merge main

.github/dependabot.yml

@@ -5,8 +5,8 @@ updates:
   - package-ecosystem: "github-actions"
     directory: "/"
     schedule:
-      # Check for updates to GitHub Actions every week
-      interval: "weekly"
+      # Check for updates to GitHub Actions every month
+      interval: "monthly"
     commit-message:
       prefix: "skip changelog" # So this PR will not be added to release-drafter
       include: "scope" # List of the updated dependencies in the commit will be added

.github/workflows/downstream_tests.yml

@@ -55,7 +55,7 @@ jobs:
       matrix:
         python-version: ["3.12"]
         os: [ubuntu-latest]
-        dependencies: ["core", "core,optional"]
+        dependencies: ["core,optional"]
 
     runs-on: ${{ matrix.os }}
     steps:
@@ -73,19 +73,27 @@ jobs:
         run: |
             git clone https://github.com/marimo-team/marimo.git --depth=1
             cd marimo
+            uv venv -p 3.12
             git log
       - name: install-basics
         run: uv pip install --upgrade tox virtualenv setuptools hatch --system
       - name: install-marimo-dev
         run: |
             cd marimo
-            uv pip install -e ".[dev]" --system
+            . .venv/bin/activate
+            uv pip install -e ".[dev]"
+            which python
       - name: install-narwhals-dev
         run: |
-            uv pip uninstall narwhals --system
-            uv pip install -e . --system
+            cd marimo
+            . .venv/bin/activate
+            uv pip uninstall narwhals
+            uv pip install -e ./..
       - name: show-deps
-        run: uv pip freeze
+        run: |
+            cd marimo
+            . .venv/bin/activate
+            uv pip freeze
       - name: Create assets directory, copy over index.html
         continue-on-error: true
         run: |
@@ -96,12 +104,13 @@ jobs:
         if: ${{ matrix.dependencies == 'core,optional' }}
         run: |
             cd marimo
-            hatch run +py=${{ matrix.python-version }} test-optional:test-narwhals
+            . .venv/bin/activate
+            # make sure that we use the .venv when running tests, so that
+            # the local narwhals install is picked up
+            sed -i '/^\[tool.hatch.envs.default\]/a path = ".venv"' pyproject.toml
+            hatch run python -c "import narwhals; print(narwhals.__file__)"
+            hatch run test-optional:test-narwhals
         timeout-minutes: 15
-      - name: Run typechecks
-        run: |
-            cd marimo
-            hatch run typecheck:check
 
   scikit-lego:
     strategy:
@@ -181,3 +190,43 @@ jobs:
         run: |
             cd py-shiny
             make narwhals-test-integration
+  
+  tubular:
+    strategy:
+      matrix:
+        python-version: ["3.12"]
+        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@v3
+        with:
+          enable-cache: "true"
+          cache-suffix: ${{ matrix.python-version }}
+          cache-dependency-glob: "**requirements*.txt"
+      - name: clone-tubular
+        run: |
+            git clone https://github.com/lvgig/tubular --depth=1
+            cd tubular
+            git log
+      - name: install-basics
+        run: uv pip install --upgrade tox virtualenv setuptools pytest-env --system
+      - name: install-tubular-dev
+        run: |
+            cd tubular
+            uv pip install -e .[dev] --system
+      - name: install-narwhals-dev
+        run: |
+            uv pip uninstall narwhals --system
+            uv pip install -e . --system
+      - name: show-deps
+        run: uv pip freeze
+      - name: Run pytest
+        run: |
+            cd tubular
+            pytest tests --config-file=pyproject.toml

.github/workflows/extremes.yml

@@ -90,7 +90,7 @@ jobs:
   nightlies:
     strategy:
       matrix:
-        python-version: ["3.12"]
+        python-version: ["3.13"]
         os: [ubuntu-latest]
     if: github.event.pull_request.head.repo.full_name == github.repository
     runs-on: ${{ matrix.os }}

.github/workflows/pytest.yml

@@ -34,7 +34,7 @@ jobs:
   pytest-windows:
     strategy:
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.10", "3.12"]
         os: [windows-latest]
 
     runs-on: ${{ matrix.os }}
@@ -61,7 +61,7 @@ jobs:
   pytest-coverage:
     strategy:
       matrix:
-        python-version: ["3.9", "3.10", "3.11", "3.12"]
+        python-version: ["3.9", "3.11", "3.13"]
         os: [ubuntu-latest]
 
     runs-on: ${{ matrix.os }}

.gitignore

@@ -17,6 +17,7 @@ coverage.xml
 # Documentation
 site/
 todo.md
+docs/this.md
 docs/api-completeness/*.md
 !docs/api-completeness/index.md
 

