flopsearch 0.1.0__cp312-cp312-musllinux_1_2_armv7l.whl → 0.1.1__cp312-cp312-musllinux_1_2_armv7l.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.
Potentially problematic release.
This version of flopsearch might be problematic. Click here for more details.
|
Binary file
|
|
@@ -0,0 +1,50 @@
|
|
|
1
|
+
Metadata-Version: 2.4
|
|
2
|
+
Name: flopsearch
|
|
3
|
+
Version: 0.1.1
|
|
4
|
+
Classifier: Programming Language :: Rust
|
|
5
|
+
Classifier: Programming Language :: Python :: Implementation :: CPython
|
|
6
|
+
Classifier: Programming Language :: Python :: Implementation :: PyPy
|
|
7
|
+
Summary: Python package providing an implementation of the FLOP causal discovery algorithm for linear additive noise models
|
|
8
|
+
Keywords: causal discovery,DAGs,Bayesian networks,structure learning
|
|
9
|
+
Author: Sebastian Weichwald, Leonard Henckel
|
|
10
|
+
Author-email: Marcel Wienöbst <marcel.wienoebst@gmx.de>
|
|
11
|
+
Requires-Python: >=3.8
|
|
12
|
+
Description-Content-Type: text/markdown; charset=UTF-8; variant=GFM
|
|
13
|
+
|
|
14
|
+
# flopsearch
|
|
15
|
+
|
|
16
|
+
Python package providing an implementation of the FLOP causal discovery algorithm for linear additive noise models.
|
|
17
|
+
|
|
18
|
+
## Installation
|
|
19
|
+
flopsearch can be installed via pip:
|
|
20
|
+
|
|
21
|
+
```bash
|
|
22
|
+
pip install flopsearch
|
|
23
|
+
```
|
|
24
|
+
|
|
25
|
+
## Citing FLOP
|
|
26
|
+
If you use FLOP in your scientific work, please cite this paper:
|
|
27
|
+
```bibtex
|
|
28
|
+
@article{cifly2025,
|
|
29
|
+
author = {Marcel Wien{"{o}}bst and Leonard Henckel and Sebastian Weichwald},
|
|
30
|
+
title = {{Embracing Discrete Search: A Reasonable Approach to Causal Structure Learning}},
|
|
31
|
+
journal = {{arXiv preprint arXiv:2510.04970}},
|
|
32
|
+
year = {2025}
|
|
33
|
+
}
|
|
34
|
+
```
|
|
35
|
+
|
|
36
|
+
## Example
|
|
37
|
+
A simple example run of the FLOP algorithm provided by flopsearch.
|
|
38
|
+
|
|
39
|
+
``` py
|
|
40
|
+
import flopsearch
|
|
41
|
+
import numpy as np
|
|
42
|
+
from scipy import linalg
|
|
43
|
+
|
|
44
|
+
p = 10
|
|
45
|
+
W = np.diag(np.ones(p - 1), 1)
|
|
46
|
+
X = np.random.randn(10000, p).dot(linalg.inv(np.eye(p) - W))
|
|
47
|
+
X_std = (X - np.mean(X, axis=0)) / np.std(X, axis=0)
|
|
48
|
+
flopsearch.flop(X_std, 2.0, restarts=20)
|
|
49
|
+
```
|
|
50
|
+
|
|
@@ -1,8 +1,8 @@
|
|
|
1
|
-
flopsearch-0.1.
|
|
2
|
-
flopsearch-0.1.
|
|
1
|
+
flopsearch-0.1.1.dist-info/METADATA,sha256=dPi3uS6mdZBkzrtRncMmOmqHL4c59PsVA8kJ_6x1DZ0,1551
|
|
2
|
+
flopsearch-0.1.1.dist-info/WHEEL,sha256=U3fWVEfQ8-Kxvc2cWwxPlkOO5a8GpkZ9qNW5c1EUVa8,107
|
|
3
3
|
flopsearch.libs/libgcc_s-0366c7ba.so.1,sha256=QjFj5R7pVqB-p92h2JTCmlyfd3UKsVGW_Y_l3SqOAaU,2753157
|
|
4
4
|
flopsearch/__init__.py,sha256=UqRJYN7saLZWFc0psFyiG39C208VD3OUvagoo2sxfq0,123
|
|
5
5
|
flopsearch/__init__.pyi,sha256=yQdOZROGWM0k0sdNj-KiielkkQcxiAcEgxaunbqJw9E,1122
|
|
6
|
-
flopsearch/flopsearch.cpython-312-arm-linux-musleabihf.so,sha256=
|
|
6
|
+
flopsearch/flopsearch.cpython-312-arm-linux-musleabihf.so,sha256=ob0XtPuGshToh7rOLSHBNFBSw8QaGz55bjMcxh10epY,801453
|
|
7
7
|
flopsearch/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
8
|
-
flopsearch-0.1.
|
|
8
|
+
flopsearch-0.1.1.dist-info/RECORD,,
|
|
@@ -1,11 +0,0 @@
|
|
|
1
|
-
Metadata-Version: 2.4
|
|
2
|
-
Name: flopsearch
|
|
3
|
-
Version: 0.1.0
|
|
4
|
-
Classifier: Programming Language :: Rust
|
|
5
|
-
Classifier: Programming Language :: Python :: Implementation :: CPython
|
|
6
|
-
Classifier: Programming Language :: Python :: Implementation :: PyPy
|
|
7
|
-
Summary: Python package providing an implementation of the FLOP causal discovery algorithm for linear additive noise models
|
|
8
|
-
Keywords: causal discovery,DAGs,Bayesian networks,structure learning
|
|
9
|
-
Author: Sebastian Weichwald, Leonard Henckel
|
|
10
|
-
Author-email: Marcel Wienöbst <marcel.wienoebst@gmx.de>
|
|
11
|
-
Requires-Python: >=3.8
|