featuresmith-core 0.1.0__tar.gz

featuresmith_core-0.1.0/LICENSE

@@ -0,0 +1,187 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship made available under
+      the License, as indicated by a copyright notice that is included in
+      or attached to the work (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean, as defined by Sections 2(b), any work of
+      authorship, including the original version of the Work and any
+      modifications or additions to that Work or Derivative Works of the Work,
+      that is intentionally submitted to the Licensor for inclusion in the Work
+      by the copyright owner or by an individual or Legal Entity authorized to
+      submit on behalf of the copyright owner. For the purposes of this
+      definition, "submitted" means any form of electronic, verbal, or written
+      communication sent to the Licensor or its representatives, including but
+      not limited to communication on electronic mailing lists, source code
+      control systems, and issue tracking systems that are managed by, or on
+      behalf of, the Licensor for the purpose of discussing and improving the
+      Work, but excluding communication that is conspicuously marked or
+      otherwise designated in writing by the copyright owner as "Not a
+      Contribution."
+
+      "Contributor" shall mean Licensor and any Legal Entity on behalf of
+      whom a Contribution has been received by the Licensor and subsequently
+      incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or Derivative
+          Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, You must include a readable copy of the
+          attribution notices contained within such NOTICE file, in
+          at least one of the following places: within a NOTICE text
+          file distributed as part of the Derivative Works; within
+          the Source form or documentation, if provided along with the
+          Derivative Works; or, within a display generated by the
+          Derivative Works, if and wherever such third-party notices
+          normally appear. The contents of the NOTICE file are for
+          informational purposes only and do not modify the License.
+          You may add Your own attribution notices within Derivative
+          Works that You distribute, alongside or as an addendum to
+          the NOTICE text from the Work, provided that such additional
+          attribution notices cannot be construed as modifying the
+          License.
+
+      You may add Your own license statement for Your modifications and
+      may provide additional grant of rights to use, copy, modify, merge,
+      publish, distribute, sublicense, and/or sell copies of the
+      Contribution, either on its own or as part of the Work.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or exemplary damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or all other
+      commercial damages or losses), even if such Contributor has been
+      advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   Copyright 2026 Featuresmith Contributors
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

featuresmith_core-0.1.0/PKG-INFO

@@ -0,0 +1,50 @@
+Metadata-Version: 2.4
+Name: featuresmith-core
+Version: 0.1.0
+Summary: Deterministic tabular data profiling and quality-rule engine.
+Author: Featuresmith contributors
+Maintainer: Featuresmith contributors
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/adityagangwani30/FeatureSmith
+Project-URL: Documentation, https://featuresmith.adityagangwani.me
+Project-URL: Repository, https://github.com/adityagangwani30/FeatureSmith
+Project-URL: Issues, https://github.com/adityagangwani30/FeatureSmith/issues
+Project-URL: Changelog, https://github.com/adityagangwani30/FeatureSmith/blob/main/CHANGELOG.md
+Keywords: data-quality,feature-engineering,profiling,tabular-data
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Typing :: Typed
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: openpyxl~=3.1
+Requires-Dist: pandas~=2.2
+Requires-Dist: polars~=1.30
+Dynamic: license-file
+
+# featuresmith-core
+
+`featuresmith-core` is the public Python SDK and deterministic analysis engine for Featuresmith.
+
+It provides:
+
+- `featuresmith.load()` for local CSV, Excel, Parquet, pandas, and Polars sources.
+- `featuresmith.profile()` for reproducible tabular profiling.
+- `featuresmith.analyze()` for data quality and leakage rule findings.
+- Typed, serializable result dataclasses and a PEP 561 `py.typed` marker.
+
+Install featuresmith-core directly from PyPI:
+
+```bash
+pip install featuresmith-core
+```
+
+For comprehensive guides and API reference, visit the official website:
+<https://featuresmith.adityagangwani.me>

featuresmith_core-0.1.0/README.md

@@ -0,0 +1,19 @@
+# featuresmith-core
+
+`featuresmith-core` is the public Python SDK and deterministic analysis engine for Featuresmith.
+
+It provides:
+
+- `featuresmith.load()` for local CSV, Excel, Parquet, pandas, and Polars sources.
+- `featuresmith.profile()` for reproducible tabular profiling.
+- `featuresmith.analyze()` for data quality and leakage rule findings.
+- Typed, serializable result dataclasses and a PEP 561 `py.typed` marker.
+
+Install featuresmith-core directly from PyPI:
+
+```bash
+pip install featuresmith-core
+```
+
+For comprehensive guides and API reference, visit the official website:
+<https://featuresmith.adityagangwani.me>

