Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Feat/new faqs #250

Merged
merged 8 commits into from
Mar 15, 2024
Merged

Feat/new faqs #250

merged 8 commits into from
Mar 15, 2024

Conversation

MMenchero
Copy link
Contributor

@MMenchero MMenchero commented Mar 12, 2024 •
edited
Loading

  • New PR for the updated FAQs done directly from a branch.
  • Replaces Added new sections to FAQs #238.
  • Has a more modular structure: questions and short answers followed by links to tutorials or relevant docs.
  • Includes new tutorial on setting up token (this information was on the previous FAQs).

@review-notebook-app Review Notebook App
Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.

Powered by ReviewNB

@github-actions GitHub Actions
Copy link
Contributor

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 2.9895 5.2116 0.0092 0.0054

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 8.486 8.9942 0.0063 0.0058

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 7.4523 7.224 0.0125 0.011

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 4.7674 4.5212 0.0088 0.0082

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 8.3514 4.4018 0.0084 0.0081

Plot:

@MMenchero MMenchero mentioned this pull request Mar 12, 2024
Closed
@MMenchero MMenchero marked this pull request as draft March 12, 2024 06:43
@MMenchero MMenchero marked this pull request as ready for review March 13, 2024 01:02
@github-actions GitHub Actions
Copy link
Contributor

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 11.4441 14.8445 0.0092 0.0052

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 4.5392 3.9223 0.0063 0.0053

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 3.6484 3.2623 0.0085 0.0088

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 6.8728 6.4361 0.0083 0.0077

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 6.822 7.1002 0.0084 0.0077

Plot:

mergenthaler
mergenthaler reviewed Mar 13, 2024
View reviewed changes
nbs/docs/getting-started/1_getting_started_short.ipynb
@@ -167,7 +167,7 @@
"id": "8e7cea32-ade9-4b23-be93-9a4fbea7c6b2",
Copy link
Member

@mergenthaler mergenthaler Mar 13, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I personally prefer to me more concise. E.g. instead of

"You can test the validity of your token calling the validate_token method"

you can simply write:

Check your token status with the validate_token method.


Reply via ReviewNB

nbs/docs/getting-started/2_setting_up_your_authentication_token.ipynb
@@ -0,0 +1,224 @@
{
Copy link
Member

@mergenthaler mergenthaler Mar 13, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There might be confusion with tokens as in input tokens and tokens as in API Key. Maybe:

A token (aka as API Key )is a unique string of characters that serves as a key to authenticate your requests to TimeGTP. This tutorial will explain how to set up your token when using the Nixtla SDK.


Reply via ReviewNB

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

thanks, I also think that can be confusing, so I added the distinction.

@github-actions GitHub Actions
Copy link
Contributor

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 7.5529 14.0402 0.0101 0.0057

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 9.4541 5.4415 0.0062 0.0052

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 4.2075 4.9485 0.0088 0.0076

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 6.9248 5.7549 0.0086 0.0079

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 9.5541 9.2938 0.0086 0.0077

Plot:

@MMenchero
Copy link
Contributor Author

Pushed new version just to see if the checks can be completed correctly.

cchallu
cchallu reviewed Mar 14, 2024
View reviewed changes
nbs/docs/misc/0_faqs.ipynb
@@ -2,509 +2,312 @@
"cells": [
Copy link
Contributor

@cchallu cchallu Mar 14, 2024 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please add that the plot method only works in interactive environments such as notebooks. We had many users asking why it doesn't work on regular scripts.

Add a separate question on : Can TimeGPT be used with limited/short data?

And mention that it requires at least two seasonalities on the given frequency. More data is needed for confidence intervals and fine-tuning. We need to confirm the minimum looking at the code.


Reply via ReviewNB

@github-actions GitHub Actions
Copy link
Contributor

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 5.5751 12.2999 0.0098 0.0057

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 8.5655 8.1926 0.0063 0.0055

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 4.6733 5.775 0.0084 0.0074

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 6.5703 4.6957 0.0085 0.008

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 7.8877 7.7183 0.0085 0.0078

Plot:

@MMenchero MMenchero merged commit 4ca9418 into main Mar 15, 2024
13 checks passed
@MMenchero MMenchero deleted the feat/new_faqs branch March 15, 2024 02:52
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@cchallu cchallu cchallu left review comments

@mergenthaler mergenthaler mergenthaler left review comments

@AzulGarza AzulGarza Awaiting requested review from AzulGarza

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@MMenchero @mergenthaler @cchallu