datra 0.1.0__tar.gz

datra-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Raphael James
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

datra-0.1.0/PKG-INFO

@@ -0,0 +1,338 @@
+Metadata-Version: 2.4
+Name: datra
+Version: 0.1.0
+Summary: A lightweight Python library for cleaning, auditing, and validating tabular data.
+Author-email: Raphael <raphaeljames897@gmail.com>
+License: MIT License
+        
+        Copyright (c) 2026 Raphael James
+        
+        Permission is hereby granted, free of charge, to any person obtaining a copy
+        of this software and associated documentation files (the "Software"), to deal
+        in the Software without restriction, including without limitation the rights
+        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+        copies of the Software, and to permit persons to whom the Software is
+        furnished to do so, subject to the following conditions:
+        
+        The above copyright notice and this permission notice shall be included in all
+        copies or substantial portions of the Software.
+        
+        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+        SOFTWARE.
+        
+Project-URL: Homepage, https://github.com/Raphaelj1/datra
+Project-URL: Repository, https://github.com/Raphaelj1/datra
+Project-URL: Issues, https://github.com/Raphaelj1/datra/issues
+Keywords: data-cleaning,data-quality,validation,pandas,data-analysis
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.13
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pandas<3.0,>=2.0
+Requires-Dist: openpyxl>=3.1
+Provides-Extra: dev
+Requires-Dist: pytest>=8; extra == "dev"
+Requires-Dist: build; extra == "dev"
+Requires-Dist: twine; extra == "dev"
+Dynamic: license-file
+
+# Datra
+
+A lightweight Python library for cleaning, auditing, and validating tabular data. It helps data scientists, analysts, and engineers quickly identify data quality issues, clean datasets using simple rules, and generate reports.
+
+## Why Datra?
+
+Data quality problems often consume more time than analysis itself. Missing values, duplicate records, inconsistent column names, and invalid entries can silently affect downstream models and business decisions.
+
+Datra provides a simple workflow for understanding and improving dataset quality before analysis or machine learning.
+
+With Datra, you can:
+
+- Audit datasets to identify quality issues.
+- Clean data using configurable rules.
+- Validate datasets against business rules.
+- Generate JSON and HTML quality reports.
+- Work directly with Pandas DataFrames or CSV and Excel files.
+
+## Features
+
+- Dataset profiling
+- Missing value analysis
+- Duplicate detection
+- Outlier detection (IQR-based)
+- Rule-based data validation
+- Automated data quality scoring
+- Configurable data cleaning
+- Column name standardization
+- Support for Pandas DataFrames
+- CSV and Excel file support
+- JSON and HTML report generation
+- Save cleaned datasets directly to disk
+
+## Installation
+
+Install Datra from PyPI:
+
+```bash
+pip install datra
+```
+
+Or install the latest development version:
+
+```bash
+git clone https://github.com/raphaelj1/datra.git
+
+cd datra
+
+pip install -e .
+```
+
+## Quick Start
+
+### Clean a dataset
+
+```python
+from datra import clean
+
+cleaned = clean(
+    "patients.csv",
+    drop_duplicates=True,
+    fill_numeric="median",
+    fill_categorical="mode",
+    standardize_columns=True,
+)
+```
+
+### Audit a dataset
+
+```python
+from datra import Audit
+
+audit = Audit("patients.csv")
+
+print(audit.profile)
+print(audit.score)
+```
+
+### Validate a dataset
+
+```python
+rules = {
+    "Age": {
+        "min": 0,
+        "max": 120,
+    },
+    "Gender": {
+        "allowed": [
+            "Male",
+            "Female",
+        ],
+    },
+}
+
+report = audit.validate(rules)
+```
+
+## Cleaning Data
+
+The `clean()` function applies one or more cleaning operations to a dataset and returns a new DataFrame. It accepts either a Pandas DataFrame or the path to a CSV or Excel file.
+
+### Using keyword arguments
+
+```python
+from datra import clean
+
+cleaned = clean(
+    "patients.csv",
+    drop_duplicates=True,
+    fill_numeric="median",
+    fill_categorical="mode",
+    standardize_columns=True,
+)
+```
+
+### Using cleaning rules
+
+```python
+rules = {
+    "duplicates": {
+        "drop": True,
+    },
+    "missing": {
+        "numeric": "median",
+        "categorical": "mode",
+    },
+    "columns": {
+        "standardize": True,
+    },
+}
+
+cleaned = clean("patients.csv", rules=rules)
+```
+
+### Save the cleaned dataset
+
+```python
+clean(
+    "patients.csv",
+    drop_duplicates=True,
+    output="cleaned_patients.xlsx",
+)
+```
+
+## Auditing Data
+
+Create an audit object to inspect dataset quality.
+
+```python
+from datra import Audit
+
+audit = Audit("patients.csv")
+```
+
+Retrieve individual quality checks.
+
+```python
+audit.profile
+
+audit.completeness
+
+audit.uniqueness
+
+audit.outliers
+
+audit.score
+```
+
+Or access all audit results at once.
+
+```python
+audit.results
+```
+
+## Validation
+
+Validate datasets against custom business rules.
+
+```python
+rules = {
+    "Age": {
+        "min": 0,
+        "max": 120,
+    },
+    "Patient ID": {
+        "unique": True,
+    },
+    "Gender": {
+        "allowed": [
+            "Male",
+            "Female",
+        ],
+    },
+}
+
+report = audit.validate(rules)
+```
+
+Validation returns a structured report describing which checks passed, which failed, and the number of violations for each rule.
+
+## Reports
+
+Build a data quality report as a Python dictionary.
+
+```python
+from datra import Audit
+
+audit = Audit("patients.csv")
+
+report = audit.build_report()
+```
+
+Save the report as JSON.
+
+```python
+audit.save_report(
+    format="json",
+)
+```
+
+Or save it as an HTML report.
+
+```python
+audit.save_report(
+    format="html",
+)
+```
+
+## Supported File Formats
+
+Datra supports both Pandas DataFrames and common tabular file formats.
+
+| Input            | Supported |
+| ---------------- | --------- |
+| Pandas DataFrame | ✅        |
+| CSV              | ✅        |
+| Excel (.xlsx)    | ✅        |
+| Excel (.xls)     | ✅        |
+
+### Report Formats
+
+| Format | Supported  |
+| ------ | ---------- |
+| JSON   | ✅         |
+| HTML   | ✅         |
+| PDF    | 🚧 Planned |
+
+## Project Structure
+
+```
+datra/
+├── datra/              # Library source code
+├── examples/           # Example usage
+├── tests/
+├── pyproject.toml
+├── README.md
+└── LICENSE
+```
+
+## Roadmap
+
+Planned improvements include:
+
+- PDF report generation
+- Command-line interface (CLI)
+- Additional cleaning operations
+- Additional validation rules
+- More data quality checks
+- Interactive HTML reports
+- Support for additional file formats
+
+## Contributing
+
+Contributions, feature requests, and bug reports are welcome.
+
+If you would like to contribute:
+
+1. Fork the repository.
+2. Create a new feature branch.
+3. Commit your changes.
+4. Open a pull request.
+
+Please ensure all tests pass before submitting a pull request.
+
+## License
+
+This project is licensed under the MIT License.

