updating Azure and trial information

[tracykteal]

Updating free trial links to dashboard.nixtla.io, rather than dashboard.nixtla.io/freetrial and related FAQs and some Azure getting-started updates.

[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	7.7417	1.6845	0.0058	0.0043

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	4040.22	4110.79	5928.17	18859.2
total_time	1.0316	1.5451	0.0046	0.0042

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	178.293	268.13	269.23	1331.02
mape	0.0234	0.0311	0.0304	0.1692
mse	121589	219485	213677	4.68961e+06
total_time	0.4423	1.7763	0.0056	0.0057

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	465.497	346.972	398.956	1119.26
mape	0.062	0.0436	0.0512	0.1583
mse	835021	403760	656723	3.17316e+06
total_time	0.4871	0.521	0.0057	0.005

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	558.673	459.757	602.926	1340.95
mape	0.0697	0.0565	0.0787	0.17
mse	1.22723e+06	739114	1.61572e+06	6.04619e+06
total_time	0.6559	1.8978	0.0059	0.0055

Plot:

[carla-cr]

Looks good to me!

[tracykteal]

Fixed some links and reviewed live. Set to merge.

[jmoralez]

Who reviewed the azure quickstart? The only supported model should be azureai, which is automatically set if an azure endpoint is detected, so there's no need to set it. Also azureai is the same as timegpt-1-long-horizon, so the sections about shorter and longer forecasts should be removed.

[tracykteal]

Thanks so much for flagging this @jmoralez. Sorry, things were working for me when I set the model as 'azureai' and wasn't working when I wasn't. I'll re-check my setup to make sure it's working without it, and take out the short and longer forecasts section.

[jmoralez]

Were you using a real azure endpoint? I think the override doesn't warn, so behind the scenes we change anything you provided as model and set it to azureai, so you wouldn't see anything, we probably need to add a warning there.

Can you also add #| eval: false to the cells in that tutorial? We run the tests against our own deployment so the CI is failing with errors like this (sample logs):

ValueError: unsupported model: azureai. supported models: ['timegpt-1', 'timegpt-1-long-horizon']

[tracykteal]

I thought I was using a real azure endpoint, but maybe that's the issue. I'll check with you on what I'm using, and see if I should be using something else.

Thanks, yes, I'll add in that #| eval: false. I'll put that in as its own PR, so the tests will start passing.