{
  "id": 82084,
  "title": "31st place, Some of Feature Engineering",
  "url": "/competitions/elo-merchant-category-recommendation/writeups/django-unchained-31st-place-some-of-feature-engine",
  "author_name": "",
  "post_date": "2020-05-12T23:25:07.847Z",
  "votes": 11,
  "comment_count": 9,
  "views": 0,
  "content": "<p>here are some feature engineering </p>\n\n<p><a href=\"https://www.kaggle.com/mks2192/feature-engineering/notebook\">https://www.kaggle.com/mks2192/feature-engineering/notebook</a></p>\n\n<p>it takes more than kernals time so i had to run it on my PC.</p>\n\n<p>This is mainly FE for cityID, subsectorID, merchantID, merchant_categoryID \nduring FE i did not used target information the way we do in mean encoding. So features are free from fear of overfitting.</p>\n\n<p>features coming out of this are here \n<a href=\"https://www.kaggle.com/mks2192/elo-features-data-7-feb\">https://www.kaggle.com/mks2192/elo-features-data-7-feb</a></p>\n\n<p>Thanks,</p>\n\n<p>PS: some of the codes are adopted from others especially <a href=\"/mitsuru\">@mitsuru</a>_fujiwara</p>",
  "messages": [
    {
      "id": "479400",
      "postDate": "02/27/2019 05:34:17",
      "content": "<p>here are some feature engineering </p>\n\n<p><a href=\"https://www.kaggle.com/mks2192/feature-engineering/notebook\">https://www.kaggle.com/mks2192/feature-engineering/notebook</a></p>\n\n<p>it takes more than kernals time so i had to run it on my PC.</p>\n\n<p>This is mainly FE for cityID, subsectorID, merchantID, merchant_categoryID \nduring FE i did not used target information the way we do in mean encoding. So features are free from fear of overfitting.</p>\n\n<p>features coming out of this are here \n<a href=\"https://www.kaggle.com/mks2192/elo-features-data-7-feb\">https://www.kaggle.com/mks2192/elo-features-data-7-feb</a></p>\n\n<p>Thanks,</p>\n\n<p>PS: some of the codes are adopted from others especially <a href=\"/mitsuru\">@mitsuru</a>_fujiwara</p>",
      "rawMarkdown": "here are some feature engineering \n\nhttps://www.kaggle.com/mks2192/feature-engineering/notebook\n\nit takes more than kernals time so i had to run it on my PC.\n\nThis is mainly FE for cityID, subsectorID, merchantID, merchant_categoryID \nduring FE i did not used target information the way we do in mean encoding. So features are free from fear of overfitting.\n\nfeatures coming out of this are here \nhttps://www.kaggle.com/mks2192/elo-features-data-7-feb\n\nThanks,\n\nPS: some of the codes are adopted from others especially @mitsuru_fujiwara",
      "votes": null
    },
    {
      "id": "479437",
      "postDate": "02/27/2019 06:18:29",
      "content": "<p>Congrats Manoj. Nice Work...</p>",
      "rawMarkdown": "Congrats Manoj. Nice Work...",
      "votes": null
    },
    {
      "id": "479451",
      "postDate": "02/27/2019 06:37:08",
      "content": "<p>Congrats, and excellent work.</p>",
      "rawMarkdown": "Congrats, and excellent work.",
      "votes": null
    },
    {
      "id": "479502",
      "postDate": "02/27/2019 07:46:43",
      "content": "<p>Congratulations <a href=\"/mks2192\">@mks2192</a>. Thanks for sharing the kernels</p>",
      "rawMarkdown": "Congratulations @mks2192. Thanks for sharing the kernels",
      "votes": null
    },
    {
      "id": "479537",
      "postDate": "02/27/2019 08:22:09",
      "content": "<p>looks like we can not visit your private kernel. would you mind switch the access for all of us?</p>",
      "rawMarkdown": "looks like we can not visit your private kernel. would you mind switch the access for all of us?",
      "votes": null
    },
    {
      "id": "479541",
      "postDate": "02/27/2019 08:27:11",
      "content": "<p>Hi Mike, i see it as shared publicly, can you check again </p>",
      "rawMarkdown": "Hi Mike, i see it as shared publicly, can you check again",
      "votes": null
    },
    {
      "id": "484467",
      "postDate": "03/06/2019 03:51:03",
      "content": "<p>It is okay now, thanks</p>",
      "rawMarkdown": "It is okay now, thanks",
      "votes": null
    },
    {
      "id": "548915",
      "postDate": "06/10/2019 05:11:58",
      "content": "<p>Hi Manoj, excellent notebook for feature engineering. Can you share the model building solution?</p>",
      "rawMarkdown": "Hi Manoj, excellent notebook for feature engineering. Can you share the model building solution?",
      "votes": null
    },
    {
      "id": "548918",
      "postDate": "06/10/2019 05:19:58",
      "content": "<p>Here you go one of the model out of many\n<a href=\"https://www.kaggle.com/mks2192/fork-of-train-test-features-old-new-combin-150-fea/notebook\">https://www.kaggle.com/mks2192/fork-of-train-test-features-old-new-combin-150-fea/notebook</a></p>",
