{ "id": 487121, "title": "Master sheet of all files and thier columns", "url": "/competitions/home-credit-credit-risk-model-stability/discussion/487121", "author_name": "Jabran Zahid", "post_date": "2024-03-27T17:53:09.145000", "votes": 39, "comment_count": 6, "views": 0, "content": "

Hi

\n

My first post on Kaggle, with my small contribution…..

\n

Since there are a large number of files and and large number of columns in them, it can be be overwhelming and hard to get an idea of the data we are dealing with, especially for a beginner like me so I have produced this excel sheet which shows the shape of all files, columns in them and each cell has a comment which gives you the description of the feature.

\n

Not sure how much its going to help but I thought it would be a good idea to have all this info in one place to make the analysis easier.

\n

Please see attached file, there are 3 tabs in it which are self explanatory.
\nCredit for producing the code where its due : ChatGPT

\n

Regards

", "messages": [ { "id": 2719439, "postDate": "2024-03-27T17:53:09.147Z", "content": "

Hi

\n

My first post on Kaggle, with my small contribution…..

\n

Since there are a large number of files and and large number of columns in them, it can be be overwhelming and hard to get an idea of the data we are dealing with, especially for a beginner like me so I have produced this excel sheet which shows the shape of all files, columns in them and each cell has a comment which gives you the description of the feature.

\n

Not sure how much its going to help but I thought it would be a good idea to have all this info in one place to make the analysis easier.

\n

Please see attached file, there are 3 tabs in it which are self explanatory.
\nCredit for producing the code where its due : ChatGPT

\n

Regards

", "rawMarkdown": "Hi \n\nMy first post on Kaggle, with my small contribution.....\n\nSince there are a large number of files and and large number of columns in them, it can be be overwhelming and hard to get an idea of the data we are dealing with, especially for a beginner like me so I have produced this excel sheet which shows the shape of all files, columns in them and each cell has a comment which gives you the description of the feature.\n\nNot sure how much its going to help but I thought it would be a good idea to have all this info in one place to make the analysis easier.\n\nPlease see attached file, there are 3 tabs in it which are self explanatory.\nCredit for producing the code where its due : ChatGPT\n\nRegards", "votes": 39 }, { "id": 2719746, "postDate": "2024-03-27T22:25:57.647Z", "content": "

Very useful @jabranzahid. You may also find helpful the enhanced feature definitions table, as available in this dataset. For each feature this table also contains

\n\n

Hope it helps.

", "rawMarkdown": "Very useful @jabranzahid. You may also find helpful the enhanced feature definitions table, as available in this [dataset](https://www.kaggle.com/datasets/kononenko/home-credit-enhanced-feature-definitions). For each feature this table also contains\n- `dtype`, type to which a feature should be resolved; \n- `tables`, a list of tables where a particular feature could be encountered.\n\nHope it helps.", "votes": 1 }, { "id": 2719538, "postDate": "2024-03-27T19:36:41.680Z", "content": "

@jabranzahid I was incidentally preparing this same file on my own and got this, thanks a lot for the file!
\nPlease be aware that we have quite a lot of tables here and one may have to resort to immense FE to churn out good models. This is indeed a gargantuan effort in my opinion!!

", "rawMarkdown": "@jabranzahid I was incidentally preparing this same file on my own and got this, thanks a lot for the file!\nPlease be aware that we have quite a lot of tables here and one may have to resort to immense FE to churn out good models. This is indeed a gargantuan effort in my opinion!!", "votes": 2 }, { "id": 2746278, "postDate": "2024-04-11T06:20:33.067Z", "content": "

great work!@jabranzahid

", "rawMarkdown": "great work!@jabranzahid" }, { "id": 2724701, "postDate": "2024-03-31T03:49:48.650Z", "rawMarkdown": "", "isDeleted": true }, { "id": 2719518, "postDate": "2024-03-27T19:15:06.087Z", "content": "

thanks! Helpful

", "rawMarkdown": "thanks! Helpful", "votes": 1 }, { "id": 2790111, "postDate": "2024-05-03T03:57:06.617Z", "content": "

Thank you!!!!!

", "rawMarkdown": "Thank you!!!!! " } ], "comments": [ { "id": 2719746, "author_name": "Oleksiy Kononenko", "author_url": "", "post_date": "2024-03-27T22:25:57.647000", "content": "

Very useful @jabranzahid. You may also find helpful the enhanced feature definitions table, as available in this dataset. For each feature this table also contains

\n\n

Hope it helps.

", "votes": 1, "replies": [] }, { "id": 2719538, "author_name": "Ravi Ramakrishnan", "author_url": "", "post_date": "2024-03-27T19:36:41.680000", "content": "

@jabranzahid I was incidentally preparing this same file on my own and got this, thanks a lot for the file!
\nPlease be aware that we have quite a lot of tables here and one may have to resort to immense FE to churn out good models. This is indeed a gargantuan effort in my opinion!!

", "votes": 2, "replies": [] }, { "id": 2746278, "author_name": "hidenov", "author_url": "", "post_date": "2024-04-11T06:20:33.067000", "content": "

great work!@jabranzahid

", "votes": 0, "replies": [] }, { "id": 2724701, "author_name": "", "author_url": "", "post_date": "2024-03-31T03:49:48.650000", "content": "", "votes": 0, "replies": [] }, { "id": 2719518, "author_name": "Shreyas Bhatt", "author_url": "", "post_date": "2024-03-27T19:15:06.087000", "content": "

thanks! Helpful

", "votes": 1, "replies": [] }, { "id": 2790111, "author_name": "Kaiyan Du", "author_url": "", "post_date": "2024-05-03T03:57:06.617000", "content": "

Thank you!!!!!

", "votes": 0, "replies": [] } ], "raw_markdown_by_id": { "2719439": "Hi \n\nMy first post on Kaggle, with my small contribution.....\n\nSince there are a large number of files and and large number of columns in them, it can be be overwhelming and hard to get an idea of the data we are dealing with, especially for a beginner like me so I have produced this excel sheet which shows the shape of all files, columns in them and each cell has a comment which gives you the description of the feature.\n\nNot sure how much its going to help but I thought it would be a good idea to have all this info in one place to make the analysis easier.\n\nPlease see attached file, there are 3 tabs in it which are self explanatory.\nCredit for producing the code where its due : ChatGPT\n\nRegards", "2719746": "Very useful @jabranzahid. You may also find helpful the enhanced feature definitions table, as available in this [dataset](https://www.kaggle.com/datasets/kononenko/home-credit-enhanced-feature-definitions). For each feature this table also contains\n- `dtype`, type to which a feature should be resolved; \n- `tables`, a list of tables where a particular feature could be encountered.\n\nHope it helps.", "2719538": "@jabranzahid I was incidentally preparing this same file on my own and got this, thanks a lot for the file!\nPlease be aware that we have quite a lot of tables here and one may have to resort to immense FE to churn out good models. This is indeed a gargantuan effort in my opinion!!", "2746278": "great work!@jabranzahid", "2724701": "", "2719518": "thanks! Helpful", "2790111": "Thank you!!!!! " } }