featuresmith_core-0.1.0/pyproject.toml

@@ -0,0 +1,58 @@
+[build-system]
+requires = ["setuptools>=77", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "featuresmith-core"
+version = "0.1.0"
+description = "Deterministic tabular data profiling and quality-rule engine."
+readme = "README.md"
+license = "Apache-2.0"
+license-files = ["LICENSE"]
+authors = [
+  { name = "Featuresmith contributors" },
+]
+maintainers = [
+  { name = "Featuresmith contributors" },
+]
+requires-python = ">=3.11"
+keywords = [
+  "data-quality",
+  "feature-engineering",
+  "profiling",
+  "tabular-data",
+]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Intended Audience :: Developers",
+  "Intended Audience :: Science/Research",
+  "Programming Language :: Python :: 3",
+  "Programming Language :: Python :: 3.11",
+  "Programming Language :: Python :: 3.12",
+  "Programming Language :: Python :: 3.13",
+  "Programming Language :: Python :: 3 :: Only",
+  "Topic :: Scientific/Engineering :: Information Analysis",
+  "Typing :: Typed",
+]
+dependencies = [
+  "openpyxl~=3.1",
+  "pandas~=2.2",
+  "polars~=1.30",
+]
+
+[project.urls]
+Homepage = "https://github.com/adityagangwani30/FeatureSmith"
+Documentation = "https://featuresmith.adityagangwani.me"
+Repository = "https://github.com/adityagangwani30/FeatureSmith"
+Issues = "https://github.com/adityagangwani30/FeatureSmith/issues"
+Changelog = "https://github.com/adityagangwani30/FeatureSmith/blob/main/CHANGELOG.md"
+
+[tool.setuptools]
+package-dir = {"" = "src"}
+
+[tool.setuptools.package-data]
+featuresmith = ["py.typed"]
+
+[tool.setuptools.packages.find]
+where = ["src"]
+include = ["featuresmith*"]

featuresmith_core-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

featuresmith_core-0.1.0/src/featuresmith/__init__.py

@@ -0,0 +1,7 @@
+"""Featuresmith core package."""
+
+from featuresmith.api import analyze, load, profile
+
+__version__ = "0.1.0"
+
+__all__ = ["analyze", "load", "profile"]

