datapruning 1.0.5__tar.gz → 1.0.6__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.
- datapruning-1.0.6/LICENSE +21 -0
- {datapruning-1.0.5/datapruning.egg-info → datapruning-1.0.6}/PKG-INFO +73 -73
- {datapruning-1.0.5 → datapruning-1.0.6}/build_src/_core.c +37984 -37974
- {datapruning-1.0.5 → datapruning-1.0.6/datapruning.egg-info}/PKG-INFO +73 -73
- {datapruning-1.0.5 → datapruning-1.0.6}/datapruning.egg-info/SOURCES.txt +1 -1
- datapruning-1.0.6/datapruning.egg-info/dependency_links.txt +1 -0
- {datapruning-1.0.5 → datapruning-1.0.6}/pyproject.toml +2 -2
- {datapruning-1.0.5 → datapruning-1.0.6}/setup.cfg +4 -4
- datapruning-1.0.6/setup.py +20 -0
- datapruning-1.0.5/MANIFEST.in +0 -2
- datapruning-1.0.5/build_src/_core.pyx +0 -227
- datapruning-1.0.5/setup.py +0 -43
- /datapruning-1.0.5/datapruning.egg-info/dependency_links.txt → /datapruning-1.0.6/MANIFEST.in +0 -0
- {datapruning-1.0.5 → datapruning-1.0.6}/README.md +0 -0
- {datapruning-1.0.5 → datapruning-1.0.6}/datapruning/__init__.py +0 -0
- {datapruning-1.0.5 → datapruning-1.0.6}/datapruning/pipeline.py +0 -0
- {datapruning-1.0.5 → datapruning-1.0.6}/datapruning.egg-info/requires.txt +0 -0
- {datapruning-1.0.5 → datapruning-1.0.6}/datapruning.egg-info/top_level.txt +0 -0
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
DataPruning Proprietary License
|
|
2
|
+
|
|
3
|
+
Copyright (c) 2026 DataPruning.
|
|
4
|
+
All rights reserved.
|
|
5
|
+
|
|
6
|
+
This software and associated files are proprietary and confidential.
|
|
7
|
+
|
|
8
|
+
Permission is granted to use the software for evaluation and
|
|
9
|
+
non-commercial purposes. Unauthorized copying, modification,
|
|
10
|
+
redistribution, reverse engineering, or commercial resale of this
|
|
11
|
+
software is prohibited.
|
|
12
|
+
|
|
13
|
+
The software is provided "as is", without warranty of any kind,
|
|
14
|
+
express or implied, including but not limited to the warranties of
|
|
15
|
+
merchantability, fitness for a particular purpose, and noninfringement.
|
|
16
|
+
|
|
17
|
+
In no event shall the authors or copyright holders be liable for any
|
|
18
|
+
claim, damages, or other liability arising from the use of the software.
|
|
19
|
+
|
|
20
|
+
For licensing inquiries:
|
|
21
|
+
https://www.datapruning.com
|
|
@@ -1,73 +1,73 @@
|
|
|
1
|
-
Metadata-Version: 2.4
|
|
2
|
-
Name: datapruning
|
|
3
|
-
Version: 1.0.
|
|
4
|
-
Summary: Intelligent data pruning for ML datasets
|
|
5
|
-
License: Proprietary
|
|
6
|
-
Project-URL: Homepage, https://www.datapruning.com
|
|
7
|
-
Classifier: Development Status :: 4 - Beta
|
|
8
|
-
Classifier: Intended Audience :: Developers
|
|
9
|
-
Classifier: Intended Audience :: Science/Research
|
|
10
|
-
Classifier: Programming Language :: Python :: 3
|
|
11
|
-
Classifier: Programming Language :: Python :: 3.10
|
|
12
|
-
Classifier: Programming Language :: Python :: 3.11
|
|
13
|
-
Classifier: Programming Language :: Python :: 3.12
|
|
14
|
-
Classifier: Programming Language :: Python :: 3.13
|
|
15
|
-
Classifier: Programming Language :: Python :: 3.14
|
|
16
|
-
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
17
|
-
Requires-Python: >=3.10
|
|
18
|
-
Description-Content-Type: text/markdown
|
|
19
|
-
Requires-Dist: numpy>=1.24.0
|
|
20
|
-
Requires-Dist: pandas>=2.0.0
|
|
21
|
-
Requires-Dist: torch>=2.0.0
|
|
22
|
-
|
|
23
|
-
# DataPruning
|
|
24
|
-
|
|
25
|
-
Intelligent dataset pruning for ML — reduces dataset size by selecting the most informative rows.
