Programming Assignment C4W1: Working with generated time series

Course Q&A TensorFlow Developer Professional Sequences, Time Series and Prediction
1

Hello

Trying to finish C4_W1 assignments, but I’m getting below errors and got 0 score from all the grade points.

train_val_split0/10 points earned
There was a problem compiling the code from your notebook, please check that you saved before submitting. Details: name ‘series_valid’ is not defined

compute_metrics ( 0 points / 10 )
There was a problem compiling the code from your notebook, please check that you saved before submitting. Details:
name ‘series_valid’ is not defined

Can you please help ?

When I ran individual cell in jupyter notebook, it generated exactly same output as the expected out - graphs / numbers etc.

Regards,

2

hi @m303b4ky1017

please go through below comment link to debug your codes

most common issue is using incorrect variable, or hard coding path, or using len function to determine smooth series.

Regards
DP

3

Thanks for creating the public topic. Please rely on function parameters and local variables when possible. For example, in function train_val_split, there’s no reason to use SPLIT_TIME for slicing the series.

4

Should we use 1100 instead of SPLIT_TIME? I thought they would be the same.

5

Hi @m303b4ky1017, I have the same problem. Did you solve it?

6

To help me assist you,

Please click on my name to start a private message. Then, attach your notebook as a .ipynb file. Please note that mentors cannot access your Coursera Jupyter workspace, so sending the notebook in a .ipynb format is essential.

7

@m303b4ky1017

The problem with the notebook is that you’ve changed the signature of train_val_split from that of the starter code. Please code in places only where the staff have asked you to code.

For reference, this is the version in starter code:

def train_val_split(time, series):

This is yours:

def train_val_split(time, series, time_step=SPLIT_TIME):