dataframely 2.3.1__tar.gz → 2.5.0__tar.gz

{dataframely-2.3.1 → dataframely-2.5.0}/.github/copilot-instructions.md

@@ -206,6 +206,29 @@ validated_df: dy.DataFrame[MySchema] = MySchema.validate(df, cast=True)
 4. **Documentation**: Update docstrings
 5. **API changes**: Ensure backward compatibility or document migration path
 
+### Pull request titles (required)
+
+Pull request titles must follow the Conventional Commits format: `<type>[!]: <Subject>`
+
+Allowed `type` values:
+
+- `feat`: A new feature
+- `fix`: A bug fix
+- `docs`: Documentation only changes
+- `style`: Changes that do not affect the meaning of the code (white-space, formatting, missing semi-colons, etc)
+- `refactor`: A code change that neither fixes a bug nor adds a feature
+- `perf`: A code change that improves performance
+- `test`: Adding missing tests or correcting existing tests
+- `build`: Changes that affect the build system or external dependencies
+- `ci`: Changes to our CI configuration files and scripts
+- `chore`: Other changes that don't modify src or test files
+- `revert`: Reverts a previous commit
+
+Additional rules:
+
+- Use `!` only for **breaking changes**
+- `Subject` must start with an **uppercase** letter and must **not** end with `.` or a trailing space
+
 ## Performance Considerations
 
 - Validation uses native polars expressions for performance

{dataframely-2.3.1 → dataframely-2.5.0}/.github/workflows/build.yml

@@ -13,11 +13,11 @@ jobs:
     permissions:
       contents: read
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
         with:
           fetch-depth: 0
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@28eb668aafebd9dede9d97c4ba1cd9989a4d0004 # v0.9.2
+        uses: prefix-dev/setup-pixi@82d477f15f3a381dbcc8adc1206ce643fe110fb7 # v0.9.3
         with:
           environments: build
       - name: Set version
@@ -25,7 +25,7 @@ jobs:
       - name: Build project
         run: pixi run -e build build-sdist
       - name: Upload package
-        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5.0.0
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0
         with:
           name: sdist
           path: dist/*
@@ -48,16 +48,16 @@ jobs:
           - target-platform: win-64
             os: windows-latest
     steps:
-      - uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+      - uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
         with:
           fetch-depth: 0
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@28eb668aafebd9dede9d97c4ba1cd9989a4d0004 # v0.9.2
+        uses: prefix-dev/setup-pixi@82d477f15f3a381dbcc8adc1206ce643fe110fb7 # v0.9.3
         with:
           environments: build
       - name: Set version
         run: pixi run -e build set-version
-      - uses: actions/setup-python@e797f83bcb11b83ae66e0230d6156d7c80228e7c # v6.0.0
+      - uses: actions/setup-python@83679a892e2d95755f2dac6acb0bfd1e9ac5d548 # v6.1.0
         with:
           python-version: "3.10"
       - name: Build wheel
@@ -70,7 +70,7 @@ jobs:
       - name: Check package
         run: pixi run -e build check-wheel
       - name: Upload package
-        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5.0.0
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0
         with:
           name: wheel-${{ matrix.target-platform }}
           path: dist/*
@@ -84,7 +84,7 @@ jobs:
       id-token: write
     environment: pypi
     steps:
-      - uses: actions/download-artifact@018cc2cf5baa6db3ef3c5f8a56943fffe632ef53 # v6.0.0
+      - uses: actions/download-artifact@37930b1c2abaa49bbe596cd826c3c89aef350131 # v7.0.0
         with:
           path: dist
           merge-multiple: true

