perpetual 0.7.8__cp311-none-win_amd64.whl → 0.7.10__cp311-none-win_amd64.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 perpetual might be problematic. Click here for more details.

Files changed (6) hide show
  1. perpetual/perpetual.cp311-win_amd64.pyd +0 -0
  2. {perpetual-0.7.8.dist-info → perpetual-0.7.10.dist-info}/METADATA +21 -2
  3. perpetual-0.7.10.dist-info/RECORD +12 -0
  4. perpetual-0.7.8.dist-info/RECORD +0 -12
  5. {perpetual-0.7.8.dist-info → perpetual-0.7.10.dist-info}/WHEEL +0 -0
  6. {perpetual-0.7.8.dist-info → perpetual-0.7.10.dist-info}/license_files/LICENSE +0 -0
perpetual/perpetual.cp311-win_amd64.pyd CHANGED
Binary file
{perpetual-0.7.8.dist-info → perpetual-0.7.10.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.3
2
2
  Name: perpetual
3
- Version: 0.7.8
3
+ Version: 0.7.10
4
4
  Classifier: Programming Language :: Rust
5
5
  Classifier: Programming Language :: Python :: 3
6
6
  Classifier: Programming Language :: Python :: 3.9
@@ -42,6 +42,7 @@ Project-URL: Source Code, https://github.com/perpetual-ml/perpetual
42
42
  [![PyPI Version](https://img.shields.io/pypi/v/perpetual.svg?logo=pypi&logoColor=white)](https://pypi.org/project/perpetual)
43
43
  [![Crates.io Version](https://img.shields.io/crates/v/perpetual?logo=rust&logoColor=white)](https://crates.io/crates/perpetual)
44
44
  [![Static Badge](https://img.shields.io/badge/join-discord-blue?logo=discord)](https://discord.gg/AyUK7rr6wy)
45
+ ![PyPI - Downloads](https://img.shields.io/pypi/dm/perpetual)
45
46
 
46
47
  </div>
47
48
 
@@ -67,7 +68,25 @@ The following table summarizes the results for the [Cover Types](https://scikit-
67
68
  | ---------------- | --------------------- | ------------------ | ----------------- | ------------------ | ----------------- |
68
69
  | 0.9 | 100 | 0.091 | 0.084 | 72x | 78x |
69
70
 
70
- You can reproduce the results using the scripts in the [examples](./python-package/examples) folder.
71
+ The results can be reproduced using the scripts in the [examples](./python-package/examples) folder.
72
+
73
+ PerpetualBooster is a GBM but behaves like AutoML so it is benchmarked also against AutoGluon (v1.2, best quality preset), the current leader in [AutoML benchmark](https://automlbenchmark.streamlit.app/cd_diagram). Top 10 datasets with the most number of rows are selected from [OpenML datasets](https://www.openml.org/). The results are summarized in the following table for regression tasks:
74
+
75
+ | OpenML Task | Perpetual Training Duration | Perpetual Inference Duration | Perpetual RMSE | AutoGluon Training Duration | AutoGluon Inference Duration | AutoGluon RMSE |
76
+ | -------------------------------------------- | --------------------------- | ----------------------------------------------------------------- | -------------- | --------------------------- | ----------------------------------------------------------------- | -------------- |
77
+ | [Airlines_DepDelay_10M](openml.org/t/359929) | 518 | 11.3 | 29.0 | 520 | 30.9 <td style="background-color:green;color:white;"> 28.8 </td> |
78
+ | [bates_regr_100](openml.org/t/361940) | 3421 | 15.1 <td style="background-color:green;color:white;"> 1.084 </td> | OOM | OOM | OOM |
79
+ | [BNG(libras_move)](openml.org/t/7327) | 1956 | 4.2 <td style="background-color:green;color:white;"> 2.51 </td> | 1922 | 97.6 | 2.53 |
80
+ | [BNG(satellite_image)](openml.org/t/7326) | 334 | 1.6 | 0.731 | 337 | 10.0 <td style="background-color:green;color:white;"> 0.721 </td> |
81
+ | [COMET_MC](openml.org/t/14949) | 44 | 1.0 <td style="background-color:green;color:white;"> 0.0615 </td> | 47 | 5.0 | 0.0662 |
82
+ | [friedman1](openml.org/t/361939) | 275 | 4.2 <td style="background-color:green;color:white;"> 1.047 </td> | 278 | 5.1 | 1.487 |
83
+ | [poker](openml.org/t/10102) | 38 | 0.6 <td style="background-color:green;color:white;"> 0.256 </td> | 41 | 1.2 | 0.722 |
84
+ | [subset_higgs](openml.org/t/361955) | 868 | 10.6 <td style="background-color:green;color:white;"> 0.420 </td> | 870 | 24.5 | 0.421 |
85
+ | [BNG(autoHorse)](openml.org/t/7319) | 107 | 1.1 <td style="background-color:green;color:white;"> 19.0 </td> | 107 | 3.2 | 20.5 |
86
+ | [BNG(pbc)](openml.org/t/7318) | 48 | 0.6 <td style="background-color:green;color:white;"> 836.5 </td> | 51 | 0.2 | 957.1 |
87
+ | average | 465 | 3.9 | - | 464 | 19.7 | - |
88
+
89
+ PerpetualBooster outperformed AutoGluon on 8 out of 10 datasets, training equally fast and inferring 5x faster. The results can be reproduced using the automlbenchmark fork [here](https://github.com/deadsoul44/automlbenchmark).
71
90
 
