merge main and maybe fix pandas

.github/release-drafter.yml

@@ -1,6 +1,7 @@
 exclude-labels:
-  - skip changelog
+  - ignore
   - release
+  - dependencies
 name-template: 'Narwhals v$RESOLVED_VERSION'
 
 change-template: '- $TITLE (#$NUMBER)' 
@@ -34,6 +35,9 @@ autolabeler:
   - label: release
     title:
       - '/^([Rr]elease)/'
+  - label: ignore
+    title:
+      - '/^\[pre-commit.ci\]/'
 
 version-resolver:
   major:

.github/workflows/downstream_tests.yml

@@ -86,3 +86,49 @@ jobs:
         run: |
             cd scikit-lego
             pytest -n auto --disable-warnings --cov=sklego -m "not cvxpy and not formulaic and not umap"
+
+  shiny:
+    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-shiny
+        run: |
+            git clone https://github.com/posit-dev/py-shiny.git
+            cd py-shiny
+            git log
+      - name: install-basics
+        run: uv pip install --upgrade tox virtualenv setuptools --system
+      - name: install-shiny-dev
+        run: |
+            cd py-shiny
+            uv pip install -e ".[dev,test]" --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 py-shiny
+            python tests/pytest/asyncio_prevent.py
+            pytest
+      - name: Run mypy
+        run: |
+            cd py-shiny
+            uv pip install mypy --system
+            mypy shiny

.github/workflows/extremes.yml

@@ -119,6 +119,8 @@ jobs:
           kaggle kernels output "marcogorelli/variable-brink-glacier"
       - name: install-polars
         run: python -m pip install *.whl
+      - name: install-pandas-nightly
+        run: pip install --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple pandas
       - name: install-reqs
         run: uv pip install --upgrade tox virtualenv setuptools pip -r requirements-dev.txt --system
       - name: uninstall pyarrow
@@ -127,8 +129,8 @@ jobs:
       #   run: uv pip install --extra-index-url https://pypi.fury.io/arrow-nightlies/ --pre pyarrow --system
       - name: uninstall pandas
         run: uv pip uninstall pandas --system
-      - name: install-pandas-nightly
-        run: uv pip install --prerelease=allow --pre --extra-index-url https://pypi.anaconda.org/scientific-python-nightly-wheels/simple pandas --system
+      - name: show-deps
+        run: uv pip freeze
       - name: uninstall numpy
         run: uv pip uninstall numpy --system
       - name: install numpy nightly

.github/workflows/pytest.yml

@@ -25,7 +25,7 @@ jobs:
           cache-suffix: ${{ matrix.python-version }}
           cache-dependency-glob: "**requirements*.txt"
       - name: install-reqs
-        run: uv pip install --upgrade tox virtualenv setuptools -r requirements-dev.txt ibis-framework[duckdb] --system
+        run: uv pip install --upgrade tox virtualenv setuptools -r requirements-dev.txt --system
       - name: show-deps
         run: uv pip freeze
       - name: Run pytest
@@ -87,7 +87,7 @@ jobs:
       - name: show-deps
         run: uv pip freeze
       - name: install ibis
-        run: uv pip install ibis-framework[duckdb] --system
+        run: uv pip install ibis-framework[duckdb]>=6.0.0 --system
         # Ibis puts upper bounds on dependencies, and requires Python3.10+,
         # which messes with other dependencies on lower Python versions
         if: matrix.python-version == '3.12'

.pre-commit-config.yaml

@@ -1,7 +1,7 @@
 repos:
 - repo: https://github.com/astral-sh/ruff-pre-commit
   # Ruff version.
-  rev: 'v0.6.5'
+  rev: 'v0.6.7'
   hooks:
     # Run the formatter.
     - id: ruff-format
@@ -46,3 +46,8 @@ repos:
       args: [--skip-errors]
       additional_dependencies:
       - black==22.12.0
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.6.0
+  hooks:
+  -   id: name-tests-test
+      exclude: ^tests/utils\.py

README.md

@@ -13,11 +13,12 @@
 Extremely lightweight and extensible compatibility layer between dataframe libraries!
 
 - **Full API support**: cuDF, Modin, pandas, Polars, PyArrow
+- **Lazy-only support**: Dask
 - **Interchange-level support**: Ibis, Vaex, anything else which implements the DataFrame Interchange Protocol
 
 Seamlessly support all, without depending on any!
 
