7. Create Observation Tables

An Observation Table is essentially a collection of historical data points that serve as a foundation for learning. Think of it as the backbone of a training dataset. Its primary role is to process and compute features, which then form the training data for Machine Learning models. For a given use case, the same Observation Table is often employed in multiple experiments. However, the specific features chosen and the Machine Learning models applied may vary between these experiments.

Step 1: Navigate to Observation Table Catalog

From the menu, go to the 'Formulate' section and access the Observation Table catalog.

Step 2: Upload Observation Table

1. Click "Create New Table"
2. Download "In-Store Customer_x_ProductGroup_2022_10K_sample.parquet" here.
3. Upload the parquet file in FeatureByte.
4. Name it "In_Store_Customer_x_ProductGroup_2022_10K".

Step 3: Link Observation Table to a Context

1. Select the table from the catalog.
2. Go to the 'About' tab.
3. Choose "In-Store Customer Engagement with ProductGroup" in the Context dropdown menu.

Step 4: Create Observation Table with Target Values

1. Start by selecting the Observation table to which you wish to add target values.
2. Navigate to the 'About' tab.
3. Click "Compute New Observation Table With Target"
4. Choose the specific target you intend to use
5. Assign a name to your newly created table. For example, you can name it "In_Store_Customer_x_ProductGroup_Spending_next_2_weeks_2022_10K" to reflect its purpose and content.

Step 5: Review Observation Tables

Verify the registration by checking the Observation Table Catalog.

Step 6: Preview Observation Table

1. Select the "In_Store_Customer_x_ProductGroup_Spending_next_2_weeks_2022_10K" table from the catalog.
2. Go to the 'Preview' tab.
3. Confirm the target is present in the table.