datra-0.1.0/README.md

@@ -0,0 +1,287 @@
+# Datra
+
+A lightweight Python library for cleaning, auditing, and validating tabular data. It helps data scientists, analysts, and engineers quickly identify data quality issues, clean datasets using simple rules, and generate reports.
+
+## Why Datra?
+
+Data quality problems often consume more time than analysis itself. Missing values, duplicate records, inconsistent column names, and invalid entries can silently affect downstream models and business decisions.
+
+Datra provides a simple workflow for understanding and improving dataset quality before analysis or machine learning.
+
+With Datra, you can:
+
+- Audit datasets to identify quality issues.
+- Clean data using configurable rules.
+- Validate datasets against business rules.
+- Generate JSON and HTML quality reports.
+- Work directly with Pandas DataFrames or CSV and Excel files.
+
+## Features
+
+- Dataset profiling
+- Missing value analysis
+- Duplicate detection
+- Outlier detection (IQR-based)
+- Rule-based data validation
+- Automated data quality scoring
+- Configurable data cleaning
+- Column name standardization
+- Support for Pandas DataFrames
+- CSV and Excel file support
+- JSON and HTML report generation
+- Save cleaned datasets directly to disk
+
+## Installation
+
+Install Datra from PyPI:
+
+```bash
+pip install datra
+```
+
+Or install the latest development version:
+
+```bash
+git clone https://github.com/raphaelj1/datra.git
+
+cd datra
+
+pip install -e .
+```
+
+## Quick Start
+
+### Clean a dataset
+
+```python
+from datra import clean
+
+cleaned = clean(
+    "patients.csv",
+    drop_duplicates=True,
+    fill_numeric="median",
+    fill_categorical="mode",
+    standardize_columns=True,
+)
+```
+
+### Audit a dataset
+
+```python
+from datra import Audit
+
+audit = Audit("patients.csv")
+
+print(audit.profile)
+print(audit.score)
+```
+
+### Validate a dataset
+
+```python
+rules = {
+    "Age": {
+        "min": 0,
+        "max": 120,
+    },
+    "Gender": {
+        "allowed": [
+            "Male",
+            "Female",
+        ],
+    },
+}
+
+report = audit.validate(rules)
+```
+
+## Cleaning Data
+
+The `clean()` function applies one or more cleaning operations to a dataset and returns a new DataFrame. It accepts either a Pandas DataFrame or the path to a CSV or Excel file.
+
+### Using keyword arguments
+
+```python
+from datra import clean
+
+cleaned = clean(
+    "patients.csv",
+    drop_duplicates=True,
+    fill_numeric="median",
+    fill_categorical="mode",
+    standardize_columns=True,
+)
+```
+
+### Using cleaning rules
+
+```python
+rules = {
+    "duplicates": {
+        "drop": True,
+    },
+    "missing": {
+        "numeric": "median",
+        "categorical": "mode",
+    },
+    "columns": {
+        "standardize": True,
+    },
+}
+
+cleaned = clean("patients.csv", rules=rules)
+```
+
+### Save the cleaned dataset
+
+```python
+clean(
+    "patients.csv",
+    drop_duplicates=True,
+    output="cleaned_patients.xlsx",
+)
+```
+
+## Auditing Data
+
+Create an audit object to inspect dataset quality.
+
+```python
+from datra import Audit
+
+audit = Audit("patients.csv")
+```
+
+Retrieve individual quality checks.
+
+```python
+audit.profile
+
+audit.completeness
+
+audit.uniqueness
+
+audit.outliers
+
+audit.score
+```
+
+Or access all audit results at once.
+
+```python
+audit.results
+```
+
+## Validation
+
+Validate datasets against custom business rules.
+
+```python
+rules = {
+    "Age": {
+        "min": 0,
+        "max": 120,
+    },
+    "Patient ID": {
+        "unique": True,
+    },
+    "Gender": {
+        "allowed": [
+            "Male",
+            "Female",
+        ],
+    },
+}
+
+report = audit.validate(rules)
+```