{dataframely-2.3.1 → dataframely-2.5.0}/.github/workflows/ci.yml

@@ -19,18 +19,18 @@ jobs:
     runs-on: ubuntu-latest
     steps:
       - name: Checkout branch
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
         with:
           # needed for 'pre-commit-mirrors-insert-license'
           fetch-depth: 0
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@28eb668aafebd9dede9d97c4ba1cd9989a4d0004 # v0.9.2
+        uses: prefix-dev/setup-pixi@82d477f15f3a381dbcc8adc1206ce643fe110fb7 # v0.9.3
         with:
           environments: default lint
       - name: Install Rust
         run: rustup show
       - name: Cache Rust dependencies
-        uses: Swatinem/rust-cache@f13886b937689c021905a6b90929199931d60db1 # v2.8.1
+        uses: Swatinem/rust-cache@779680da715d629ac1d338a641029a2f4372abb5 # v2.8.2
       - name: pre-commit
         run: pixi run pre-commit-run --color=always --show-diff-on-failure
 
@@ -56,9 +56,9 @@ jobs:
             with_optionals: true
     steps:
       - name: Checkout branch
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@28eb668aafebd9dede9d97c4ba1cd9989a4d0004 # v0.9.2
+        uses: prefix-dev/setup-pixi@82d477f15f3a381dbcc8adc1206ce643fe110fb7 # v0.9.3
         with:
           environments: ${{ matrix.environment }}
           # FIXME: Remove when `s3_server` fixture does not start a process anymore
@@ -66,13 +66,13 @@ jobs:
       - name: Install Rust
         run: rustup show
       - name: Cache Rust dependencies
-        uses: Swatinem/rust-cache@f13886b937689c021905a6b90929199931d60db1 # v2.8.1
+        uses: Swatinem/rust-cache@779680da715d629ac1d338a641029a2f4372abb5 # v2.8.2
       - name: Install repository
         run: pixi run -e ${{ matrix.environment }} postinstall
       - name: Run pytest
         run: pixi run -e ${{ matrix.environment }} test-coverage --color=yes ${{ matrix.with_optionals && '-m with_optionals' || '-m "not with_optionals"'}} --cov=dataframely --cov-report=xml
       - name: Upload codecov
-        uses: codecov/codecov-action@5a1091511ad55cbe89839c7260b706298ca349f7 # v5.5.1
+        uses: codecov/codecov-action@671740ac38dd9b0130fbe1cec585b89eea48d3de # v5.5.2
         with:
           files: ./coverage.xml
           token: ${{ secrets.CODECOV_TOKEN }}

{dataframely-2.3.1 → dataframely-2.5.0}/.github/workflows/copilot-setup-steps.yml

@@ -13,14 +13,14 @@ jobs:
       id-token: write
     steps:
       - name: Checkout branch
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@28eb668aafebd9dede9d97c4ba1cd9989a4d0004 # v0.9.2
+        uses: prefix-dev/setup-pixi@82d477f15f3a381dbcc8adc1206ce643fe110fb7 # v0.9.3
         with:
           environments: default
       - name: Install Rust
         run: rustup show
       - name: Cache Rust dependencies
-        uses: Swatinem/rust-cache@f13886b937689c021905a6b90929199931d60db1 # v2.8.1
+        uses: Swatinem/rust-cache@779680da715d629ac1d338a641029a2f4372abb5 # v2.8.2
       - name: Install repository
         run: pixi run postinstall

{dataframely-2.3.1 → dataframely-2.5.0}/.github/workflows/nightly.yml

@@ -23,9 +23,9 @@ jobs:
         os: [ubuntu-latest, windows-latest]
     steps:
       - name: Checkout branch
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@28eb668aafebd9dede9d97c4ba1cd9989a4d0004 # v0.9.2
+        uses: prefix-dev/setup-pixi@82d477f15f3a381dbcc8adc1206ce643fe110fb7 # v0.9.3
         with:
           environments: nightly
       - name: Install polars nightly

{dataframely-2.3.1 → dataframely-2.5.0}/.github/workflows/scorecard.yml

@@ -35,7 +35,7 @@ jobs:
 
     steps:
       - name: "Checkout code"
-        uses: actions/checkout@08c6903cd8c0fde910a37f88322edcfb5dd907a8 # v5.0.0
+        uses: actions/checkout@8e8c483db84b4bee98b60c0593521ed34d9990e8 # v6.0.1
         with:
           persist-credentials: false
 
