Programming Assignment Grading Error

Course Q&A TensorFlow Developer Professional Sequences, Time Series and Prediction
9

hi @Xin_Liu1

There are code errors in your assignment. You have tried to use numpy function recall everywhere which you were not suppose to.

  1. while compute metric, you didn’t require to assign true and pred labels to the value you have used.

  2. You didn’t share naive forecast codes, so cannot confirm

  3. Your moving average forecast, where you forecast append, you have used np.mean which you did not require. use mean( ) to forecast.append code

Also the time-window_size: time is incorrect, it should be time:time+window_size

  1. you didn’t share diff_series codes

  2. for diff_moving_avg where you perform correct slicing, that is again incorrect, taking len of series_valid will not get you diff moving avg.
    it should be [SPLIT_TIME-365-WINDOW_SIZE:]

  3. You applied the same logic for calculating past series where you used len of series valid which is again incorrect, you are suppose to use SERIES.
    if your naive_forecast codes are correct (as I didn’t see the codes), apply the same logic as used in naive forecast, only value here would 365 and in naive forecast it is 1.

Also from next time, please create first topic, if a mentor wants to see your codes they will ask for it. Don’t send direct DM for different topics, rather create a new topic. You can always tag anyone using @ if you want any particular mentor to look at your codes.

Whenever I used to come across a grader failure for my assignment, I used to go back to videos and u graded labs, on how I can make changes to my codes to get successful submission, this is is just a suggestion on how I used to debug my codes.

Regards
DP