datawash 0.2.0__tar.gz → 0.2.1__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {datawash-0.2.0/src/datawash.egg-info → datawash-0.2.1}/PKG-INFO +13 -13
- {datawash-0.2.0 → datawash-0.2.1}/README.md +12 -12
- {datawash-0.2.0 → datawash-0.2.1}/pyproject.toml +1 -1
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/__init__.py +1 -1
- {datawash-0.2.0 → datawash-0.2.1/src/datawash.egg-info}/PKG-INFO +13 -13
- {datawash-0.2.0 → datawash-0.2.1}/LICENSE +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/setup.cfg +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/adapters/__init__.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/adapters/base.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/adapters/csv_adapter.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/adapters/excel_adapter.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/adapters/json_adapter.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/adapters/parquet_adapter.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/cli/__init__.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/cli/formatters.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/cli/main.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/codegen/__init__.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/codegen/generator.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/core/__init__.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/core/cache.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/core/config.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/core/dtypes.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/core/exceptions.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/core/models.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/core/report.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/core/sampling.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/detectors/__init__.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/detectors/base.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/detectors/duplicate_detector.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/detectors/format_detector.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/detectors/missing_detector.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/detectors/outlier_detector.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/detectors/registry.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/detectors/similarity_detector.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/detectors/type_detector.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/profiler/__init__.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/profiler/engine.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/profiler/parallel.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/profiler/patterns.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/profiler/statistics.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/suggestors/__init__.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/suggestors/base.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/suggestors/engine.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/suggestors/prioritizer.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/transformers/__init__.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/transformers/base.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/transformers/categories.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/transformers/columns.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/transformers/duplicates.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/transformers/formats.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/transformers/missing.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/transformers/registry.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash/transformers/types.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash.egg-info/SOURCES.txt +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash.egg-info/dependency_links.txt +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash.egg-info/entry_points.txt +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash.egg-info/requires.txt +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/src/datawash.egg-info/top_level.txt +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_adapters.