@@ -65,7 +65,7 @@ jobs:
       # Upload the results as artifacts (optional). Commenting out will disable uploads of run results in SARIF
       # format to the repository Actions tab.
       - name: "Upload artifact"
-        uses: actions/upload-artifact@330a01c490aca151604b8cf639adc76d48f6c5d4 # v5.0.0
+        uses: actions/upload-artifact@b7c566a772e6b6bfb58ed0dc250532a479d7789f # v6.0.0
         with:
           name: SARIF file
           path: results.sarif
@@ -74,6 +74,6 @@ jobs:
       # Upload the results to GitHub's code scanning dashboard (optional).
       # Commenting out will disable upload of results to your repo's Code Scanning dashboard
       - name: "Upload to code-scanning"
-        uses: github/codeql-action/upload-sarif@0499de31b99561a6d14a36a5f662c2a54f91beee # v3.29.5
+        uses: github/codeql-action/upload-sarif@5d4e8d1aca955e8d8589aabd499c5cae939e33c7 # v3.29.5
         with:
           sarif_file: results.sarif

{dataframely-2.3.1 → dataframely-2.5.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataframely
-Version: 2.3.1
+Version: 2.5.0
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.10
 Classifier: Programming Language :: Python :: 3.11

{dataframely-2.3.1 → dataframely-2.5.0}/dataframely/_base_schema.py

@@ -162,6 +162,19 @@ class SchemaMeta(ABCMeta):
                     f"Did you forget to add parentheses?"
                 )
 
+            # Check for pl.DataType instance or type (e.g., pl.String() or pl.String instead of dy.String())
+            if isinstance(value, pl.DataType) or (
+                isinstance(value, type) and issubclass(value, pl.DataType)
+            ):
+                value_type = "instance" if isinstance(value, pl.DataType) else "type"
+                example = (
+                    "pl.String()" if isinstance(value, pl.DataType) else "pl.String"
+                )
+                raise TypeError(
+                    f"Schema member '{attr}' is a polars DataType {value_type}. "
+                    f"Use dataframely column types (e.g., dy.String()) instead of polars types (e.g., {example})."
+                )
+
         return cls
 
     if not TYPE_CHECKING:

{dataframely-2.3.1 → dataframely-2.5.0}/dataframely/_compat.py

@@ -1,4 +1,4 @@
-# Copyright (c) QuantCo 2025-2025
+# Copyright (c) QuantCo 2025-2026
 # SPDX-License-Identifier: BSD-3-Clause
 
 
@@ -29,6 +29,7 @@ except ImportError:
 try:
     import sqlalchemy as sa
     import sqlalchemy.dialects.mssql as sa_mssql
+    import sqlalchemy.dialects.postgresql as sa_postgresql
     from sqlalchemy import Dialect
     from sqlalchemy.dialects.mssql.pyodbc import MSDialect_pyodbc
     from sqlalchemy.dialects.postgresql.psycopg2 import PGDialect_psycopg2
@@ -36,6 +37,7 @@ try:
 except ImportError:
     sa = _DummyModule("sqlalchemy")  # type: ignore
     sa_mssql = _DummyModule("sqlalchemy")  # type: ignore
+    sa_postgresql = _DummyModule("sqlalchemy")  # type: ignore
 
     class sa_TypeEngine:  # type: ignore # noqa: N801
         pass
@@ -81,6 +83,7 @@ __all__ = [
     "pydantic_core_schema",
     "pydantic",
     "sa_mssql",
+    "sa_postgresql",
     "sa_TypeEngine",
     "sa",
 ]

