We are back with the Third edition of Kaggle BIPOC Mentor Stories . This is series which captures the Kaggling journey of myself and my mentee Muskan Jain .
\nOwing to COVID , we were only able to work on the competition for four days. We learnt a lot during the four days . Hear it from Muskan on her learning experience in this competition
\nThis is my third Kaggle competition and also the first time I dealt with location and navigation data.One of the very important aspects of such kinds of competition is understanding and visualizing the data. Visualizing the data in this competition was a challenge but through some very awesome notebooks , I was able to understand the data and the various visualizations. One of the new things that I learned through this competition was the concept of post-processing. Post-processing procedures usually act as a filter for noisy,imprecise or non-user-friendly data.I also came across various post processing techniques and models such as snap to grid, cost minimization etc. in this competition which further broadened my understanding of the data involved.Another new thing that I came across was dealing with the leakage in the data. Also, one of the techniques commonly used in the competition is ensembling the scores of the best notebooks/models. I was familiar with the concept but putting it into a practical application made me realise the importance and advantages of using proper ensembling methods. Further visualizing the predictions also proved quite helpful.The public notebooks and discussions were really very helpful in getting an understanding of the data and also in deciding the approach that can be taken if you are a beginner in this field.Although I couldn’t devote much time, I learned a lot of new things in this competition.
\nThanks and Regards,
\nTensor Girl and Muskan Jain
", "messages": [ { "id": "1312412", "postDate": "05/18/2021 03:33:18", "content": "We are back with the Third edition of Kaggle BIPOC Mentor Stories . This is series which captures the Kaggling journey of myself and my mentee Muskan Jain .
\nOwing to COVID , we were only able to work on the competition for four days. We learnt a lot during the four days . Hear it from Muskan on her learning experience in this competition
\nThis is my third Kaggle competition and also the first time I dealt with location and navigation data.One of the very important aspects of such kinds of competition is understanding and visualizing the data. Visualizing the data in this competition was a challenge but through some very awesome notebooks , I was able to understand the data and the various visualizations. One of the new things that I learned through this competition was the concept of post-processing. Post-processing procedures usually act as a filter for noisy,imprecise or non-user-friendly data.I also came across various post processing techniques and models such as snap to grid, cost minimization etc. in this competition which further broadened my understanding of the data involved.Another new thing that I came across was dealing with the leakage in the data. Also, one of the techniques commonly used in the competition is ensembling the scores of the best notebooks/models. I was familiar with the concept but putting it into a practical application made me realise the importance and advantages of using proper ensembling methods. Further visualizing the predictions also proved quite helpful.The public notebooks and discussions were really very helpful in getting an understanding of the data and also in deciding the approach that can be taken if you are a beginner in this field.Although I couldn’t devote much time, I learned a lot of new things in this competition.
\nThanks and Regards,
\nTensor Girl and Muskan Jain
", "rawMarkdown": "We are back with the Third edition of Kaggle BIPOC Mentor Stories . This is series which captures the Kaggling journey of myself and my mentee Muskan Jain .\n\nOwing to COVID , we were only able to work on the competition for four days. We learnt a lot during the four days . Hear it from Muskan on her learning experience in this competition \n\n\n\n**This is my third Kaggle competition and also the first time I dealt with location and navigation data.One of the very important aspects of such kinds of competition is understanding and visualizing the data. Visualizing the data in this competition was a challenge but through some very awesome notebooks , I was able to understand the data and the various visualizations. One of the new things that I learned through this competition was the concept of post-processing. Post-processing procedures usually act as a filter for noisy,imprecise or non-user-friendly data.I also came across various post processing techniques and models such as snap to grid, cost minimization etc. in this competition which further broadened my understanding of the data involved.Another new thing that I came across was dealing with the leakage in the data. Also, one of the techniques commonly used in the competition is ensembling the scores of the best notebooks/models. I was familiar with the concept but putting it into a practical application made me realise the importance and advantages of using proper ensembling methods. Further visualizing the predictions also proved quite helpful.The public notebooks and discussions were really very helpful in getting an understanding of the data and also in deciding the approach that can be taken if you are a beginner in this field.Although I couldn’t devote much time, I learned a lot of new things in this competition.**\n\nThanks and Regards,\n\nTensor Girl and Muskan Jain", "votes": null }, { "id": "1315901", "postDate": "05/20/2021 07:16:09", "content": "Hi @usharengaraju … I really love your notebooks and discussion topics. Subscribed …! Thank you for sharing!
