{
  "id": 115822,
  "title": "A simple code to get stage 1 test result",
  "url": "/competitions/rsna-intracranial-hemorrhage-detection/discussion/115822",
  "author_name": "Yiheng Wang",
  "post_date": "2019-11-05T13:42:50.272000",
  "votes": 4,
  "comment_count": 1,
  "views": 0,
  "content": "<p>Hi all, I just wrote a simple code which is used to calculate your stage 1 submission file's result, you can choose to calculate the original result, or the result which ignores the samples that have duplicate patientID in training set.\ncode Link: <a href=\"https://www.kaggle.com/yiheng/get-stage1-test-result\">https://www.kaggle.com/yiheng/get-stage1-test-result</a>\nIt is my first public kernel, if there are any bugs, feel free to correct it, thanks!</p>",
  "messages": [
    {
      "id": 665887,
      "postDate": "2019-11-05T13:50:34.547Z",
      "content": "<p>```\nimport pandas as pd</p>\n\n<p>stage_2_train = pd.read_csv(\"../input/stage_2_train.csv\")\nstage_1_test  = pd.read_csv(\"../input/stage_1_sample_submission.csv\")</p>\n\n<p>stage_1_test = stage_2_train[stage_2_train.ID.isin(stage_1_test.ID)]\nstage_1_test.to_csv(\"../input/stage_1_test.csv\", index=None)\n```</p>",
      "rawMarkdown": "```\nimport pandas as pd\n\nstage_2_train = pd.read_csv(\"../input/stage_2_train.csv\")\nstage_1_test  = pd.read_csv(\"../input/stage_1_sample_submission.csv\")\n\nstage_1_test = stage_2_train[stage_2_train.ID.isin(stage_1_test.ID)]\nstage_1_test.to_csv(\"../input/stage_1_test.csv\", index=None)\n```",
      "votes": 4
    },
    {
      "id": 665878,
      "postDate": "2019-11-05T13:42:50.273Z",
      "content": "<p>Hi all, I just wrote a simple code which is used to calculate your stage 1 submission file's result, you can choose to calculate the original result, or the result which ignores the samples that have duplicate patientID in training set.\ncode Link: <a href=\"https://www.kaggle.com/yiheng/get-stage1-test-result\">https://www.kaggle.com/yiheng/get-stage1-test-result</a>\nIt is my first public kernel, if there are any bugs, feel free to correct it, thanks!</p>",
      "rawMarkdown": "Hi all, I just wrote a simple code which is used to calculate your stage 1 submission file's result, you can choose to calculate the original result, or the result which ignores the samples that have duplicate patientID in training set.\ncode Link: https://www.kaggle.com/yiheng/get-stage1-test-result\nIt is my first public kernel, if there are any bugs, feel free to correct it, thanks!",
      "votes": 4
    }
  ],
  "comments": [
    {
      "id": 665887,
      "author_name": "Oleg Yaroshevskiy",
      "author_url": "",
      "post_date": "2019-11-05T13:50:34.547000",
      "content": "<p>```\nimport pandas as pd</p>\n\n<p>stage_2_train = pd.read_csv(\"../input/stage_2_train.csv\")\nstage_1_test  = pd.read_csv(\"../input/stage_1_sample_submission.csv\")</p>\n\n<p>stage_1_test = stage_2_train[stage_2_train.ID.isin(stage_1_test.ID)]\nstage_1_test.to_csv(\"../input/stage_1_test.csv\", index=None)\n```</p>",
      "votes": 4,
      "replies": []
    }
  ],
  "raw_markdown_by_id": {
    "665887": "```\nimport pandas as pd\n\nstage_2_train = pd.read_csv(\"../input/stage_2_train.csv\")\nstage_1_test  = pd.read_csv(\"../input/stage_1_sample_submission.csv\")\n\nstage_1_test = stage_2_train[stage_2_train.ID.isin(stage_1_test.ID)]\nstage_1_test.to_csv(\"../input/stage_1_test.csv\", index=None)\n```",
    "665878": "Hi all, I just wrote a simple code which is used to calculate your stage 1 submission file's result, you can choose to calculate the original result, or the result which ignores the samples that have duplicate patientID in training set.\ncode Link: https://www.kaggle.com/yiheng/get-stage1-test-result\nIt is my first public kernel, if there are any bugs, feel free to correct it, thanks!"
  }
}