{
  "id": 412098,
  "title": "Supplemental data for the competition!",
  "url": "/competitions/predict-student-performance-from-game-play/discussion/412098",
  "author_name": "",
  "post_date": "2023-05-22T08:25:15.123760500Z",
  "votes": 26,
  "comment_count": 7,
  "views": 0,
  "content": "<p>Hello, Kagglers! ✋</p>\n<p>I wanted to share my latest project of extracting raw data and creating a dataset to use as supplemental data for our models. I've made this dataset available <a href=\"https://www.kaggle.com/datasets/glipko/additional-data-predict-students-performance\" target=\"_blank\">here</a> so you can take a look at the first shots of the data and explore its format. I am updating the dataset frequently with new processed data.</p>\n<p>Since I am currently studying at the university, I don't have enough time to work on the competition itself, so I wanted to share this dataset with the Kaggle community. I have tried my best to make the dataset's format as close to the competition's format as possible. I hope this dataset will be helpful in your research.</p>",
  "messages": [
    {
      "id": "2269122",
      "postDate": "05/22/2023 08:25:15",
      "content": "<p>Hello, Kagglers! ✋</p>\n<p>I wanted to share my latest project of extracting raw data and creating a dataset to use as supplemental data for our models. I've made this dataset available <a href=\"https://www.kaggle.com/datasets/glipko/additional-data-predict-students-performance\" target=\"_blank\">here</a> so you can take a look at the first shots of the data and explore its format. I am updating the dataset frequently with new processed data.</p>\n<p>Since I am currently studying at the university, I don't have enough time to work on the competition itself, so I wanted to share this dataset with the Kaggle community. I have tried my best to make the dataset's format as close to the competition's format as possible. I hope this dataset will be helpful in your research.</p>",
      "rawMarkdown": "Hello, Kagglers! ✋\n\nI wanted to share my latest project of extracting raw data and creating a dataset to use as supplemental data for our models. I've made this dataset available [here](https://www.kaggle.com/datasets/glipko/additional-data-predict-students-performance) so you can take a look at the first shots of the data and explore its format. I am updating the dataset frequently with new processed data.\n\nSince I am currently studying at the university, I don't have enough time to work on the competition itself, so I wanted to share this dataset with the Kaggle community. I have tried my best to make the dataset's format as close to the competition's format as possible. I hope this dataset will be helpful in your research.",
      "votes": null
    },
    {
      "id": "2271079",
      "postDate": "05/23/2023 15:56:41",
      "content": "<p>Thanks for sharing this! Did you have a chance to double-check your final dataset (by, for example, generating data for a subset of users in the competition's dataset and compare the new data with the competition's data)?</p>",
      "rawMarkdown": "Thanks for sharing this! Did you have a chance to double-check your final dataset (by, for example, generating data for a subset of users in the competition's dataset and compare the new data with the competition's data)?",
      "votes": null
    },
    {
      "id": "2271177",
      "postDate": "05/23/2023 17:10:23",
      "content": "<p>Thank you for your comment! I plan to compare the distribution of important metrics between the two datasets in order to validate my dataset when I complete my data processing!</p>",
      "rawMarkdown": "Thank you for your comment! I plan to compare the distribution of important metrics between the two datasets in order to validate my dataset when I complete my data processing!",
      "votes": null
    },
    {
      "id": "2271941",
      "postDate": "05/24/2023 07:45:34",
      "content": "<p>Great !! Thanks for sharing <a href=\"https://www.kaggle.com/glipko\" target=\"_blank\">@glipko</a> 🔥</p>",