{dataframely-2.3.1 → dataframely-2.5.0}/dataframely/columns/array.py

@@ -1,4 +1,4 @@
-# Copyright (c) QuantCo 2025-2025
+# Copyright (c) QuantCo 2025-2026
 # SPDX-License-Identifier: BSD-3-Clause
 
 from __future__ import annotations
@@ -97,8 +97,17 @@ class Array(Column):
         }
 
     def sqlalchemy_dtype(self, dialect: sa.Dialect) -> sa_TypeEngine:
-        # NOTE: We might want to add support for PostgreSQL's ARRAY type or use JSON in the future.
-        raise NotImplementedError("SQL column cannot have 'Array' type.")
+        match dialect.name:
+            case "postgresql":
+                # Note that the length of the array in each dimension is not supported in SQLAlchemy
+                # That is because PostgreSQL does not enforce the length anyway
+                return sa.ARRAY(
+                    self.inner.sqlalchemy_dtype(dialect), dimensions=len(self.shape)
+                )
+            case _:
+                raise NotImplementedError(
+                    f"SQL column cannot have 'Array' type for dialect '{dialect}'."
+                )
 
     def _pyarrow_field_of_shape(self, shape: Sequence[int]) -> pa.Field:
         if shape:

{dataframely-2.3.1 → dataframely-2.5.0}/dataframely/columns/binary.py

@@ -1,4 +1,4 @@
-# Copyright (c) QuantCo 2025-2025
+# Copyright (c) QuantCo 2025-2026
 # SPDX-License-Identifier: BSD-3-Clause
 
 from __future__ import annotations
@@ -21,9 +21,11 @@ class Binary(Column):
         return pl.Binary()
 
     def sqlalchemy_dtype(self, dialect: sa.Dialect) -> sa_TypeEngine:
-        if dialect.name == "mssql":
-            return sa.VARBINARY()
-        return sa.LargeBinary()
+        match dialect.name:
+            case "mssql":
+                return sa.VARBINARY()
+            case _:
+                return sa.LargeBinary()
 
     @property
     def pyarrow_dtype(self) -> pa.DataType:

{dataframely-2.3.1 → dataframely-2.5.0}/dataframely/columns/decimal.py

@@ -98,7 +98,11 @@ class Decimal(OrdinalMixin[decimal.Decimal], Column):
         return pl.Decimal(self.precision, self.scale)
 
     def validate_dtype(self, dtype: PolarsDataType) -> bool:
-        return dtype.is_decimal()
+        return (
+            isinstance(dtype, pl.Decimal)
+            and dtype.scale == self.scale
+            and (self.precision is None or dtype.precision == self.precision)
+        )
 
     def sqlalchemy_dtype(self, dialect: sa.Dialect) -> sa_TypeEngine:
         if self.scale and not self.precision:

{dataframely-2.3.1 → dataframely-2.5.0}/dataframely/columns/list.py

@@ -1,4 +1,4 @@
-# Copyright (c) QuantCo 2025-2025
+# Copyright (c) QuantCo 2025-2026
 # SPDX-License-Identifier: BSD-3-Clause
 
 from __future__ import annotations
@@ -120,8 +120,13 @@ class List(Column):
         }
 
     def sqlalchemy_dtype(self, dialect: sa.Dialect) -> sa_TypeEngine:
-        # NOTE: We might want to add support for PostgreSQL's ARRAY type or use JSON in the future.
-        raise NotImplementedError("SQL column cannot have 'List' type.")
+        match dialect.name:
+            case "postgresql":
+                return sa.ARRAY(self.inner.sqlalchemy_dtype(dialect))
+            case _:
+                raise NotImplementedError(
+                    f"SQL column cannot have 'List' type for dialect '{dialect}'."
+                )
 
     @property
     def pyarrow_dtype(self) -> pa.DataType:
@@ -131,9 +136,12 @@ class List(Column):
     def _sample_unchecked(self, generator: Generator, n: int) -> pl.Series:
         # First, sample the number of items per list element
         # NOTE: We default to 32 for the upper bound as we need some kind of reasonable
-        #  upper bound if none is set.
+        #  upper bound if none is set. If min_length is greater than 32, we use
+        #  min_length as the default upper bound instead.
+        min_len = self.min_length or 0
+        default_max = max(32, min_len)
         element_lengths = generator.sample_int(
-            n, min=self.min_length or 0, max=(self.max_length or 32) + 1
+            n, min=min_len, max=(self.max_length or default_max) + 1
         )
 
