Merge branch 'main' into remove-unused-ignores-1

.github/workflows/check_tpch_queries.yml

@@ -25,7 +25,7 @@ jobs:
           cache-suffix: ${{ matrix.python-version }}
           cache-dependency-glob: "pyproject.toml"
       - name: local-install
-        run: uv pip install -U --pre -e ".[dev, core, dask]" --system
+        run: uv pip install -U --pre -e ".[tests, core, dask]" --system
       - name: generate-data
         run: cd tpch && python generate_data.py
       - name: tpch-tests 

.github/workflows/downstream_tests.yml

@@ -220,7 +220,7 @@ jobs:
         run: |
           cd tea-tasting
           pdm remove narwhals
-          pdm add ./..[dev]
+          pdm add ./..[tests]
       - name: show-deps
         run: |
           cd tea-tasting

.github/workflows/extremes.yml

@@ -28,7 +28,7 @@ jobs:
         run: uv pip install pipdeptree tox virtualenv setuptools pandas==0.25.3 polars==0.20.3 numpy==1.17.5 pyarrow==11.0.0 "pyarrow-stubs<17" scipy==1.5.0 scikit-learn==1.1.0 duckdb==1.0 tzdata --system
       - name: install-reqs
         run: |
-          uv pip install -e ".[dev]" --system
+          uv pip install -e ".[tests]" --system
       - name: show-deps
         run: uv pip freeze
       - name: Assert dependencies
@@ -64,7 +64,7 @@ jobs:
       - name: install-pretty-old-versions
         run: uv pip install pipdeptree tox virtualenv setuptools pandas==1.1.5 polars==0.20.3 numpy==1.17.5 pyarrow==11.0.0 "pyarrow-stubs<17" pyspark==3.5.0 scipy==1.5.0 scikit-learn==1.1.0 duckdb==1.0 tzdata --system
       - name: install-reqs
-        run: uv pip install -e ".[dev]" --system
+        run: uv pip install -e ".[tests]" --system
       - name: show-deps
         run: uv pip freeze
       - name: show-deptree
@@ -103,7 +103,7 @@ jobs:
       - name: install-not-so-old-versions
         run: uv pip install tox virtualenv setuptools pandas==2.0.3 polars==0.20.8 numpy==1.24.4 pyarrow==15.0.0 "pyarrow-stubs<17" pyspark==3.5.0 scipy==1.8.0 scikit-learn==1.3.0 duckdb==1.0 dask[dataframe]==2024.10 tzdata --system
       - name: install-reqs
-        run: uv pip install -e ".[dev]" --system
+        run: uv pip install -e ".[tests]" --system
       - name: show-deps
         run: uv pip freeze
       - name: Assert not so old versions dependencies
@@ -140,7 +140,7 @@ jobs:
           cache-suffix: ${{ matrix.python-version }}
           cache-dependency-glob: "pyproject.toml"
       - name: install-reqs
-        run: uv pip install -e ".[dev]" --system
+        run: uv pip install -e ".[tests]" --system
       - name: install-kaggle
         run: uv pip install kaggle --system
       - name: Download Kaggle notebook artifact

.github/workflows/pytest.yml

@@ -25,7 +25,7 @@ jobs:
           cache-dependency-glob: "pyproject.toml"
       - name: install-reqs
         # Python3.8 is technically at end-of-life, so we don't test everything
-        run: uv pip install -e ".[dev, core]" --system
+        run: uv pip install -e ".[tests, core]" --system
       - name: show-deps
         run: uv pip freeze
       - name: Run pytest
@@ -49,7 +49,7 @@ jobs:
           cache-suffix: ${{ matrix.python-version }}
           cache-dependency-glob: "pyproject.toml"
       - name: install-reqs
-        run: uv pip install -e ".[dev, core, extra, dask, modin]" --system
+        run: uv pip install -e ".[tests, core, extra, dask, modin]" --system
       - name: install pyspark
         run: uv pip install -e ".[pyspark]" --system
         # PySpark is not yet available on Python3.12+
@@ -83,7 +83,7 @@ jobs:
           cache-suffix: ${{ matrix.python-version }}
           cache-dependency-glob: "pyproject.toml"
       - name: install-reqs
-        run: uv pip install -e ".[dev, core, extra, modin, dask]" --system
+        run: uv pip install -e ".[tests, core, extra, modin, dask]" --system
       - name: install pyspark
         run: uv pip install -e ".[pyspark]" --system
         # PySpark is not yet available on Python3.12+

