HAMMAD MODULE: DATA SOURCING, DATA UNDERSTANDING & DATA PREPARATION
Olist E-commerce BI Project | Group C
1. DATA SOURCING & UNDERSTANDING
Five CSV sources are imported. Statistics nodes inspect structure, missingness and distributions.
2. DELIVERY TARGET ENGINEERING
Convert order timestamps, calculate actual-versus-estimated delay, and create late_delivery.
3. ORDER-LEVEL AGGREGATION
Payments and items are aggregated by order_id before joining, preventing one-to-many duplication.
4. INTEGRATION & FEATURE ENGINEERING
Join orders + payments + items + customers, remove duplicate join keys, then derive purchase-time and delivery-window features.
FINAL OUTPUT
One-row-per-order analytical master table: 99,441 rows.
To use this workflow in KNIME, download it from the below URL and open it in KNIME:
Deploy, schedule, execute, and monitor your KNIME workflows locally, in the cloud or on-premises – with our brand new NodePit Runner.