-- ✅ **Just use** a subset of **the Polars API**, no need to learn anything new
+- ✅ **Just use** [a subset of **the Polars API**](https://narwhals-dev.github.io/narwhals/api-reference/), no need to learn anything new
 - ✅ **Zero dependencies**, Narwhals only uses what
   the user passes in so your library can stay lightweight
 - ✅ Separate **lazy** and eager APIs, use **expressions**
@@ -117,6 +118,9 @@ Narwhals has been featured in several talks, podcasts, and blog posts:
 - [Talk Python to me Podcast](https://youtu.be/FSH7BZ0tuE0)
   Ahoy, Narwhals are bridging the data science APIs
 
+- [Python Bytes Podcast](https://www.youtube.com/live/N7w_ESVW40I?si=y-wN1uCsAuJOKlOT&t=382)
+  Episode 402, topic #2
+
 - [Super Data Science: ML & AI Podcast](https://www.youtube.com/watch?v=TeG4U8R0U8U)  
   Narwhals: For Pandas-to-Polars DataFrame Compatibility
 

docs/api-reference/dataframe.md

@@ -41,6 +41,7 @@
         - to_numpy
         - to_pandas
         - unique
+        - unpivot
         - with_columns
         - with_row_index
         - write_csv

docs/api-reference/dtypes.md

@@ -4,6 +4,9 @@
     handler: python
     options:
       members:
+        - Array
+        - List
+        - Struct
         - Int64
         - Int32
         - Int16

docs/api-reference/expr_str.md

@@ -8,9 +8,9 @@
         - ends_with
         - head
         - len_chars
-        - slice
         - replace
         - replace_all
+        - slice
         - starts_with
         - strip_chars
         - tail

docs/api-reference/lazyframe.md

@@ -25,6 +25,7 @@
         - tail
         - to_native
         - unique
+        - unpivot
         - with_columns
         - with_row_index
       show_root_heading: false

docs/api-reference/narwhals.md

@@ -11,6 +11,7 @@ Here are the top-level functions available in Narwhals.
         - any_horizontal
         - col
         - concat
+        - concat_str
         - from_dict
         - from_native
         - get_level
@@ -22,12 +23,14 @@ Here are the top-level functions available in Narwhals.
         - maybe_align_index
         - maybe_convert_dtypes
         - maybe_get_index
+        - maybe_reset_index
         - maybe_set_index
         - mean
         - mean_horizontal
         - min
         - narwhalify
         - new_series
+        - nth
         - sum
         - sum_horizontal
         - when

docs/api-reference/series.md

@@ -6,6 +6,7 @@
       members:
         - __arrow_c_stream__
         - __getitem__
+        - __iter__
         - abs
         - alias
         - all
@@ -42,6 +43,7 @@
         - null_count
         - pipe
         - quantile
+        - rename
         - round
         - sample
         - scatter

docs/api-reference/series_str.md

@@ -14,5 +14,8 @@
         - starts_with
         - strip_chars
         - tail
+        - to_datetime
+        - to_lowercase
+        - to_uppercase
       show_source: false
       show_bases: false

docs/backcompat.md

@@ -74,8 +74,8 @@ users of `narwhals.stable.v1` will have their code unaffected.
 Which should you use? In general we recommend:
 
 - When prototyping, use `import narwhals as nw`, so you can iterate quickly.
-- Once you're happy with what you've got and what to release something production-ready and stable,
-  when switch out your `import narwhals as nw` usage for `import narwhals.stable.v1 as nw`.
+- Once you're happy with what you've got and want to release something production-ready and stable,
+  then switch out your `import narwhals as nw` usage for `import narwhals.stable.v1 as nw`.
 
 ## Exceptions
 

docs/extending.md

@@ -2,7 +2,7 @@
 
 ## List of supported libraries (and how to add yours!)
 
-Currently, Narwhals supports the following libraries as inputs:
+Currently, Narwhals has full API support for the following libraries:
 
 | Library  | 🔗 Link 🔗 |
 | ------------- | ------------- |
@@ -12,46 +12,13 @@ Currently, Narwhals supports the following libraries as inputs:
 | Modin | [github.com/modin-project/modin](https://github.com/modin-project/modin) |
 | PyArrow ⇶ | [arrow.apache.org/docs/python](https://arrow.apache.org/docs/python/index.html) |
 
-If you want your own library to be recognised too, you're welcome open a PR (with tests)!
-Alternatively, if you can't do that (for example, if you library is closed-source), see
-the next section for what else you can do.
-
-To check which methods are supported for which backend in depth, please refer to the
-[API completeness page](api-completeness/index.md).
-
-## Extending Narwhals
-
-We love open source, but we're not "open source absolutists". If you're unable to open
-source you library, then this is how you can make your library compatible with Narwhals.
-
-Make sure that, in addition to the public Narwhals API, you also define:
-
-  - `DataFrame.__narwhals_dataframe__`: return an object which implements public methods
-    from `Narwhals.DataFrame`
-  - `DataFrame.__narwhals_namespace__`: return an object which implements public top-level
-    functions from `narwhals` (e.g. `narwhals.col`, `narwhals.concat`, ...)
-  - `DataFrame.__native_namespace__`: return a native namespace object which must have a
-    `from_dict` method
-  - `LazyFrame.__narwhals_lazyframe__`: return an object which implements public methods
-    from `Narwhals.LazyFrame`
-  - `LazyFrame.__narwhals_namespace__`: return an object which implements public top-level
-    functions from `narwhals` (e.g. `narwhals.col`, `narwhals.concat`, ...)
-  - `LazyFrame.__native_namespace__`: return a native namespace object which must have a
-    `from_dict` method
-  - `Series.__narwhals_series__`: return an object which implements public methods
-    from `Narwhals.Series`
-
-  If your library doesn't distinguish between lazy and eager, then it's OK for your dataframe
-  object to implement both `__narwhals_dataframe__` and `__narwhals_lazyframe__`. In fact,
-  that's currently what `narwhals._pandas_like.dataframe.PandasLikeDataFrame` does. So, if you're stuck,
-  take a look at the source code to see how it's done!
-
-Note that the "extension" mechanism is still experimental. If anything is not clear, or
-doesn't work, please do raise an issue or contact us on Discord (see the link on the README).
+It also has lazy-only support for [Dask](https://github.com/dask/dask), and interchange-only support
+for [DuckDB](https://github.com/duckdb/duckdb) and [Ibis](https://github.com/ibis-project/ibis).
 