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_cache.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_cli.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_codegen.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_detectors.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_dtypes.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_edge_cases.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_integration.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_parallel.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_profiler.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_sampling.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_suggestors.py +0 -0
- {datawash-0.2.0 → datawash-0.2.1}/tests/test_transformers.py +0 -0
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: datawash
|
|
3
|
-
Version: 0.2.
|
|
3
|
+
Version: 0.2.1
|
|
4
4
|
Summary: Intelligent data cleaning and quality analysis
|
|
5
5
|
Author: Sai Pranav Krovvidi
|
|
6
6
|
License: MIT
|
|
@@ -220,10 +220,10 @@ We provide ready-to-run examples in the `examples/` directory:
|
|
|
220
220
|
|
|
221
221
|
| Example | Description |
|
|
222
222
|
|---------|-------------|
|
|
223
|
-
| [`quickstart.py`](examples/quickstart.py) | Basic workflow: analyze → suggest → apply → codegen |
|
|
224
|
-
| [`csv_cleaning.py`](examples/csv_cleaning.py) | Load CSV, clean, save with CLI equivalents |
|
|
225
|
-
| [`ml_preprocessing.py`](examples/ml_preprocessing.py) | ML-optimized cleaning workflow |
|
|
226
|
-
| [`jupyter_demo.ipynb`](examples/jupyter_demo.ipynb) | Interactive notebook with visualizations |
|
|
223
|
+
| [`quickstart.py`](https://github.com/Pranav1011/DataWash/blob/main/examples/quickstart.py) | Basic workflow: analyze → suggest → apply → codegen |
|
|
224
|
+
| [`csv_cleaning.py`](https://github.com/Pranav1011/DataWash/blob/main/examples/csv_cleaning.py) | Load CSV, clean, save with CLI equivalents |
|
|
225
|
+
| [`ml_preprocessing.py`](https://github.com/Pranav1011/DataWash/blob/main/examples/ml_preprocessing.py) | ML-optimized cleaning workflow |
|
|
226
|
+
| [`jupyter_demo.ipynb`](https://github.com/Pranav1011/DataWash/blob/main/examples/jupyter_demo.ipynb) | Interactive notebook with visualizations |
|
|
227
227
|
|
|
228
228
|
**Sample datasets** in `examples/sample_data/`:
|
|
229
229
|
- `customers_messy.csv` - Names, emails, phones with various issues
|
|
@@ -239,12 +239,12 @@ python examples/quickstart.py
|
|
|
239
239
|
|
|
240
240
|
| Document | Description |
|
|
241
241
|
|----------|-------------|
|
|
242
|
-
| [Getting Started](docs/getting-started.md) | Installation and first steps |
|
|
243
|
-
| [User Guide](docs/user-guide.md) | Complete feature walkthrough |
|
|
244
|
-
| [API Reference](docs/api-reference.md) | Detailed API documentation |
|
|
245
|
-
| [CLI Reference](docs/cli-reference.md) | Command-line interface guide |
|
|
246
|
-
| [Configuration](docs/configuration.md) | Customization options |
|
|
247
|
-
| [Contributing](docs/contributing.md) | How to contribute |
|
|
242
|
+
| [Getting Started](https://github.com/Pranav1011/DataWash/blob/main/docs/getting-started.md) | Installation and first steps |
|
|
243
|
+
| [User Guide](https://github.com/Pranav1011/DataWash/blob/main/docs/user-guide.md) | Complete feature walkthrough |
|
|
244
|
+
| [API Reference](https://github.com/Pranav1011/DataWash/blob/main/docs/api-reference.md) | Detailed API documentation |
|
|
245
|
+
| [CLI Reference](https://github.com/Pranav1011/DataWash/blob/main/docs/cli-reference.md) | Command-line interface guide |
|
|
246
|
+
| [Configuration](https://github.com/Pranav1011/DataWash/blob/main/docs/configuration.md) | Customization options |
|
|
247
|
+
| [Contributing](https://github.com/Pranav1011/DataWash/blob/main/docs/contributing.md) | How to contribute |
|
|
248
248
|
|
|
249
249
|
## Use Cases
|
|
250
250
|
|
|
@@ -335,7 +335,7 @@ ruff check src tests
|
|
|
335
335
|
|
|
336
336
|
## Contributing
|
|
337
337
|
|
|
338
|
-
Contributions welcome! See [CONTRIBUTING.md](docs/contributing.md) for guidelines.
|
|
338
|
+
Contributions welcome! See [CONTRIBUTING.md](https://github.com/Pranav1011/DataWash/blob/main/docs/contributing.md) for guidelines.
|
|
339
339
|
|
|
340
340
|
**Areas where help is needed:**
|
