feat: change default to write parquet statistics

pola-rs · Apr 11, 2024 · 9df2ca1 · 9df2ca1
1 parent 31df06d
commit 9df2ca1
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 6 deletions.
diff --git a/crates/polars-io/src/parquet/write.rs b/crates/polars-io/src/parquet/write.rs
@@ -121,7 +121,7 @@ where
         ParquetWriter {
             writer,
             compression: ParquetCompression::default().into(),
-            statistics: false,
+            statistics: true,
             row_group_size: None,
             data_page_size: None,
             parallel: true,

diff --git a/py-polars/polars/dataframe/frame.py b/py-polars/polars/dataframe/frame.py
@@ -3302,7 +3302,7 @@ def write_parquet(
         *,
         compression: ParquetCompression = "zstd",
         compression_level: int | None = None,
-        statistics: bool = False,
+        statistics: bool = True,
         row_group_size: int | None = None,
         data_page_size: int | None = None,
         use_pyarrow: bool = False,
@@ -3329,7 +3329,7 @@ def write_parquet(
             - "zstd" : min-level: 1, max-level: 22.
 
         statistics
-            Write statistics to the parquet headers. This requires extra compute.
+            Write statistics to the parquet headers. This is the default behavior.
         row_group_size
             Size of the row groups in number of rows. Defaults to 512^2 rows.
         data_page_size

diff --git a/py-polars/polars/lazyframe/frame.py b/py-polars/polars/lazyframe/frame.py
@@ -2116,7 +2116,7 @@ def sink_parquet(
         *,
         compression: str = "zstd",
         compression_level: int | None = None,
-        statistics: bool = False,
+        statistics: bool = True,
         row_group_size: int | None = None,
         data_pagesize_limit: int | None = None,
         maintain_order: bool = True,
@@ -2126,7 +2126,7 @@ def sink_parquet(
         simplify_expression: bool = True,
         slice_pushdown: bool = True,
         no_optimization: bool = False,
-    ) -> DataFrame:
+    ) -> None:
         """
         Evaluate the query in streaming mode and write to a Parquet file.
 
@@ -2153,7 +2153,7 @@ def sink_parquet(
             - "brotli" : min-level: 0, max-level: 11.
             - "zstd" : min-level: 1, max-level: 22.
         statistics
-            Write statistics to the parquet headers. This requires extra compute.
+            Write statistics to the parquet headers. This is the default behavior.
         row_group_size
             Size of the row groups in number of rows.
             If None (default), the chunks of the `DataFrame` are