fabric-mlvlisted

# Fabric Materialized Lake Views (MLV) Declarative SQL/PySpark transformations that persist as Delta tables in a schema-enabled lakehouse. Fabric handles refresh strategy, dependency order, and data quality enforcement so you don't write notebook orchestration. ## When to use vs not Use MLVs for medallion bronze→silver→gold pipelines, frequently-queried aggregates, declarative data quality, and reporting datasets that need automatic refresh. Skip them for one-off queries, sub-second streaming (use Real-Time Intelligence), or transformations that need ML inference / external API calls / non-SQL Python (use a regular Spark notebook). ## Prerequisites - **Schema-enabled lakehouse** — required. `enableSchemas` is immutable per lakehouse; you can't retrofit it. - **Fabric Runtime 1.3** — earlier runtimes can't author MLVs. - **Region** — not available in South Central US (as of 2026-04). - **CDF on source tables** — required for incremental refresh: `ALTER TABLE bronze.x SET TBLPROPERTIES (delta.enableChangeDataFeed = true)`. Without it, optimal refresh degrades to skip-or-full only. ## Spark SQL — CREATE ```sql CREATE [OR REPLACE] MATERIALIZED LAKE VIEW [IF NOT EXISTS] [workspace.lakehouse.schema].MLV_Identifier [( CONSTRAINT name1 CHECK (expr1) [ON MISMATCH DROP | FAIL], CONSTRAINT name2 CHECK (expr2) [ON MISMATCH DROP | FAIL] )] [PARTITIONED BY (col1, col2, ...)] [COMMENT "..."] [TBLPROPERTIES ("k1"="v1", ...)] AS select_statement ``` | Clause | Notes | |---|-