      "rawMarkdown": "Great !! Thanks for sharing @glipko 🔥",
      "votes": null
    },
    {
      "id": "2282885",
      "postDate": "05/31/2023 22:02:34",
      "content": "<p><a href=\"https://www.kaggle.com/phuhoang26\" target=\"_blank\">@phuhoang26</a>, hi :)<br>\n&nbsp;Thank you for your great work!&nbsp;I'd like to crosscheck my dataset and yours.&nbsp;At what time can we meet at Zoom for 15 minutes to discuss it?&nbsp;I can at any time.What time is best for you?Then I send to this topic a public invite to the Zoom room.&nbsp;My attempt to make a dataset:<br>\n<a href=\"https://www.kaggle.com/datasets/liudacheldieva/game-log/\" target=\"_blank\">https://www.kaggle.com/datasets/liudacheldieva/game-log/</a><br>\n&nbsp;<br>\nI find how to calculate the \"index\" column:) Field index equal to original 90%. Other fields about 99%.</p>",
      "rawMarkdown": "phuhoang26, hi :)\n Thank you for your great work! I'd like to crosscheck my dataset and yours. At what time can we meet at Zoom for 15 minutes to discuss it? I can at any time.What time is best for you?Then I send to this topic a public invite to the Zoom room. My attempt to make a dataset:\nhttps://www.kaggle.com/datasets/liudacheldieva/game-log/\n \nI find how to calculate the \"index\" column:) Field index equal to original 90%. Other fields about 99%.",
      "votes": null
    },
    {
      "id": "2288383",
      "postDate": "06/05/2023 10:52:22",
      "content": "<p>this is 2022-04:<br>\n<a href=\"https://www.kaggle.com/datasets/liudacheldieva/game-train-2022-04\" target=\"_blank\">https://www.kaggle.com/datasets/liudacheldieva/game-train-2022-04</a></p>\n<p>train_2022_04.csv<br>\nlabels_2022_04.csv</p>",
      "rawMarkdown": "this is 2022-04:\nhttps://www.kaggle.com/datasets/liudacheldieva/game-train-2022-04\n\ntrain_2022_04.csv\nlabels_2022_04.csv",
      "votes": null
    },
    {
      "id": "2289897",
      "postDate": "06/06/2023 12:22:58",
      "content": "<p>Thank you for sharing. Could you please to share your notebook for preprocess ra raw data into train and label</p>",
      "rawMarkdown": "Thank you for sharing. Could you please to share your notebook for preprocess ra raw data into train and label",
      "votes": null
    },
    {
      "id": "2291032",
      "postDate": "06/07/2023 09:25:06",
      "content": "<p>I checked both yours and Gleb's additional data and I found 288 mismatched labels. For instance sessionid: 22030008214087468 question 18, which one is correct?</p>",
      "rawMarkdown": "I checked both yours and Gleb's additional data and I found 288 mismatched labels. For instance sessionid: 22030008214087468 question 18, which one is correct?",
      "votes": null
    }
  ],
  "comments": [
    {
      "id": 2271079,
      "author_name": "hoangnguyen719",
      "author_url": "",
      "post_date": "05/23/2023 15:56:41",
      "content": "<p>Thanks for sharing this! Did you have a chance to double-check your final dataset (by, for example, generating data for a subset of users in the competition's dataset and compare the new data with the competition's data)?</p>",
      "votes": null,
      "replies": [
        {
          "id": 2271177,
          "author_name": "glipko",
          "author_url": "",
          "post_date": "05/23/2023 17:10:23",
          "content": "<p>Thank you for your comment! I plan to compare the distribution of important metrics between the two datasets in order to validate my dataset when I complete my data processing!</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 2271941,
      "author_name": "scipygaurav",
      "author_url": "",
      "post_date": "05/24/2023 07:45:34",
      "content": "<p>Great !! Thanks for sharing <a href=\"https://www.kaggle.com/glipko\" target=\"_blank\">@glipko</a> 🔥</p>",
      "votes": null,
      "replies": []
    },
    {
      "id": 2282885,
      "author_name": "",
      "author_url": "",
      "post_date": "05/31/2023 22:02:34",
