Merge remote-tracking branch 'apache/main' into alamb/document_analysis

.github/workflows/dev.yml

@@ -30,7 +30,7 @@ jobs:
       - name: Checkout
         uses: actions/checkout@v4
       - name: Setup Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: "3.10"
       - name: Audit licenses

.github/workflows/dev_pr.yml

@@ -46,7 +46,7 @@ jobs:
           github.event_name == 'pull_request_target' &&
             (github.event.action == 'opened' ||
              github.event.action == 'synchronize')
-        uses: actions/labeler@v4.3.0
+        uses: actions/labeler@v5.0.0
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           configuration-path: .github/workflows/dev_pr/labeler.yml

.github/workflows/dev_pr/labeler.yml

@@ -16,35 +16,37 @@
 # under the License.
 
 development-process:
-  - dev/**.*
-  - .github/**.*
-  - ci/**.*
-  - .asf.yaml
+- changed-files:
+  - any-glob-to-any-file: ['dev/**.*', '.github/**.*', 'ci/**.*', '.asf.yaml']
 
 documentation:
-  - docs/**.*
-  - README.md
-  - ./**/README.md
-  - DEVELOPERS.md
-  - datafusion/docs/**.*
+- changed-files:
+  - any-glob-to-any-file: ['docs/**.*', 'README.md', './**/README.md', 'DEVELOPERS.md', 'datafusion/docs/**.*']
 
 sql:
-  - datafusion/sql/**/*
+- changed-files:
+  - any-glob-to-any-file: ['datafusion/sql/**/*']
 
 logical-expr:
-  - datafusion/expr/**/*
+- changed-files:
+  - any-glob-to-any-file: ['datafusion/expr/**/*']
 
 physical-expr:
-  - datafusion/physical-expr/**/*
+- changed-files:
+  - any-glob-to-any-file: ['datafusion/physical-expr/**/*']
 
 optimizer:
-  - datafusion/optimizer/**/*
+- changed-files:
+  - any-glob-to-any-file: ['datafusion/optimizer/**/*']
 
 core:
-  - datafusion/core/**/*
+- changed-files:
+  - any-glob-to-any-file: ['datafusion/core/**/*']
 
 substrait:
-  - datafusion/substrait/**/*
+- changed-files:
+  - any-glob-to-any-file: ['datafusion/substrait/**/*']
 
 sqllogictest:
-  - datafusion/sqllogictest/**/*
+- changed-files:
+  - any-glob-to-any-file: ['datafusion/sqllogictest/**/*']

.github/workflows/docs.yaml

@@ -24,7 +24,7 @@ jobs:
           path: asf-site
 
       - name: Setup Python
-        uses: actions/setup-python@v4
+        uses: actions/setup-python@v5
         with:
           python-version: "3.10"
 

.github/workflows/rust.yml

@@ -348,7 +348,7 @@ jobs:
       - uses: actions/checkout@v4
         with:
           submodules: true
-      - uses: actions/setup-python@v4
+      - uses: actions/setup-python@v5
         with:
           python-version: "3.8"
       - name: Install PyArrow

Cargo.toml

@@ -85,7 +85,7 @@ parquet = { version = "49.0.0", default-features = false, features = ["arrow", "
 rand = "0.8"
 rstest = "0.18.0"
 serde_json = "1"
-sqlparser = { version = "0.39.0", features = ["visitor"] }
+sqlparser = { version = "0.40.0", features = ["visitor"] }
 tempfile = "3"
 thiserror = "1.0.44"
 chrono = { version = "0.4.31", default-features = false }

README.md

@@ -28,6 +28,7 @@ in-memory format. [Python Bindings](https://github.com/apache/arrow-datafusion-p
 Here are links to some important information
 
 - [Project Site](https://arrow.apache.org/datafusion)
+- [Installation](https://arrow.apache.org/datafusion/user-guide/cli.html#installation)
 - [Rust Getting Started](https://arrow.apache.org/datafusion/user-guide/example-usage.html)
 - [Rust DataFrame API](https://arrow.apache.org/datafusion/user-guide/dataframe.html)
 - [Rust API docs](https://docs.rs/datafusion/latest/datafusion)

benchmarks/compare.py

@@ -109,7 +109,6 @@ def compare(
     noise_threshold: float,
 ) -> None:
     baseline = BenchmarkRun.load_from_file(baseline_path)
-
     comparison = BenchmarkRun.load_from_file(comparison_path)
 
     console = Console()
@@ -124,27 +123,57 @@ def compare(
     table.add_column(comparison_header, justify="right", style="dim")
     table.add_column("Change", justify="right", style="dim")
 
+    faster_count = 0
+    slower_count = 0
+    no_change_count = 0
+    total_baseline_time = 0
+    total_comparison_time = 0
+
     for baseline_result, comparison_result in zip(baseline.queries, comparison.queries):
         assert baseline_result.query == comparison_result.query
 
+        total_baseline_time += baseline_result.execution_time
+        total_comparison_time += comparison_result.execution_time
+
         change = comparison_result.execution_time / baseline_result.execution_time
 
         if (1.0 - noise_threshold) <= change <= (1.0 + noise_threshold):
-            change = "no change"
+            change_text = "no change"
+            no_change_count += 1
         elif change < 1.0:
-            change = f"+{(1 / change):.2f}x faster"
+            change_text = f"+{(1 / change):.2f}x faster"
+            faster_count += 1
         else:
-            change = f"{change:.2f}x slower"
+            change_text = f"{change:.2f}x slower"
+            slower_count += 1
 
         table.add_row(
             f"Q{baseline_result.query}",
             f"{baseline_result.execution_time:.2f}ms",
             f"{comparison_result.execution_time:.2f}ms",
-            change,
+            change_text,
         )
 
     console.print(table)
 
+    # Calculate averages
+    avg_baseline_time = total_baseline_time / len(baseline.queries)
+    avg_comparison_time = total_comparison_time / len(comparison.queries)
+
+    # Summary table
+    summary_table = Table(show_header=True, header_style="bold magenta")
+    summary_table.add_column("Benchmark Summary", justify="left", style="dim")
+    summary_table.add_column("", justify="right", style="dim")
+
+    summary_table.add_row(f"Total Time ({baseline_header})", f"{total_baseline_time:.2f}ms")
+    summary_table.add_row(f"Total Time ({comparison_header})", f"{total_comparison_time:.2f}ms")
+    summary_table.add_row(f"Average Time ({baseline_header})", f"{avg_baseline_time:.2f}ms")
+    summary_table.add_row(f"Average Time ({comparison_header})", f"{avg_comparison_time:.2f}ms")
+    summary_table.add_row("Queries Faster", str(faster_count))
+    summary_table.add_row("Queries Slower", str(slower_count))
+    summary_table.add_row("Queries with No Change", str(no_change_count))
+
+    console.print(summary_table)
 
 def main() -> None:
     parser = ArgumentParser()