> ## Documentation Index > Fetch the complete documentation index at: https://kumo.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Column Preprocessing ## Data Type and Semantic Type Kumo automatically detects column types for preprocessing, but you can manually adjust them as needed. If a mismatch is detected, Kumo will provide recommendations or alert you with an invalid data type error. Ensure that the **semantic type** (`Type`) aligns with the **data type** (`Data Type`) to avoid inconsistencies. ### Supported Column Types Kumo supports **preprocessing** for the following data types: * **Numerical** – Integers and floats where numerical ordering is meaningful (e.g., product price, discount percentage). * **Categorical** – Single-token strings or booleans with a limited set of unique values (up to 4,000 by default), such as product type or subscription status. * **Multi-Categorical** – Comma-separated lists of categorical values (e.g., restaurant tags: `"vegetarian, italian, pickup_only"`). * **ID** – Unique identifiers with no numerical meaning, such as customer IDs or product group numbers. * **Text** – Multi-token strings where semantic meaning is important (e.g., product descriptions, reviews). * **Timestamp** – Date/time values in a valid format (preferably **ISO 8601** or epoch time). For Parquet data, ensure timestamps are correctly cast to a `DATE/TIME/TIMESTAMP` type. * **Embedding** – Lists of equal-length floats, typically representations from AI models. ### Unsupported Column Types The following column types **are not supported** for preprocessing in Kumo. If needed, consider **transforming** them before ingestion: * **Full URLs** – Extract meaningful components (e.g., domain, path) and treat them as categorical values. * **Lat/Long Coordinates** – Convert to categorical geographic areas. * **IP Addresses** – Remove PII, extract high-level details (e.g., subnet), and treat as categorical elements. * **Phone Numbers** – Remove PII, extract relevant components (e.g., area code), and treat as categorical values. ### Handling Nested or Complex Data Kumo does not support **nested schemas, arrays, or maps**. To use such data, transform it into a string format: **Example: Converting an array to a string** **Before:** `["TV", "electronics", "promotion"]` **After:** `"TV, electronics, promotion"` ## Column Properties ### **Primary Key Column** Each row should have a **unique Primary key** (e.g., `user_id`). If duplicate rows share the same key, only one will be retained, and the rest will be dropped. ### **Create Date Column** The **Create date column** represents when a row was created or when the data became valid. This helps define training timelines and ensures predictions use the correct time-based data. ### **End Date Column** The **end date column** restricts training and predictions to a specific timeframe. * For **temporal tasks**, training will include only data valid within this timeframe. * For **batch predictions**, only rows where the **Create date** is on or before the prediction time and the **End date** is before the prediction time will be used. **Example Use Case: End Date for Product Availability** If a product goes out of stock on a particular date, set **End date** to the column tracking this date. **End\_Date-aware sampling is currently supported only in the following contexts:** * The **entity table** (the table referenced after FOR EACH in a predictive query). * The **RHS table** in **link prediction** tasks (the table referenced after `LIST_DISTINCT`).