-## Levels
+### Levels
 
-Narwhals comes with two levels of support: "full" and "interchange".
+Narwhals comes with two levels of support ("full" and "interchange"), and we are working on defining
+a "lazy-only" level too.
 
 Libraries for which we have full support can benefit from the whole
 [Narwhals API](https://narwhals-dev.github.io/narwhals/api-reference/).
@@ -91,4 +58,38 @@ def func(df: Any) -> Schema:
     return df.schema
 ```
 is also supported, meaning that, in addition to the libraries mentioned above, you can
-also pass Ibis, Vaex, PyArrow, and any other library which implements the protocol.
+also pass Ibis, DuckDB, Vaex, and any library which implements the protocol.
+
+### Extending Narwhals
+
+If you want your own library to be recognised too, you're welcome open a PR (with tests)!.
+Alternatively, if you can't do that (for example, if you library is closed-source), see
+the next section for what else you can do.
+
+We love open source, but we're not "open source absolutists". If you're unable to open
+source you library, then this is how you can make your library compatible with Narwhals.
+
+Make sure that, in addition to the public Narwhals API, you also define:
+
+  - `DataFrame.__narwhals_dataframe__`: return an object which implements public methods
+    from `Narwhals.DataFrame`
+  - `DataFrame.__narwhals_namespace__`: return an object which implements public top-level
+    functions from `narwhals` (e.g. `narwhals.col`, `narwhals.concat`, ...)
+  - `DataFrame.__native_namespace__`: return a native namespace object which must have a
+    `from_dict` method
+  - `LazyFrame.__narwhals_lazyframe__`: return an object which implements public methods
+    from `Narwhals.LazyFrame`
+  - `LazyFrame.__narwhals_namespace__`: return an object which implements public top-level
+    functions from `narwhals` (e.g. `narwhals.col`, `narwhals.concat`, ...)
+  - `LazyFrame.__native_namespace__`: return a native namespace object which must have a
+    `from_dict` method
+  - `Series.__narwhals_series__`: return an object which implements public methods
+    from `Narwhals.Series`
+
+  If your library doesn't distinguish between lazy and eager, then it's OK for your dataframe
+  object to implement both `__narwhals_dataframe__` and `__narwhals_lazyframe__`. In fact,
+  that's currently what `narwhals._pandas_like.dataframe.PandasLikeDataFrame` does. So, if you're stuck,
+  take a look at the source code to see how it's done!
+
+Note that this "extension" mechanism is still experimental. If anything is not clear, or
+doesn't work, please do raise an issue or contact us on Discord (see the link on the README).

docs/how_it_works.md

@@ -75,6 +75,7 @@ from narwhals.utils import parse_version
 pn = PandasLikeNamespace(
     implementation=Implementation.PANDAS,
     backend_version=parse_version(pd.__version__),
+    dtypes=nw.dtypes,
 )
 print(nw.col("a")._call(pn))
 ```
@@ -101,13 +102,15 @@ import pandas as pd
 pn = PandasLikeNamespace(
     implementation=Implementation.PANDAS,
     backend_version=parse_version(pd.__version__),
+    dtypes=nw.dtypes,
 )
 
 df_pd = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})
 df = PandasLikeDataFrame(
     df_pd,
     implementation=Implementation.PANDAS,
     backend_version=parse_version(pd.__version__),
+    dtypes=nw.dtypes,
 )
 expression = pn.col("a") + 1
 result = expression._call(df)
@@ -196,6 +199,7 @@ import pandas as pd
 pn = PandasLikeNamespace(
     implementation=Implementation.PANDAS,
     backend_version=parse_version(pd.__version__),
+    dtypes=nw.dtypes,
 )
 
 df_pd = pd.DataFrame({"a": [1, 2, 3], "b": [4, 5, 6]})
@@ -210,6 +214,7 @@ backend, and it does so by passing a Narwhals-compliant namespace to `nw.Expr._c
 pn = PandasLikeNamespace(
     implementation=Implementation.PANDAS,
     backend_version=parse_version(pd.__version__),
+    dtypes=nw.dtypes,
 )
 expr = (nw.col("a") + 1)._call(pn)
 print(expr)