dataframely 1.3.1__tar.gz → 1.5.0__tar.gz

{dataframely-1.3.1 → dataframely-1.5.0}/.copier-answers.yml

@@ -1,5 +1,5 @@
 # This file is managed by Copier; DO NOT EDIT OR REMOVE.
-_commit: v0.3.0
+_commit: v0.4.1
 _src_path: https://github.com/quantco/copier-template-python-open-source
 add_autobump_workflow: false
 author_email: oliver.borchert@quantco.com

dataframely-1.5.0/.gitattributes

@@ -0,0 +1 @@
+pixi.lock merge=binary linguist-language=YAML linguist-generated=true

{dataframely-1.3.1 → dataframely-1.5.0}/.github/workflows/build.yml

@@ -10,6 +10,8 @@ jobs:
   build-sdist:
     name: Build Sdist
     runs-on: ubuntu-latest
+    permissions:
+      contents: read
     steps:
       - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:

{dataframely-1.3.1 → dataframely-1.5.0}/.github/workflows/chore.yml

@@ -21,14 +21,14 @@ jobs:
     steps:
       - name: Check valid conventional commit message
         id: lint
-        uses: amannn/action-semantic-pull-request@v5
+        uses: amannn/action-semantic-pull-request@0723387faaf9b38adef4775cd42cfd5155ed6017 # v5.5.3
         with:
           subjectPattern: ^[A-Z].+[^. ]$ # subject must start with uppercase letter and may not end with a dot/space
         env:
           GITHUB_TOKEN: ${{ github.token }}
       - name: Post comment about invalid PR title
         if: failure()
-        uses: marocchino/sticky-pull-request-comment@v2
+        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728 # v2.9.1
         with:
           header: conventional-commit-pr-title
           message: |
@@ -45,7 +45,7 @@ jobs:
             </details>
       - name: Delete comment about invalid PR title
         if: success()
-        uses: marocchino/sticky-pull-request-comment@v2
+        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728 # v2.9.1
         with:
           header: conventional-commit-pr-title
           delete: true
@@ -58,7 +58,7 @@ jobs:
       pull-requests: write
     steps:
       - name: ${{ github.event_name == 'pull_request_target' && 'Assign labels' || 'Update release draft' }}
-        uses: release-drafter/release-drafter@v6
+        uses: release-drafter/release-drafter@b1476f6e6eb133afa41ed8589daba6dc69b4d3f5 # v6.1.0
         with:
           disable-releaser: ${{ github.event_name == 'pull_request_target' }}
           disable-autolabeler: ${{ github.event_name == 'push' }}

{dataframely-1.3.1 → dataframely-1.5.0}/.github/workflows/ci.yml

@@ -9,6 +9,9 @@ concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
   cancel-in-progress: true
 
+permissions:
+  contents: read
+
 jobs:
   pre-commit-checks:
     name: Pre-commit Checks
@@ -40,7 +43,7 @@ jobs:
         environment: [py311, py312, py313]
     steps:
       - name: Checkout branch
-        uses: actions/checkout@v4
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Set up pixi
         uses: prefix-dev/setup-pixi@19eac09b398e3d0c747adc7921926a6d802df4da # v0.8.8
         with:
@@ -50,7 +53,7 @@ jobs:
       - name: Run pytest
         run: pixi run -e ${{ matrix.environment }} test-coverage --color=yes
       - name: Upload codecov
-        uses: codecov/codecov-action@v5
+        uses: codecov/codecov-action@18283e04ce6e62d37312384ff67231eb8fd56d24 # v5.4.3
         with:
           files: ./coverage.xml
           token: ${{ secrets.CODECOV_TOKEN }}