.github/workflows/random_ci_pytest.yml

@@ -27,7 +27,7 @@ jobs:
       - name: install-random-verions
         run: uv pip install -r random-requirements.txt --system
       - name: install-narwhals
-        run: uv pip install -e ".[dev]" --system
+        run: uv pip install -e ".[tests]" --system
       - name: show versions
         run: uv pip freeze
       - name: Run pytest

.github/workflows/typing.yml

@@ -0,0 +1,40 @@
+name: Type checking
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  mypy:
+    strategy:
+      matrix:
+        python-version: ["3.11"]
+        os: [ubuntu-latest]
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v4
+      - uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Install uv
+        uses: astral-sh/setup-uv@v5
+        with:
+          enable-cache: "true"
+          cache-suffix: ${{ matrix.python-version }}
+          cache-dependency-glob: "pyproject.toml"
+      - name: Create venv
+        run: uv venv .venv
+      - name: install-reqs
+        # TODO: add more dependencies/backends incrementally
+        run: |
+          source .venv/bin/activate
+          uv pip install -e ".[tests, typing, core]"
+      - name: show-deps
+        run: |
+          source .venv/bin/activate
+          uv pip freeze
+      - name: Run mypy
+        run: |
+          source .venv/bin/activate
+          make typing

.pre-commit-config.yaml

@@ -1,5 +1,6 @@
 ci:
   autoupdate_schedule: monthly
+  skip: [mypy]
 repos:
 - repo: https://github.com/astral-sh/ruff-pre-commit
   # Ruff version.
@@ -13,12 +14,6 @@ repos:
     - id: ruff
       alias: check-docstrings
       entry: python utils/check_docstrings.py
-- repo: https://github.com/pre-commit/mirrors-mypy
-  rev: 'v1.14.1'
-  hooks:
-    - id: mypy
-      additional_dependencies: ['polars==1.4.1', 'pytest==8.3.2']
-      files: ^(narwhals|tests)/
 - repo: https://github.com/codespell-project/codespell
   rev: 'v2.4.1'
   hooks:
@@ -84,6 +79,13 @@ repos:
       entry: pull_request_target
       language: pygrep
       files: ^\.github/workflows/
+    - id: mypy
+      name: mypy
+      entry: make typing
+      files: ^(narwhals|tests)/
+      language: system
+      types: [python]
+      require_serial: true
 - repo: https://github.com/adamchainz/blacken-docs
   rev: "1.19.1"  # replace with latest tag on GitHub
   hooks:

Makefile

@@ -0,0 +1,23 @@
+# Mostly based on polars Makefile
+# https://github.com/pola-rs/polars/blob/main/py-polars/Makefile
+
+.DEFAULT_GOAL := help
+
+SHELL=bash
+VENV=./.venv
+
+ifeq ($(OS),Windows_NT)
+	VENV_BIN=$(VENV)/Scripts
+else
+	VENV_BIN=$(VENV)/bin
+endif
+
+
+.PHONY: help
+help:  ## Display this help screen
+	@echo -e "\033[1mAvailable commands:\033[0m"
+	@grep -E '^[a-z.A-Z_-]+:.*?## .*$$' $(MAKEFILE_LIST) | awk 'BEGIN {FS = ":.*?## "}; {printf "  \033[36m%-22s\033[0m %s\n", $$1, $$2}' | sort
+
+.PHONY: typing
+typing: ## Run typing checks
+	$(VENV_BIN)/mypy

docs/api-reference/series.md

@@ -30,6 +30,7 @@
         - filter
         - gather_every
         - head
+        - hist
         - implementation
         - is_between
         - is_duplicated

docs/installation.md

@@ -30,7 +30,7 @@ To verify the installation, start the Python REPL and execute:
 ```python
 >>> import narwhals
 >>> narwhals.__version__
-'1.25.2'
+'1.26.0'
 ```
 
 If you see the version number, then the installation was successful!

narwhals/__init__.py

@@ -79,7 +79,7 @@
 from narwhals.utils import maybe_reset_index
 from narwhals.utils import maybe_set_index
 
-__version__ = "1.25.2"
+__version__ = "1.26.0"
 
 __all__ = [
     "Array",

narwhals/_arrow/dataframe.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-from itertools import chain
 from typing import TYPE_CHECKING
 from typing import Any
 from typing import Iterator
@@ -44,10 +43,10 @@
     from typing_extensions import Self
     from typing_extensions import TypeAlias
 
+    from narwhals._arrow.expr import ArrowExpr
     from narwhals._arrow.group_by import ArrowGroupBy
     from narwhals._arrow.namespace import ArrowNamespace
     from narwhals._arrow.series import ArrowSeries
-    from narwhals._arrow.typing import IntoArrowExpr
     from narwhals.dtypes import DType
     from narwhals.typing import SizeUnit
     from narwhals.typing import _1DArray
@@ -342,8 +341,11 @@ def simple_select(self, *column_names: str) -> Self:
             self._native_frame.select(list(column_names)), validate_column_names=False
         )
 
