Use case on missing values
Open
MMenchero
opened this issue 1 year ago
•
5 comments
Description
- Includes a new use case on how to deal with missing values in TimeGPT.
Check out this pull request on 
See visual diffs & provide feedback on Jupyter Notebooks.
Powered by ReviewNB
Experiment Results
Experiment 1: air-passengers
Description:
| variable |
experiment |
| h |
12 |
| season_length |
12 |
| freq |
MS |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
12.6793 |
11.0623 |
47.8333 |
76 |
| mape |
0.027 |
0.0232 |
0.0999 |
0.1425 |
| mse |
213.936 |
199.132 |
2571.33 |
10604.2 |
| total_time |
3.1642 |
2.8472 |
0.0088 |
0.0048 |
Plot:

Experiment 2: air-passengers
Description:
| variable |
experiment |
| h |
24 |
| season_length |
12 |
| freq |
MS |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
58.1031 |
58.4587 |
71.25 |
115.25 |
| mape |
0.1257 |
0.1267 |
0.1552 |
0.2358 |
| mse |
4040.21 |
4110.79 |
5928.17 |
18859.2 |
| total_time |
6.5954 |
6.6675 |
0.0058 |
0.0049 |
Plot:

Experiment 3: electricity-multiple-series
Description:
| variable |
experiment |
| h |
24 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
142.394 |
196.363 |
269.23 |
1331.02 |
| mape |
0.0203 |
0.0234 |
0.0304 |
0.1692 |
| mse |
63464.7 |
123119 |
213677 |
4.68961e+06 |
| total_time |
8.2968 |
10.4669 |
0.0077 |
0.0068 |
Plot:

Experiment 4: electricity-multiple-series
Description:
| variable |
experiment |
| h |
168 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
522.427 |
353.528 |
398.956 |
1119.26 |
| mape |
0.069 |
0.0454 |
0.0512 |
0.1583 |
| mse |
966294 |
422332 |
656723 |
3.17316e+06 |
| total_time |
8.4404 |
6.6992 |
0.0074 |
0.0069 |
Plot:

Experiment 5: electricity-multiple-series
Description:
| variable |
experiment |
| h |
336 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
478.362 |
361.033 |
602.926 |
1340.95 |
| mape |
0.0622 |
0.046 |
0.0787 |
0.17 |
| mse |
805038 |
441118 |
1.61572e+06 |
6.04619e+06 |
| total_time |
11.1168 |
5.8744 |
0.0077 |
0.007 |
Plot:

This is not compatible with the new structure of the docs, but this will be fixed once the new structure has been merged with main.
Experiment Results
Experiment 1: air-passengers
Description:
| variable |
experiment |
| h |
12 |
| season_length |
12 |
| freq |
MS |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
12.6793 |
11.0623 |
47.8333 |
76 |
| mape |
0.027 |
0.0232 |
0.0999 |
0.1425 |
| mse |
213.936 |
199.132 |
2571.33 |
10604.2 |
| total_time |
3.95 |
3.91 |
0.0084 |
0.0047 |
Plot:

Experiment 2: air-passengers
Description:
| variable |
experiment |
| h |
24 |
| season_length |
12 |
| freq |
MS |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
58.1031 |
58.4587 |
71.25 |
115.25 |
| mape |
0.1257 |
0.1267 |
0.1552 |
0.2358 |
| mse |
4040.21 |
4110.79 |
5928.17 |
18859.2 |
| total_time |
3.8363 |
3.2235 |
0.0055 |
0.0047 |
Plot:

Experiment 3: electricity-multiple-series
Description:
| variable |
experiment |
| h |
24 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
142.394 |
196.363 |
269.23 |
1331.02 |
| mape |
0.0203 |
0.0234 |
0.0304 |
0.1692 |
| mse |
63464.7 |
123119 |
213677 |
4.68961e+06 |
| total_time |
3.4 |
4.0678 |
0.0075 |
0.0066 |
Plot:

Experiment 4: electricity-multiple-series
Description:
| variable |
experiment |
| h |
168 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
522.427 |
353.528 |
398.956 |
1119.26 |
| mape |
0.069 |
0.0454 |
0.0512 |
0.1583 |
| mse |
966294 |
422332 |
656723 |
3.17316e+06 |
| total_time |
10.3619 |
11.0153 |
0.0074 |
0.0069 |
Plot:

Experiment 5: electricity-multiple-series
Description:
| variable |
experiment |
| h |
336 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
478.362 |
361.033 |
602.926 |
1340.95 |
| mape |
0.0622 |
0.046 |
0.0787 |
0.17 |
| mse |
805039 |
441118 |
1.61572e+06 |
6.04619e+06 |
| total_time |
9.7457 |
10.7976 |
0.0077 |
0.0071 |
Plot:

