[DOCS] New structure

[elephaint]

• New structure for TimeGPT documentation

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[github-actions]

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	2.7237	4.9671	0.0088	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	5.8228	3.4514	0.0057	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	6.9634	11.1484	0.0076	0.0072

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	7.8535	10.1359	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	9.59	8.0666	0.0074	0.0068

Plot:

[github-actions]

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	2.4769	2.316	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	2.5733	3.6086	0.0059	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	6.3708	11.5688	0.0079	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	966294	422332	656723	3.17316e+06
total_time	8.9982	9.636	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	9.4874	8.7631	0.0075	0.0071

Plot:

[github-actions]

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	3.3792	2.475	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	2.8248	3.6102	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	9.9964	11.2208	0.008	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	9.86	9.0932	0.0075	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	10.3661	8.2005	0.0076	0.0071

Plot:

[github-actions]

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	2.7659	2.1958	0.0096	0.0053

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	2.232	2.5971	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	2.2647	2.7549	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	3.5927	2.5734	0.0076	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	5.5425	4.9067	0.0076	0.0071

Plot:

[mergenthaler]

@AzulGarza, this is ready for review.

[mergenthaler]

Quick question @elephaint (and @AzulGarza ). From what I understand, the order of the documents in the sidebar from readme.com is given by the slug flag passed in the create readme script. Right now the order is given by increasing the counter.
My two questions:
Does this mean that we have to make sure the files are ordered correctly in the folders?
Is this file iteration logic ok or should we explore something different?

[elephaint]

Quick question @elephaint (and @AzulGarza ). From what I understand, the order of the documents in the sidebar from readme.com is given by the slug flag passed in the create readme script. Right now the order is given by increasing the counter. My two questions: Does this mean that we have to make sure the files are ordered correctly in the folders? Is this file iteration logic ok or should we explore something different?

Good point, this was actually a thing I was still exploring / tinkering with. In the mint.json, I tried to force the order that I wanted, but just did not yet find out how to enforce it for the sidebar. Also because I was tinkering with subgroups there (see updated mint.json). I wanted to avoid explicit file ordering except for the high level structure because I thought it maybe easier for future additions.

Also, I noticed that in the rendered readme often blank lines in the notebooks are ignored, as well as some bullet lists. So there is still a lot of reformatting to do (but that can be done separately from having the structure in place already).

[mergenthaler]

Makes sense @elephaint. Let's see what @AzulGarza thinks. But if she agrees, I'm ok with merging this PR and creating a new one that deals specifically with ordering nbs inside the subfolders. I think ultimately, being able to define the order makes a lot of sense.

[github-actions]

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	4.8444	3.372	0.0088	0.0046

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	9.0112	3.8872	0.006	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	3.891	7.5877	0.0079	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	966294	422332	656723	3.17316e+06
total_time	8.7387	8.7676	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	8.8864	9.8009	0.0076	0.007

Plot:

[AzulGarza]

thanks @elephaint @mergenthaler!

Also, I noticed that in the rendered readme often blank lines in the notebooks are ignored, as well as some bullet lists. So there is still a lot of reformatting to do (but that can be done separately from having the structure in place already).

i agree, i think we should also fix some rendering issues with the images. eg hierarchical:

i'm merging this pr to have the new structure in main and iterating on that.