Now that we have another tabular data competition, you may find out my Kaggle pipeline (github)** to be useful.
\nThis is an Open Source Python based pipeline (195 ⭐ at github) for Kaggle tabular data competitions. Although it is customized for Kaggle TPS August 2022, with limited code changes, this project can be used as a pipeline for any tabular data competition. This project includes APIs for most of the ML competition related tasks:
\nThe code is highly modular. You can pick python functions and start using those in Kaggle kernel. For example, here are utility functions related to feature engineering or time series.
\nSteps to execute this pipeline is documented in the README.md file.
\nIf you want to just browse the code (to get an understanding of it), you may start from:
\nkaggle_pipeline_tps_aug_22ainscriptslgb_baseline.py\nIf you have any queries, please let me know, I will try to answer that.
\nLink to the github repo: https://github.com/arnabbiswas1/kaggle_pipeline_tps_aug_22
\nIf you find the repository to be helpful, please feel free to let me know what you like and dislike about it. Also, save the repo at github with a star.
", "messages": [ { "id": "2427313", "postDate": "09/07/2023 06:51:28", "content": "Now that we have another tabular data competition, you may find out my Kaggle pipeline (github)** to be useful.
\nThis is an Open Source Python based pipeline (195 ⭐ at github) for Kaggle tabular data competitions. Although it is customized for Kaggle TPS August 2022, with limited code changes, this project can be used as a pipeline for any tabular data competition. This project includes APIs for most of the ML competition related tasks:
\nThe code is highly modular. You can pick python functions and start using those in Kaggle kernel. For example, here are utility functions related to feature engineering or time series.
\nSteps to execute this pipeline is documented in the README.md file.
\nIf you want to just browse the code (to get an understanding of it), you may start from:
\nkaggle_pipeline_tps_aug_22ainscriptslgb_baseline.py\nIf you have any queries, please let me know, I will try to answer that.
\nLink to the github repo: https://github.com/arnabbiswas1/kaggle_pipeline_tps_aug_22
\nIf you find the repository to be helpful, please feel free to let me know what you like and dislike about it. Also, save the repo at github with a star.
", "rawMarkdown": "Now that we have another tabular data competition, you may find out my Kaggle pipeline ([github](https://github.com/arnabbiswas1/kaggle_pipeline_tps_aug_22))** to be useful.\n\nThis is an **Open Source** Python based pipeline (**195 ⭐ at github**) for Kaggle tabular data competitions. Although it is customized for Kaggle TPS August 2022, with limited code changes, this project can be used as a pipeline for any tabular data competition. This project includes APIs for most of the ML competition related tasks:\n\n1. data processing\n2. visualization\n3. feature engineering\n4. training\n5. ensembling\n6. feature selection\n7. hyperparameter optimization\n8. experiment tracking\n9. submission of prediction to kaggle\n\nThe code is highly modular. You can pick python functions and start using those in Kaggle kernel. For example, here are utility functions related to [feature engineering](https://github.com/arnabbiswas1/kaggle_pipeline_tps_aug_22/blob/main/src/fe/fe_util.py) or [time series](https://github.com/arnabbiswas1/kaggle_pipeline_tps_aug_22/blob/main/src/ts/ts_util.py).\n\nSteps to execute this pipeline is documented in the README.md file. \n\nIf you want to just browse the code (to get an understanding of it), you may start from:\n\n\tkaggle_pipeline_tps_aug_22/blob/main/src/scripts/training/lgb_baseline.py\n\nIf you have any queries, please let me know, I will try to answer that.\n\nLink to the github repo: https://github.com/arnabbiswas1/kaggle_pipeline_tps_aug_22\n\n**If you find the repository to be helpful, please feel free to let me know what you like and dislike about it. Also, save the repo at github with a star.**", "votes": null }, { "id": "2427349", "postDate": "09/07/2023 07:12:23", "content": "👏 Wow, this Kaggle pipeline looks like a fantastic resource for anyone diving into tabular data competitions! Thanks for sharing it with the community. It's evident that you've put a lot of effort into making it a valuable tool for Kagglers.
\nThe fact that it's open source is especially commendable as it allows for collaboration and improvement from the community. The extensive list of functionalities it covers, from data processing to submission of predictions to Kaggle, is impressive and can save competitors a lot of time.
\nFor those interested, the modular nature of the code is a significant advantage. You can easily integrate specific Python functions into your Kaggle kernels, making it adaptable to various competition requirements.
\nThe link to your GitHub repository is a valuable resource, and I encourage everyone interested in tabular data competitions to check it out. It's always great to support and acknowledge the hard work of fellow data scientists by starring the repository if you find it helpful.
\nIf you have any questions or need assistance with using this pipeline, it's excellent that you're open to queries and willing to help others understand and use your resource effectively.
