Navigating TIM Studio
To appropriately navigate TIM Studio, a user will first need to get an understanding of the structure of the repository that lies underneath. This section of the documentation walks through the different elements in this structure and how they relate to eachother.
A user will start out in their personal environment, in which they'll immediately be able to create user groups. A user group is a group of people collaborating on the same projects and with the same data.
The work of a user group is organized by workspaces, allowing them to collaborate in a structured way. A workspace serves as an assembly place for all use cases shared by a user group, potentially split by topic.
Within workspaces, use cases provide an intuitive overview of the efforts in a project. A use case serves as an assembly place for all information related to a business use case in one single place.
For each use case, users can provide all relevant information, to serve as explanation for others who might benefit from their work, and to serve as a reminder should they return to the work at a later point. They can also keep track of all the experiments contained in the use case, and get an overview of who is working on what, when.
Each use case revolves around a single dataset.
Users can upload, preview, manage and explore datasets too. Users will be able to leverage TIM’s time series database, and TIM Studio will give users an overview of metadata and statistics that might be relevant in the data exploration and preparation phase.
The repository also includes version management, so you can keep track of your version history and update your datasets as new data becomes available.
Within a use case, multiple experiments are contained. An experiment is the working point in the TIM platform, where users will find the core of the analytics. Each experiment is focused on a single type of analytics: either forecasting or anomaly detection.
Within an experiment, users get to explore the data, again, and can browse through configuration options. Once the desired settings are selected, an ML request can be triggered and TIM Studio will show how the calculation progresses.
After the model has been built and applied, it’s time to examine the results. Users can get insights into the models that were used, measure the performance and adjust were needed by iterating over the job.
Using the navigation sidebar¶
Expanding the sidebar gives a user easy access to the structure described above.
At the top of the sidebar, the user can select the user group they're currently working in. The rest of the sidebar will automatically update to match the selected user group.
The main part of the sidebar contains a list of all workspaces of the selected user group. By clicking it the user can browse directly through to the workspace. The arrow next to it allows the user to dive deeper into the structure directly in the sidebar: it will show the use cases contained in the selected workspace. Again, those use cases link through to their respective pages, and again, the arrow next to it allows for diving deeper in the structure, straight to the experiments. That way, the user can also access any experiment directly from the sidebar.
The bottom part of the sidebar contains the Manage section. This section allows a user to browse directly to the overview of all their user groups, workspaces and datasets, by clicking the relevant title.
Right above the Manage section, quick actions can be found. Currently, this includes the Quick Forecast functionality. This action can be triggered by clicking the button or using the ctrl + e shortcut. It gives the user the choice to select or upload a dataset, and allows them to immediately start forecasting with it. When a quick forecast is started, TIM Studio takes care of all actions leading up to this (creating a use case, linking the dataset to it, creating an experiment...) and opens up the experiment.