Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

add more coverage for dataframe #12

Merged
merged 3 commits into from
Mar 17, 2024
Merged

add more coverage for dataframe #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
abc7da1
add more coverage for dataframe
Mar 17, 2024
a62d082
Merge remote-tracking branch 'origin/main' into increase-coverage
MarcoGorelli Mar 17, 2024
0084729
add modin to requirements
MarcoGorelli Mar 17, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 3 additions & 0 deletions narwhals/pandas_like/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -99,13 +99,16 @@ def parse_into_expr(implementation: str, into_expr: IntoPandasExpr) -> PandasExp
from narwhals.expression import Expr
from narwhals.pandas_like.expr import PandasExpr
from narwhals.pandas_like.namespace import PandasNamespace
from narwhals.pandas_like.series import PandasSeries

plx = PandasNamespace(implementation=implementation)

if isinstance(into_expr, PandasExpr):
return into_expr
if isinstance(into_expr, Expr):
return into_expr._call(plx)
if isinstance(into_expr, PandasSeries):
return plx._create_expr_from_series(into_expr)
if isinstance(into_expr, str):
return plx.col(into_expr)
msg = f"Expected IntoExpr, got {type(into_expr)}"
Expand Down
6 changes: 6 additions & 0 deletions narwhals/series.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,3 +134,9 @@ def mean(self) -> Any:

def std(self) -> Any:
return self._series.std()

def __gt__(self, other: Any) -> Series:
return self._series.__gt__(self._extract_native(other)) # type: ignore[no-any-return]

def __lt__(self, other: Any) -> Series:
return self._series.__lt__(self._extract_native(other)) # type: ignore[no-any-return]
1 change: 1 addition & 0 deletions requirements-dev.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
covdefaults
modin[dask]
pandas
polars
pre-commit
Expand Down
62 changes: 51 additions & 11 deletions tests/test_common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,9 @@
from __future__ import annotations

import warnings
from typing import Any

import modin.pandas as mpd
import numpy as np
import pandas as pd
import polars as pl
Expand All @@ -13,6 +15,11 @@
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]})
with warnings.catch_warnings():
warnings.filterwarnings("ignore", category=UserWarning)
df_mpd = mpd.DataFrame(
pd.DataFrame({"a": [1, 3, 2], "b": [4, 4, 6], "z": [7.0, 8, 9]})
)


@pytest.mark.parametrize(
Expand All @@ -33,7 +40,7 @@ def test_sort(df_raw: Any) -> None:

@pytest.mark.parametrize(
"df_raw",
[df_pandas, df_polars, df_lazy],
[df_pandas, df_lazy],
)
def test_filter(df_raw: Any) -> None:
df = nw.LazyFrame(df_raw)
Expand All @@ -45,7 +52,19 @@ def test_filter(df_raw: Any) -> None:

@pytest.mark.parametrize(
"df_raw",
[df_pandas, df_polars, df_lazy],
[df_pandas],
)
def test_filter_series(df_raw: Any) -> None:
df = nw.DataFrame(df_raw)
result = df.filter(df["a"] > 1)
result_native = nw.to_native(result)
expected = {"a": [3, 2], "b": [4, 6], "z": [8.0, 9.0]}
compare_dicts(result_native, expected)


@pytest.mark.parametrize(
"df_raw",
[df_pandas, df_lazy],
)
def test_add(df_raw: Any) -> None:
df = nw.LazyFrame(df_raw)
Expand All @@ -66,7 +85,7 @@ def test_add(df_raw: Any) -> None:

@pytest.mark.parametrize(
"df_raw",
[df_pandas, df_polars, df_lazy],
[df_pandas, df_lazy],
)
def test_double(df_raw: Any) -> None:
df = nw.LazyFrame(df_raw)
Expand All @@ -76,7 +95,7 @@ def test_double(df_raw: Any) -> None:
compare_dicts(result_native, expected)


@pytest.mark.parametrize("df_raw", [df_pandas, df_polars, df_lazy])
@pytest.mark.parametrize("df_raw", [df_pandas, df_lazy])
def test_sumh(df_raw: Any) -> None:
df = nw.LazyFrame(df_raw)
result = df.with_columns(horizonal_sum=nw.sum_horizontal(nw.col("a"), nw.col("b")))
Expand All @@ -90,7 +109,7 @@ def test_sumh(df_raw: Any) -> None:
compare_dicts(result_native, expected)


