{
  "id": 25397,
  "title": "Solution using Apache Spark ML?",
  "url": "/competitions/bosch-production-line-performance/writeups/rahnamvh-solution-using-apache-spark-ml",
  "author_name": "",
  "post_date": "2016-11-13T16:05:02.097Z",
  "votes": 1,
  "comment_count": 5,
  "views": 635,
  "content": "<p>Any one used Apache Spark ML and managed to get a good score in private LB?. If yes please share solution/strategy.</p>\n\n<p>Thanks.</p>",
  "messages": [
    {
      "id": "144288",
      "postDate": "11/13/2016 16:05:02",
      "content": "<p>Any one used Apache Spark ML and managed to get a good score in private LB?. If yes please share solution/strategy.</p>\n\n<p>Thanks.</p>",
      "rawMarkdown": "Any one used Apache Spark ML and managed to get a good score in private LB?. If yes please share solution/strategy.\r\n\r\nThanks.",
      "votes": null
    },
    {
      "id": "144305",
      "postDate": "11/13/2016 17:38:14",
      "content": "<p>I did, even if the score was not so good, but I did not work on features engineering. Anyhow I'm preparing a github repo to share  the code either in scala or python. </p>",
      "rawMarkdown": "I did, even if the score was not so good, but I did not work on features engineering. Anyhow I'm preparing a github repo to share  the code either in scala or python.",
      "votes": null
    },
    {
      "id": "144319",
      "postDate": "11/13/2016 18:48:52",
      "content": "<p>I started using the Spark Machine Learning library with python API, then I moved to Scala to integrate the xgboost j4 package for Spark. As many others in the competition, I started getting good score after the leak or &quot;data property&quot; were made public by <strong>Faron</strong>.\nThanks also to <strong>CPMP</strong>  for his notebook for best threshold selection.</p>\n\n<p>Here it is the <a href=\"https://github.com/elenacuoco/bosch-kaggle-competition-spark\">github repo</a> for my spark code.</p>",
      "rawMarkdown": "I started using the Spark Machine Learning library with python API, then I moved to Scala to integrate the xgboost j4 package for Spark. As many others in the competition, I started getting good score after the leak or \"data property\" were made public by **Faron**.\r\nThanks also to **CPMP**  for his notebook for best threshold selection.\r\n\r\nHere it is the [github repo][1] for my spark code.\r\n\r\n\r\n  [1]: https://github.com/elenacuoco/bosch-kaggle-competition-spark",
      "votes": null
    },
    {
      "id": "144461",
      "postDate": "11/14/2016 09:06:49",
      "content": "<p>Hi Elena,\nGood job. Would you provide your CSV files ? happy.csv and magic.csv.</p>\n\n<p>I am curious to know what you put in them. \nThanks</p>",
      "rawMarkdown": "Hi Elena,\r\nGood job. Would you provide your CSV files ? happy.csv and magic.csv.\r\n\r\nI am curious to know what you put in them. \r\nThanks",
      "votes": null
    },
    {
      "id": "144596",
      "postDate": "11/14/2016 18:52:11",
      "content": "<p>[quote=Xavier Van Ausloos;144461]</p>\n\n<p>Hi Elena,\nGood job. Would you provide your CSV files ? happy.csv and magic.csv.</p>\n\n<p>I am curious to know what you put in them. \nThanks</p>\n\n<p>[/quote]</p>\n\n<p>they are the features from Faron  and others who played with row orders </p>",
      "rawMarkdown": "[quote=Xavier Van Ausloos;144461]\r\n\r\nHi Elena,\r\nGood job. Would you provide your CSV files ? happy.csv and magic.csv.\r\n\r\nI am curious to know what you put in them. \r\nThanks\r\n\r\n[/quote]\r\n\r\nthey are the features from Faron  and others who played with row orders",
      "votes": null
    },
    {
      "id": "144657",
      "postDate": "11/15/2016 00:08:26",
      "content": "<p>Thanks Elena.Appreciate it.\n[quote=Elena Cuoco;144319]</p>\n\n<p>I started using the Spark Machine Learning library with python API, then I moved to Scala to integrate the xgboost j4 package for Spark. As many others in the competition, I started getting good score after the leak or &quot;data property&quot; were made public by <strong>Faron</strong>.\nThanks also to <strong>CPMP</strong>  for his notebook for best threshold selection.</p>\n\n<p>Here it is the <a href=\"https://github.com/elenacuoco/bosch-kaggle-competition-spark\">github repo</a> for my spark code.</p>\n\n<p>[/quote]</p>",
      "rawMarkdown": "Thanks Elena.Appreciate it.\r\n[quote=Elena Cuoco;144319]\r\n\r\nI started using the Spark Machine Learning library with python API, then I moved to Scala to integrate the xgboost j4 package for Spark. As many others in the competition, I started getting good score after the leak or \"data property\" were made public by **Faron**.\r\nThanks also to **CPMP**  for his notebook for best threshold selection.\r\n\r\nHere it is the [github repo][1] for my spark code.\r\n\r\n\r\n  [1]: https://github.com/elenacuoco/bosch-kaggle-competition-spark\r\n\r\n[/quote]",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 144305,
