{ "id": 454700, "title": "PYBOOST - breakthrough gradient boosting for MULTI-target tasks", "url": "/competitions/open-problems-single-cell-perturbations/discussion/454700", "author_name": "Alexander Chervov", "post_date": "2023-11-11T09:12:22.151000", "votes": 33, "comment_count": 0, "views": 0, "content": "

Here is the public notebook with an example of the \"PYBOOST\" - breakthrough gradient boosting for MULTI-target tasks: https://www.kaggle.com/code/alexandervc/pyboost-secret-grandmaster-s-tool
\nWelcome to try, tune and get better score.

\n

PYBOOST - is the best boosting for MULTI-target tasks

\n

It designed especially for MULTI-Target(!) tasks. For such tasks it consitenly outperforms the other boostings, as well as incomparably faster.

\n

PYBOOST -> Gold on Kaggle

\n

Pyboost is created by team lead by the Kaggle Grandmaster - Btbpanda - Anton Vakhrushev https://www.kaggle.com/btbpanda

\n

He and others got many gold medals on Kaggle: recent CAFA5 (https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/434064 ), last year \"Open Problems\" top7-team \"Chromosom\", and public top2 team, etc.

\n

Some inpendent check - PyBoost outperaforming other boostings: \"Table 2. Performance of Kinase Activity Prediction Modelsa\" https://pubs.acs.org/doi/full/10.1021/acs.jcim.3c00132

\n

PYBOOST - easy to use - similar interface and params as other boostings and sklearn models

\n
model = GradientBoosting()\nmodel.fit(X,Y)\nmodel.predict(X)\n\n\n\n\n\n\n\n\n\nmodel = GradientBoosting(, ntrees=ntrees, lr=lr,  max_depth=max_depth  , subsample=subsample, colsample=colsample, min_data_in_leaf=, min_gain_to_split=, verbose=  )\n
\n

OP2 - easily LB-score 0.604 - welcome improve it - see suggestions in the notebook.

\n
References:
\n

Github: https://github.com/sb-ai-lab/Py-Boost
\nIosipoi, Leonid, and Anton Vakhrushev. \"SketchBoost: Fast Gradient Boosted Decision Tree for Multioutput Problems.\" Advances in Neural Information Processing Systems 35 (2022): 25422-25435. https://openreview.net/forum?id=WSxarC8t-T

", "messages": [ { "id": 2520896, "postDate": "2023-11-11T09:12:22.150Z", "content": "

Here is the public notebook with an example of the \"PYBOOST\" - breakthrough gradient boosting for MULTI-target tasks: https://www.kaggle.com/code/alexandervc/pyboost-secret-grandmaster-s-tool
\nWelcome to try, tune and get better score.

\n

PYBOOST - is the best boosting for MULTI-target tasks

\n

It designed especially for MULTI-Target(!) tasks. For such tasks it consitenly outperforms the other boostings, as well as incomparably faster.

\n

PYBOOST -> Gold on Kaggle

\n

Pyboost is created by team lead by the Kaggle Grandmaster - Btbpanda - Anton Vakhrushev https://www.kaggle.com/btbpanda

\n

He and others got many gold medals on Kaggle: recent CAFA5 (https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/434064 ), last year \"Open Problems\" top7-team \"Chromosom\", and public top2 team, etc.

\n

Some inpendent check - PyBoost outperaforming other boostings: \"Table 2. Performance of Kinase Activity Prediction Modelsa\" https://pubs.acs.org/doi/full/10.1021/acs.jcim.3c00132

\n

PYBOOST - easy to use - similar interface and params as other boostings and sklearn models

\n
model = GradientBoosting()\nmodel.fit(X,Y)\nmodel.predict(X)\n\n\n\n\n\n\n\n\n\nmodel = GradientBoosting(, ntrees=ntrees, lr=lr,  max_depth=max_depth  , subsample=subsample, colsample=colsample, min_data_in_leaf=, min_gain_to_split=, verbose=  )\n
\n

OP2 - easily LB-score 0.604 - welcome improve it - see suggestions in the notebook.