|
|
26
|
-
|
|
27
|
-
## Installation
|
|
28
|
-
|
|
29
|
-
```bash
|
|
30
|
-
pip install datapruning
|
|
31
|
-
```
|
|
32
|
-
|
|
33
|
-
**Note:** PyTorch (~2 GB) is a required dependency.
|
|
34
|
-
|
|
35
|
-
## Requirements
|
|
36
|
-
|
|
37
|
-
- Python >= 3.10
|
|
38
|
-
- PyTorch 2.0+
|
|
39
|
-
- Pandas 2.0+
|
|
40
|
-
- NumPy 1.24+
|
|
41
|
-
|
|
42
|
-
## Limits
|
|
43
|
-
|
|
44
|
-
- Minimum: 1,000 rows per dataset
|
|
45
|
-
- Maximum: 300,000 rows per dataset
|
|
46
|
-
|
|
47
|
-
## Usage
|
|
48
|
-
|
|
49
|
-
```python
|
|
50
|
-
import pandas as pd
|
|
51
|
-
from datapruning import Pruner
|
|
52
|
-
|
|
53
|
-
df = pd.read_csv("dataset.csv")
|
|
54
|
-
p = Pruner(df)
|
|
55
|
-
filtered = p.prune(target_col="label", keep_ratio=0.5)
|
|
56
|
-
|
|
57
|
-
print(f"Kept {len(filtered)} / {len(df)} rows")
|
|
58
|
-
```
|
|
59
|
-
|
|
60
|
-
## Features
|
|
61
|
-
|
|
62
|
-
- Runs locally, no data upload
|
|
63
|
-
- Pre-training dataset optimization
|
|
64
|
-
- Pandas DataFrame input / output
|
|
65
|
-
- Compiled processing module
|
|
66
|
-
|
|
67
|
-
## Links
|
|
68
|
-
|
|
69
|
-
- Website: [datapruning.com](https://www.datapruning.com)
|
|
70
|
-
|
|
71
|
-
## License
|
|
72
|
-
|
|
73
|
-
Proprietary. See LICENSE file.
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: datapruning
|
|
3
|
+
Version: 1.0.6
|
|
4
|
+
Summary: Intelligent data pruning for ML datasets
|
|
5
|
+
License: Proprietary
|
|
6
|
+
Project-URL: Homepage, https://www.datapruning.com
|
|
7
|
+
Classifier: Development Status :: 4 - Beta
|
|
8
|
+
Classifier: Intended Audience :: Developers
|
|
9
|
+
Classifier: Intended Audience :: Science/Research
|
|
10
|
+
Classifier: Programming Language :: Python :: 3
|
|
11
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
12
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
13
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
14
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
15
|
+
Classifier: Programming Language :: Python :: 3.14
|
|
16
|
+
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
17
|
+
Requires-Python: >=3.10
|
|
18
|
+
Description-Content-Type: text/markdown
|
|
19
|
+
Requires-Dist: numpy>=1.24.0
|
|
20
|
+
Requires-Dist: pandas>=2.0.0
|
|
21
|
+
Requires-Dist: torch>=2.0.0
|
|
22
|
+
|
|
23
|
+
# DataPruning
|
|
24
|
+
|
|
25
|
+
Intelligent dataset pruning for ML — reduces dataset size by selecting the most informative rows.
|
|
26
|
+
|
|
27
|
+
## Installation
|
|
28
|
+
|
|
29
|
+
```bash
|
|
30
|
+
pip install datapruning
|
|
31
|
+
```
|
|
32
|
+
|
|
33
|
+
**Note:** PyTorch (~2 GB) is a required dependency.
|
|
34
|
+
|
|
35
|
+
## Requirements
|
|
36
|
+
|
|
37
|
+
- Python >= 3.10
|
|
38
|
+
- PyTorch 2.0+
|
|
39
|
+
- Pandas 2.0+
|
|
40
|
+
- NumPy 1.24+
|
|
41
|
+
|
|
42
|
+
## Limits
|
|
43
|
+
|
|
44
|
+
- Minimum: 1,000 rows per dataset
|
|
45
|
+
- Maximum: 300,000 rows per dataset
|
|
46
|
+
|
|
47
|
+
## Usage
|
|
48
|
+
|
|
49
|
+
```python
|
|
50
|
+
import pandas as pd
|
|
51
|
+
from datapruning import Pruner
|
|
52
|
+
|
|
53
|
+
df = pd.read_csv("dataset.csv")
|
|
54
|
+
p = Pruner(df)
|
|
55
|
+
filtered = p.prune(target_col="label", keep_ratio=0.5)
|
|
56
|
+
|
|
57
|
+
print(f"Kept {len(filtered)} / {len(df)} rows")
|
|
58
|
+
```
|
|
59
|
+
|
|
60
|
+
## Features
|
|
61
|
+
|
|
62
|
+
- Runs locally, no data upload
|
|
63
|
+
- Pre-training dataset optimization
|
|
64
|
+
- Pandas DataFrame input / output
|
|
65
|
+
- Compiled processing module
|
|
66
|
+
|
|
67
|
+
## Links
|
|
68
|
+
|
|
69
|
+
- Website: [datapruning.com](https://www.datapruning.com)
|
|
70
|
+
|
|
71
|
+
## License
|
|
72
|
+
|
|
73
|
+
Proprietary. See LICENSE file.
|