featuresmith_core-0.1.0/src/featuresmith/api.py

@@ -0,0 +1,180 @@
+"""Public SDK entry module for Featuresmith."""
+
+from __future__ import annotations
+
+from typing import Any
+
+from featuresmith.connectors.registry import default_registry
+from featuresmith.core.dataset import Dataset as Dataset
+from featuresmith.core.exceptions import (
+    ConnectorError as ConnectorError,
+)
+from featuresmith.core.exceptions import (
+    SourceNotFoundError as SourceNotFoundError,
+)
+from featuresmith.core.exceptions import (
+    SourceParseError as SourceParseError,
+)
+from featuresmith.core.exceptions import (
+    UnsupportedFormatError as UnsupportedFormatError,
+)
+from featuresmith.core.profile_result import ProfileResult as ProfileResult
+from featuresmith.core.rule_result import RuleResult as RuleResult
+from featuresmith.profiling import profile_dataset
+
+
+def load(source: object) -> Dataset:
+    """Load a supported tabular source into a normalized Dataset.
+
+    Args:
+        source: The data source to load. This can be a string representing a
+            local file path (CSV, Excel, Parquet), or an in-memory pandas
+            DataFrame or Polars DataFrame.
+
+    Returns:
+        Dataset: A normalized view of the loaded tabular dataset, containing
+            the dataframe backend, schema, dtypes, and metadata.
+
+    Raises:
+        ConnectorError: If the source is missing, has an unsupported format,
+            is corrupted, or is of an invalid type.
+
+    Notes:
+        For file paths, Featuresmith utilizes Polars for CSV and Parquet formats
+        by default, and pandas for Excel formats. In-memory dataframes are
+        wrapped without copying the underlying memory.
+
+    Examples:
+        >>> import pandas as pd
+        >>> import featuresmith as fs
+        >>> df = pd.DataFrame({"a": [1, 2, 3]})
+        >>> dataset = fs.load(df)
+        >>> dataset.row_count
+        3
+    """
+    return default_registry().load(source)
+
+
+def profile(
+    source: object,
+    *,
+    max_correlation_columns: int = 100,
+    max_frequency_table_size: int = 1000,
+) -> ProfileResult:
+    """Profile a supported source or Dataset and compute statistical summaries.
+
+    Args:
+        source: The data source to profile. This can be a pre-loaded Dataset
+            object, a string representing a local file path (CSV, Excel,
+            Parquet), or an in-memory pandas or Polars DataFrame.
+        max_correlation_columns: Limit correlation computations to prevent
+            combinatorial blowup (default 100).
+        max_frequency_table_size: Maximum entries to keep in categorical
+            frequency tables (default 1000).
+
+    Returns:
+        ProfileResult: A strongly-typed statistical profile containing dataset
+            summaries, column profiles, correlations, and logical types.
+
+    Raises:
+        ConnectorError: If the source is a file path or dataframe that fails to
+            load before profiling.
+
+    Notes:
+        This is a deterministic profiling engine. The statistical calculations
+        run on the underlying dataframe backend using vectorized Polars or pandas
+        APIs. The resulting ProfileResult is frozen and fully serializable.
+
+    Examples:
+        >>> import polars as pl
+        >>> import featuresmith as fs
+        >>> df = pl.DataFrame({"a": [1.0, 2.0, None]})
+        >>> prof = fs.profile(df)
+        >>> prof.dataset_summary.column_count
+        1
+        >>> prof.column_profiles["a"].missing_count
+        1
+    """
+    if isinstance(source, Dataset):
+        dataset = source
+    else:
+        dataset = load(source)
+    return profile_dataset(
+        dataset,
+        max_correlation_columns=max_correlation_columns,
+        max_frequency_table_size=max_frequency_table_size,
+    )
+
+
+def analyze(
+    source: object,
+    *,
+    target_column: str | None = None,
+    enabled_rules: list[str] | None = None,
+    rule_config: dict[str, Any] | None = None,
+    max_correlation_columns: int = 100,
+    max_frequency_table_size: int = 1000,
+) -> RuleResult:
+    """Analyze a tabular source or Dataset, computing profile stats and running rules.
+
+    Args:
+        source: The data source to analyze. This can be a pre-loaded Dataset
+            object, a string representing a local file path (CSV, Excel,
+            Parquet), or an in-memory pandas or Polars DataFrame.
+        target_column: Optional name of the target column in the dataset, used
+            specifically for evaluating potential target leakage.
+        enabled_rules: Optional list of rule IDs to execute. If not provided,
+            the engine runs all rules that are enabled by default.
+        rule_config: Optional dictionary of configurations keyed by rule ID.
+            For example, `{"quality.missing_value_threshold": {"threshold": 15.0}}`.
+        max_correlation_columns: Limit correlation computations during profiling to
+            prevent combinatorial blowup (default 100).
+        max_frequency_table_size: Maximum entries to keep in categorical
+            frequency tables (default 1000).
+
+    Returns:
+        RuleResult: The canonical output of the Rule Engine containing the
+            computed ProfileResult, aggregated list of RuleFindings, list of
+            executed rule IDs, and execution time metadata.
+
+    Raises:
+        ConnectorError: If the source is a file path or dataframe that fails to
+            load before profiling.
+
+    Notes:
+        This function integrates connector loading, profiling, and rule
+        evaluation into a single public endpoint. The evaluation of rules is
+        deterministic and isolated; a crash in any single rule does not cause
+        the function to fail, but is recorded in the failed_rules mapping.
+
+    Examples:
+        >>> import pandas as pd
+        >>> import featuresmith as fs
+        >>> df = pd.DataFrame({
+        ...     "x": [1, 2, 3, 4, 5],
+        ...     "y": [1.0, 2.0, 3.0, 4.0, 5.0],
+        ...     "target": [0, 1, 0, 1, 0]
+        ... })
+        >>> result = fs.analyze(df, target_column="target")
+        >>> len(result.findings) >= 0
+        True
+    """
+    if isinstance(source, Dataset):
+        dataset = source
+    else:
+        dataset = load(source)
+    prof_res = profile(
+        dataset,
+        max_correlation_columns=max_correlation_columns,
+        max_frequency_table_size=max_frequency_table_size,
+    )
+
+    from featuresmith.rules.engine import RuleEngine
+
+    engine = RuleEngine()
+    return engine.run(
+        prof_res,
+        target_column=target_column,
+        enabled_rules=enabled_rules,
+        rule_config=rule_config,
+    )