-    def select(self: Self, *exprs: IntoArrowExpr, **named_exprs: IntoArrowExpr) -> Self:
-        new_series: list[ArrowSeries] = evaluate_into_exprs(self, *exprs, **named_exprs)
+    def aggregate(self: Self, *exprs: ArrowExpr) -> Self:
+        return self.select(*exprs)
+
+    def select(self: Self, *exprs: ArrowExpr) -> Self:
+        new_series: list[ArrowSeries] = evaluate_into_exprs(self, *exprs)
         if not new_series:
             # return empty dataframe, like Polars does
             return self._from_native_frame(
@@ -353,11 +355,9 @@ def select(self: Self, *exprs: IntoArrowExpr, **named_exprs: IntoArrowExpr) -> S
         df = pa.Table.from_arrays(broadcast_series(new_series), names=names)
         return self._from_native_frame(df, validate_column_names=False)
 
-    def with_columns(
-        self: Self, *exprs: IntoArrowExpr, **named_exprs: IntoArrowExpr
-    ) -> Self:
+    def with_columns(self: Self, *exprs: ArrowExpr) -> Self:
         native_frame = self._native_frame
-        new_columns: list[ArrowSeries] = evaluate_into_exprs(self, *exprs, **named_exprs)
+        new_columns: list[ArrowSeries] = evaluate_into_exprs(self, *exprs)
 
         length = len(self)
         columns = self.columns
@@ -407,9 +407,9 @@ def join(
             )
 
             return self._from_native_frame(
-                self.with_columns(**{key_token: plx.lit(0, None)})
+                self.with_columns(plx.lit(0, None).alias(key_token))
                 ._native_frame.join(
-                    other.with_columns(**{key_token: plx.lit(0, None)})._native_frame,
+                    other.with_columns(plx.lit(0, None).alias(key_token))._native_frame,
                     keys=key_token,
                     right_keys=key_token,
                     join_type="inner",
@@ -532,23 +532,12 @@ def with_row_index(self: Self, name: str) -> Self:
             df.append_column(name, row_indices).select([name, *cols])
         )
 
-    def filter(self: Self, *predicates: IntoArrowExpr, **constraints: Any) -> Self:
-        if (
-            len(predicates) == 1
-            and isinstance(predicates[0], list)
-            and all(isinstance(x, bool) for x in predicates[0])
-            and not constraints
-        ):
-            mask_native = predicates[0]
+    def filter(self: Self, predicate: ArrowExpr | list[bool]) -> Self:
+        if isinstance(predicate, list):
+            mask_native = predicate
         else:
-            plx = self.__narwhals_namespace__()
-            expr = plx.all_horizontal(
-                *chain(
-                    predicates, (plx.col(name) == v for name, v in constraints.items())
-                )
-            )
-            # `[0]` is safe as all_horizontal's expression only returns a single column
-            mask = expr._call(self)[0]
+            # `[0]` is safe as the predicate's expression only returns a single column
+            mask = evaluate_into_exprs(self, predicate)[0]
             mask_native = broadcast_and_extract_dataframe_comparand(
                 length=len(self), other=mask, backend_version=self._backend_version
             )
@@ -769,7 +758,8 @@ def unique(
             )
 
         keep_idx = self.simple_select(*subset).is_unique()
-        return self.filter(keep_idx)
+        plx = self.__narwhals_namespace__()
+        return self.filter(plx._create_expr_from_series(keep_idx))
 
     def gather_every(self: Self, n: int, offset: int) -> Self:
         return self._from_native_frame(

narwhals/_arrow/expr.py

@@ -25,7 +25,6 @@
 
     from narwhals._arrow.dataframe import ArrowDataFrame
     from narwhals._arrow.namespace import ArrowNamespace
-    from narwhals._arrow.typing import IntoArrowExpr
     from narwhals.dtypes import DType
     from narwhals.utils import Version
 
@@ -189,7 +188,7 @@ def __invert__(self: Self) -> Self:
     def len(self: Self) -> Self:
         return reuse_series_implementation(self, "len", returns_scalar=True)
 
-    def filter(self: Self, *predicates: IntoArrowExpr) -> Self:
+    def filter(self: Self, *predicates: ArrowExpr) -> Self:
         plx = self.__narwhals_namespace__()
         other = plx.all_horizontal(*predicates)
         return reuse_series_implementation(self, "filter", other=other)