72
91
  ## Usage
73
92
 
perpetual-0.7.10.dist-info/RECORD ADDED
@@ -0,0 +1,12 @@
1
+ perpetual-0.7.10.dist-info/METADATA,sha256=wVzy1s0FfRlDOW-NIyCxaKAPTgwqbIQYgQl924a-AwQ,9843
2
+ perpetual-0.7.10.dist-info/WHEEL,sha256=DzHgklH-N2Rm5CKeMVkz9xJT6rK_2P-i_Xf1Csdhcdo,95
3
+ perpetual-0.7.10.dist-info/license_files/LICENSE,sha256=YpyY33_TKPAOHPZllvDC4KKcSwyBG5nY9k6rxusNu30,35014
4
+ perpetual-0.7.10.dist-info/license_files/LICENSE,sha256=YpyY33_TKPAOHPZllvDC4KKcSwyBG5nY9k6rxusNu30,35014
5
+ perpetual/booster.py,sha256=ICWJRuSxoaUgRHo9N8hodz1MlyRBVKPhVnfQJOes968,46919
6
+ perpetual/data.py,sha256=HiDsv2i1p9cLkXe8vnekxfpafyuxfWXwXrucdIir3xk,614
7
+ perpetual/serialize.py,sha256=FeW4JsUFVsrft9N7gz-ebn5mXvDv4LiJC2sgBEeGxYo,1957
8
+ perpetual/types.py,sha256=idZNsDErNTur_rJ_5Co8Pb6fik-AUn9lkrXmjbQJVX0,3381
9
+ perpetual/utils.py,sha256=i_7EB5xQXAGtODONhrOwfxRfH3YR7U0cQJvL8eUNFK8,7444
10
+ perpetual/__init__.py,sha256=V0RhghaG0CuKxKrzYUBYqrf7Drb-gjmznsbz9KT12lk,122
11
+ perpetual/perpetual.cp311-win_amd64.pyd,sha256=Nr_5AwSBh-ZeYLuCakFxd-chDCh464J5W-GhM45KdcI,1522176
12
+ perpetual-0.7.10.dist-info/RECORD,,
perpetual-0.7.8.dist-info/RECORD DELETED
@@ -1,12 +0,0 @@
1
- perpetual-0.7.8.dist-info/METADATA,sha256=1UfqObGdV53oWZMVyTM5HXi-CaVsoieGH76XX49LwfU,5679
2
- perpetual-0.7.8.dist-info/WHEEL,sha256=DzHgklH-N2Rm5CKeMVkz9xJT6rK_2P-i_Xf1Csdhcdo,95
3
- perpetual-0.7.8.dist-info/license_files/LICENSE,sha256=YpyY33_TKPAOHPZllvDC4KKcSwyBG5nY9k6rxusNu30,35014
4
- perpetual-0.7.8.dist-info/license_files/LICENSE,sha256=YpyY33_TKPAOHPZllvDC4KKcSwyBG5nY9k6rxusNu30,35014
5
- perpetual/booster.py,sha256=ICWJRuSxoaUgRHo9N8hodz1MlyRBVKPhVnfQJOes968,46919
6
- perpetual/data.py,sha256=HiDsv2i1p9cLkXe8vnekxfpafyuxfWXwXrucdIir3xk,614
7
- perpetual/serialize.py,sha256=FeW4JsUFVsrft9N7gz-ebn5mXvDv4LiJC2sgBEeGxYo,1957
8
- perpetual/types.py,sha256=idZNsDErNTur_rJ_5Co8Pb6fik-AUn9lkrXmjbQJVX0,3381
9
- perpetual/utils.py,sha256=i_7EB5xQXAGtODONhrOwfxRfH3YR7U0cQJvL8eUNFK8,7444
10
- perpetual/__init__.py,sha256=V0RhghaG0CuKxKrzYUBYqrf7Drb-gjmznsbz9KT12lk,122
11
- perpetual/perpetual.cp311-win_amd64.pyd,sha256=oym-J0XCSKX0UNq4HOu2gIOYjAXURQP_0-aOfcmqFGQ,1499136
12
- perpetual-0.7.8.dist-info/RECORD,,