Merge pull request #35 from MarcoGorelli/extra-ci

extra ci

.github/workflows/extremes.yml

@@ -0,0 +1,69 @@
+name: ci
+
+on:
+  pull_request:
+  push:
+    branches: [main]
+
+jobs:
+  minimum_versions:
+    strategy:
+      matrix:
+        python-version: ["3.8"]
+        os: [ubuntu-latest]
+
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Cache multiple paths
+        uses: actions/cache@v3
+        with:
+          path: |
+            ~/.cache/pip
+            $RUNNER_TOOL_CACHE/Python/*
+            ~\AppData\Local\pip\Cache
+          key: ${{ runner.os }}-build-${{ matrix.python-version }}
+      - name: install-reqs
+        run: python -m pip install --upgrade tox virtualenv setuptools pip -r requirements-dev.txt
+      - name: install-modin
+        run: python -m pip install pandas==2.0.0 polars==0.20.5 modin[dask]
+      - name: Run pytest
+        run: pytest tests --cov=narwhals --cov=tests --cov-fail-under=50
+      - name: Run doctests
+        run: pytest narwhals --doctest-modules
+
+  nightlies:
+    strategy:
+      matrix:
+        python-version: ["3.12"]
+        os: [ubuntu-latest]
+
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v3
+      - uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+      - name: Cache multiple paths
+        uses: actions/cache@v3
+        with:
+          path: |
+            ~/.cache/pip
+            $RUNNER_TOOL_CACHE/Python/*
+            ~\AppData\Local\pip\Cache
+          key: ${{ runner.os }}-build-${{ matrix.python-version }}
+      - name: install-reqs
+        run: python -m pip install --upgrade tox virtualenv setuptools pip -r requirements-dev.txt
+      - name: uninstall pandas
+        run: python -m pip uninstall pandas -y
+      - name: install-modin
+        run: pip install modin[dask]
+      - name: install-nightly
+        run: python -m pip install --pre --extra-index https://pypi.anaconda.org/scientific-python-nightly-wheels/simple pandas
+      - name: Run pytest
+        run: pytest tests --cov=narwhals --cov=tests --cov-fail-under=50
+      - name: Run doctests
+        run: pytest narwhals --doctest-modules

narwhals/dataframe.py

@@ -435,8 +435,7 @@ def rename(self, mapping: dict[str, str]) -> Self:
         Rename column names.
 
         Arguments:
-            mapping: Key value pairs that map from old name to new name, or a function
-                      that takes the old name as input and returns the new name.
+            mapping: Key value pairs that map from old name to new name.
 
         Examples:
             >>> import polars as pl
@@ -462,23 +461,6 @@ def rename(self, mapping: dict[str, str]) -> Self:
             │ 2     ┆ 7   ┆ b   │
             │ 3     ┆ 8   ┆ c   │
             └───────┴─────┴─────┘
-            >>> dframe = df.rename(lambda column_name: "f" + column_name[1:])
-            >>> dframe
-            ┌─────────────────────────────────────────────────┐
-            | Narwhals DataFrame                              |
-            | Use `narwhals.to_native()` to see native output |
-            └─────────────────────────────────────────────────┘
-            >>> nw.to_native(dframe)
-            shape: (3, 3)
-            ┌─────┬─────┬─────┐
-            │ foo ┆ far ┆ fam │
-            │ --- ┆ --- ┆ --- │
-            │ i64 ┆ i64 ┆ str │
-            ╞═════╪═════╪═════╡
-            │ 1   ┆ 6   ┆ a   │
-            │ 2   ┆ 7   ┆ b   │
-            │ 3   ┆ 8   ┆ c   │
-            └─────┴─────┴─────┘
         """
         return super().rename(mapping)
 

