Could you help me again?
Many thanks to be patient