      "author_name": "elenacuoco",
      "author_url": "",
      "post_date": "11/13/2016 17:38:14",
      "content": "<p>I did, even if the score was not so good, but I did not work on features engineering. Anyhow I'm preparing a github repo to share  the code either in scala or python. </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 144319,
      "author_name": "elenacuoco",
      "author_url": "",
      "post_date": "11/13/2016 18:48:52",
      "content": "<p>I started using the Spark Machine Learning library with python API, then I moved to Scala to integrate the xgboost j4 package for Spark. As many others in the competition, I started getting good score after the leak or &quot;data property&quot; were made public by <strong>Faron</strong>.\nThanks also to <strong>CPMP</strong>  for his notebook for best threshold selection.</p>\n\n<p>Here it is the <a href=\"https://github.com/elenacuoco/bosch-kaggle-competition-spark\">github repo</a> for my spark code.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 144461,
      "author_name": "vanausloos",
      "author_url": "",
      "post_date": "11/14/2016 09:06:49",
      "content": "<p>Hi Elena,\nGood job. Would you provide your CSV files ? happy.csv and magic.csv.</p>\n\n<p>I am curious to know what you put in them. \nThanks</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 144596,
      "author_name": "elenacuoco",
      "author_url": "",
      "post_date": "11/14/2016 18:52:11",
      "content": "<p>[quote=Xavier Van Ausloos;144461]</p>\n\n<p>Hi Elena,\nGood job. Would you provide your CSV files ? happy.csv and magic.csv.</p>\n\n<p>I am curious to know what you put in them. \nThanks</p>\n\n<p>[/quote]</p>\n\n<p>they are the features from Faron  and others who played with row orders </p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 144657,
      "author_name": "manhardsvh",
      "author_url": "",
      "post_date": "11/15/2016 00:08:26",
      "content": "<p>Thanks Elena.Appreciate it.\n[quote=Elena Cuoco;144319]</p>\n\n<p>I started using the Spark Machine Learning library with python API, then I moved to Scala to integrate the xgboost j4 package for Spark. As many others in the competition, I started getting good score after the leak or &quot;data property&quot; were made public by <strong>Faron</strong>.\nThanks also to <strong>CPMP</strong>  for his notebook for best threshold selection.</p>\n\n<p>Here it is the <a href=\"https://github.com/elenacuoco/bosch-kaggle-competition-spark\">github repo</a> for my spark code.</p>\n\n<p>[/quote]</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "144288": "Any one used Apache Spark ML and managed to get a good score in private LB?. If yes please share solution/strategy.\r\n\r\nThanks.",
    "144305": "I did, even if the score was not so good, but I did not work on features engineering. Anyhow I'm preparing a github repo to share  the code either in scala or python.",
    "144319": "I started using the Spark Machine Learning library with python API, then I moved to Scala to integrate the xgboost j4 package for Spark. As many others in the competition, I started getting good score after the leak or \"data property\" were made public by **Faron**.\r\nThanks also to **CPMP**  for his notebook for best threshold selection.\r\n\r\nHere it is the [github repo][1] for my spark code.\r\n\r\n\r\n  [1]: https://github.com/elenacuoco/bosch-kaggle-competition-spark",
    "144461": "Hi Elena,\r\nGood job. Would you provide your CSV files ? happy.csv and magic.csv.\r\n\r\nI am curious to know what you put in them. \r\nThanks",
    "144596": "[quote=Xavier Van Ausloos;144461]\r\n\r\nHi Elena,\r\nGood job. Would you provide your CSV files ? happy.csv and magic.csv.\r\n\r\nI am curious to know what you put in them. \r\nThanks\r\n\r\n[/quote]\r\n\r\nthey are the features from Faron  and others who played with row orders",
    "144657": "Thanks Elena.Appreciate it.\r\n[quote=Elena Cuoco;144319]\r\n\r\nI started using the Spark Machine Learning library with python API, then I moved to Scala to integrate the xgboost j4 package for Spark. As many others in the competition, I started getting good score after the leak or \"data property\" were made public by **Faron**.\r\nThanks also to **CPMP**  for his notebook for best threshold selection.\r\n\r\nHere it is the [github repo][1] for my spark code.\r\n\r\n\r\n  [1]: https://github.com/elenacuoco/bosch-kaggle-competition-spark\r\n\r\n[/quote]"
  },
  "source": "meta"
}