.pre-commit-config.yaml

@@ -1,15 +1,17 @@
+ci:
+  autoupdate_schedule: monthly
 repos:
 - repo: https://github.com/astral-sh/ruff-pre-commit
   # Ruff version.
-  rev: 'v0.6.9'
+  rev: 'v0.7.1'
   hooks:
     # Run the formatter.
     - id: ruff-format
     # Run the linter.
     - id: ruff
       args: [--fix]
 - repo: https://github.com/pre-commit/mirrors-mypy
-  rev: 'v1.11.2'
+  rev: 'v1.13.0'
   hooks:
     - id: mypy
       additional_dependencies: ['polars==1.4.1', 'pytest==8.3.2']
@@ -40,7 +42,7 @@ repos:
   hooks:
     - id: nbstripout
 - repo: https://github.com/adamchainz/blacken-docs
-  rev: "1.19.0"  # replace with latest tag on GitHub
+  rev: "1.19.1"  # replace with latest tag on GitHub
   hooks:
   -   id: blacken-docs
       args: [--skip-errors]

CONTRIBUTING.md

@@ -109,6 +109,10 @@ nox
 
 Notice that nox will also require to have all the python versions that are defined in the `noxfile.py` installed in your system.
 
+#### Testing cuDF
+
+We can't currently test in CI against cuDF, but you can test it manually in Kaggle using GPUs. Please follow this [Kaggle notebook](https://www.kaggle.com/code/marcogorelli/testing-cudf-in-narwhals) to run the tests.
+
 ### 7. Building docs
 
 To build the docs, run `mkdocs serve`, and then open the link provided in a browser.

README.md

@@ -43,10 +43,13 @@ Join the party!
 
 - [Altair](https://github.com/vega/altair/)
 - [Hamilton](https://github.com/DAGWorks-Inc/hamilton/tree/main/examples/narwhals)
+- [marimo](https://github.com/marimo-team/marimo)
+- [pymarginaleffects](https://github.com/vincentarelbundock/pymarginaleffects)
 - [scikit-lego](https://github.com/koaning/scikit-lego)
 - [scikit-playtime](https://github.com/koaning/scikit-playtime)
 - [timebasedcv](https://github.com/FBruzzesi/timebasedcv)
-- [marimo](https://github.com/marimo-team/marimo)
+- [tubular](https://github.com/lvgig/tubular)
+- [wimsey](https://github.com/benrutter/wimsey)
 
 Feel free to add your project to the list if it's missing, and/or
 [chat with us on Discord](https://discord.gg/V3PqtB4VA4) if you'd like any support.

docs/api-reference/dependencies.md

@@ -11,14 +11,20 @@
         - get_polars
         - get_pyarrow
         - is_cudf_dataframe
+        - is_cudf_index
         - is_cudf_series
         - is_dask_dataframe
         - is_ibis_table
+        - is_into_dataframe
+        - is_into_series
         - is_modin_dataframe
+        - is_modin_index
         - is_modin_series
         - is_numpy_array
         - is_pandas_dataframe
+        - is_pandas_index
         - is_pandas_like_dataframe
+        - is_pandas_like_index
         - is_pandas_like_series
         - is_pandas_series
         - is_polars_dataframe

docs/api-reference/expr_dt.md

@@ -6,22 +6,23 @@
       members:
         - convert_time_zone
         - date
-        - year
-        - month
         - day
-        - ordinal_day
         - hour
-        - minute
-        - second
-        - millisecond
         - microsecond
+        - millisecond
+        - minute
+        - month
         - nanosecond
+        - ordinal_day
         - replace_time_zone
-        - total_minutes
-        - total_seconds
-        - total_milliseconds
+        - second
+        - timestamp
         - total_microseconds
+        - total_milliseconds
+        - total_minutes
         - total_nanoseconds
+        - total_seconds
         - to_string
+        - year
       show_source: false
       show_bases: false

docs/api-reference/narwhals.md

@@ -15,6 +15,7 @@ Here are the top-level functions available in Narwhals.
         - from_dict
         - from_native
         - from_arrow
+        - generate_temporary_column_name
         - get_level
         - get_native_namespace
         - is_ordered_categorical

