{
  "id": 541910,
  "title": "Time-series module for prediction? ",
  "url": "/competitions/jane-street-real-time-market-data-forecasting/discussion/541910",
  "author_name": "",
  "post_date": "2024-10-22T00:29:56.719116900Z",
  "votes": 2,
  "comment_count": 3,
  "views": 0,
  "content": "<p>Training Phase</p>\n<p>Your notebook must use the time-series module to make predictions</p>\n<p>Anyone knows what is it? The codes I saw are all using LightGBM, XGboost to make predictions. </p>\n<p>Thank you</p>",
  "messages": [
    {
      "id": "3024756",
      "postDate": "10/22/2024 00:29:56",
      "content": "<p>Training Phase</p>\n<p>Your notebook must use the time-series module to make predictions</p>\n<p>Anyone knows what is it? The codes I saw are all using LightGBM, XGboost to make predictions. </p>\n<p>Thank you</p>",
      "rawMarkdown": "Training Phase\n\nYour notebook must use the time-series module to make predictions\n\n\nAnyone knows what is it? The codes I saw are all using LightGBM, XGboost to make predictions. \n\nThank you",
      "votes": null
    },
    {
      "id": "3032590",
      "postDate": "10/31/2024 06:02:03",
      "content": "<p>I was wondering about this too! Any help would be greatly appreciated.</p>",
      "rawMarkdown": "I was wondering about this too! Any help would be greatly appreciated.",
      "votes": null
    },
    {
      "id": "3059039",
      "postDate": "11/30/2024 08:40:23",
      "content": "<p>Same question, it's the use of \"the\" that sounds very specific: \"the time-series module\"</p>",
      "rawMarkdown": "Same question, it's the use of \"the\" that sounds very specific: \"the time-series module\"",
      "votes": null
    },
    {
      "id": "3064737",
      "postDate": "12/06/2024 00:14:47",
      "content": "<p>I had the same problem. I believe the answer you are looking for is found here:</p>\n<p><a href=\"https://www.kaggle.com/c/jane-street-market-prediction\" target=\"_blank\">https://www.kaggle.com/c/jane-street-market-prediction</a></p>\n<p>Under Overview you will find:</p>\n<p>Submission File<br>\nYou must submit to this competition using the provided python time-series API, which ensures that models do not peek forward in time. To use the API, follow the following template in Kaggle Notebooks:</p>\n<p>import janestreet<br>\nenv = janestreet.make_env() # initialize the environment<br>\niter_test = env.iter_test() # an iterator which loops over the test set</p>\n<p>for (test_df, sample_prediction_df) in iter_test:<br>\n    sample_prediction_df.action = 0 #make your 0/1 prediction here<br>\n    env.predict(sample_prediction_df)</p>",
      "rawMarkdown": "I had the same problem. I believe the answer you are looking for is found here:\n\nhttps://www.kaggle.com/c/jane-street-market-prediction\n\nUnder Overview you will find:\n\nSubmission File\nYou must submit to this competition using the provided python time-series API, which ensures that models do not peek forward in time. To use the API, follow the following template in Kaggle Notebooks:\n\nimport janestreet\nenv = janestreet.make_env() # initialize the environment\niter_test = env.iter_test() # an iterator which loops over the test set\n\nfor (test_df, sample_prediction_df) in iter_test:\n    sample_prediction_df.action = 0 #make your 0/1 prediction here\n    env.predict(sample_prediction_df)",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 3032590,
      "author_name": "alekslinya",
      "author_url": "",
      "post_date": "10/31/2024 06:02:03",
      "content": "<p>I was wondering about this too! Any help would be greatly appreciated.</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 3059039,
      "author_name": "jimbeno",
      "author_url": "",
      "post_date": "11/30/2024 08:40:23",
      "content": "<p>Same question, it's the use of \"the\" that sounds very specific: \"the time-series module\"</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 3064737,
      "author_name": "loganedmiston",
      "author_url": "",
      "post_date": "12/06/2024 00:14:47",
      "content": "<p>I had the same problem. I believe the answer you are looking for is found here:</p>\n<p><a href=\"https://www.kaggle.com/c/jane-street-market-prediction\" target=\"_blank\">https://www.kaggle.com/c/jane-street-market-prediction</a></p>\n<p>Under Overview you will find:</p>\n<p>Submission File<br>\nYou must submit to this competition using the provided python time-series API, which ensures that models do not peek forward in time. To use the API, follow the following template in Kaggle Notebooks:</p>\n<p>import janestreet<br>\nenv = janestreet.make_env() # initialize the environment<br>\niter_test = env.iter_test() # an iterator which loops over the test set</p>\n<p>for (test_df, sample_prediction_df) in iter_test:<br>\n    sample_prediction_df.action = 0 #make your 0/1 prediction here<br>\n    env.predict(sample_prediction_df)</p>",
      "votes": null,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "3024756": "Training Phase\n\nYour notebook must use the time-series module to make predictions\n\n\nAnyone knows what is it? The codes I saw are all using LightGBM, XGboost to make predictions. \n\nThank you",
    "3032590": "I was wondering about this too! Any help would be greatly appreciated.",
    "3059039": "Same question, it's the use of \"the\" that sounds very specific: \"the time-series module\"",
    "3064737": "I had the same problem. I believe the answer you are looking for is found here:\n\nhttps://www.kaggle.com/c/jane-street-market-prediction\n\nUnder Overview you will find:\n\nSubmission File\nYou must submit to this competition using the provided python time-series API, which ensures that models do not peek forward in time. To use the API, follow the following template in Kaggle Notebooks:\n\nimport janestreet\nenv = janestreet.make_env() # initialize the environment\niter_test = env.iter_test() # an iterator which loops over the test set\n\nfor (test_df, sample_prediction_df) in iter_test:\n    sample_prediction_df.action = 0 #make your 0/1 prediction here\n    env.predict(sample_prediction_df)"
  },
  "source": "meta"
}