dataframely-1.5.0/.github/workflows/scorecard.yml

@@ -0,0 +1,79 @@
+# This workflow uses actions that are not certified by GitHub. They are provided
+# by a third-party and are governed by separate terms of service, privacy
+# policy, and support documentation.
+
+name: Scorecard supply-chain security
+on:
+  # For Branch-Protection check. Only the default branch is supported. See
+  # https://github.com/ossf/scorecard/blob/main/docs/checks.md#branch-protection
+  branch_protection_rule:
+  # To guarantee Maintained check is occasionally updated. See
+  # https://github.com/ossf/scorecard/blob/main/docs/checks.md#maintained
+  schedule:
+    - cron: "34 5 * * 0"
+  workflow_dispatch:
+  push:
+    branches: ["main"]
+
+# Declare default permissions as read only.
+permissions: read-all
+
+jobs:
+  analysis:
+    name: Scorecard analysis
+    runs-on: ubuntu-latest
+    # `publish_results: true` only works when run from the default branch. conditional can be removed if disabled.
+    if: (github.event.repository.default_branch == github.ref_name || github.event_name == 'pull_request') && github.repository == 'quantco/dataframely'
+    permissions:
+      # Needed to upload the results to code-scanning dashboard.
+      security-events: write
+      # Needed to publish results and get a badge (see publish_results below).
+      id-token: write
+      # Uncomment the permissions below if installing in a private repository.
+      # contents: read
+      # actions: read
+
+    steps:
+      - name: "Checkout code"
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+        with:
+          persist-credentials: false
+
+      - name: "Run analysis"
+        uses: ossf/scorecard-action@05b42c624433fc40578a4040d5cf5e36ddca8cde # v2.4.2
+        with:
+          results_file: results.sarif
+          results_format: sarif
+          # (Optional) "write" PAT token. Uncomment the `repo_token` line below if:
+          # - you want to enable the Branch-Protection check on a *public* repository, or
+          # - you are installing Scorecard on a *private* repository
+          # To create the PAT, follow the steps in https://github.com/ossf/scorecard-action?tab=readme-ov-file#authentication-with-fine-grained-pat-optional.
+          # repo_token: ${{ secrets.SCORECARD_TOKEN }}
+
+          # Public repositories:
+          #   - Publish results to OpenSSF REST API for easy access by consumers
+          #   - Allows the repository to include the Scorecard badge.
+          #   - See https://github.com/ossf/scorecard-action#publishing-results.
+          # For private repositories:
+          #   - `publish_results` will always be set to `false`, regardless
+          #     of the value entered here.
+          publish_results: true
+
+          # (Optional) Uncomment file_mode if you have a .gitattributes with files marked export-ignore
+          # file_mode: git
+
+      # 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@ea165f8d65b6e75b540449e92b4886f43607fa02 # v4.6.2
+        with:
+          name: SARIF file
+          path: results.sarif
+          retention-days: 5
+
+      # 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@ff0a06e83cb2de871e5a09832bc6a81e7276941f # v3.28.18
+        with:
+          sarif_file: results.sarif

{dataframely-1.3.1 → dataframely-1.5.0}/PKG-INFO

@@ -1,19 +1,19 @@
 Metadata-Version: 2.4
 Name: dataframely
-Version: 1.3.1
+Version: 1.5.0
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
 Classifier: Programming Language :: Python :: 3.13
 Requires-Dist: numpy
-Requires-Dist: polars>=1.12
+Requires-Dist: polars>=1.30
 License-File: LICENSE
 Summary: A declarative, polars-native data frame validation library
 Author-email: Andreas Albert <andreas.albert@quantco.com>, Daniel Elsner <daniel.elsner@quantco.com>, Oliver Borchert <oliver.borchert@quantco.com>
 Requires-Python: >=3.11
 Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
-Project-URL: Repository, https://github.com/quantco/dataframely
 Project-URL: Documentation, https://dataframely.readthedocs.io/
+Project-URL: Repository, https://github.com/quantco/dataframely
 
 <!-- LOGO -->
 <br />

dataframely-1.5.0/SECURITY.md

@@ -0,0 +1,7 @@
+# Reporting Security Issues
+
+We take security bugs in our projects seriously. We appreciate your efforts to responsibly disclose your findings, and will make every effort to acknowledge your contributions.
+
+To report a security issue, please use the GitHub Security Advisory ["Report a Vulnerability"](https://github.com/quantco/dataframely/security/advisories/new) tab.
+
+We will send a response indicating the next steps in handling your report. After the initial reply to your report, the security team will keep you informed of the progress towards a fix and full announcement, and may ask for additional information or guidance.