featuresmith_core-0.1.0/src/featuresmith/connectors/__init__.py

@@ -0,0 +1,18 @@
+"""Connector package for Featuresmith."""
+
+from featuresmith.connectors.base import BaseConnector
+from featuresmith.connectors.csv_connector import CsvConnector
+from featuresmith.connectors.dataframe_connector import DataFrameConnector
+from featuresmith.connectors.excel_connector import ExcelConnector
+from featuresmith.connectors.parquet_connector import ParquetConnector
+from featuresmith.connectors.registry import ConnectorRegistry, default_registry
+
+__all__ = [
+    "BaseConnector",
+    "ConnectorRegistry",
+    "CsvConnector",
+    "DataFrameConnector",
+    "ExcelConnector",
+    "ParquetConnector",
+    "default_registry",
+]

featuresmith_core-0.1.0/src/featuresmith/connectors/_paths.py

@@ -0,0 +1,25 @@
+"""Private helpers shared by local-file connectors."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+from featuresmith.core.exceptions import SourceNotFoundError, UnsupportedFormatError
+
+
+def validate_file_source(source: object, suffixes: tuple[str, ...]) -> Path:
+    """Return a validated local file path for one of the supplied suffixes."""
+    if not isinstance(source, (str, Path)):
+        raise UnsupportedFormatError("Expected a local file path.")
+
+    path = Path(source)
+    if path.suffix.lower() not in suffixes:
+        formats = ", ".join(suffixes)
+        raise UnsupportedFormatError(
+            f"Unsupported file format. Expected one of: {formats}."
+        )
+    if not path.exists():
+        raise SourceNotFoundError(f"Source file does not exist: {path}.")
+    if not path.is_file():
+        raise SourceNotFoundError(f"Source path is not a file: {path}.")
+    return path

featuresmith_core-0.1.0/src/featuresmith/connectors/base.py

@@ -0,0 +1,54 @@
+"""Base contract for source connectors."""
+
+from __future__ import annotations
+
+from abc import ABC, abstractmethod
+
+from featuresmith.core.dataset import Dataset
+
+
+class BaseConnector(ABC):
+    """Abstract base class for all Featuresmith data connectors.
+
+    Connectors are responsible for loading and normalizing external tabular
+    sources (such as files or database connections) or in-memory representations
+    into a standardized Dataset object.
+    """
+
+    @abstractmethod
+    def can_load(self, source: object) -> bool:
+        """Determine whether the connector supports the supplied source.
+
+        Args:
+            source: The input source object (e.g. file path or DataFrame).
+
+        Returns:
+            bool: True if this connector supports loading from the source,
+                False otherwise.
+        """
+
+    @abstractmethod
+    def validate(self, source: object) -> None:
+        """Validate the source structurally or raise a typed connector error.
+
+        Args:
+            source: The input source object to validate.
+
+        Raises:
+            ConnectorError: If validation fails because the source is missing,
+                unsupported, or invalid.
+        """
+
+    @abstractmethod
+    def load(self, source: object) -> Dataset:
+        """Load and normalize a validated source into a Dataset.
+
+        Args:
+            source: The input source object to load.
+
+        Returns:
+            Dataset: The loaded and normalized dataset wrapper.
+
+        Raises:
+            ConnectorError: If loading fails due to parsing or read errors.
+        """

featuresmith_core-0.1.0/src/featuresmith/connectors/csv_connector.py

@@ -0,0 +1,44 @@
+"""CSV connector backed by Polars."""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+import polars as pl
+
+from featuresmith.connectors._paths import validate_file_source
+from featuresmith.connectors.base import BaseConnector
+from featuresmith.core.dataset import Dataset
+from featuresmith.core.exceptions import SourceParseError
+
+
+class CsvConnector(BaseConnector):
+    """Load local CSV files into Polars-backed datasets."""
+
+    _SUFFIXES = (".csv",)
+
+    def can_load(self, source: object) -> bool:
+        """Return whether the source is a CSV path."""
+        return (
+            isinstance(source, (str, Path))
+            and Path(source).suffix.lower() in self._SUFFIXES
+        )
+
+    def validate(self, source: object) -> None:
+        """Validate that the CSV source exists and is a regular file."""
+        validate_file_source(source, self._SUFFIXES)
+
+    def load(self, source: object) -> Dataset:
+        """Load a CSV file as a normalized Polars dataset."""
+        path = validate_file_source(source, self._SUFFIXES)
+        try:
+            dataframe = pl.read_csv(path)
+        except (OSError, pl.exceptions.PolarsError) as error:
+            raise SourceParseError(f"Could not read CSV file '{path}'.") from error
+        return Dataset.from_dataframe(
+            dataframe,
+            backend="polars",
+            source=str(path),
+            file_size=path.stat().st_size,
+            metadata={"format": "csv"},
+        )