duckrun 0.2.18.dev1__tar.gz → 0.2.18.dev2__tar.gz

{duckrun-0.2.18.dev1 → duckrun-0.2.18.dev2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.18.dev1
+Version: 0.2.18.dev2
 Summary: Helper library for Fabric Python using duckdb, arrow and delta_rs (orchestration, queries, etc.)
 Author: mim
 License: MIT

{duckrun-0.2.18.dev1 → duckrun-0.2.18.dev2}/duckrun/__init__.py

@@ -3,7 +3,7 @@
 from duckrun.core import Duckrun
 from duckrun.notebook import import_notebook_from_web, import_notebook
 
-__version__ = "0.2.18.dev1"
+__version__ = "0.2.18.dev2"
 
 # Expose unified connect method at module level
 connect = Duckrun.connect

{duckrun-0.2.18.dev1 → duckrun-0.2.18.dev2}/duckrun/core.py

@@ -1035,12 +1035,13 @@ class Duckrun(WorkspaceOperationsMixin):
         """Get underlying DuckDB connection"""
         return self.con
 
-    def get_stats(self, source: str):
+    def get_stats(self, source: str = None):
         """
         Get comprehensive statistics for Delta Lake tables.
         
         Args:
-            source: Can be one of:
+            source: Optional. Can be one of:
+                   - None: Use all tables in the connection's schema (default)
                    - Table name: 'table_name' (uses current schema)
                    - Schema.table: 'schema.table_name' (specific table in schema)
                    - Schema only: 'schema' (all tables in schema)
@@ -1052,6 +1053,9 @@ class Duckrun(WorkspaceOperationsMixin):
         Examples:
             con = duckrun.connect("tmp/data.lakehouse/aemo")
             
+            # All tables in current schema (aemo)
+            stats = con.get_stats()
+            
             # Single table in current schema
             stats = con.get_stats('price')
             

{duckrun-0.2.18.dev1 → duckrun-0.2.18.dev2}/duckrun/semantic_model.py

@@ -130,13 +130,24 @@ def check_dataset_exists(dataset_name, workspace_id, client):
 
 
 def refresh_dataset(dataset_name, workspace_id, client, dataset_id=None):
-    """Refresh a dataset and monitor progress using Power BI API"""
+    """Refresh a dataset and monitor progress using Power BI API
+    
+    For DirectLake models, performs a two-step refresh:
+    1. clearValues - Purges data from memory
+    2. full - Reframes data from Delta tables
+    """
     
     # If dataset_id not provided, look it up by name
     if not dataset_id:
         dataset_id = get_dataset_id(dataset_name, workspace_id, client)
     
-    payload = {
+    # Use Power BI API for refresh (not Fabric API)
+    powerbi_url = f"https://api.powerbi.com/v1.0/myorg/datasets/{dataset_id}/refreshes"
+    headers = client._get_headers()
+    
+    # Step 1: clearValues - Purge data from memory
+    print("   Step 1: Clearing values from memory...")
+    clearvalues_payload = {
         "type": "clearValues",
         "commitMode": "transactional",
         "maxParallelism": 10,
@@ -144,11 +155,24 @@ def refresh_dataset(dataset_name, workspace_id, client, dataset_id=None):
         "objects": []
     }
     
-    # Use Power BI API for refresh (not Fabric API)
-    powerbi_url = f"https://api.powerbi.com/v1.0/myorg/datasets/{dataset_id}/refreshes"
-    headers = client._get_headers()
+    response = requests.post(powerbi_url, headers=headers, json=clearvalues_payload)
+    
+    if response.status_code in [200, 202]:
+        print("   ✓ Clear values completed")
+    else:
+        response.raise_for_status()
+    
+    # Step 2: full refresh - Reframe data from Delta tables
+    print("   Step 2: Full refresh to reframe data...")
+    full_payload = {
+        "type": "full",
+        "commitMode": "transactional",
+        "maxParallelism": 10,
+        "retryCount": 2,
+        "objects": []
+    }
     
-    response = requests.post(powerbi_url, headers=headers, json=payload)
+    response = requests.post(powerbi_url, headers=headers, json=full_payload)
     
     if response.status_code in [200, 202]:
         print(f"✓ Refresh initiated")
@@ -471,13 +495,13 @@ def deploy_semantic_model(workspace_name_or_id, lakehouse_name_or_id, schema_nam
         dataset_exists = check_dataset_exists(dataset_name, workspace_id, client)
         
         if dataset_exists:
-            print(f"\n✓ Dataset exists - refreshing...")
+            print(f"✓ Dataset '{dataset_name}' already exists - skipping deployment")
             
             if wait_seconds > 0:
                 print(f"   Waiting {wait_seconds} seconds...")
                 time.sleep(wait_seconds)
             
-            print("\n[Step 6/6] Refreshing semantic model...")
+            print("\n[Step 3/3] Refreshing existing semantic model...")
             refresh_dataset(dataset_name, workspace_id, client)
             
             print("\n" + "=" * 70)

{duckrun-0.2.18.dev1 → duckrun-0.2.18.dev2}/duckrun/stats.py

@@ -60,13 +60,14 @@ def _get_existing_tables_in_schema(duckrun_instance, schema_name: str) -> list:
         return []
 
 
-def get_stats(duckrun_instance, source: str):
+def get_stats(duckrun_instance, source: str = None):
     """
     Get comprehensive statistics for Delta Lake tables.
     
     Args:
         duckrun_instance: The Duckrun connection instance
-        source: Can be one of:
+        source: Optional. Can be one of:
+               - None: Use all tables in the connection's schema (default)
                - Table name: 'table_name' (uses main schema in DuckDB)
                - Schema.table: 'schema.table_name' (specific table in schema, if multi-schema)
                - Schema only: 'schema' (all tables in schema, if multi-schema)
@@ -78,6 +79,9 @@ def get_stats(duckrun_instance, source: str):
     Examples:
         con = duckrun.connect("tmp/data.lakehouse/test")
         
+        # All tables in the connection's schema
+        stats = con.get_stats()
+        
         # Single table in main schema (DuckDB uses 'main', not 'test')
         stats = con.get_stats('price_today')
         
@@ -93,6 +97,10 @@ def get_stats(duckrun_instance, source: str):
     duckdb_schema = "main"
     url_schema = duckrun_instance.schema  # This is from the connection URL path
     
+    # If source is not provided, default to all tables in the connection's schema
+    if source is None:
+        source = url_schema
+    
     # Parse the source and validate existence
     if '.' in source:
         # Format: schema.table - only valid if multi-schema is enabled

{duckrun-0.2.18.dev1 → duckrun-0.2.18.dev2}/duckrun.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.18.dev1
+Version: 0.2.18.dev2
 Summary: Helper library for Fabric Python using duckdb, arrow and delta_rs (orchestration, queries, etc.)
 Author: mim
 License: MIT

{duckrun-0.2.18.dev1 → duckrun-0.2.18.dev2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "duckrun"
-version = "0.2.18.dev1"
+version = "0.2.18.dev2"
 description = "Helper library for Fabric Python using duckdb, arrow and delta_rs (orchestration, queries, etc.)"
 readme = "README.md"
 license = {text = "MIT"}