Here’s a public example project to give you a taste of neptune.ai’s API and the app.
It’s a time series forecasting project that relies on structured tabular data. It shows how to use Neptune with popular time series forecasting algorithms like ARIMA, LSTM, and Prophet.
You can just open the project and play with the app, no registration is needed. And if you want to see the code behind it, go to the example’s GitHub repo.
What’s in this time series example project?
Here are a few most important things you can see in the project:
- Runs table and comparison charts – when you open the project, you will land in the view that shows both the runs table and the comparison charts.
If you want to see only the list of runs, you can change the view by clicking the Runs table tab at the top. The Runs table shows all the experiments (with associated metadata) that were performed when training the model.
- In the Compare runs tab, you can switch from Charts comparison to Images comparison or Side-by-side comparison. If you’ve logged artifacts, you can also compare datasets between runs (not visible in this example).
By the way, you can choose which runs you want to compare by clicking the eye icon in the runs table.
- You can also inspect a single run. Click the Runs details tab at the top of your screen, and you’ll land in the single run’s view. Just below the name of the run, you can see different dashboards.
The first one is the All metadata dashboard with everything that was logged to Neptune (organized in a folder-like structure).
And then, there are Charts, Images, Monitoring, Source code, and more.
- Finally, at the end of the list, you can see some custom dashboards that combine different metadata types in one place. We talk more about custom dashboards and show a few time series-specific examples here.
Other useful resources
Watch the webinar Time-series Forecasting With Model Types: ARIMAX, FBProphet, LSTM, with a live demo.
Contact us if you’d like to get a live customized demo specific to your use case.