Merge remote-tracking branch 'upstream/main' into expr-first

Author: dangotbanned

.github/workflows/extremes.yml

@@ -124,10 +124,6 @@ jobs:
       matrix:
         python-version: ["3.12"]
         os: [ubuntu-latest]
-    env:
-      KAGGLE_USERNAME: ${{ secrets.KAGGLE_USERNAME }}
-      KAGGLE_KEY: ${{ secrets.KAGGLE_KEY }}
-    if: github.event_name == 'push' && github.ref == 'refs/heads/main' || github.event.pull_request.head.repo.full_name == github.repository
     runs-on: ${{ matrix.os }}
     steps:
       - uses: actions/checkout@v4

.pre-commit-config.yaml

@@ -74,7 +74,7 @@ repos:
       exclude: |
         (?x)
           ^(
-            narwhals/utils\.py|
+            narwhals/_utils\.py|
             narwhals/stable/v1/_dtypes.py|
             narwhals/.*__init__.py|
             narwhals/.*typing\.py

CONTRIBUTING.md

@@ -174,6 +174,11 @@ If you add code that should be tested, please add tests.
 - DuckDB / PySpark / anything lazy-only:
 
   - Never assume that your data is ordered in any pre-defined way.
+  - Never materialise your data (only exception: `collect`).
+  - Avoid calling the schema / column names unnecessarily.
+  - For DuckDB, use the Python API as much as possible, only falling
+    back to SQL as the last resort for operations not yet supported
+    in their Python API (e.g. `over`).
 
 ### Test Failure Patterns
 

docs/api-reference/expr.md

@@ -21,6 +21,7 @@
         - diff
         - drop_nulls
         - ewm_mean
+        - exp
         - fill_null
         - filter
         - first
@@ -36,6 +37,7 @@
         - is_nan
         - is_null
         - is_unique
+        - kurtosis
         - len
         - log
         - map_batches
@@ -60,6 +62,7 @@
         - shift
         - sort
         - skew
+        - sqrt
         - std
         - sum
         - tail

docs/api-reference/index.md

@@ -25,3 +25,4 @@
 - [narwhals.exceptions](exceptions.md)
 - [narwhals.selectors](selectors.md)
 - [narwhals.typing](typing.md)
+- [narwhals.utils](utils.md)

docs/api-reference/series.md

@@ -26,6 +26,7 @@
         - drop_nulls
         - dtype
         - ewm_mean
+        - exp
         - fill_null
         - filter
         - first
@@ -45,6 +46,7 @@
         - is_sorted
         - is_unique
         - item
+        - kurtosis
         - len
         - log
         - max
@@ -71,6 +73,7 @@
         - shift
         - sort
         - skew
+        - sqrt
         - std
         - sum
         - tail

docs/api-reference/typing.md

@@ -17,6 +17,7 @@ Narwhals comes fully statically typed. In addition to `nw.DataFrame`, `nw.Expr`,
         - IntoFrameT
         - IntoSeries
         - IntoSeriesT
+        - IntoDType
         - SizeUnit
         - TimeUnit
         - AsofJoinStrategy

docs/api-reference/utils.md

@@ -0,0 +1,12 @@
+# `narwhals.utils`
+
+::: narwhals.utils
+    handler: python
+    options:
+      members:
+        - parse_version
+        - Implementation
+        - Version
+      show_root_heading: false
+      show_source: false
+      show_bases: false

docs/concepts/empty_aggregations.md

@@ -70,7 +70,7 @@ import pandas as pd
 import narwhals as nw
 from narwhals._pandas_like.namespace import PandasLikeNamespace
 from narwhals._pandas_like.utils import Implementation
-from narwhals.utils import parse_version, Version
+from narwhals._utils import parse_version, Version
 
 pn = PandasLikeNamespace(
     implementation=Implementation.PANDAS,
@@ -96,7 +96,7 @@ import narwhals as nw
 from narwhals._pandas_like.namespace import PandasLikeNamespace
 from narwhals._pandas_like.utils import Implementation
 from narwhals._pandas_like.dataframe import PandasLikeDataFrame
-from narwhals.utils import parse_version, Version
+from narwhals._utils import parse_version, Version
 import pandas as pd
 
 pn = PandasLikeNamespace(
@@ -194,7 +194,7 @@ import narwhals as nw
 from narwhals._pandas_like.namespace import PandasLikeNamespace
 from narwhals._pandas_like.utils import Implementation
 from narwhals._pandas_like.dataframe import PandasLikeDataFrame
-from narwhals.utils import parse_version, Version
+from narwhals._utils import parse_version, Version
 import pandas as pd
 
 pn = PandasLikeNamespace(