      "rawMarkdown": "Here you go one of the model out of many\nhttps://www.kaggle.com/mks2192/fork-of-train-test-features-old-new-combin-150-fea/notebook",
      "votes": null
    },
    {
      "id": "548941",
      "postDate": "06/10/2019 05:59:26",
      "content": "<p>Thanks Manoj. Can you put the github link of solution? That would help to understand every aspect of your work. </p>",
      "rawMarkdown": "Thanks Manoj. Can you put the github link of solution? That would help to understand every aspect of your work.",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 479437,
      "author_name": "onielg",
      "author_url": "",
      "post_date": "02/27/2019 06:18:29",
      "content": "<p>Congrats Manoj. Nice Work...</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 479451,
      "author_name": "liewmanchoi",
      "author_url": "",
      "post_date": "02/27/2019 06:37:08",
      "content": "<p>Congrats, and excellent work.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 479502,
      "author_name": "karthik7395",
      "author_url": "",
      "post_date": "02/27/2019 07:46:43",
      "content": "<p>Congratulations <a href=\"/mks2192\">@mks2192</a>. Thanks for sharing the kernels</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 479537,
      "author_name": "nklinzhiming",
      "author_url": "",
      "post_date": "02/27/2019 08:22:09",
      "content": "<p>looks like we can not visit your private kernel. would you mind switch the access for all of us?</p>",
      "votes": null,
      "replies": [
        {
          "id": 479541,
          "author_name": "mks2192",
          "author_url": "",
          "post_date": "02/27/2019 08:27:11",
          "content": "<p>Hi Mike, i see it as shared publicly, can you check again </p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 484467,
          "author_name": "nklinzhiming",
          "author_url": "",
          "post_date": "03/06/2019 03:51:03",
          "content": "<p>It is okay now, thanks</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 548915,
      "author_name": "nupurkamble",
      "author_url": "",
      "post_date": "06/10/2019 05:11:58",
      "content": "<p>Hi Manoj, excellent notebook for feature engineering. Can you share the model building solution?</p>",
      "votes": null,
      "replies": [
        {
          "id": 548918,
          "author_name": "mks2192",
          "author_url": "",
          "post_date": "06/10/2019 05:19:58",
          "content": "<p>Here you go one of the model out of many\n<a href=\"https://www.kaggle.com/mks2192/fork-of-train-test-features-old-new-combin-150-fea/notebook\">https://www.kaggle.com/mks2192/fork-of-train-test-features-old-new-combin-150-fea/notebook</a></p>",
          "votes": null,
          "replies": []
        },
        {
          "id": 548941,
          "author_name": "nupurkamble",
          "author_url": "",
          "post_date": "06/10/2019 05:59:26",
          "content": "<p>Thanks Manoj. Can you put the github link of solution? That would help to understand every aspect of your work. </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "479400": "here are some feature engineering \n\nhttps://www.kaggle.com/mks2192/feature-engineering/notebook\n\nit takes more than kernals time so i had to run it on my PC.\n\nThis is mainly FE for cityID, subsectorID, merchantID, merchant_categoryID \nduring FE i did not used target information the way we do in mean encoding. So features are free from fear of overfitting.\n\nfeatures coming out of this are here \nhttps://www.kaggle.com/mks2192/elo-features-data-7-feb\n\nThanks,\n\nPS: some of the codes are adopted from others especially @mitsuru_fujiwara",
    "479437": "Congrats Manoj. Nice Work...",
    "479451": "Congrats, and excellent work.",
    "479502": "Congratulations @mks2192. Thanks for sharing the kernels",
    "479537": "looks like we can not visit your private kernel. would you mind switch the access for all of us?",
    "479541": "Hi Mike, i see it as shared publicly, can you check again",
    "484467": "It is okay now, thanks",
    "548915": "Hi Manoj, excellent notebook for feature engineering. Can you share the model building solution?",
    "548918": "Here you go one of the model out of many\nhttps://www.kaggle.com/mks2192/fork-of-train-test-features-old-new-combin-150-fea/notebook",
    "548941": "Thanks Manoj. Can you put the github link of solution? That would help to understand every aspect of your work."
  },
  "source": "existing_discussion",
  "complete": true,
  "competition_id": 10445,
  "competition_slug": "elo-merchant-category-recommendation",
  "team_id": 2443283,
  "solution_url": "/competitions/elo-merchant-category-recommendation/writeups/django-unchained-31st-place-some-of-feature-engine"
}