dataframely 1.6.0__tar.gz → 1.7.1__tar.gz

{dataframely-1.6.0 → dataframely-1.7.1}/.github/workflows/build.yml

@@ -17,7 +17,7 @@ jobs:
         with:
           fetch-depth: 0
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@19eac09b398e3d0c747adc7921926a6d802df4da # v0.8.8
+        uses: prefix-dev/setup-pixi@14c8aabd75893f83f4ab30c03e7cf853c8208961 # v0.8.10
         with:
           environments: build
       - name: Set version
@@ -52,13 +52,13 @@ jobs:
         with:
           fetch-depth: 0
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@19eac09b398e3d0c747adc7921926a6d802df4da # v0.8.8
+        uses: prefix-dev/setup-pixi@14c8aabd75893f83f4ab30c03e7cf853c8208961 # v0.8.10
         with:
           environments: build
       - name: Set version
         run: pixi run -e build set-version
       - name: Build wheel
-        uses: PyO3/maturin-action@aef21716ff3dcae8a1c301d23ec3e4446972a6e3 # v1.49.1
+        uses: PyO3/maturin-action@e10f6c464b90acceb5f640d31beda6d586ba7b4a # v1.49.3
         with:
           command: build
           args: --out dist -i python3.11

{dataframely-1.6.0 → dataframely-1.7.1}/.github/workflows/chore.yml

@@ -28,7 +28,7 @@ jobs:
           GITHUB_TOKEN: ${{ github.token }}
       - name: Post comment about invalid PR title
         if: failure()
-        uses: marocchino/sticky-pull-request-comment@52423e01640425a022ef5fd42c6fb5f633a02728 # v2.9.1
+        uses: marocchino/sticky-pull-request-comment@d2ad0de260ae8b0235ce059e63f2949ba9e05943 # v2.9.3
         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@52423e01640425a022ef5fd42c6fb5f633a02728 # v2.9.1
+        uses: marocchino/sticky-pull-request-comment@d2ad0de260ae8b0235ce059e63f2949ba9e05943 # v2.9.3
         with:
           header: conventional-commit-pr-title
           delete: true

{dataframely-1.6.0 → dataframely-1.7.1}/.github/workflows/ci.yml

@@ -24,7 +24,7 @@ jobs:
           # needed for 'pre-commit-mirrors-insert-license'
           fetch-depth: 0
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@19eac09b398e3d0c747adc7921926a6d802df4da # v0.8.8
+        uses: prefix-dev/setup-pixi@14c8aabd75893f83f4ab30c03e7cf853c8208961 # v0.8.10
         with:
           environments: default lint
       - name: Install repository
@@ -45,7 +45,7 @@ jobs:
       - name: Checkout branch
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
       - name: Set up pixi
-        uses: prefix-dev/setup-pixi@19eac09b398e3d0c747adc7921926a6d802df4da # v0.8.8
+        uses: prefix-dev/setup-pixi@14c8aabd75893f83f4ab30c03e7cf853c8208961 # v0.8.10
         with:
           environments: ${{ matrix.environment }}
       - name: Install repository

dataframely-1.7.1/.github/workflows/nightly.yml

@@ -0,0 +1,36 @@
+name: Nightly CI
+on:
+  schedule:
+    - cron: "0 0 * * *" # Runs every day at midnight UTC
+  workflow_dispatch:
+
+# Automatically stop old builds on the same branch/PR
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: true
+
+permissions:
+  contents: read
+
+jobs:
+  unit-tests:
+    name: Unit Tests (${{ matrix.os == 'ubuntu-latest' && 'Linux' || 'Windows' }})
+    timeout-minutes: 30
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: true
+      matrix:
+        os: [ubuntu-latest, windows-latest]
+    steps:
+      - name: Checkout branch
+        uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
+      - name: Set up pixi
+        uses: prefix-dev/setup-pixi@14c8aabd75893f83f4ab30c03e7cf853c8208961 # v0.8.10
+        with:
+          environments: nightly
+      - name: Install polars nightly
+        run: pixi run -e nightly install-polars-nightly
+      - name: Install repository
+        run: pixi run -e nightly postinstall
+      - name: Run pytest
+        run: pixi run -e nightly test-coverage --color=yes