dataframely-1.5.0/dataframely/_deprecation.py

@@ -0,0 +1,39 @@
+# Copyright (c) QuantCo 2025-2025
+# SPDX-License-Identifier: BSD-3-Clause
+
+import os
+import warnings
+from collections.abc import Callable
+from functools import wraps
+
+TRUTHY_VALUES = ["1", "true"]
+
+
+def skip_if(env: str) -> Callable:
+    """Decorator to skip warnings based on environment variable.
+
+    If the environment variable is equivalent to any of TRUTHY_VALUES, the wrapped
+    function is skipped.
+    """
+
+    def decorator(fun: Callable) -> Callable:
+        @wraps(fun)
+        def wrapper() -> None:
+            if os.getenv(env, "").lower() in TRUTHY_VALUES:
+                return
+            fun()
+
+        return wrapper
+
+    return decorator
+
+
+@skip_if(env="DATAFRAMELY_NO_FUTURE_WARNINGS")
+def warn_nullable_default_change() -> None:
+    warnings.warn(
+        "The 'nullable' argument was not explicitly set. In a future release, "
+        "'nullable=False' will be the default if 'nullable' is not specified. "
+        "Explicitly set 'nullable=True' if you want your column to be nullable.",
+        FutureWarning,
+        stacklevel=4,
+    )

{dataframely-1.3.1 → dataframely-1.5.0}/dataframely/collection.py

@@ -1,12 +1,11 @@
 # Copyright (c) QuantCo 2025-2025
 # SPDX-License-Identifier: BSD-3-Clause
 
-import sys
 import warnings
 from abc import ABC
 from collections.abc import Mapping, Sequence
 from pathlib import Path
-from typing import Any, Generic, Self, TypeVar, cast
+from typing import Any, Self, cast
 
 import polars as pl
 import polars.exceptions as plexc
@@ -18,15 +17,8 @@ from ._polars import FrameType, join_all_inner, join_all_outer
 from .failure import FailureInfo
 from .random import Generator
 
-if sys.version_info >= (3, 13):
-    SamplingType = TypeVar(
-        "SamplingType", bound=Mapping[str, Any], default=Mapping[str, Any]
-    )
-else:  # pragma: no cover
-    SamplingType = TypeVar("SamplingType", bound=Mapping[str, Any])
 
-
-class Collection(BaseCollection, ABC, Generic[SamplingType]):
+class Collection(BaseCollection, ABC):
     """Base class for all collections of data frames with a predefined schema.
 
     A collection is comprised of a set of *members* which are collectively "consistent",
@@ -86,7 +78,7 @@ class Collection(BaseCollection, ABC, Generic[SamplingType]):
         cls,
         num_rows: int | None = None,
         *,
-        overrides: Sequence[SamplingType] | None = None,
+        overrides: Sequence[Mapping[str, Any]] | None = None,
         generator: Generator | None = None,
     ) -> Self:
         """Create a random sample from the members of this collection.
@@ -162,10 +154,11 @@ class Collection(BaseCollection, ABC, Generic[SamplingType]):
         samples = (
             overrides
             if overrides is not None
-            else [cast(SamplingType, {}) for _ in range(cast(int, num_rows))]
+            else [{} for _ in range(cast(int, num_rows))]
         )
         processed_samples = [
-            cls._preprocess_sample(sample, i, g) for i, sample in enumerate(samples)
+            cls._preprocess_sample(dict(sample.items()), i, g)
+            for i, sample in enumerate(samples)
         ]
 
         # 2) Ensure that all samples have primary keys assigned to ensure that we
@@ -234,8 +227,8 @@ class Collection(BaseCollection, ABC, Generic[SamplingType]):
 
     @classmethod
     def _preprocess_sample(
-        cls, sample: SamplingType, index: int, generator: Generator
-    ) -> SamplingType:
+        cls, sample: dict[str, Any], index: int, generator: Generator
+    ) -> dict[str, Any]:
         """Overridable method to preprocess a sample passed to :meth:`sample`.
 
