undo std::simd incorrect aggregation (#2852)

pola-rs · Mar 8, 2022 · 68f8040 · 68f8040
1 parent 34f8792
commit 68f8040
Show file tree

Hide file tree

Showing 5 changed files with 56 additions and 10 deletions.
diff --git a/polars/polars-arrow/Cargo.toml b/polars/polars-arrow/Cargo.toml
@@ -9,8 +9,8 @@ description = "Arrow interfaces for Polars DataFrame library"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
-arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "81bfaddb92f432ae25bff4e9fdf200159ecebafe", default-features = false }
-# arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "csv_write", default-features = false }
+# arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "81bfaddb92f432ae25bff4e9fdf200159ecebafe", default-features = false }
+arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "cherry_pick", default-features = false }
 # arrow = { package = "arrow2", version = "0.9", default-features = false, features = ["compute_concatenate"] }
 hashbrown = "0.12"
 num = "^0.4"

diff --git a/polars/polars-core/Cargo.toml b/polars/polars-core/Cargo.toml
@@ -163,10 +163,10 @@ thiserror = "^1.0"
 
 [dependencies.arrow]
 package = "arrow2"
-git = "https://github.com/jorgecarleitao/arrow2"
-# git = "https://github.com/ritchie46/arrow2"
-rev = "81bfaddb92f432ae25bff4e9fdf200159ecebafe"
-# branch = "csv_write"
+# git = "https://github.com/jorgecarleitao/arrow2"
+git = "https://github.com/ritchie46/arrow2"
+# rev = "81bfaddb92f432ae25bff4e9fdf200159ecebafe"
+branch = "cherry_pick"
 # version = "0.9"
 default-features = false
 features = [

diff --git a/polars/polars-io/Cargo.toml b/polars/polars-io/Cargo.toml
@@ -34,8 +34,8 @@ private = []
 [dependencies]
 ahash = "0.7"
 anyhow = "1.0"
-arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "81bfaddb92f432ae25bff4e9fdf200159ecebafe", default-features = false }
-# arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "csv_write", default-features = false }
+# arrow = { package = "arrow2", git = "https://github.com/jorgecarleitao/arrow2", rev = "81bfaddb92f432ae25bff4e9fdf200159ecebafe", default-features = false }
+arrow = { package = "arrow2", git = "https://github.com/ritchie46/arrow2", branch = "cherry_pick", default-features = false }
 # arrow = { package = "arrow2", version = "0.9", default-features = false }
 csv-core = { version = "0.1.10", optional = true }
 dirs = "4.0"

diff --git a/py-polars/Cargo.lock b/py-polars/Cargo.lock
diff --git a/py-polars/tests/db-benchmark/various.py b/py-polars/tests/db-benchmark/various.py
@@ -23,3 +23,32 @@
 assert np.isclose(
     df.with_column(pl.col("value").cast(pl.Int32)).get_column("value").mean(), mean
 )
+
+# https://github.com/pola-rs/polars/issues/2850
+df = pl.DataFrame(
+    {
+        "id": [
+            130352432,
+            130352277,
+            130352611,
+            130352833,
+            130352305,
+            130352258,
+            130352764,
+            130352475,
+            130352368,
+            130352346,
+        ]
+    }
+)
+
+minimum = 130352258
+maximum = 130352833.0
+
+for _ in range(10):
+    permuted = df.sample(frac=1.0)
+    computed = permuted.select(
+        [pl.col("id").min().alias("min"), pl.col("id").max().alias("max")]
+    )
+    assert computed[0, "min"] == minimum
+    assert computed[0, "max"] == maximum