Experiment Results
Experiment 1: air-passengers
Description:
| variable |
experiment |
| h |
12 |
| season_length |
12 |
| freq |
MS |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
12.6793 |
11.0623 |
47.8333 |
76 |
| mape |
0.027 |
0.0232 |
0.0999 |
0.1425 |
| mse |
213.936 |
199.132 |
2571.33 |
10604.2 |
| total_time |
3.6164 |
3.0437 |
0.0084 |
0.0047 |
Plot:

Experiment 2: air-passengers
Description:
| variable |
experiment |
| h |
24 |
| season_length |
12 |
| freq |
MS |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
58.1031 |
58.4587 |
71.25 |
115.25 |
| mape |
0.1257 |
0.1267 |
0.1552 |
0.2358 |
| mse |
4040.21 |
4110.79 |
5928.17 |
18859.2 |
| total_time |
3.382 |
3.3543 |
0.006 |
0.0049 |
Plot:

Experiment 3: electricity-multiple-series
Description:
| variable |
experiment |
| h |
24 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
142.394 |
196.363 |
269.23 |
1331.02 |
| mape |
0.0203 |
0.0234 |
0.0304 |
0.1692 |
| mse |
63464.7 |
123119 |
213677 |
4.68961e+06 |
| total_time |
3.1439 |
3.8042 |
0.0079 |
0.0068 |
Plot:

Experiment 4: electricity-multiple-series
Description:
| variable |
experiment |
| h |
168 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
522.427 |
353.528 |
398.956 |
1119.26 |
| mape |
0.069 |
0.0454 |
0.0512 |
0.1583 |
| mse |
966294 |
422332 |
656723 |
3.17316e+06 |
| total_time |
4.7335 |
3.2496 |
0.0074 |
0.0068 |
Plot:

Experiment 5: electricity-multiple-series
Description:
| variable |
experiment |
| h |
336 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
478.362 |
361.033 |
602.926 |
1340.95 |
| mape |
0.0622 |
0.046 |
0.0787 |
0.17 |
| mse |
805039 |
441118 |
1.61572e+06 |
6.04619e+06 |
| total_time |
6.0284 |
4.1286 |
0.0074 |
0.0069 |
Plot:

This now includes the missing values tutorial and the glossary under the new docs structure.
Glossary follows the style of Mistral's glossary; it is concise and focuses on essential concepts only.
Experiment Results
Experiment 1: air-passengers
Description:
| variable |
experiment |
| h |
12 |
| season_length |
12 |
| freq |
MS |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
12.6793 |
11.0623 |
47.8333 |
76 |
| mape |
0.027 |
0.0232 |
0.0999 |
0.1425 |
| mse |
213.936 |
199.132 |
2571.33 |
10604.2 |
| total_time |
14.4382 |
13.9886 |
0.0085 |
0.0048 |
Plot:

Experiment 2: air-passengers
Description:
| variable |
experiment |
| h |
24 |
| season_length |
12 |
| freq |
MS |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
58.1031 |
58.4587 |
71.25 |
115.25 |
| mape |
0.1257 |
0.1267 |
0.1552 |
0.2358 |
| mse |
4040.21 |
4110.79 |
5928.17 |
18859.2 |
| total_time |
14.09 |
17.05 |
0.0058 |
0.0048 |
Plot:

Experiment 3: electricity-multiple-series
Description:
| variable |
experiment |
| h |
24 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
142.394 |
196.363 |
269.23 |
1331.02 |
| mape |
0.0203 |
0.0234 |
0.0304 |
0.1692 |
| mse |
63464.7 |
123119 |
213677 |
4.68961e+06 |
| total_time |
14.9778 |
15.6176 |
0.0078 |
0.007 |
Plot:

Experiment 4: electricity-multiple-series
Description:
| variable |
experiment |
| h |
168 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
522.427 |
353.528 |
398.956 |
1119.26 |
| mape |
0.069 |
0.0454 |
0.0512 |
0.1583 |
| mse |
966295 |
422332 |
656723 |
3.17316e+06 |
| total_time |
13.7921 |
13.5347 |
0.0074 |
0.007 |
Plot:

Experiment 5: electricity-multiple-series
Description:
| variable |
experiment |
| h |
336 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
478.362 |
361.033 |
602.926 |
1340.95 |
| mape |
0.0622 |
0.046 |
0.0787 |
0.17 |
| mse |
805039 |
441118 |
1.61572e+06 |
6.04619e+06 |
| total_time |
13.4097 |
12.4501 |
0.0075 |
0.007 |
Plot:

