feat: polars implementation of table (#744)

Closes #638
Closes #641
Closes #649
Closes #712

### Summary of Changes

Implement our table using polars as backend.

---------

Co-authored-by: megalinter-bot <[email protected]>

benchmarks/table/column_operations_polars.py

@@ -0,0 +1,50 @@
+from timeit import timeit
+
+from safeds.data.tabular.containers import ExperimentalTable
+
+from benchmarks.table.utils import create_synthetic_table_polars
+
+REPETITIONS = 10
+
+
+def _run_remove_columns_with_missing_values() -> None:
+    table.remove_columns_with_missing_values()._lazy_frame.collect()
+
+
+def _run_remove_non_numeric_columns() -> None:
+    table.remove_non_numeric_columns()._lazy_frame.collect()
+
+
+def _run_summarize_statistics() -> None:
+    table.summarize_statistics()._lazy_frame.collect()
+
+
+if __name__ == "__main__":
+    # Create a synthetic Table
+    table = create_synthetic_table_polars(100, 5000)
+
+    # Run the benchmarks
+    timings: dict[str, float] = {
+        "remove_columns_with_missing_values": timeit(
+            _run_remove_columns_with_missing_values,
+            number=REPETITIONS,
+        ),
+        "remove_non_numeric_columns": timeit(
+            _run_remove_non_numeric_columns,
+            number=REPETITIONS,
+        ),
+        "summarize_statistics": timeit(
+            _run_summarize_statistics,
+            number=REPETITIONS,
+        ),
+    }
+
+    # Print the timings
+    print(
+        ExperimentalTable(
+            {
+                "method": list(timings.keys()),
+                "timing": list(timings.values()),
+            }
+        )
+    )

benchmarks/table/row_operations_polars.py

@@ -1,6 +1,8 @@
 from timeit import timeit
 
-from safeds.data.tabular.containers import Table
+import polars as pl
+
+from safeds.data.tabular.containers import ExperimentalTable
 
 from benchmarks.table.utils import create_synthetic_table_polars
 
@@ -15,14 +17,18 @@ def _run_remove_rows_with_missing_values() -> None:
     table.remove_rows_with_missing_values()._lazy_frame.collect()
 
 
-# def _run_remove_rows_with_outliers() -> None:
-#     table.remove_rows_with_outliers()
+def _run_remove_rows_with_outliers() -> None:
+    table.remove_rows_with_outliers()
 
 
 def _run_remove_rows() -> None:
     table.remove_rows(lambda row: row.get_value("column_0") % 2 == 0)._lazy_frame.collect()
 
 
+def _run_remove_rows_by_column() -> None:
+    table.remove_rows_by_column("column_0", lambda cell: cell % 2 == 0)._lazy_frame.collect()
+
+
 def _run_shuffle_rows() -> None:
     table.shuffle_rows()._lazy_frame.collect()
 
@@ -63,14 +69,18 @@ def _run_transform_column() -> None:
             _run_remove_rows_with_missing_values,
             number=REPETITIONS,
         ),
-        # "remove_rows_with_outliers": timeit(
-        #     _run_remove_rows_with_outliers,
-        #     number=REPETITIONS,
-        # ),
+        "remove_rows_with_outliers": timeit(
+            _run_remove_rows_with_outliers,
+            number=REPETITIONS,
+        ),
         "remove_rows": timeit(
             _run_remove_rows,
             number=REPETITIONS,
         ),
+        "remove_rows_by_column": timeit(
+            _run_remove_rows_by_column,
+            number=REPETITIONS,
+        ),
         "shuffle_rows": timeit(
             _run_shuffle_rows,
             number=REPETITIONS,
@@ -98,11 +108,14 @@ def _run_transform_column() -> None:
     }
 
     # Print the timings
-    print(
-        Table(
-            {
-                "method": list(timings.keys()),
-                "timing": list(timings.values()),
-            }
+    with pl.Config(
+        tbl_rows=-1,
+    ):
+        print(
+            ExperimentalTable(
+                {
+                    "method": list(timings.keys()),
+                    "timing": list(timings.values()),
+                }
+            )
         )
-    )

benchmarks/table/utils/create_synthetic_table.py

@@ -10,7 +10,8 @@ def create_synthetic_table(
     min_value: int = 0,
     max_value: int = 1000,
 ) -> Table:
-    """Create a synthetic Table with random numerical data.
+    """
+    Create a synthetic Table with random numerical data.
 
     Parameters
     ----------

benchmarks/table/utils/create_synthetic_table_polars.py

@@ -10,7 +10,8 @@ def create_synthetic_table_polars(
     min_value: int = 0,
     max_value: int = 1000,
 ) -> ExperimentalTable:
-    """Create a synthetic Table with random numerical data.
+    """
+    Create a synthetic Table with random numerical data.
 
