{
  "id": 374768,
  "title": "issue in making prediction  can you help ?",
  "url": "/competitions/rsna-breast-cancer-detection/discussion/374768",
  "author_name": "Ahmed___Gaber____",
  "post_date": "2022-12-28T17:40:29.370000",
  "votes": 1,
  "comment_count": 2,
  "views": 0,
  "content": "<p>Dear all ,<br>\nI have easy question that we have in train csv file has 14 column and in test csv file have 9 column ,so how we can make prediction as when i pass test data to model it will refuse to predict due to feature not equal in train and test files <br>\nRegards,<br>\nGaber</p>",
  "messages": [
    {
      "id": 2078843,
      "postDate": "2022-12-28T17:40:29.370Z",
      "content": "<p>Dear all ,<br>\nI have easy question that we have in train csv file has 14 column and in test csv file have 9 column ,so how we can make prediction as when i pass test data to model it will refuse to predict due to feature not equal in train and test files <br>\nRegards,<br>\nGaber</p>",
      "rawMarkdown": "Dear all ,\nI have easy question that we have in train csv file has 14 column and in test csv file have 9 column ,so how we can make prediction as when i pass test data to model it will refuse to predict due to feature not equal in train and test files \nRegards,\nGaber",
      "votes": 1
    },
    {
      "id": 2078885,
      "postDate": "2022-12-28T18:33:08.470Z",
      "content": "<p>Hi, <br>\nYou should train the model in such a way that, on input, it accepts only the information that you are able to provide it with during inference (at the submission), that is, the information that is in the test data.</p>\n<p>If you don't know where to start, I would suggest analyzing the well-crafted baseline training notebooks from <a href=\"https://www.kaggle.com/radek1\" target=\"_blank\">@radek1</a> <a href=\"https://www.kaggle.com/code/radek1/fast-ai-starter-pack-train-inference\" target=\"_blank\">https://www.kaggle.com/code/radek1/fast-ai-starter-pack-train-inference</a> or <a href=\"https://www.kaggle.com/awsaf49\" target=\"_blank\">@awsaf49</a> <a href=\"https://www.kaggle.com/code/awsaf49/rsna-bcd-efficientnet-tf-tpu-1vm-train\" target=\"_blank\">https://www.kaggle.com/code/awsaf49/rsna-bcd-efficientnet-tf-tpu-1vm-train</a></p>",
      "rawMarkdown": "Hi, \nYou should train the model in such a way that, on input, it accepts only the information that you are able to provide it with during inference (at the submission), that is, the information that is in the test data.\n\nIf you don't know where to start, I would suggest analyzing the well-crafted baseline training notebooks from @radek1 https://www.kaggle.com/code/radek1/fast-ai-starter-pack-train-inference or @awsaf49 https://www.kaggle.com/code/awsaf49/rsna-bcd-efficientnet-tf-tpu-1vm-train",
      "votes": 2
    },
    {
      "id": 2078960,
      "postDate": "2022-12-28T19:49:23.097Z",
      "rawMarkdown": "",
      "isDeleted": true
    }
  ],
  "comments": [
    {
      "id": 2078885,
      "author_name": "Pandas Warrior",
      "author_url": "",
      "post_date": "2022-12-28T18:33:08.470000",
      "content": "<p>Hi, <br>\nYou should train the model in such a way that, on input, it accepts only the information that you are able to provide it with during inference (at the submission), that is, the information that is in the test data.</p>\n<p>If you don't know where to start, I would suggest analyzing the well-crafted baseline training notebooks from <a href=\"https://www.kaggle.com/radek1\" target=\"_blank\">@radek1</a> <a href=\"https://www.kaggle.com/code/radek1/fast-ai-starter-pack-train-inference\" target=\"_blank\">https://www.kaggle.com/code/radek1/fast-ai-starter-pack-train-inference</a> or <a href=\"https://www.kaggle.com/awsaf49\" target=\"_blank\">@awsaf49</a> <a href=\"https://www.kaggle.com/code/awsaf49/rsna-bcd-efficientnet-tf-tpu-1vm-train\" target=\"_blank\">https://www.kaggle.com/code/awsaf49/rsna-bcd-efficientnet-tf-tpu-1vm-train</a></p>",
      "votes": 2,
      "replies": []
    },
    {
      "id": 2078960,
      "author_name": "",
      "author_url": "",
      "post_date": "2022-12-28T19:49:23.097000",
      "content": "",
      "votes": 0,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "2078843": "Dear all ,\nI have easy question that we have in train csv file has 14 column and in test csv file have 9 column ,so how we can make prediction as when i pass test data to model it will refuse to predict due to feature not equal in train and test files \nRegards,\nGaber",
    "2078885": "Hi, \nYou should train the model in such a way that, on input, it accepts only the information that you are able to provide it with during inference (at the submission), that is, the information that is in the test data.\n\nIf you don't know where to start, I would suggest analyzing the well-crafted baseline training notebooks from @radek1 https://www.kaggle.com/code/radek1/fast-ai-starter-pack-train-inference or @awsaf49 https://www.kaggle.com/code/awsaf49/rsna-bcd-efficientnet-tf-tpu-1vm-train",
    "2078960": ""
  }
}