         The purpose of this method is to (1) set the primary key columns to enable

{dataframely-1.3.1 → dataframely-1.5.0}/dataframely/columns/_base.py

@@ -4,12 +4,14 @@
 from __future__ import annotations
 
 from abc import ABC, abstractmethod
+from collections import Counter
 from collections.abc import Callable
 from typing import Any
 
 import polars as pl
 
 from dataframely._compat import pa, sa, sa_TypeEngine
+from dataframely._deprecation import warn_nullable_default_change
 from dataframely._polars import PolarsDataType
 from dataframely.random import Generator
 
@@ -28,19 +30,36 @@ class Column(ABC):
     def __init__(
         self,
         *,
-        nullable: bool = True,
+        nullable: bool | None = None,
         primary_key: bool = False,
-        check: Callable[[pl.Expr], pl.Expr] | None = None,
+        check: (
+            Callable[[pl.Expr], pl.Expr]
+            | list[Callable[[pl.Expr], pl.Expr]]
+            | dict[str, Callable[[pl.Expr], pl.Expr]]
+            | None
+        ) = None,
         alias: str | None = None,
         metadata: dict[str, Any] | None = None,
     ):
         """
         Args:
             nullable: Whether this column may contain null values.
+                Explicitly set `nullable=True` if you want your column to be nullable.
+                In a future release, `nullable=False` will be the default if `nullable`
+                is not specified.
             primary_key: Whether this column is part of the primary key of the schema.
                 If ``True``, ``nullable`` is automatically set to ``False``.
-            check: A custom check to run for this column. Must return a non-aggregated
-                boolean expression.
+            check: A custom rule or multiple rules to run for this column. This can be:
+                - A single callable that returns a non-aggregated boolean expression.
+                The name of the rule is derived from the callable name, or defaults to
+                "check" for lambdas.
+                - A list of callables, where each callable returns a non-aggregated
+                boolean expression. The name of the rule is derived from the callable
+                name, or defaults to "check" for lambdas. Where multiple rules result
+                in the same name, the suffix __i is appended to the name.
+                - A dictionary mapping rule names to callables, where each callable
+                returns a non-aggregated boolean expression.
+                All rule names provided here are given the prefix "check_".
             alias: An overwrite for this column's name which allows for using a column
                 name that is not a valid Python identifier. Especially note that setting
                 this option does _not_ allow to refer to the column with two different
@@ -48,6 +67,10 @@ class Column(ABC):
                 internally sets the alias to the column's name in the parent schema.
             metadata: A dictionary of metadata to attach to the column.
         """
+        if nullable is None:
+            warn_nullable_default_change()
+            nullable = True
+
         self.nullable = nullable and not primary_key
         self.primary_key = primary_key
         self.check = check
@@ -96,10 +119,59 @@ class Column(ABC):
         result = {}
         if not self.nullable:
             result["nullability"] = expr.is_not_null()
+
         if self.check is not None:
-            result["check"] = self.check(expr)
+            if isinstance(self.check, dict):
+                for rule_name, rule_callable in self.check.items():
+                    result[f"check__{rule_name}"] = rule_callable(expr)
+            else:
+                list_of_rules = (
+                    self.check if isinstance(self.check, list) else [self.check]
+                )
+                # Get unique names for rules from callables
+                rule_names = self._derive_check_rule_names(list_of_rules)
+                for rule_name, rule_callable in zip(rule_names, list_of_rules):
+                    result[rule_name] = rule_callable(expr)
+
         return result
 