{dataframely-1.6.0 → dataframely-1.7.1}/.github/workflows/scorecard.yml

@@ -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@ff0a06e83cb2de871e5a09832bc6a81e7276941f # v3.28.18
+        uses: github/codeql-action/upload-sarif@181d5eefc20863364f96762470ba6f862bdef56b # v3.29.2
         with:
           sarif_file: results.sarif

{dataframely-1.6.0 → dataframely-1.7.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: dataframely
-Version: 1.6.0
+Version: 1.7.1
 Classifier: Programming Language :: Python :: 3
 Classifier: Programming Language :: Python :: 3.11
 Classifier: Programming Language :: Python :: 3.12
@@ -25,6 +25,7 @@ Project-URL: Repository, https://github.com/quantco/dataframely
   </h3>
 
 [![CI](https://img.shields.io/github/actions/workflow/status/quantco/dataframely/ci.yml?style=flat-square&branch=main)](https://github.com/quantco/dataframely/actions/workflows/ci.yml)
+[![Nightly CI](https://img.shields.io/github/actions/workflow/status/quantco/dataframely/nightly.yml?style=flat-square&branch=main)](https://github.com/quantco/dataframely/actions/workflows/nightly.yml)
 [![conda-forge](https://img.shields.io/conda/vn/conda-forge/dataframely?logoColor=white&logo=conda-forge&style=flat-square)](https://prefix.dev/channels/conda-forge/packages/dataframely)
 [![pypi-version](https://img.shields.io/pypi/v/dataframely.svg?logo=pypi&logoColor=white&style=flat-square)](https://pypi.org/project/dataframely)
 [![python-version](https://img.shields.io/pypi/pyversions/dataframely?logoColor=white&logo=python&style=flat-square)](https://pypi.org/project/dataframely)
@@ -68,7 +69,7 @@ class HouseSchema(dy.Schema):
     price = dy.Float64(nullable=False)
 
     @dy.rule()
-    def reasonable_bathroom_to_bedrooom_ratio() -> pl.Expr:
+    def reasonable_bathroom_to_bedroom_ratio() -> pl.Expr:
         ratio = pl.col("num_bathrooms") / pl.col("num_bedrooms")
         return (ratio >= 1 / 3) & (ratio <= 3)
 

{dataframely-1.6.0 → dataframely-1.7.1}/README.md

@@ -8,6 +8,7 @@
   </h3>
 
 [![CI](https://img.shields.io/github/actions/workflow/status/quantco/dataframely/ci.yml?style=flat-square&branch=main)](https://github.com/quantco/dataframely/actions/workflows/ci.yml)
+[![Nightly CI](https://img.shields.io/github/actions/workflow/status/quantco/dataframely/nightly.yml?style=flat-square&branch=main)](https://github.com/quantco/dataframely/actions/workflows/nightly.yml)
 [![conda-forge](https://img.shields.io/conda/vn/conda-forge/dataframely?logoColor=white&logo=conda-forge&style=flat-square)](https://prefix.dev/channels/conda-forge/packages/dataframely)
 [![pypi-version](https://img.shields.io/pypi/v/dataframely.svg?logo=pypi&logoColor=white&style=flat-square)](https://pypi.org/project/dataframely)
 [![python-version](https://img.shields.io/pypi/pyversions/dataframely?logoColor=white&logo=python&style=flat-square)](https://pypi.org/project/dataframely)
@@ -51,7 +52,7 @@ class HouseSchema(dy.Schema):
     price = dy.Float64(nullable=False)
 
     @dy.rule()
-    def reasonable_bathroom_to_bedrooom_ratio() -> pl.Expr:
+    def reasonable_bathroom_to_bedroom_ratio() -> pl.Expr:
         ratio = pl.col("num_bathrooms") / pl.col("num_bedrooms")
         return (ratio >= 1 / 3) & (ratio <= 3)
 

{dataframely-1.6.0 → dataframely-1.7.1}/dataframely/__init__.py

@@ -15,7 +15,7 @@ from ._base_collection import CollectionMember
 from ._filter import filter
 from ._rule import rule
 from ._typing import DataFrame, LazyFrame
-from .collection import Collection
+from .collection import Collection, deserialize_collection
 from .columns import (
     Any,
     Array,
@@ -51,7 +51,7 @@ from .functional import (
     filter_relationship_one_to_at_least_one,
     filter_relationship_one_to_one,
 )
-from .schema import Schema, deserialize_schema
+from .schema import Schema, deserialize_schema, read_parquet_metadata_schema
 