docs/api-reference/series_dt.md

@@ -6,22 +6,23 @@
       members:
         - convert_time_zone
         - date
-        - year
-        - month
         - day
-        - ordinal_day
         - hour
-        - minute
-        - second
-        - millisecond
         - microsecond
+        - millisecond
+        - minute
+        - month
         - nanosecond
+        - ordinal_day
         - replace_time_zone
-        - total_minutes
-        - total_seconds
-        - total_milliseconds
+        - second
+        - timestamp
         - total_microseconds
+        - total_milliseconds
+        - total_minutes
         - total_nanoseconds
+        - total_seconds
         - to_string
+        - year
       show_source: false
       show_bases: false

docs/basics/dataframe_conversion.md

@@ -0,0 +1,76 @@
+# Conversion between libraries
+
+Some library maintainers must apply complex dataframe operations, using methods and functions that may not (yet) be implemented in Narwhals. In such cases, Narwhals can still be highly beneficial, by allowing easy dataframe conversion.
+
+## Dataframe X in, pandas out
+
+Imagine that you maintain a library with a function that operates on pandas dataframes to produce automated reports. You want to allow users to supply a dataframe in any format to that function (pandas, Polars, DuckDB, cuDF, Modin, etc.) without adding all those dependencies to your own project and without special-casing each input library's variation of `to_pandas` / `toPandas` / `to_pandas_df` / `df` ...
+
+One solution is to use Narwhals as a thin Dataframe ingestion layer, to convert user-supplied dataframe to the format that your library uses internally. Since Narwhals is zero-dependency, this is a much more lightweight solution than including all the dataframe libraries as dependencies,
+and easier to write than special casing each input library's `to_pandas` method (if it even exists!).
+
+To illustrate, we create dataframes in various formats:
+
+```python exec="1" source="above" session="conversion"
+import narwhals as nw
+from narwhals.typing import IntoDataFrame
+
+import duckdb
+import polars as pl
+import pandas as pd
+
+df_polars = pl.DataFrame(
+    {
+        "A": [1, 2, 3, 4, 5],
+        "fruits": ["banana", "banana", "apple", "apple", "banana"],
+        "B": [5, 4, 3, 2, 1],
+        "cars": ["beetle", "audi", "beetle", "beetle", "beetle"],
+    }
+)
+df_pandas = df_polars.to_pandas()
+df_duckdb = duckdb.sql("SELECT * FROM df_polars")
+```
+
+Now, we define a function that can ingest any dataframe type supported by Narwhals, and convert it to a pandas DataFrame for internal use:
+
+```python exec="1" source="above" session="conversion" result="python"
+def df_to_pandas(df: IntoDataFrame) -> pd.DataFrame:
+    return nw.from_native(df).to_pandas()
+
+
+print(df_to_pandas(df_polars))
+```
+
+## Dataframe X in, Polars out
+
+### Via PyCapsule Interface
+
+Similarly, if your library uses Polars internally, you can convert any user-supplied dataframe to Polars format using Narwhals.
+
+```python exec="1" source="above" session="conversion" result="python"
+def df_to_polars(df: IntoDataFrame) -> pl.DataFrame:
+    return nw.from_arrow(nw.from_native(df), native_namespace=pl).to_native()
+
+
+print(df_to_polars(df_duckdb))  # You can only execute this line of code once.
+```
+
+It works to pass Polars to `native_namespace` here because Polars supports the [PyCapsule Interface](https://arrow.apache.org/docs/format/CDataInterface/PyCapsuleInterface.html) for import.
+
+Note that the PyCapsule Interface makes no guarantee that you can call it repeatedly, so the approach above only works if you
+only expect to perform the conversion a single time on each input object.
+
+### Via PyArrow
+
+If you need to ingest the same dataframe multiple times, then you may want to go via PyArrow instead.
+This may be less efficient than the PyCapsule approach above (and always requires PyArrow!), but is more forgiving:
+
+```python exec="1" source="above" session="conversion" result="python"
+def df_to_polars(df: IntoDataFrame) -> pl.DataFrame:
+    return pl.DataFrame(nw.from_native(df).to_arrow())
+
+
+df_duckdb = duckdb.sql("SELECT * FROM df_polars")
+print(df_to_polars(df_duckdb))  # We can execute this...
+print(df_to_polars(df_duckdb))  # ...as many times as we like!
+```