@pytest.mark.parametrize("df_raw", [df_pandas, df_polars, df_lazy])
@pytest.mark.parametrize("df_raw", [df_pandas, df_lazy])
def test_sumh_literal(df_raw: Any) -> None:
df = nw.LazyFrame(df_raw)
result = df.with_columns(horizonal_sum=nw.sum_horizontal("a", nw.col("b")))
Expand All @@ -104,7 +123,7 @@ def test_sumh_literal(df_raw: Any) -> None:
compare_dicts(result_native, expected)


@pytest.mark.parametrize("df_raw", [df_pandas, df_polars, df_lazy])
@pytest.mark.parametrize("df_raw", [df_pandas, df_lazy])
def test_sum_all(df_raw: Any) -> None:
df = nw.LazyFrame(df_raw)
result = df.select(nw.all().sum())
Expand All @@ -113,7 +132,7 @@ def test_sum_all(df_raw: Any) -> None:
compare_dicts(result_native, expected)


@pytest.mark.parametrize("df_raw", [df_pandas, df_polars, df_lazy])
@pytest.mark.parametrize("df_raw", [df_pandas, df_lazy])
def test_double_selected(df_raw: Any) -> None:
df = nw.LazyFrame(df_raw)
result = df.select(nw.col("a", "b") * 2)
Expand All @@ -122,7 +141,7 @@ def test_double_selected(df_raw: Any) -> None:
compare_dicts(result_native, expected)


@pytest.mark.parametrize("df_raw", [df_pandas, df_polars, df_lazy])
@pytest.mark.parametrize("df_raw", [df_pandas, df_lazy])
def test_rename(df_raw: Any) -> None:
df = nw.LazyFrame(df_raw)
result = df.rename({"a": "x", "b": "y"})
Expand All @@ -131,7 +150,7 @@ def test_rename(df_raw: Any) -> None:
compare_dicts(result_native, expected)


@pytest.mark.parametrize("df_raw", [df_pandas, df_polars, df_lazy])
@pytest.mark.parametrize("df_raw", [df_pandas, df_lazy])
def test_join(df_raw: Any) -> None:
df = nw.LazyFrame(df_raw)
df_right = df.rename({"z": "z_right"})
Expand All @@ -141,15 +160,15 @@ def test_join(df_raw: Any) -> None:
compare_dicts(result_native, expected)


@pytest.mark.parametrize("df_raw", [df_pandas, df_polars, df_lazy])
@pytest.mark.parametrize("df_raw", [df_pandas, df_lazy])
def test_schema(df_raw: Any) -> None:
df = nw.LazyFrame(df_raw)
result = df.schema
expected = {"a": nw.dtypes.Int64, "b": nw.dtypes.Int64, "z": nw.dtypes.Float64}
assert result == expected


@pytest.mark.parametrize("df_raw", [df_pandas, df_polars, df_lazy])
@pytest.mark.parametrize("df_raw", [df_pandas, df_lazy])
def test_columns(df_raw: Any) -> None:
df = nw.LazyFrame(df_raw)
result = df.columns
Expand All @@ -158,8 +177,29 @@ def test_columns(df_raw: Any) -> None:
assert all(x == y for x, y in zip(result, expected))


@pytest.mark.parametrize("df_raw", [df_lazy])
def test_lazy_instantiation(df_raw: Any) -> None:
with pytest.raises(
TypeError, match="Can't instantiate DataFrame from Polars LazyFrame."
):
_ = nw.DataFrame(df_raw).shape


@pytest.mark.parametrize("df_raw", [df_polars, df_pandas, df_mpd])
def test_eager_instantiation(df_raw: Any) -> None:
result = nw.DataFrame(df_raw)
result_native = nw.to_native(result)
expected = {"a": [1, 3, 2], "b": [4, 4, 6], "z": [7.0, 8, 9]}
compare_dicts(result_native, expected)


def test_accepted_dataframes() -> None:
array = np.array([[0, 4.0], [2, 5]])
with pytest.raises(
TypeError,
match="Expected pandas-like dataframe, Polars dataframe, or Polars lazyframe, got: <class 'numpy.ndarray'>",
):
nw.DataFrame(array)
with pytest.raises(
TypeError,
match="Expected pandas-like dataframe, Polars dataframe, or Polars lazyframe, got: <class 'numpy.ndarray'>",
Expand Down
Loading