duckrun 0.2.19.dev4__tar.gz → 0.2.19.dev5__tar.gz

{duckrun-0.2.19.dev4 → duckrun-0.2.19.dev5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.19.dev4
+Version: 0.2.19.dev5
 Summary: Helper library for Fabric Python using duckdb, arrow and delta_rs (orchestration, queries, etc.)
 Author: mim
 License: MIT

{duckrun-0.2.19.dev4 → duckrun-0.2.19.dev5}/duckrun/rle.py

@@ -238,22 +238,21 @@ def calculate_cardinality_ratio(con, source: str, limit: int = None, is_parquet:
     Calculate cardinality ratio for each column (distinct_values / total_rows).
     Lower ratio = better for RLE compression (more repetition).
     
-    NEVER uses sampling - always scans full dataset with exact or approximate distinct counts.
+    NEVER uses sampling - always scans full dataset with exact distinct counts.
     
     Args:
         con: DuckDB connection
         source: Either a table name (default) or parquet file path
         limit: DEPRECATED - kept for backward compatibility but ignored. Always scans full dataset.
         is_parquet: If True, source is a parquet file path; if False, source is a table name
-        use_approx: If True, use HyperLogLog (approx). If False, use exact COUNT(DISTINCT).
-                    If None (default), auto-decide based on table size threshold.
-        approx_threshold: Row count threshold for using HyperLogLog (default: 100M rows)
+        use_approx: DEPRECATED - always uses exact COUNT(DISTINCT)
+        approx_threshold: DEPRECATED - always uses exact COUNT(DISTINCT)
     
     Returns:
         Dictionary mapping column names to dict with keys:
         - 'cardinality_ratio': distinct/total, range 0-1, lower is better for RLE
         - 'total_rows': total row count
-        - 'distinct_values': number of distinct values (exact or approximate)
+        - 'distinct_values': number of distinct values (exact)
     """
     # Build the FROM clause based on source type
     if is_parquet:
@@ -274,26 +273,15 @@ def calculate_cardinality_ratio(con, source: str, limit: int = None, is_parquet:
     if not column_names:
         return {}
     
-    # Auto-decide whether to use approximate or exact based on table size
-    if use_approx is None:
-        # Quick row count check
-        total_rows = con.sql(f"SELECT COUNT(*) FROM {from_clause}").fetchone()[0]
-        use_approx = total_rows > approx_threshold
-        if use_approx:
-            print(f"   Table has {total_rows:,} rows (>{approx_threshold:,}) - using HyperLogLog approximation")
-        else:
-            print(f"   Table has {total_rows:,} rows (<={approx_threshold:,}) - using exact COUNT(DISTINCT)")
-    else:
-        total_rows = None  # Will be calculated in main query
+    # Get row count
+    total_rows = con.sql(f"SELECT COUNT(*) FROM {from_clause}").fetchone()[0]
+    print(f"   Table has {total_rows:,} rows - using exact COUNT(DISTINCT)")
     
-    # Build a single query that calculates all NFV scores in one pass
+    # Build a single query that calculates all cardinality in one pass
     # This scans the data only ONCE instead of once per column
     select_clauses = []
     for col in column_names:
-        if use_approx:
-            select_clauses.append(f"approx_count_distinct({col}) as distinct_{col}")
-        else:
-            select_clauses.append(f"COUNT(DISTINCT {col}) as distinct_{col}")
+        select_clauses.append(f"COUNT(DISTINCT {col}) as distinct_{col}")
     
     query = f"""
         SELECT 
@@ -307,8 +295,7 @@ def calculate_cardinality_ratio(con, source: str, limit: int = None, is_parquet:
     if not result:
         return {}
     
-    if total_rows is None:
-        total_rows = result[0]
+    total_rows = result[0]
     
     nfv_stats = {}
     

{duckrun-0.2.19.dev4 → duckrun-0.2.19.dev5}/duckrun.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: duckrun
-Version: 0.2.19.dev4
+Version: 0.2.19.dev5
 Summary: Helper library for Fabric Python using duckdb, arrow and delta_rs (orchestration, queries, etc.)
 Author: mim
 License: MIT

{duckrun-0.2.19.dev4 → duckrun-0.2.19.dev5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "duckrun"
-version = "0.2.19.dev4"
+version = "0.2.19.dev5"
 description = "Helper library for Fabric Python using duckdb, arrow and delta_rs (orchestration, queries, etc.)"
 readme = "README.md"
 license = {text = "MIT"}