New to machine learning and data science? No question is too basic or too simple. Feel free to start your own thread, or use this thread as a place to post any first-timer clarifying questions for the Kaggle community to help you with!
\nIf you would consider yourself a beginner but don't know where to get started, let other Kagglers help you take your first steps here!
\nNew to Kaggle? Take a look at a few videos Dr. Rachael Tatman has put together to learn a bit more about site etiquette, or Kaggle lingo.
\nRemember: Kaggle is for everyone. Whether you're teaming up or sharing tips in the competition forum, we expect everyone to follow our Kaggle community guidelines.
\nA tip on sharing content - Kaggle is a collaborative community, whereby sharing techniques, starter notebooks, and ideas in the discussion forums are highly encouraged throughout the competition. However, as the competition draws closer to the final deadline it's customary to keep high-scoring notebooks withheld until after the competition has concluded. This maintains the spirit of the competition, while also allowing individuals to submit their own creative work without jeopardy of a higher-scoring notebook being available for an automatic higher rank (through copy/submit). We disable publishing of public notebooks within the final week of the competition, but encourage you to use your best judgment prior to that deadline.
\nHappy Modeling!
", "messages": [ { "id": 2226343, "postDate": "2023-04-18T21:09:17.013Z", "content": "New to machine learning and data science? No question is too basic or too simple. Feel free to start your own thread, or use this thread as a place to post any first-timer clarifying questions for the Kaggle community to help you with!
\nIf you would consider yourself a beginner but don't know where to get started, let other Kagglers help you take your first steps here!
\nNew to Kaggle? Take a look at a few videos Dr. Rachael Tatman has put together to learn a bit more about site etiquette, or Kaggle lingo.
\nRemember: Kaggle is for everyone. Whether you're teaming up or sharing tips in the competition forum, we expect everyone to follow our Kaggle community guidelines.
\nA tip on sharing content - Kaggle is a collaborative community, whereby sharing techniques, starter notebooks, and ideas in the discussion forums are highly encouraged throughout the competition. However, as the competition draws closer to the final deadline it's customary to keep high-scoring notebooks withheld until after the competition has concluded. This maintains the spirit of the competition, while also allowing individuals to submit their own creative work without jeopardy of a higher-scoring notebook being available for an automatic higher rank (through copy/submit). We disable publishing of public notebooks within the final week of the competition, but encourage you to use your best judgment prior to that deadline.
\nHappy Modeling!
", "rawMarkdown": "New to machine learning and data science? No question is too basic or too simple. Feel free to start your own thread, or use this thread as a place to post any first-timer clarifying questions for the Kaggle community to help you with!\n\nIf you would consider yourself a beginner but don't know where to get started, let other Kagglers help you take your first steps here!\n\nNew to Kaggle? Take a look at a few videos Dr. Rachael Tatman has put together to learn a bit more about [site etiquette](https://www.youtube.com/watch?v=aIus8si_Et0), or [Kaggle lingo](https://www.youtube.com/watch?v=sEJHyuWKd-s).\n\nRemember: Kaggle is for everyone. Whether you're teaming up or sharing tips in the competition forum, we expect everyone to follow our [Kaggle community guidelines](https://www.kaggle.com/community-guidelines).\n\nA tip on sharing content - Kaggle is a collaborative community, whereby sharing techniques, starter notebooks, and ideas in the discussion forums are highly encouraged throughout the competition. However, as the competition draws closer to the final deadline it's customary to keep high-scoring notebooks withheld until after the competition has concluded. This maintains the spirit of the competition, while also allowing individuals to submit their own creative work without jeopardy of a higher-scoring notebook being available for an automatic higher rank (through copy/submit). We disable publishing of public notebooks within the final week of the competition, but encourage you to use your best judgment prior to that deadline.\n\nHappy Modeling!", "votes": 7 }, { "id": 2237630, "postDate": "2023-04-27T19:54:08.093Z", "content": "Thank you😄 I am a complete newbie, but fascinated by bioinformatics😻
", "rawMarkdown": "Thank you😄 I am a complete newbie, but fascinated by bioinformatics😻", "votes": 1 }, { "id": 2227358, "postDate": "2023-04-19T17:36:15.230Z", "content": "I am new to data science and machine learning, I am just starting out and got to know that kaggle is a data science community , currently I learning python and then I will move to advance steps but I am feeling overwhelmed y the amount of information out there ,If you guys can help me out I m a quick learner I will hopefully be half ready for this project by august if anyone can take me in there team as a newbie that would be of great help because you can guide me in this journey, 👀👀 thank you so much .