tests/test_series.py

@@ -0,0 +1,153 @@
+from __future__ import annotations
+
+from typing import Any
+
+import pandas as pd
+import polars as pl
+import pytest
+
+import narwhals as nw
+
+df_pandas = pd.DataFrame({"a": [1, 3, 2], "b": [4, 4, 6], "z": [7.0, 8, 9]})
+df_polars = pl.DataFrame({"a": [1, 3, 2], "b": [4, 4, 6], "z": [7.0, 8, 9]})
+df_lazy = pl.LazyFrame({"a": [1, 3, 2], "b": [4, 4, 6], "z": [7.0, 8, 9]})
+
+
+@pytest.mark.parametrize("df_raw", [df_pandas, df_lazy])
+def test_len(df_raw: Any) -> None:
+    result = len(nw.LazyFrame(df_raw).collect()["a"])
+    assert result == 3
+    result = len(nw.to_native(nw.LazyFrame(df_raw).collect()["a"]))
+    assert result == 3
+
+
+@pytest.mark.parametrize("df_raw", [df_pandas, df_lazy])
+def test_dtype(df_raw: Any) -> None:
+    result = nw.LazyFrame(df_raw).collect()["a"].dtype
+    assert result == nw.Int64
+    assert result.is_numeric()
+
+
+def test_dtypes() -> None:
+    df = pl.DataFrame(
+        {
+            "a": [1],
+            "b": [1],
+            "c": [1],
+            "d": [1],
+            "e": [1],
+            "f": [1],
+            "g": [1],
+            "h": [1],
+            "i": [1],
+            "j": [1],
+            "k": [1],
+            "l": [1],
+            "m": [True],
+        },
+        schema={
+            "a": pl.Int64,
+            "b": pl.Int32,
+            "c": pl.Int16,
+            "d": pl.Int8,
+            "e": pl.UInt64,
+            "f": pl.UInt32,
+            "g": pl.UInt16,
+            "h": pl.UInt8,
+            "i": pl.Float64,
+            "j": pl.Float32,
+            "k": pl.String,
+            "l": pl.Datetime,
+            "m": pl.Boolean,
+        },
+    )
+    result = nw.DataFrame(df).schema
+    expected = {
+        "a": nw.Int64,
+        "b": nw.Int32,
+        "c": nw.Int16,
+        "d": nw.Int8,
+        "e": nw.UInt64,
+        "f": nw.UInt32,
+        "g": nw.UInt16,
+        "h": nw.UInt8,
+        "i": nw.Float64,
+        "j": nw.Float32,
+        "k": nw.String,
+        "l": nw.Datetime,
+        "m": nw.Boolean,
+    }
+    assert result == expected
+    result_pd = nw.DataFrame(df.to_pandas()).schema
+    assert result_pd == expected
+
+
+def test_cast() -> None:
+    df = pl.DataFrame(
+        {
+            "a": [1],
+            "b": [1],
+            "c": [1],
+            "d": [1],
+            "e": [1],
+            "f": [1],
+            "g": [1],
+            "h": [1],
+            "i": [1],
+            "j": [1],
+            "k": [1],
+            "l": [1],
+            "m": [True],
+        },
+        schema={
+            "a": pl.Int64,
+            "b": pl.Int32,
+            "c": pl.Int16,
+            "d": pl.Int8,
+            "e": pl.UInt64,
+            "f": pl.UInt32,
+            "g": pl.UInt16,
+            "h": pl.UInt8,
+            "i": pl.Float64,
+            "j": pl.Float32,
+            "k": pl.String,
+            "l": pl.Datetime,
+            "m": pl.Boolean,
+        },
+    )
+    df = nw.DataFrame(df).select(  # type: ignore[assignment]
+        nw.col("a").cast(nw.Int32),
+        nw.col("b").cast(nw.Int16),
+        nw.col("c").cast(nw.Int8),
+        nw.col("d").cast(nw.Int64),
+        nw.col("e").cast(nw.UInt32),
+        nw.col("f").cast(nw.UInt16),
+        nw.col("g").cast(nw.UInt8),
+        nw.col("h").cast(nw.UInt64),
+        nw.col("i").cast(nw.Float32),
+        nw.col("j").cast(nw.Float64),
+        nw.col("k").cast(nw.String),
+        nw.col("l").cast(nw.Datetime),
+        nw.col("m").cast(nw.Int8),
+        n=nw.col("m").cast(nw.Boolean),
+    )
+    result = df.schema
+    expected = {
+        "a": nw.Int32,
+        "b": nw.Int16,
+        "c": nw.Int8,
+        "d": nw.Int64,
+        "e": nw.UInt32,
+        "f": nw.UInt16,
+        "g": nw.UInt8,
+        "h": nw.UInt64,
+        "i": nw.Float32,
+        "j": nw.Float64,
+        "k": nw.String,
+        "l": nw.Datetime,
+        "m": nw.Int8,
+        "n": nw.Boolean,
+    }
+    assert result == expected
+    result_pd = nw.from_native(df.to_pandas()).schema
+    assert result_pd == expected