Given a raw dataset in Python, write a script using Pandas to handle missing data, normalize numerical features, and export the cleaned data.
For this SQL version, return an export-ready result from raw_dataset. Replace missing numerical values with the median of their respective columns, then scale each numerical feature to the 0 to 1 range.
record_id, source_label, and cleaned normalized values named age_normalized, annual_income_normalized, and engagement_score_normalized.record_id ascending.| Column | Type | Description |
|---|---|---|
| record_idPK | INT | Unique input record identifier |
| source_label | VARCHAR(50) | Source label associated with the record |
| age | INT | Age value requiring cleaning and normalization |
| annual_income | DECIMAL(12,2) | Annual income value requiring cleaning and normalization |
| engagement_score | DECIMAL(5,2) | Numerical engagement score requiring cleaning and normalization |