", "rawMarkdown": "👏 Wow, this Kaggle pipeline looks like a fantastic resource for anyone diving into tabular data competitions! Thanks for sharing it with the community. It's evident that you've put a lot of effort into making it a valuable tool for Kagglers.\n\nThe fact that it's open source is especially commendable as it allows for collaboration and improvement from the community. The extensive list of functionalities it covers, from data processing to submission of predictions to Kaggle, is impressive and can save competitors a lot of time.\n\nFor those interested, the modular nature of the code is a significant advantage. You can easily integrate specific Python functions into your Kaggle kernels, making it adaptable to various competition requirements.\n\nThe link to your GitHub repository is a valuable resource, and I encourage everyone interested in tabular data competitions to check it out. It's always great to support and acknowledge the hard work of fellow data scientists by starring the repository if you find it helpful.\n\nIf you have any questions or need assistance with using this pipeline, it's excellent that you're open to queries and willing to help others understand and use your resource effectively.", "votes": null }, { "id": "2427467", "postDate": "09/07/2023 08:36:27", "content": "Thanks a lot for your kind words.
", "rawMarkdown": "Thanks a lot for your kind words.", "votes": null } ], "comments": [ { "id": 2427349, "author_name": "", "author_url": "", "post_date": "09/07/2023 07:12:23", "content": "👏 Wow, this Kaggle pipeline looks like a fantastic resource for anyone diving into tabular data competitions! Thanks for sharing it with the community. It's evident that you've put a lot of effort into making it a valuable tool for Kagglers.
\nThe fact that it's open source is especially commendable as it allows for collaboration and improvement from the community. The extensive list of functionalities it covers, from data processing to submission of predictions to Kaggle, is impressive and can save competitors a lot of time.
\nFor those interested, the modular nature of the code is a significant advantage. You can easily integrate specific Python functions into your Kaggle kernels, making it adaptable to various competition requirements.
\nThe link to your GitHub repository is a valuable resource, and I encourage everyone interested in tabular data competitions to check it out. It's always great to support and acknowledge the hard work of fellow data scientists by starring the repository if you find it helpful.
\nIf you have any questions or need assistance with using this pipeline, it's excellent that you're open to queries and willing to help others understand and use your resource effectively.
", "votes": null, "replies": [ { "id": 2427467, "author_name": "arnabbiswas1", "author_url": "", "post_date": "09/07/2023 08:36:27", "content": "Thanks a lot for your kind words.
", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "2427313": "Now that we have another tabular data competition, you may find out my Kaggle pipeline ([github](https://github.com/arnabbiswas1/kaggle_pipeline_tps_aug_22))** to be useful.\n\nThis is an **Open Source** Python based pipeline (**195 ⭐ at github**) for Kaggle tabular data competitions. Although it is customized for Kaggle TPS August 2022, with limited code changes, this project can be used as a pipeline for any tabular data competition. This project includes APIs for most of the ML competition related tasks:\n\n1. data processing\n2. visualization\n3. feature engineering\n4. training\n5. ensembling\n6. feature selection\n7. hyperparameter optimization\n8. experiment tracking\n9. submission of prediction to kaggle\n\nThe code is highly modular. You can pick python functions and start using those in Kaggle kernel. For example, here are utility functions related to [feature engineering](https://github.com/arnabbiswas1/kaggle_pipeline_tps_aug_22/blob/main/src/fe/fe_util.py) or [time series](https://github.com/arnabbiswas1/kaggle_pipeline_tps_aug_22/blob/main/src/ts/ts_util.py).\n\nSteps to execute this pipeline is documented in the README.md file. \n\nIf you want to just browse the code (to get an understanding of it), you may start from:\n\n\tkaggle_pipeline_tps_aug_22/blob/main/src/scripts/training/lgb_baseline.py\n\nIf you have any queries, please let me know, I will try to answer that.\n\nLink to the github repo: https://github.com/arnabbiswas1/kaggle_pipeline_tps_aug_22\n\n**If you find the repository to be helpful, please feel free to let me know what you like and dislike about it. Also, save the repo at github with a star.**", "2427349": "👏 Wow, this Kaggle pipeline looks like a fantastic resource for anyone diving into tabular data competitions! Thanks for sharing it with the community. It's evident that you've put a lot of effort into making it a valuable tool for Kagglers.\n\nThe fact that it's open source is especially commendable as it allows for collaboration and improvement from the community. The extensive list of functionalities it covers, from data processing to submission of predictions to Kaggle, is impressive and can save competitors a lot of time.\n\nFor those interested, the modular nature of the code is a significant advantage. You can easily integrate specific Python functions into your Kaggle kernels, making it adaptable to various competition requirements.\n\nThe link to your GitHub repository is a valuable resource, and I encourage everyone interested in tabular data competitions to check it out. It's always great to support and acknowledge the hard work of fellow data scientists by starring the repository if you find it helpful.\n\nIf you have any questions or need assistance with using this pipeline, it's excellent that you're open to queries and willing to help others understand and use your resource effectively.", "2427467": "Thanks a lot for your kind words." }, "source": "meta" }