         # Then, we can sample the inner elements in a flat series

{dataframely-2.3.1 → dataframely-2.5.0}/dataframely/columns/string.py

@@ -14,6 +14,8 @@ from dataframely.random import Generator
 from ._base import Check, Column
 from ._registry import register
 
+DEFAULT_SAMPLING_REGEX = r"[0-9a-zA-Z]"
+
 
 @register
 class String(Column):
@@ -126,9 +128,9 @@ class String(Column):
             str_max = f"{self.max_length}" if self.max_length is not None else ""
             # NOTE: We generate single-byte unicode characters here as validation uses
             #  `len_bytes()`. Potentially we need to be more accurate at some point...
-            regex = f"[\x01-\x7a]{{{str_min},{str_max}}}"
+            regex = f"{DEFAULT_SAMPLING_REGEX}{{{str_min},{str_max}}}"
         else:
-            regex = r"[\x01-\x7a]*"
+            regex = rf"{DEFAULT_SAMPLING_REGEX}*"
 
         return generator.sample_string(
             n,

{dataframely-2.3.1 → dataframely-2.5.0}/dataframely/columns/struct.py

@@ -1,4 +1,4 @@
-# Copyright (c) QuantCo 2025-2025
+# Copyright (c) QuantCo 2025-2026
 # SPDX-License-Identifier: BSD-3-Clause
 
 from __future__ import annotations
@@ -8,7 +8,7 @@ from typing import Any, cast
 
 import polars as pl
 
-from dataframely._compat import pa, sa, sa_TypeEngine
+from dataframely._compat import pa, sa, sa_postgresql, sa_TypeEngine
 from dataframely._polars import PolarsDataType
 from dataframely.random import Generator
 
@@ -107,8 +107,11 @@ class Struct(Column):
         }
 
     def sqlalchemy_dtype(self, dialect: sa.Dialect) -> sa_TypeEngine:
-        # NOTE: We might want to add support for PostgreSQL's JSON in the future.
-        raise NotImplementedError("SQL column cannot have 'Struct' type.")
+        match dialect.name:
+            case "postgresql":
+                return sa_postgresql.JSONB()
+            case _:
+                raise NotImplementedError("SQL column cannot have 'Struct' type.")
 
     @property
     def pyarrow_dtype(self) -> pa.DataType:

{dataframely-2.3.1 → dataframely-2.5.0}/dataframely/schema.py

@@ -7,7 +7,7 @@ import json
 import sys
 import warnings
 from abc import ABC
-from collections.abc import Iterable, Mapping, Sequence
+from collections.abc import Mapping, Sequence
 from json import JSONDecodeError
 from pathlib import Path
 from typing import IO, Any, Literal, overload
@@ -177,7 +177,7 @@ class Schema(BaseSchema, ABC):
         num_rows: int | None = None,
         *,
         overrides: (
-            Mapping[str, Iterable[Any]] | Sequence[Mapping[str, Any]] | None
+            Mapping[str, Sequence[Any] | Any] | Sequence[Mapping[str, Any]] | None
         ) = None,
         generator: Generator | None = None,
     ) -> DataFrame[Self]:
@@ -234,26 +234,22 @@ class Schema(BaseSchema, ABC):
         g = generator or Generator()
 
