{
  "id": 177878,
  "title": "Lyft data as CSV files",
  "url": "/competitions/lyft-motion-prediction-autonomous-vehicles/discussion/177878",
  "author_name": "",
  "post_date": "2020-08-27T16:49:39.948445600Z",
  "votes": 16,
  "comment_count": 4,
  "views": 0,
  "content": "<p>I'm  converting the competition dataset into a csv handy format in order to allow easy experimentation and easy model building via conventional tools.</p>\n<p>For instant, only the first 500 scenes of the train are converted. But, I will keep updating the dataset, just stay tuned.</p>\n<p>You can <a href=\"https://www.kaggle.com/kneroma/lyft-motion-prediction-autonomous-vehicles-as-csv\" target=\"_blank\">take a look on the dataset here</a>. Feel free using it in your kernels  (EDA, LGBM, NN, …).</p>\n<p>[Updates]</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/kneroma/lgbm-on-lyft-tabular-data-inference\" target=\"_blank\">I finally train a LGBM model on a tabular version of the comeptition data. Feel free to comment with your ideas.</a></li>\n<li><a href=\"https://www.kaggle.com/kneroma/zarr-files-and-l5kit-data-for-dummies\" target=\"_blank\">An explanation of the whole dataset conversion step</a></li>\n</ul>\n<p>The datasets used to train and predict with LGBM models are :</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/kneroma/lyft-motion-prediction-autonomous-vehicles-as-csv\" target=\"_blank\">train sample</a></li>\n<li><a href=\"https://www.kaggle.com/kneroma/lyft-test-set-as-csv\" target=\"_blank\">test set as tabular data</a></li>\n<li><a href=\"https://www.kaggle.com/kneroma/lyft-models\" target=\"_blank\">LGBM checkpoints</a></li>\n</ul>",
  "messages": [
    {
      "id": "987960",
      "postDate": "08/27/2020 16:49:39",
      "content": "<p>I'm  converting the competition dataset into a csv handy format in order to allow easy experimentation and easy model building via conventional tools.</p>\n<p>For instant, only the first 500 scenes of the train are converted. But, I will keep updating the dataset, just stay tuned.</p>\n<p>You can <a href=\"https://www.kaggle.com/kneroma/lyft-motion-prediction-autonomous-vehicles-as-csv\" target=\"_blank\">take a look on the dataset here</a>. Feel free using it in your kernels  (EDA, LGBM, NN, …).</p>\n<p>[Updates]</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/kneroma/lgbm-on-lyft-tabular-data-inference\" target=\"_blank\">I finally train a LGBM model on a tabular version of the comeptition data. Feel free to comment with your ideas.</a></li>\n<li><a href=\"https://www.kaggle.com/kneroma/zarr-files-and-l5kit-data-for-dummies\" target=\"_blank\">An explanation of the whole dataset conversion step</a></li>\n</ul>\n<p>The datasets used to train and predict with LGBM models are :</p>\n<ul>\n<li><a href=\"https://www.kaggle.com/kneroma/lyft-motion-prediction-autonomous-vehicles-as-csv\" target=\"_blank\">train sample</a></li>\n<li><a href=\"https://www.kaggle.com/kneroma/lyft-test-set-as-csv\" target=\"_blank\">test set as tabular data</a></li>\n<li><a href=\"https://www.kaggle.com/kneroma/lyft-models\" target=\"_blank\">LGBM checkpoints</a></li>\n</ul>",
      "rawMarkdown": "I'm  converting the competition dataset into a csv handy format in order to allow easy experimentation and easy model building via conventional tools.\n\nFor instant, only the first 500 scenes of the train are converted. But, I will keep updating the dataset, just stay tuned.\n\nYou can [take a look on the dataset here](https://www.kaggle.com/kneroma/lyft-motion-prediction-autonomous-vehicles-as-csv). Feel free using it in your kernels  (EDA, LGBM, NN, ...).\n\n[Updates]\n* [I finally train a LGBM model on a tabular version of the comeptition data. Feel free to comment with your ideas.](https://www.kaggle.com/kneroma/lgbm-on-lyft-tabular-data-inference)\n* [An explanation of the whole dataset conversion step](https://www.kaggle.com/kneroma/zarr-files-and-l5kit-data-for-dummies)\n\nThe datasets used to train and predict with LGBM models are :\n* [train sample](https://www.kaggle.com/kneroma/lyft-motion-prediction-autonomous-vehicles-as-csv)\n* [test set as tabular data](https://www.kaggle.com/kneroma/lyft-test-set-as-csv)\n* [LGBM checkpoints](https://www.kaggle.com/kneroma/lyft-models)",