      "content": "<p><a href=\"https://www.kaggle.com/phuhoang26\" target=\"_blank\">@phuhoang26</a>, hi :)<br>\n&nbsp;Thank you for your great work!&nbsp;I'd like to crosscheck my dataset and yours.&nbsp;At what time can we meet at Zoom for 15 minutes to discuss it?&nbsp;I can at any time.What time is best for you?Then I send to this topic a public invite to the Zoom room.&nbsp;My attempt to make a dataset:<br>\n<a href=\"https://www.kaggle.com/datasets/liudacheldieva/game-log/\" target=\"_blank\">https://www.kaggle.com/datasets/liudacheldieva/game-log/</a><br>\n&nbsp;<br>\nI find how to calculate the \"index\" column:) Field index equal to original 90%. Other fields about 99%.</p>",
      "votes": null,
      "replies": [
        {
          "id": 2291032,
          "author_name": "jakubzeman",
          "author_url": "",
          "post_date": "06/07/2023 09:25:06",
          "content": "<p>I checked both yours and Gleb's additional data and I found 288 mismatched labels. For instance sessionid: 22030008214087468 question 18, which one is correct?</p>",
          "votes": null,
          "replies": []
        }
      ]
    },
    {
      "id": 2288383,
      "author_name": "",
      "author_url": "",
      "post_date": "06/05/2023 10:52:22",
      "content": "<p>this is 2022-04:<br>\n<a href=\"https://www.kaggle.com/datasets/liudacheldieva/game-train-2022-04\" target=\"_blank\">https://www.kaggle.com/datasets/liudacheldieva/game-train-2022-04</a></p>\n<p>train_2022_04.csv<br>\nlabels_2022_04.csv</p>",
      "votes": null,
      "replies": [
        {
          "id": 2289897,
          "author_name": "lamphambatung",
          "author_url": "",
          "post_date": "06/06/2023 12:22:58",
          "content": "<p>Thank you for sharing. Could you please to share your notebook for preprocess ra raw data into train and label</p>",
          "votes": null,
          "replies": []
        }
      ]
    }
  ],
  "raw_markdown_by_id": {
    "2269122": "Hello, Kagglers! ✋\n\nI wanted to share my latest project of extracting raw data and creating a dataset to use as supplemental data for our models. I've made this dataset available [here](https://www.kaggle.com/datasets/glipko/additional-data-predict-students-performance) so you can take a look at the first shots of the data and explore its format. I am updating the dataset frequently with new processed data.\n\nSince I am currently studying at the university, I don't have enough time to work on the competition itself, so I wanted to share this dataset with the Kaggle community. I have tried my best to make the dataset's format as close to the competition's format as possible. I hope this dataset will be helpful in your research.",
    "2271079": "Thanks for sharing this! Did you have a chance to double-check your final dataset (by, for example, generating data for a subset of users in the competition's dataset and compare the new data with the competition's data)?",
    "2271177": "Thank you for your comment! I plan to compare the distribution of important metrics between the two datasets in order to validate my dataset when I complete my data processing!",
    "2271941": "Great !! Thanks for sharing @glipko 🔥",
    "2282885": "phuhoang26, hi :)\n Thank you for your great work! I'd like to crosscheck my dataset and yours. At what time can we meet at Zoom for 15 minutes to discuss it? I can at any time.What time is best for you?Then I send to this topic a public invite to the Zoom room. My attempt to make a dataset:\nhttps://www.kaggle.com/datasets/liudacheldieva/game-log/\n \nI find how to calculate the \"index\" column:) Field index equal to original 90%. Other fields about 99%.",
    "2288383": "this is 2022-04:\nhttps://www.kaggle.com/datasets/liudacheldieva/game-train-2022-04\n\ntrain_2022_04.csv\nlabels_2022_04.csv",
    "2289897": "Thank you for sharing. Could you please to share your notebook for preprocess ra raw data into train and label",
    "2291032": "I checked both yours and Gleb's additional data and I found 288 mismatched labels. For instance sessionid: 22030008214087468 question 18, which one is correct?"
  },
  "source": "meta"
}