+    def _derive_check_rule_names(
+        self, rules: list[Callable[[pl.Expr], pl.Expr]]
+    ) -> list[str]:
+        """Generate unique names for rule callables.
+
+        For callables with the same name, appends a suffix __i where i is the index
+        of occurrence (starting from 0), but only if there are duplicates.
+
+        Args:
+            rules: List of rule callables.
+
+        Returns:
+            List of unique names corresponding to the rule callables.
+        """
+        base_names = [
+            f"check__{rule.__name__}" if rule.__name__ != "<lambda>" else "check"
+            for rule in rules
+        ]
+
+        # Count occurrences using Counter
+        name_counts = Counter(base_names)
+
+        # Append suffixes to names that are duplicated
+        final_names = []
+        duplicate_counter: dict[str, int] = {
+            name: 0 for name in name_counts if name_counts[name] > 1
+        }
+        for name in base_names:
+            if name_counts[name] > 1:
+                postfix = duplicate_counter[name]
+                final_names.append(f"{name}__{postfix}")
+                duplicate_counter[name] += 1
+            else:
+                final_names.append(name)
+
+        return final_names
+
     # -------------------------------------- SQL ------------------------------------- #
 
     def sqlalchemy_column(self, name: str, dialect: sa.Dialect) -> sa.Column:

{dataframely-1.3.1 → dataframely-1.5.0}/dataframely/columns/any.py

@@ -25,14 +25,28 @@ class Any(Column):
     def __init__(
         self,
         *,
-        check: Callable[[pl.Expr], pl.Expr] | None = None,
+        check: (
+            Callable[[pl.Expr], pl.Expr]
+            | list[Callable[[pl.Expr], pl.Expr]]
+            | dict[str, Callable[[pl.Expr], pl.Expr]]
+            | None
+        ) = None,
         alias: str | None = None,
         metadata: dict[str, Any] | None = None,
     ):
         """
         Args:
-            check: A custom check to run for this column. Must return a non-aggregated
-                boolean expression.
+            check: A custom rule or multiple rules to run for this column. This can be:
+                - A single callable that returns a non-aggregated boolean expression.
+                The name of the rule is derived from the callable name, or defaults to
+                "check" for lambdas.
+                - A list of callables, where each callable returns a non-aggregated
+                boolean expression. The name of the rule is derived from the callable
+                name, or defaults to "check" for lambdas. Where multiple rules result
+                in the same name, the suffix __i is appended to the name.
+                - A dictionary mapping rule names to callables, where each callable
+                returns a non-aggregated boolean expression.
+                All rule names provided here are given the prefix "check_".
             alias: An overwrite for this column's name which allows for using a column
                 name that is not a valid Python identifier. Especially note that setting
                 this option does _not_ allow to refer to the column with two different

{dataframely-1.3.1 → dataframely-1.5.0}/dataframely/columns/array.py

@@ -28,7 +28,12 @@ class Array(Column):
         # polars doesn't yet support grouping by arrays,
         # see https://github.com/pola-rs/polars/issues/22574
         primary_key: Literal[False] = False,
-        check: Callable[[pl.Expr], pl.Expr] | None = None,
+        check: (
+            Callable[[pl.Expr], pl.Expr]
+            | list[Callable[[pl.Expr], pl.Expr]]
+            | dict[str, Callable[[pl.Expr], pl.Expr]]
+            | None
+        ) = None,
         alias: str | None = None,
         metadata: dict[str, Any] | None = None,
     ):
@@ -39,8 +44,17 @@ class Array(Column):
             nullable: Whether this column may contain null values.
             primary_key: Whether this column is part of the primary key of the schema.
                 Not yet supported for the Array type.
-            check: A custom check to run for this column. Must return a non-aggregated
-                boolean expression.
+            check: A custom rule or multiple rules to run for this column. This can be:
+                - A single callable that returns a non-aggregated boolean expression.
+                The name of the rule is derived from the callable name, or defaults to
+                "check" for lambdas.
+                - A list of callables, where each callable returns a non-aggregated
+                boolean expression. The name of the rule is derived from the callable
+                name, or defaults to "check" for lambdas. Where multiple rules result
+                in the same name, the suffix __i is appended to the name.
+                - A dictionary mapping rule names to callables, where each callable
+                returns a non-aggregated boolean expression.
+                All rule names provided here are given the prefix "check_".
             alias: An overwrite for this column's name which allows for using a column
                 name that is not a valid Python identifier. Especially note that setting
                 this option does _not_ allow to refer to the column with two different