\n
References:
\n

Github: https://github.com/sb-ai-lab/Py-Boost
\nIosipoi, Leonid, and Anton Vakhrushev. \"SketchBoost: Fast Gradient Boosted Decision Tree for Multioutput Problems.\" Advances in Neural Information Processing Systems 35 (2022): 25422-25435. https://openreview.net/forum?id=WSxarC8t-T

", "rawMarkdown": "Here is the public notebook with an example of the \"PYBOOST\" - breakthrough gradient boosting for MULTI-target tasks: https://www.kaggle.com/code/alexandervc/pyboost-secret-grandmaster-s-tool\nWelcome to try, tune and get better score. \n\n### PYBOOST - is the best boosting for MULTI-target tasks\n\nIt designed especially for MULTI-Target(!) tasks. For such tasks it consitenly outperforms the other boostings, as well as incomparably faster.\n\n### PYBOOST -> Gold on Kaggle\nPyboost is created by team lead by the Kaggle Grandmaster - Btbpanda - Anton Vakhrushev https://www.kaggle.com/btbpanda\n\nHe and others got many gold medals on Kaggle: recent CAFA5 (https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/434064 ), last year \"Open Problems\" top7-team \"Chromosom\", and public top2 team, etc.\n\nSome inpendent check - PyBoost outperaforming other boostings: \"Table 2. Performance of Kinase Activity Prediction Modelsa\" https://pubs.acs.org/doi/full/10.1021/acs.jcim.3c00132\n\n### PYBOOST - easy to use - similar interface and params as other boostings and sklearn models\n```python\nmodel = GradientBoosting('mse')\nmodel.fit(X,Y)\nmodel.predict(X)\n\n# Main params are similar to other boostings:\n# ntrees - number of trees (iterations)\n# lr - learning rate\n# max_depth - maximal depth for trees\n# subsample - subsampling fraction\n# colsample - subsampleling fraction for columns\n# Etc \n# Example:\nmodel = GradientBoosting('mse', ntrees=ntrees, lr=lr, max_depth=max_depth , subsample=subsample, colsample=colsample, min_data_in_leaf=1, min_gain_to_split=0, verbose=100 )\n```\n\nOP2 - easily LB-score 0.604 - welcome improve it - see suggestions in the notebook.\n\n\n##### References:\n\nGithub: https://github.com/sb-ai-lab/Py-Boost\nIosipoi, Leonid, and Anton Vakhrushev. \"SketchBoost: Fast Gradient Boosted Decision Tree for Multioutput Problems.\" Advances in Neural Information Processing Systems 35 (2022): 25422-25435. https://openreview.net/forum?id=WSxarC8t-T\n", "votes": 33 } ], "comments": [], "raw_markdown_by_id": { "2520896": "Here is the public notebook with an example of the \"PYBOOST\" - breakthrough gradient boosting for MULTI-target tasks: https://www.kaggle.com/code/alexandervc/pyboost-secret-grandmaster-s-tool\nWelcome to try, tune and get better score. \n\n### PYBOOST - is the best boosting for MULTI-target tasks\n\nIt designed especially for MULTI-Target(!) tasks. For such tasks it consitenly outperforms the other boostings, as well as incomparably faster.\n\n### PYBOOST -> Gold on Kaggle\nPyboost is created by team lead by the Kaggle Grandmaster - Btbpanda - Anton Vakhrushev https://www.kaggle.com/btbpanda\n\nHe and others got many gold medals on Kaggle: recent CAFA5 (https://www.kaggle.com/competitions/cafa-5-protein-function-prediction/discussion/434064 ), last year \"Open Problems\" top7-team \"Chromosom\", and public top2 team, etc.\n\nSome inpendent check - PyBoost outperaforming other boostings: \"Table 2. Performance of Kinase Activity Prediction Modelsa\" https://pubs.acs.org/doi/full/10.1021/acs.jcim.3c00132\n\n### PYBOOST - easy to use - similar interface and params as other boostings and sklearn models\n```python\nmodel = GradientBoosting('mse')\nmodel.fit(X,Y)\nmodel.predict(X)\n\n# Main params are similar to other boostings:\n# ntrees - number of trees (iterations)\n# lr - learning rate\n# max_depth - maximal depth for trees\n# subsample - subsampling fraction\n# colsample - subsampleling fraction for columns\n# Etc \n# Example:\nmodel = GradientBoosting('mse', ntrees=ntrees, lr=lr, max_depth=max_depth , subsample=subsample, colsample=colsample, min_data_in_leaf=1, min_gain_to_split=0, verbose=100 )\n```\n\nOP2 - easily LB-score 0.604 - welcome improve it - see suggestions in the notebook.\n\n\n##### References:\n\nGithub: https://github.com/sb-ai-lab/Py-Boost\nIosipoi, Leonid, and Anton Vakhrushev. \"SketchBoost: Fast Gradient Boosted Decision Tree for Multioutput Problems.\" Advances in Neural Information Processing Systems 35 (2022): 25422-25435. https://openreview.net/forum?id=WSxarC8t-T\n" } }