", "rawMarkdown": "Hi @usharengaraju ... I really love your notebooks and discussion topics. Subscribed ...! Thank you for sharing!", "votes": null }, { "id": "1316055", "postDate": "05/20/2021 09:24:24", "content": "Thanks very much for another great episode @muskan2006 and @usharengaraju. By the way, it looks like you probably meant Amidst in the title.
", "rawMarkdown": "Thanks very much for another great episode @muskan2006 and @usharengaraju. By the way, it looks like you probably meant Amidst in the title.", "votes": null }, { "id": "1316083", "postDate": "05/20/2021 09:40:02", "content": "@jbomitchell Thank you John . Corrected it now
", "rawMarkdown": "jbomitchell Thank you John . Corrected it now", "votes": null } ], "comments": [ { "id": 1315901, "author_name": "remekkinas", "author_url": "", "post_date": "05/20/2021 07:16:09", "content": "Hi @usharengaraju … I really love your notebooks and discussion topics. Subscribed …! Thank you for sharing!
", "votes": null, "replies": [] }, { "id": 1316055, "author_name": "jbomitchell", "author_url": "", "post_date": "05/20/2021 09:24:24", "content": "Thanks very much for another great episode @muskan2006 and @usharengaraju. By the way, it looks like you probably meant Amidst in the title.
", "votes": null, "replies": [ { "id": 1316083, "author_name": "usharengaraju", "author_url": "", "post_date": "05/20/2021 09:40:02", "content": "@jbomitchell Thank you John . Corrected it now
", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "1312412": "We are back with the Third edition of Kaggle BIPOC Mentor Stories . This is series which captures the Kaggling journey of myself and my mentee Muskan Jain .\n\nOwing to COVID , we were only able to work on the competition for four days. We learnt a lot during the four days . Hear it from Muskan on her learning experience in this competition \n\n\n\n**This is my third Kaggle competition and also the first time I dealt with location and navigation data.One of the very important aspects of such kinds of competition is understanding and visualizing the data. Visualizing the data in this competition was a challenge but through some very awesome notebooks , I was able to understand the data and the various visualizations. One of the new things that I learned through this competition was the concept of post-processing. Post-processing procedures usually act as a filter for noisy,imprecise or non-user-friendly data.I also came across various post processing techniques and models such as snap to grid, cost minimization etc. in this competition which further broadened my understanding of the data involved.Another new thing that I came across was dealing with the leakage in the data. Also, one of the techniques commonly used in the competition is ensembling the scores of the best notebooks/models. I was familiar with the concept but putting it into a practical application made me realise the importance and advantages of using proper ensembling methods. Further visualizing the predictions also proved quite helpful.The public notebooks and discussions were really very helpful in getting an understanding of the data and also in deciding the approach that can be taken if you are a beginner in this field.Although I couldn’t devote much time, I learned a lot of new things in this competition.**\n\nThanks and Regards,\n\nTensor Girl and Muskan Jain", "1315901": "Hi @usharengaraju ... I really love your notebooks and discussion topics. Subscribed ...! Thank you for sharing!", "1316055": "Thanks very much for another great episode @muskan2006 and @usharengaraju. By the way, it looks like you probably meant Amidst in the title.", "1316083": "jbomitchell Thank you John . Corrected it now" }, "source": "meta" }