      "votes": null
    },
    {
      "id": "989749",
      "postDate": "08/29/2020 05:01:32",
      "content": "<p>Nice work!</p>",
      "rawMarkdown": "Nice work!",
      "votes": null
    },
    {
      "id": "989811",
      "postDate": "08/29/2020 06:02:09",
      "content": "<p>Nice work! Using which data are you building this? The data comes with competition or full data hosted differently? <a href=\"https://www.kaggle.com/philculliton/lyft-full-training-set\" target=\"_blank\">https://www.kaggle.com/philculliton/lyft-full-training-set</a></p>",
      "rawMarkdown": "Nice work! Using which data are you building this? The data comes with competition or full data hosted differently? https://www.kaggle.com/philculliton/lyft-full-training-set",
      "votes": null
    },
    {
      "id": "989974",
      "postDate": "08/29/2020 08:44:00",
      "content": "<p>The one inside the competition</p>",
      "rawMarkdown": "The one inside the competition",
      "votes": null
    },
    {
      "id": "989976",
      "postDate": "08/29/2020 08:44:54",
      "content": "<p>Thanks              </p>",
      "rawMarkdown": "Thanks",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 989811,
      "author_name": "kaushal2896",
      "author_url": "",
      "post_date": "08/29/2020 06:02:09",
      "content": "<p>Nice work! Using which data are you building this? The data comes with competition or full data hosted differently? <a href=\"https://www.kaggle.com/philculliton/lyft-full-training-set\" target=\"_blank\">https://www.kaggle.com/philculliton/lyft-full-training-set</a></p>",
      "votes": null,
      "replies": [
        {
          "id": 989974,
          "author_name": "kneroma",
          "author_url": "",
          "post_date": "08/29/2020 08:44:00",
          "content": "<p>The one inside the competition</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 989749,
      "author_name": "sauljoseoviedoleon",
      "author_url": "",
      "post_date": "08/29/2020 05:01:32",
      "content": "<p>Nice work!</p>",
      "votes": null,
      "replies": [
        {
          "id": 989976,
          "author_name": "kneroma",
          "author_url": "",
          "post_date": "08/29/2020 08:44:54",
          "content": "<p>Thanks              </p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "987960": "I'm  converting the competition dataset into a csv handy format in order to allow easy experimentation and easy model building via conventional tools.\n\nFor instant, only the first 500 scenes of the train are converted. But, I will keep updating the dataset, just stay tuned.\n\nYou can [take a look on the dataset here](https://www.kaggle.com/kneroma/lyft-motion-prediction-autonomous-vehicles-as-csv). Feel free using it in your kernels  (EDA, LGBM, NN, ...).\n\n[Updates]\n* [I finally train a LGBM model on a tabular version of the comeptition data. Feel free to comment with your ideas.](https://www.kaggle.com/kneroma/lgbm-on-lyft-tabular-data-inference)\n* [An explanation of the whole dataset conversion step](https://www.kaggle.com/kneroma/zarr-files-and-l5kit-data-for-dummies)\n\nThe datasets used to train and predict with LGBM models are :\n* [train sample](https://www.kaggle.com/kneroma/lyft-motion-prediction-autonomous-vehicles-as-csv)\n* [test set as tabular data](https://www.kaggle.com/kneroma/lyft-test-set-as-csv)\n* [LGBM checkpoints](https://www.kaggle.com/kneroma/lyft-models)",
    "989749": "Nice work!",
    "989811": "Nice work! Using which data are you building this? The data comes with competition or full data hosted differently? https://www.kaggle.com/philculliton/lyft-full-training-set",
    "989974": "The one inside the competition",
    "989976": "Thanks"
  },
  "source": "meta"
}