", "rawMarkdown": "I am new to data science and machine learning, I am just starting out and got to know that kaggle is a data science community , currently I learning python and then I will move to advance steps but I am feeling overwhelmed y the amount of information out there ,If you guys can help me out I m a quick learner I will hopefully be half ready for this project by august if anyone can take me in there team as a newbie that would be of great help because you can guide me in this journey, 👀👀 thank you so much .", "votes": 1 }, { "id": 2347475, "postDate": "2023-07-17T02:22:38.237Z", "content": "Thank you for the post. I've been reading a ton on kaggle and can tell this is an amazing community.
\nI would appreciate clarification on a few questions:
\nIt seems like most models are trained locally (or in the cloud), then uploaded to kaggle to make predictions for the submission file (especially for large datasets). Is this accurate?
It seems like feature engineering is more important typically than hyperparameter tuning. Is this true?
It seems like successful kagglers pick a library (like xgboost, pytorch, or tensorflow) really get to know it, then after they've got a good grip on it jump into a new library when they see it's having better success on certain types of data. Is this true?
Looking forward to learning from this community!
", "rawMarkdown": "Thank you for the post. I've been reading a ton on kaggle and can tell this is an amazing community. \n\n I would appreciate clarification on a few questions:\n\n1. It seems like most models are trained locally (or in the cloud), then uploaded to kaggle to make predictions for the submission file (especially for large datasets). Is this accurate?\n\n2. It seems like feature engineering is more important typically than hyperparameter tuning. Is this true?\n\n3. It seems like successful kagglers pick a library (like xgboost, pytorch, or tensorflow) really get to know it, then after they've got a good grip on it jump into a new library when they see it's having better success on certain types of data. Is this true?\n\nLooking forward to learning from this community!" }, { "id": 2345275, "postDate": "2023-07-15T08:42:59.443Z", "content": "I'm trying to create datasets from embeddings, which each file is around 1.5 Gb, and I have problems in kaggle. I have checked my quota, and also reduced the number of files for the creation, and always I get the same error:
\nThe first part:
\n\nWe are processing your data
\n
\n We estimate this dataset will take 10s to process.
\n To start working with your Dataset, click 'Go to Dataset' and close this dialog.
\n And after 30 secs. I always got the same error:
\n Oh no! Upload failed
\n Unfortunately we could not create your dataset.
\n Failed to check creation status. Please try again later.
Please @addisonhoward can you give me some clue that can be happening, there is some size limit in the files?
", "rawMarkdown": "I'm trying to create datasets from embeddings, which each file is around 1.5 Gb, and I have problems in kaggle. I have checked my quota, and also reduced the number of files for the creation, and always I get the same error:\nThe first part:\n>We are processing your data\nWe estimate this dataset will take 10s to process.\nTo start working with your Dataset, click 'Go to Dataset' and close this dialog.\nAnd after 30 secs. I always got the same error:\n>Oh no! Upload failed\nUnfortunately we could not create your dataset.\nFailed to check creation status. Please try again later.\n\nPlease @addisonhoward can you give me some clue that can be happening, there is some size limit in the files?" }, { "id": 2262136, "postDate": "2023-05-16T18:47:51.633Z", "rawMarkdown": "", "isDeleted": true }, { "id": 2226517, "postDate": "2023-04-19T02:18:02.643Z", "rawMarkdown": "", "votes": 1, "isDeleted": true } ], "comments": [ { "id": 2237630, "author_name": "Julia Collet", "author_url": "", "post_date": "2023-04-27T19:54:08.093000", "content": "Thank you😄 I am a complete newbie, but fascinated by bioinformatics😻
", "votes": 1, "replies": [] }, { "id": 2227358, "author_name": "ritika rawat 28", "author_url": "", "post_date": "2023-04-19T17:36:15.230000", "content": "I am new to data science and machine learning, I am just starting out and got to know that kaggle is a data science community , currently I learning python and then I will move to advance steps but I am feeling overwhelmed y the amount of information out there ,If you guys can help me out I m a quick learner I will hopefully be half ready for this project by august if anyone can take me in there team as a newbie that would be of great help because you can guide me in this journey, 👀👀 thank you so much .
", "votes": 1, "replies": [] }, { "id": 2347475, "author_name": "Landon Yurica", "author_url": "", "post_date": "2023-07-17T02:22:38.237000", "content": "Thank you for the post. I've been reading a ton on kaggle and can tell this is an amazing community.
\nI would appreciate clarification on a few questions:
\nIt seems like most models are trained locally (or in the cloud), then uploaded to kaggle to make predictions for the submission file (especially for large datasets). Is this accurate?
It seems like feature engineering is more important typically than hyperparameter tuning. Is this true?
