datapruning 1.0.0__cp39-cp39-win32.whl
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/__init__.py
ADDED
|
@@ -0,0 +1 @@
|
|
|
1
|
+
from ._core import Pruner
|
|
Binary file
|
|
@@ -0,0 +1,79 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: datapruning
|
|
3
|
+
Version: 1.0.0
|
|
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 :: 3.9
|
|
12
|
+
Classifier: Programming Language :: Python :: 3.10
|
|
13
|
+
Classifier: Programming Language :: Python :: 3.11
|
|
14
|
+
Classifier: Programming Language :: Python :: 3.12
|
|
15
|
+
Classifier: Programming Language :: Python :: 3.13
|
|
16
|
+
Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
|
|
17
|
+
Requires-Python: >=3.9
|
|
18
|
+
Description-Content-Type: text/markdown
|
|
19
|
+
License-File: LICENSE
|
|
20
|
+
Requires-Dist: numpy>=1.24.0
|
|
21
|
+
Requires-Dist: pandas>=2.0.0
|
|
22
|
+
Requires-Dist: torch>=2.0.0
|
|
23
|
+
Dynamic: license-file
|
|
24
|
+
|
|
25
|
+
# DataPruning Lite
|
|
26
|
+
|
|
27
|
+
Local-first dataset pruning. Free for datasets up to 100K rows.
|
|
28
|
+
|
|
29
|
+
## Overview
|
|
30
|
+
|
|
31
|
+
DataPruning reduces dataset size before training by selecting a smaller,
|
|
32
|
+
more informative subset of data. Runs entirely on your machine through a
|
|
33
|
+
compiled SDK — no data upload, no external processing.
|
|
34
|
+
|
|
35
|
+
## Installation
|
|
36
|
+
|
|
37
|
+
```bash
|
|
38
|
+
pip install datapruning
|
|
39
|
+
```
|
|
40
|
+
|
|
41
|
+
**Note:** PyTorch (~2 GB) is a required dependency and will be installed
|
|
42
|
+
automatically. See [pytorch.org](https://pytorch.org) for GPU/CPU options.
|
|
43
|
+
|
|
44
|
+
## Requirements
|
|
45
|
+
|
|
46
|
+
- Python 3.9–3.13
|
|
47
|
+
- PyTorch 2.0+
|
|
48
|
+
- Pandas 2.0+
|
|
49
|
+
- NumPy 1.24+
|
|
50
|
+
|
|
51
|
+
## Usage
|
|
52
|
+
|
|
53
|
+
```python
|
|
54
|
+
import pandas as pd
|
|
55
|
+
from datapruning import Pruner
|
|
56
|
+
|
|
57
|
+
df = pd.read_csv("dataset.csv")
|
|
58
|
+
p = Pruner(df)
|
|
59
|
+
filtered = p.prune(target_col="label", keep_ratio=0.5)
|
|
60
|
+
|
|
61
|
+
print(f"Kept {len(filtered)} / {len(df)} rows")
|
|
62
|
+
```
|
|
63
|
+
|
|
64
|
+
## Features
|
|
65
|
+
|
|
66
|
+
- Local execution, no data upload
|
|
67
|
+
- Pre-training dataset optimization
|
|
68
|
+
- Pandas DataFrame input
|
|
69
|
+
- Compiled processing module
|
|
70
|
+
- Free tier: up to 100K rows per dataset
|
|
71
|
+
|
|
72
|
+
## Limits
|
|
73
|
+
|
|
74
|
+
Datasets exceeding 100,000 rows require an enterprise license.
|
|
75
|
+
Visit https://www.datapruning.com for details.
|
|
76
|
+
|
|
77
|
+
## License
|
|
78
|
+
|
|
79
|
+
Proprietary software. See LICENSE file.
|
|
@@ -0,0 +1,7 @@
|
|
|
1
|
+
datapruning/__init__.py,sha256=k-yo1nj1HA336hVFCyb6ptCiCGqPsu_nf3vkeGvQGCI,27
|
|
2
|
+
datapruning/_core.cp39-win32.pyd,sha256=WrV5vpWuu1cK7Ri_VAmbFO60Ok7MfJc87Ti4eVkYstM,300032
|
|
3
|
+
datapruning-1.0.0.dist-info/licenses/LICENSE,sha256=Tm61pd8l_wyeRImUqQVythDI-IWUU2o6CUf_csbVpwA,791
|
|
4
|
+
datapruning-1.0.0.dist-info/METADATA,sha256=5NP1SUAAlxVlfh1JiOZPfNu6IbvPD-rv67hS9u7YZO4,2127
|
|
5
|
+
datapruning-1.0.0.dist-info/WHEEL,sha256=PC2P4cbO3o4K-7H6cS-uBFm9qAILDgbBrB8W9jD4fmM,95
|
|
6
|
+
datapruning-1.0.0.dist-info/top_level.txt,sha256=HHitOoBY_0KeZGXmSViQTKsbSMkUJNPSc7oUMAoxlF8,12
|
|
7
|
+
datapruning-1.0.0.dist-info/RECORD,,
|
|
@@ -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
|
|
@@ -0,0 +1 @@
|
|
|
1
|
+
datapruning
|