 __all__ = [
     "random",
@@ -61,6 +61,7 @@ __all__ = [
     "LazyFrame",
     "Collection",
     "CollectionMember",
+    "deserialize_collection",
     "Config",
     "FailureInfo",
     "concat_collection_members",
@@ -68,6 +69,7 @@ __all__ = [
     "filter_relationship_one_to_one",
     "Schema",
     "deserialize_schema",
+    "read_parquet_metadata_schema",
     "Any",
     "Bool",
     "Column",

{dataframely-1.6.0 → dataframely-1.7.1}/dataframely/_base_schema.py

@@ -171,7 +171,11 @@ class BaseSchema(metaclass=SchemaMeta):
     @classmethod
     def columns(cls) -> dict[str, Column]:
         """The column definitions of this schema."""
-        return getattr(cls, _COLUMN_ATTR)
+        columns: dict[str, Column] = getattr(cls, _COLUMN_ATTR)
+        for name in columns.keys():
+            # Dynamically set the name of the columns.
+            columns[name]._name = name
+        return columns
 
     @classmethod
     def primary_keys(cls) -> list[str]:

{dataframely-1.6.0 → dataframely-1.7.1}/dataframely/_serialization.py

@@ -1,6 +1,7 @@
 # Copyright (c) QuantCo 2025-2025
 # SPDX-License-Identifier: BSD-3-Clause
 
+import base64
 import datetime as dt
 import decimal
 from io import BytesIO
@@ -9,6 +10,20 @@ from typing import Any, cast
 
 import polars as pl
 
+SCHEMA_METADATA_KEY = "dataframely_schema"
+SERIALIZATION_FORMAT_VERSION = "1"
+
+
+def serialization_versions() -> dict[str, str]:
+    """Return the versions of the serialization format and the libraries used."""
+    from dataframely import __version__
+
+    return {
+        "format": SERIALIZATION_FORMAT_VERSION,
+        "dataframely": __version__,
+        "polars": pl.__version__,
+    }
+
 
 class SchemaJSONEncoder(JSONEncoder):
     """Custom JSON encoder to properly serialize all types serialized by schemas."""
@@ -32,6 +47,11 @@ class SchemaJSONEncoder(JSONEncoder):
                     "__type__": "expression",
                     "value": obj.meta.serialize(format="json"),
                 }
+            case pl.LazyFrame():
+                return {
+                    "__type__": "lazyframe",
+                    "value": base64.b64encode(obj.serialize()).decode("utf-8"),
+                }
             case decimal.Decimal():
                 return {"__type__": "decimal", "value": str(obj)}
             case dt.datetime():
@@ -68,6 +88,11 @@ class SchemaJSONDecoder(JSONDecoder):
             case "expression":
                 data = BytesIO(cast(str, dct["value"]).encode("utf-8"))
                 return pl.Expr.deserialize(data, format="json")
+            case "lazyframe":
+                data = BytesIO(
+                    base64.b64decode(cast(str, dct["value"]).encode("utf-8"))
+                )
+                return pl.LazyFrame.deserialize(data)
             case "decimal":
                 return decimal.Decimal(dct["value"])
             case "datetime":

{dataframely-1.6.0 → dataframely-1.7.1}/dataframely/_typing.py

@@ -4,7 +4,7 @@
 from __future__ import annotations
 
 from collections.abc import Callable
-from typing import TYPE_CHECKING, Any, Concatenate, Generic, ParamSpec, TypeVar
+from typing import TYPE_CHECKING, Any, Concatenate, Generic, Literal, ParamSpec, TypeVar
 
 import polars as pl
 
@@ -15,6 +15,8 @@ S = TypeVar("S", bound=BaseSchema, covariant=True)
 P = ParamSpec("P")
 R = TypeVar("R")
 
+Validation = Literal["allow", "forbid", "warn", "skip"]
+
 
 def inherit_signature(  # pragma: no cover
     target_fn: Callable[P, Any],