     Parameters
     ----------

pyproject.toml

@@ -20,7 +20,7 @@ matplotlib = "^3.6.3"
 openpyxl = "^3.1.2"
 pandas = "^2.0.0"
 pillow = ">=9.5,<11.0"
-polars = {extras = ["numpy", "pyarrow"], version = "^0.20.24"}
+polars = {extras = ["numpy", "pyarrow"], version = "^0.20.25"}
 scikit-learn = "^1.2.0"
 seaborn = "^0.13.0"
 statsmodels = "^0.14.1"

src/resources/from_json_file_2.json

@@ -0,0 +1,6 @@
+{
+    "columns": [
+        { "name": "a", "datatype": "Int64", "bit_settings": "", "values": [1, 2, 3] },
+        { "name": "b", "datatype": "Int64", "bit_settings": "", "values": [4, 5, 6] }
+    ]
+}

src/resources/to_json_file_2.json

@@ -0,0 +1,6 @@
+{
+    "columns": [
+        { "name": "a", "datatype": "Int64", "bit_settings": "", "values": [1, 2, 3] },
+        { "name": "b", "datatype": "Int64", "bit_settings": "", "values": [4, 5, 6] }
+    ]
+}

src/safeds/_config/__init__.py

@@ -5,17 +5,19 @@
 import apipkg
 
 if TYPE_CHECKING:
-    from ._device import _get_device, _init_default_device
+    from ._torch import _get_device, _init_default_device, _set_default_device
 
 apipkg.initpkg(
     __name__,
     {
-        "_get_device": "._device:_get_device",
-        "_init_default_device": "._device:_init_default_device",
+        "_get_device": "._torch:_get_device",
+        "_init_default_device": "._torch:_init_default_device",
+        "_set_default_device": "._torch:_set_default_device",
     },
 )
 
 __all__ = [
     "_get_device",
     "_init_default_device",
+    "_set_default_device",
 ]

src/safeds/_config/_polars.py

@@ -0,0 +1,17 @@
+from __future__ import annotations
+
+from typing import TYPE_CHECKING
+
+if TYPE_CHECKING:
+    import polars as pl
+
+
+def _get_polars_config() -> pl.Config:
+    import polars as pl
+
+    return pl.Config(
+        float_precision=5,
+        tbl_cell_numeric_alignment="RIGHT",
+        tbl_formatting="ASCII_FULL_CONDENSED",
+        tbl_hide_dataframe_shape=True,
+    )

src/safeds/_config/_device.py → src/safeds/_config/_torch.py

@@ -18,7 +18,7 @@ def _get_device() -> Device:
 def _init_default_device() -> None:
     import torch
 
-    global _default_device
+    global _default_device  # noqa: PLW0603
 
     if _default_device is None:
         _default_device = torch.device("cuda") if torch.cuda.is_available() else torch.device("cpu")
@@ -28,7 +28,7 @@ def _init_default_device() -> None:
 
 def _set_default_device(device: Device) -> None:
     # This changes all future tensors, but not any tensor that already exists
-    global _default_device
+    global _default_device  # noqa: PLW0603
 
     _default_device = device
     _init_default_device()

src/safeds/_utils/__init__.py

@@ -7,16 +7,22 @@
 if TYPE_CHECKING:
     from ._file_io import _check_and_normalize_file_path
     from ._hashing import _structural_hash
+    from ._plotting import _figure_to_image
+    from ._random import _get_random_seed
 
 apipkg.initpkg(
     __name__,
     {
         "_check_and_normalize_file_path": "._file_io:_check_and_normalize_file_path",
         "_structural_hash": "._hashing:_structural_hash",
+        "_figure_to_image": "._plotting:_figure_to_image",
+        "_get_random_seed": "._random:_get_random_seed",
     },
 )
 
 __all__ = [
     "_check_and_normalize_file_path",
     "_structural_hash",
+    "_figure_to_image",
+    "_get_random_seed",
 ]

src/safeds/_utils/_plotting.py

@@ -0,0 +1,32 @@
+from __future__ import annotations
+
+import io
+from typing import TYPE_CHECKING
+
+from safeds.data.image.containers import Image
+
+if TYPE_CHECKING:
+    import matplotlib.pyplot as plt
+
+
+def _figure_to_image(figure: plt.Figure) -> Image:
+    """
+    Store the figure as an image and closes it.
+
+    Parameters
+    ----------
+    figure:
+        The figure to store.
+
+    Returns
+    -------
+    image:
+        The figure as an image.
+    """
+    import matplotlib.pyplot as plt
+
+    buffer = io.BytesIO()
+    figure.savefig(buffer, format="png")
+    plt.close(figure)  # Prevents the figure from being displayed directly
+    buffer.seek(0)
+    return Image.from_bytes(buffer.read())

src/safeds/data/labeled/containers/__init__.py

@@ -5,20 +5,23 @@
 import apipkg
 
 if TYPE_CHECKING:
+    from ._experimental_tabular_dataset import ExperimentalTabularDataset
     from ._image_dataset import ImageDataset
     from ._tabular_dataset import TabularDataset
     from ._time_series_dataset import TimeSeriesDataset
 
 apipkg.initpkg(
     __name__,
     {
+        "ExperimentalTabularDataset": "._experimental_tabular_dataset:ExperimentalTabularDataset",
         "ImageDataset": "._image_dataset:ImageDataset",
         "TabularDataset": "._tabular_dataset:TabularDataset",
         "TimeSeriesDataset": "._time_series_dataset:TimeSeriesDataset",
     },
 )
 
 __all__ = [
+    "ExperimentalTabularDataset",
     "ImageDataset",
     "TabularDataset",
     "TimeSeriesDataset",