|
341
341
|
- ML module implementation (sentence-transformers)
|
|
@@ -346,7 +346,7 @@ Contributions welcome! See [CONTRIBUTING.md](docs/contributing.md) for guideline
|
|
|
346
346
|
|
|
347
347
|
## License
|
|
348
348
|
|
|
349
|
-
MIT License - see [LICENSE](LICENSE) for details.
|
|
349
|
+
MIT License - see [LICENSE](https://github.com/Pranav1011/DataWash/blob/main/LICENSE) for details.
|
|
350
350
|
|
|
351
351
|
## Acknowledgments
|
|
352
352
|
|
|
@@ -172,10 +172,10 @@ We provide ready-to-run examples in the `examples/` directory:
|
|
|
172
172
|
|
|
173
173
|
| Example | Description |
|
|
174
174
|
|---------|-------------|
|
|
175
|
-
| [`quickstart.py`](examples/quickstart.py) | Basic workflow: analyze → suggest → apply → codegen |
|
|
176
|
-
| [`csv_cleaning.py`](examples/csv_cleaning.py) | Load CSV, clean, save with CLI equivalents |
|
|
177
|
-
| [`ml_preprocessing.py`](examples/ml_preprocessing.py) | ML-optimized cleaning workflow |
|
|
178
|
-
| [`jupyter_demo.ipynb`](examples/jupyter_demo.ipynb) | Interactive notebook with visualizations |
|
|
175
|
+
| [`quickstart.py`](https://github.com/Pranav1011/DataWash/blob/main/examples/quickstart.py) | Basic workflow: analyze → suggest → apply → codegen |
|
|
176
|
+
| [`csv_cleaning.py`](https://github.com/Pranav1011/DataWash/blob/main/examples/csv_cleaning.py) | Load CSV, clean, save with CLI equivalents |
|
|
177
|
+
| [`ml_preprocessing.py`](https://github.com/Pranav1011/DataWash/blob/main/examples/ml_preprocessing.py) | ML-optimized cleaning workflow |
|
|
178
|
+
| [`jupyter_demo.ipynb`](https://github.com/Pranav1011/DataWash/blob/main/examples/jupyter_demo.ipynb) | Interactive notebook with visualizations |
|
|
179
179
|
|
|
180
180
|
**Sample datasets** in `examples/sample_data/`:
|
|
181
181
|
- `customers_messy.csv` - Names, emails, phones with various issues
|
|
@@ -191,12 +191,12 @@ python examples/quickstart.py
|
|
|
191
191
|
|
|
192
192
|
| Document | Description |
|
|
193
193
|
|----------|-------------|
|
|
194
|
-
| [Getting Started](docs/getting-started.md) | Installation and first steps |
|
|
195
|
-
| [User Guide](docs/user-guide.md) | Complete feature walkthrough |
|
|
196
|
-
| [API Reference](docs/api-reference.md) | Detailed API documentation |
|
|
197
|
-
| [CLI Reference](docs/cli-reference.md) | Command-line interface guide |
|
|
198
|
-
| [Configuration](docs/configuration.md) | Customization options |
|
|
199
|
-
| [Contributing](docs/contributing.md) | How to contribute |
|
|
194
|
+
| [Getting Started](https://github.com/Pranav1011/DataWash/blob/main/docs/getting-started.md) | Installation and first steps |
|
|
195
|
+
| [User Guide](https://github.com/Pranav1011/DataWash/blob/main/docs/user-guide.md) | Complete feature walkthrough |
|
|
196
|
+
| [API Reference](https://github.com/Pranav1011/DataWash/blob/main/docs/api-reference.md) | Detailed API documentation |
|
|
197
|
+
| [CLI Reference](https://github.com/Pranav1011/DataWash/blob/main/docs/cli-reference.md) | Command-line interface guide |
|
|
198
|
+
| [Configuration](https://github.com/Pranav1011/DataWash/blob/main/docs/configuration.md) | Customization options |
|
|
199
|
+
| [Contributing](https://github.com/Pranav1011/DataWash/blob/main/docs/contributing.md) | How to contribute |
|
|
200
200
|
|
|
201
201
|
## Use Cases
|
|
202
202
|
|
|
@@ -287,7 +287,7 @@ ruff check src tests
|
|
|
287
287
|
|
|
288
288
|
## Contributing
|
|
289
289
|
|
|
290
|
-
Contributions welcome! See [CONTRIBUTING.md](docs/contributing.md) for guidelines.
|
|
290
|
+
Contributions welcome! See [CONTRIBUTING.md](https://github.com/Pranav1011/DataWash/blob/main/docs/contributing.md) for guidelines.
|
|
291
291
|
|
|
292
292
|
**Areas where help is needed:**
|
|
293
293
|
- ML module implementation (sentence-transformers)
|
|
@@ -298,7 +298,7 @@ Contributions welcome! See [CONTRIBUTING.md](docs/contributing.md) for guideline
|
|
|
298
298
|
|
|
299
299
|
## License
|
|
300
300
|
|
|
301
|
-
MIT License - see [LICENSE](LICENSE) for details.
|
|
301
|
+
MIT License - see [LICENSE](https://github.com/Pranav1011/DataWash/blob/main/LICENSE) for details.
|
|
302
302
|
|
|
303
303
|
## Acknowledgments
|
|
304
304
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.4
|
|
2
2
|
Name: datawash
|
|
3
|
-
Version: 0.2.