It seems like successful kagglers pick a library (like xgboost, pytorch, or tensorflow) really get to know it, then after they've got a good grip on it jump into a new library when they see it's having better success on certain types of data. Is this true?
Looking forward to learning from this community!
", "votes": 0, "replies": [] }, { "id": 2345275, "author_name": "Victor Fernandez Albor", "author_url": "", "post_date": "2023-07-15T08:42:59.443000", "content": "I'm trying to create datasets from embeddings, which each file is around 1.5 Gb, and I have problems in kaggle. I have checked my quota, and also reduced the number of files for the creation, and always I get the same error:
\nThe first part:
\n\nWe are processing your data
\n
\n We estimate this dataset will take 10s to process.
\n To start working with your Dataset, click 'Go to Dataset' and close this dialog.
\n And after 30 secs. I always got the same error:
\n Oh no! Upload failed
\n Unfortunately we could not create your dataset.
\n Failed to check creation status. Please try again later.
Please @addisonhoward can you give me some clue that can be happening, there is some size limit in the files?
", "votes": 0, "replies": [] }, { "id": 2262136, "author_name": "", "author_url": "", "post_date": "2023-05-16T18:47:51.633000", "content": "", "votes": 0, "replies": [] }, { "id": 2226517, "author_name": "", "author_url": "", "post_date": "2023-04-19T02:18:02.643000", "content": "", "votes": 1, "replies": [] } ], "raw_markdown_by_id": { "2226343": "New to machine learning and data science? No question is too basic or too simple. Feel free to start your own thread, or use this thread as a place to post any first-timer clarifying questions for the Kaggle community to help you with!\n\nIf you would consider yourself a beginner but don't know where to get started, let other Kagglers help you take your first steps here!\n\nNew to Kaggle? Take a look at a few videos Dr. Rachael Tatman has put together to learn a bit more about [site etiquette](https://www.youtube.com/watch?v=aIus8si_Et0), or [Kaggle lingo](https://www.youtube.com/watch?v=sEJHyuWKd-s).\n\nRemember: Kaggle is for everyone. Whether you're teaming up or sharing tips in the competition forum, we expect everyone to follow our [Kaggle community guidelines](https://www.kaggle.com/community-guidelines).\n\nA tip on sharing content - Kaggle is a collaborative community, whereby sharing techniques, starter notebooks, and ideas in the discussion forums are highly encouraged throughout the competition. However, as the competition draws closer to the final deadline it's customary to keep high-scoring notebooks withheld until after the competition has concluded. This maintains the spirit of the competition, while also allowing individuals to submit their own creative work without jeopardy of a higher-scoring notebook being available for an automatic higher rank (through copy/submit). We disable publishing of public notebooks within the final week of the competition, but encourage you to use your best judgment prior to that deadline.\n\nHappy Modeling!", "2237630": "Thank you😄 I am a complete newbie, but fascinated by bioinformatics😻", "2227358": "I am new to data science and machine learning, I am just starting out and got to know that kaggle is a data science community , currently I learning python and then I will move to advance steps but I am feeling overwhelmed y the amount of information out there ,If you guys can help me out I m a quick learner I will hopefully be half ready for this project by august if anyone can take me in there team as a newbie that would be of great help because you can guide me in this journey, 👀👀 thank you so much .", "2347475": "Thank you for the post. I've been reading a ton on kaggle and can tell this is an amazing community. \n\n I would appreciate clarification on a few questions:\n\n1. It seems like most models are trained locally (or in the cloud), then uploaded to kaggle to make predictions for the submission file (especially for large datasets). Is this accurate?\n\n2. It seems like feature engineering is more important typically than hyperparameter tuning. Is this true?\n\n3. It seems like successful kagglers pick a library (like xgboost, pytorch, or tensorflow) really get to know it, then after they've got a good grip on it jump into a new library when they see it's having better success on certain types of data. Is this true?\n\nLooking forward to learning from this community!", "2345275": "I'm trying to create datasets from embeddings, which each file is around 1.5 Gb, and I have problems in kaggle. I have checked my quota, and also reduced the number of files for the creation, and always I get the same error:\nThe first part:\n>We are processing your data\nWe estimate this dataset will take 10s to process.\nTo start working with your Dataset, click 'Go to Dataset' and close this dialog.\nAnd after 30 secs. I always got the same error:\n>Oh no! Upload failed\nUnfortunately we could not create your dataset.\nFailed to check creation status. Please try again later.\n\nPlease @addisonhoward can you give me some clue that can be happening, there is some size limit in the files?", "2262136": "", "2226517": "" } }