+
+Validation returns a structured report describing which checks passed, which failed, and the number of violations for each rule.
+
+## Reports
+
+Build a data quality report as a Python dictionary.
+
+```python
+from datra import Audit
+
+audit = Audit("patients.csv")
+
+report = audit.build_report()
+```
+
+Save the report as JSON.
+
+```python
+audit.save_report(
+    format="json",
+)
+```
+
+Or save it as an HTML report.
+
+```python
+audit.save_report(
+    format="html",
+)
+```
+
+## Supported File Formats
+
+Datra supports both Pandas DataFrames and common tabular file formats.
+
+| Input            | Supported |
+| ---------------- | --------- |
+| Pandas DataFrame | ✅        |
+| CSV              | ✅        |
+| Excel (.xlsx)    | ✅        |
+| Excel (.xls)     | ✅        |
+
+### Report Formats
+
+| Format | Supported  |
+| ------ | ---------- |
+| JSON   | ✅         |
+| HTML   | ✅         |
+| PDF    | 🚧 Planned |
+
+## Project Structure
+
+```
+datra/
+├── datra/              # Library source code
+├── examples/           # Example usage
+├── tests/
+├── pyproject.toml
+├── README.md
+└── LICENSE
+```
+
+## Roadmap
+
+Planned improvements include:
+
+- PDF report generation
+- Command-line interface (CLI)
+- Additional cleaning operations
+- Additional validation rules
+- More data quality checks
+- Interactive HTML reports
+- Support for additional file formats
+
+## Contributing
+
+Contributions, feature requests, and bug reports are welcome.
+
+If you would like to contribute:
+
+1. Fork the repository.
+2. Create a new feature branch.
+3. Commit your changes.
+4. Open a pull request.
+
+Please ensure all tests pass before submitting a pull request.
+
+## License
+
+This project is licensed under the MIT License.

datra-0.1.0/datra/__init__.py

@@ -0,0 +1,4 @@
+from .audit import Audit
+from .cleaner import clean
+
+__all__ = ["Audit", "clean"]

datra-0.1.0/datra/audit.py

@@ -0,0 +1,60 @@
+from functools import cached_property
+
+from datra.io import load
+from datra.checks.validate import validate as validate_df
+from datra.checks.completeness import completeness as check_completeness
+from datra.checks.uniqueness import uniqueness as check_uniqueness
+from datra.checks.outliers import outliers as check_outliers
+from datra.checks.profile import profile as check_profile
+from datra.scoring.score import calculate_score
+from datra.reports import build_report, save_report
+
+
+class Audit:
+    def __init__(self, input_data):
+        self.df = load(input_data)
+    
+    @cached_property
+    def completeness(self):
+        return check_completeness(self.df)
+
+    @cached_property
+    def uniqueness(self):
+        return check_uniqueness(self.df)
+
+    @cached_property
+    def outliers(self):
+        return check_outliers(self.df)
+
+    @cached_property
+    def profile(self):
+        return check_profile(self.df)
+
+    @cached_property
+    def score(self):
+        metrics_payload = {
+            "completeness": self.completeness,
+            "uniqueness": self.uniqueness,
+            "outliers": self.outliers,
+        }
+        return calculate_score(metrics_payload)
+
+    @property
+    def results(self):
+        return {
+            "profile": self.profile,
+            "completeness": self.completeness,
+            "uniqueness": self.uniqueness,
+            "outliers": self.outliers,
+            "score": self.score,
+        }
+
+    def validate(self, rules: dict):
+        return validate_df(self.df, rules)
+
+    def build_report(self):
+        return build_report(self.results)
+
+    def save_report(self, path="outputs", format="json"):
+        report = self.build_report()
+        return save_report(report, output=path, format=format)