         # Precondition: valid overrides. We put them into a data frame to remember which
-        # values have been used in the algorithm below.
-        if overrides:
+        # values have been used in the algorithm below. When the user passes a sequence
+        # of mappings, they do not require to have the same keys. Hence, we have to
+        # remember that the data frame has "holes".
+        missing_override_indices: dict[str, pl.Series] = {}
+        if overrides is not None:
             override_keys = (
-                set(overrides) if isinstance(overrides, Mapping) else set(overrides[0])
+                set(overrides)
+                if isinstance(overrides, Mapping)
+                else (
+                    set.union(*[set(o.keys()) for o in overrides])
+                    if len(overrides) > 0
+                    else set()
+                )
             )
-            if isinstance(overrides, Sequence):
-                # Check that overrides entries are consistent. Not necessary for mapping
-                # overrides as polars checks the series lists upon data frame construction.
-                inconsistent_override_keys = [
-                    index
-                    for index, current in enumerate(overrides)
-                    if set(current) != override_keys
-                ]
-                if len(inconsistent_override_keys) > 0:
-                    raise ValueError(
-                        "The `overrides` entries at the following indices "
-                        "do not provide the same keys as the first entry: "
-                        f"{inconsistent_override_keys}."
-                    )
 
+            # Check that all override keys refer to valid columns
             column_names = set(cls.column_names())
             if not override_keys.issubset(column_names):
                 raise ValueError(
@@ -261,6 +257,19 @@ class Schema(BaseSchema, ABC):
                     "which are not in the schema."
                 )
 
+            # Remember the "holes" of the inputs if overrides are provided as a sequence
+            if isinstance(overrides, Sequence):
+                for key in override_keys:
+                    indices = [
+                        i for i, override in enumerate(overrides) if key not in override
+                    ]
+                    if len(indices) > 0:
+                        missing_override_indices[key] = pl.Series(indices)
+
+            # NOTE: Even if the user-provided overrides have "holes", we can still just
+            #  create the data frame. Polars will fill the missing values with nulls, we
+            #  will replace them later during sampling. If we were to already replace
+            #  them here, we would not be able to resample these values.
             values = pl.DataFrame(
                 overrides,
                 schema={
@@ -323,6 +332,7 @@ class Schema(BaseSchema, ABC):
             used_values=values.slice(0, 0),
             remaining_values=values,
             override_expressions=override_expressions,
+            missing_value_indices=missing_override_indices,
         )
 
         sampling_rounds = 1
@@ -360,6 +370,7 @@ class Schema(BaseSchema, ABC):
                 used_values=used_values,
                 remaining_values=remaining_values,
                 override_expressions=override_expressions,
+                missing_value_indices=missing_override_indices,
             )
             sampling_rounds += 1
 
@@ -388,6 +399,7 @@ class Schema(BaseSchema, ABC):
         used_values: pl.DataFrame,
         remaining_values: pl.DataFrame,
         override_expressions: list[pl.Expr],
+        missing_value_indices: dict[str, pl.Series],
     ) -> tuple[pl.DataFrame, pl.DataFrame, pl.DataFrame]:
         """Private method to sample a data frame with the schema including subsequent
         filtering.
@@ -406,6 +418,33 @@ class Schema(BaseSchema, ABC):
             }
         )
 
+        # If we have missing value indices, we need to sample new values for the
+        # indices that overlap with indices in the remaining values and replace them
+        # in the sampled data frame.
+        for name, indices in missing_value_indices.items():
+            remapped_indices = (
+                indices.to_frame("idx")
+                .join(
+                    remaining_values.select("__row_index__").with_row_index(
+                        "__row_index_loop__"
+                    ),
+                    left_on="idx",
+                    right_on="__row_index__",
+                )
+                .select("__row_index_loop__")
+                .to_series()
+            )
+            if (num := len(remapped_indices)) > 0:
+                sampled_values = cls.columns()[name].sample(generator, num)
+                sampled = sampled.with_columns(
+                    sampled[name]
+                    # NOTE: We need to sort here as `scatter` requires sorted indices.
+                    #  Due to concatenations in `remaining_values`, the indices can go
+                    #  out of order.
+                    .scatter(remapped_indices.sort(), sampled_values)
+                    .alias(name)
+                )
+
         combined_dataframe = pl.concat([previous_result, sampled])
         # Pre-process columns before filtering.
         combined_dataframe = combined_dataframe.with_columns(override_expressions)