|
|
3
|
+
Version: 0.2.1
|
|
4
4
|
Summary: Intelligent data cleaning and quality analysis
|
|
5
5
|
Author: Sai Pranav Krovvidi
|
|
6
6
|
License: MIT
|
|
@@ -220,10 +220,10 @@ We provide ready-to-run examples in the `examples/` directory:
|
|
|
220
220
|
|
|
221
221
|
| Example | Description |
|
|
222
222
|
|---------|-------------|
|
|
223
|
-
| [`quickstart.py`](examples/quickstart.py) | Basic workflow: analyze → suggest → apply → codegen |
|
|
224
|
-
| [`csv_cleaning.py`](examples/csv_cleaning.py) | Load CSV, clean, save with CLI equivalents |
|
|
225
|
-
| [`ml_preprocessing.py`](examples/ml_preprocessing.py) | ML-optimized cleaning workflow |
|
|
226
|
-
| [`jupyter_demo.ipynb`](examples/jupyter_demo.ipynb) | Interactive notebook with visualizations |
|
|
223
|
+
| [`quickstart.py`](https://github.com/Pranav1011/DataWash/blob/main/examples/quickstart.py) | Basic workflow: analyze → suggest → apply → codegen |
|
|
224
|
+
| [`csv_cleaning.py`](https://github.com/Pranav1011/DataWash/blob/main/examples/csv_cleaning.py) | Load CSV, clean, save with CLI equivalents |
|
|
225
|
+
| [`ml_preprocessing.py`](https://github.com/Pranav1011/DataWash/blob/main/examples/ml_preprocessing.py) | ML-optimized cleaning workflow |
|
|
226
|
+
| [`jupyter_demo.ipynb`](https://github.com/Pranav1011/DataWash/blob/main/examples/jupyter_demo.ipynb) | Interactive notebook with visualizations |
|
|
227
227
|
|
|
228
228
|
**Sample datasets** in `examples/sample_data/`:
|
|
229
229
|
- `customers_messy.csv` - Names, emails, phones with various issues
|
|
@@ -239,12 +239,12 @@ python examples/quickstart.py
|
|
|
239
239
|
|
|
240
240
|
| Document | Description |
|
|
241
241
|
|----------|-------------|
|
|
242
|
-
| [Getting Started](docs/getting-started.md) | Installation and first steps |
|
|
243
|
-
| [User Guide](docs/user-guide.md) | Complete feature walkthrough |
|
|
244
|
-
| [API Reference](docs/api-reference.md) | Detailed API documentation |
|
|
245
|
-
| [CLI Reference](docs/cli-reference.md) | Command-line interface guide |
|
|
246
|
-
| [Configuration](docs/configuration.md) | Customization options |
|
|
247
|
-
| [Contributing](docs/contributing.md) | How to contribute |
|
|
242
|
+
| [Getting Started](https://github.com/Pranav1011/DataWash/blob/main/docs/getting-started.md) | Installation and first steps |
|
|
243
|
+
| [User Guide](https://github.com/Pranav1011/DataWash/blob/main/docs/user-guide.md) | Complete feature walkthrough |
|
|
244
|
+
| [API Reference](https://github.com/Pranav1011/DataWash/blob/main/docs/api-reference.md) | Detailed API documentation |
|
|
245
|
+
| [CLI Reference](https://github.com/Pranav1011/DataWash/blob/main/docs/cli-reference.md) | Command-line interface guide |
|
|
246
|
+
| [Configuration](https://github.com/Pranav1011/DataWash/blob/main/docs/configuration.md) | Customization options |
|
|
247
|
+
| [Contributing](https://github.com/Pranav1011/DataWash/blob/main/docs/contributing.md) | How to contribute |
|
|
248
248
|
|
|
249
249
|
## Use Cases
|
|
250
250
|
|
|
@@ -335,7 +335,7 @@ ruff check src tests
|
|
|
335
335
|
|
|
336
336
|
## Contributing
|
|
337
337
|
|
|
338
|
-
Contributions welcome! See [CONTRIBUTING.md](docs/contributing.md) for guidelines.
|
|
338
|
+
Contributions welcome! See [CONTRIBUTING.md](https://github.com/Pranav1011/DataWash/blob/main/docs/contributing.md) for guidelines.
|
|
339
339
|
|
|
340
340
|
**Areas where help is needed:**
|
|
341
341
|
- ML module implementation (sentence-transformers)
|
|
@@ -346,7 +346,7 @@ Contributions welcome! See [CONTRIBUTING.md](docs/contributing.md) for guideline
|
|
|
346
346
|
|
|
347
347
|
## License
|
|
348
348
|
|
|
349
|
-
MIT License - see [LICENSE](LICENSE) for details.
|
|
349
|
+
MIT License - see [LICENSE](https://github.com/Pranav1011/DataWash/blob/main/LICENSE) for details.
|
|
350
350
|
|
|
351
351
|
## Acknowledgments
|
|
352
352
|
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|