Experiment Results
Experiment 1: air-passengers
Description:
| variable |
experiment |
| h |
12 |
| season_length |
12 |
| freq |
MS |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
12.6793 |
11.0623 |
47.8333 |
76 |
| mape |
0.027 |
0.0232 |
0.0999 |
0.1425 |
| mse |
213.936 |
199.132 |
2571.33 |
10604.2 |
| total_time |
3.4393 |
4.973 |
0.0092 |
0.0051 |
Plot:

Experiment 2: air-passengers
Description:
| variable |
experiment |
| h |
24 |
| season_length |
12 |
| freq |
MS |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
58.1031 |
58.4587 |
71.25 |
115.25 |
| mape |
0.1257 |
0.1267 |
0.1552 |
0.2358 |
| mse |
4040.21 |
4110.79 |
5928.17 |
18859.2 |
| total_time |
3.9789 |
2.6655 |
0.0059 |
0.005 |
Plot:

Experiment 3: electricity-multiple-series
Description:
| variable |
experiment |
| h |
24 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
142.394 |
196.363 |
269.23 |
1331.02 |
| mape |
0.0203 |
0.0234 |
0.0304 |
0.1692 |
| mse |
63464.8 |
123119 |
213677 |
4.68961e+06 |
| total_time |
4.8373 |
2.9323 |
0.0082 |
0.0071 |
Plot:

Experiment 4: electricity-multiple-series
Description:
| variable |
experiment |
| h |
168 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
522.427 |
353.528 |
398.956 |
1119.26 |
| mape |
0.069 |
0.0454 |
0.0512 |
0.1583 |
| mse |
966294 |
422332 |
656723 |
3.17316e+06 |
| total_time |
4.0098 |
4.4704 |
0.0075 |
0.007 |
Plot:

Experiment 5: electricity-multiple-series
Description:
| variable |
experiment |
| h |
336 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
478.362 |
361.033 |
602.926 |
1340.95 |
| mape |
0.0622 |
0.046 |
0.0787 |
0.17 |
| mse |
805039 |
441118 |
1.61572e+06 |
6.04619e+06 |
| total_time |
5.0848 |
4.4581 |
0.0075 |
0.0074 |
Plot:

This is ready for review @AzulGarza @mergenthaler
Experiment Results
Experiment 1: air-passengers
Description:
| variable |
experiment |
| h |
12 |
| season_length |
12 |
| freq |
MS |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
12.6793 |
11.0623 |
47.8333 |
76 |
| mape |
0.027 |
0.0232 |
0.0999 |
0.1425 |
| mse |
213.936 |
199.132 |
2571.33 |
10604.2 |
| total_time |
2.6991 |
2.4486 |
0.0082 |
0.0045 |
Plot:

Experiment 2: air-passengers
Description:
| variable |
experiment |
| h |
24 |
| season_length |
12 |
| freq |
MS |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
58.1031 |
58.4587 |
71.25 |
115.25 |
| mape |
0.1257 |
0.1267 |
0.1552 |
0.2358 |
| mse |
4040.21 |
4110.79 |
5928.17 |
18859.2 |
| total_time |
2.6519 |
3.4681 |
0.0057 |
0.0046 |
Plot:

Experiment 3: electricity-multiple-series
Description:
| variable |
experiment |
| h |
24 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
142.394 |
196.363 |
269.23 |
1331.02 |
| mape |
0.0203 |
0.0234 |
0.0304 |
0.1692 |
| mse |
63464.7 |
123119 |
213677 |
4.68961e+06 |
| total_time |
2.939 |
3.0241 |
0.0078 |
0.0067 |
Plot:

Experiment 4: electricity-multiple-series
Description:
| variable |
experiment |
| h |
168 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
522.427 |
353.528 |
398.956 |
1119.26 |
| mape |
0.069 |
0.0454 |
0.0512 |
0.1583 |
| mse |
966294 |
422332 |
656723 |
3.17316e+06 |
| total_time |
4.2128 |
4.0458 |
0.0073 |
0.0068 |
Plot:

Experiment 5: electricity-multiple-series
Description:
| variable |
experiment |
| h |
336 |
| season_length |
24 |
| freq |
H |
| level |
None |
| n_windows |
1 |
Results:
| metric |
timegpt-1 |
timegpt-1-long-horizon |
SeasonalNaive |
Naive |
| mae |
478.362 |
361.033 |
602.926 |
1340.95 |
| mape |
0.0622 |
0.046 |
0.0787 |
0.17 |
| mse |
805039 |
441118 |
1.61572e+06 |
6.04619e+06 |
| total_time |
8.3146 |
11.6802 |
0.0073 |
0.0069 |
Plot:
