![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F5307432%2F7dc06261774baf09e2bdc9fec66aaf6a%2FScreenshot%20from%202023-05-24%2012-06-03.png?generation=1684910180626301&alt=media\")
When i Submit my inference notebook, after completely running the notebook. I am getting \"submission scoring error\"
\nI checked some discussion, nothing seems to be solving the issue.
Can anyone help me in figuring out, why the submission scoring error is happening? & its solution
\n
Code :
\nlimits = {'0-4':(1,4), '5-12':(4,14), '13-22':(14,19)}\nt1 = datetime.datetime.now()\nfor (test, sample_submission) in iter_test:\n print\n test = test.sort_values(by='index')\n grp = test.level_group.values[0]\n session_id = test.session_id.values[0]\n df = (pl.from_pandas(test))\n df = feature_engineer(df)\n a,b = limits[grp]\n df = model_data_1(df, grp)\n preds = []\n for q in range(a, b):\n model = models[q-1] \n pred = model.predict_proba(df)[0, 1]\n mask = sample_submission.session_id.str.contains(f'q{q}')\n sample_submission.loc[mask,'correct'] = int(pred > threshold[q-1]) \n env.predict(sample_submission)\n\nt2 = datetime.datetime.now()\nprint('Run in ', t2-t1)\nIts completely fine when i run inference for first time. But for 1+ times, i saw the data is being appended to the submission.csv
\n![\"\"](\"https://www.googleapis.com/download/storage/v1/b/kaggle-forum-message-attachments/o/inbox%2F5307432%2Ffe7c0b0c695c6f31ec7befadf95a986b%2FScreenshot%20from%202023-05-24%2012-10-10.png?generation=1684910436297781&alt=media\")
''
Thank you
", "messages": [ { "id": "2271832", "postDate": "05/24/2023 06:41:05", "content": "When i Submit my inference notebook, after completely running the notebook. I am getting \"submission scoring error\"
\nI checked some discussion, nothing seems to be solving the issue.
Can anyone help me in figuring out, why the submission scoring error is happening? & its solution
\n
Code :
\nlimits = {'0-4':(1,4), '5-12':(4,14), '13-22':(14,19)}\nt1 = datetime.datetime.now()\nfor (test, sample_submission) in iter_test:\n print\n test = test.sort_values(by='index')\n grp = test.level_group.values[0]\n session_id = test.session_id.values[0]\n df = (pl.from_pandas(test))\n df = feature_engineer(df)\n a,b = limits[grp]\n df = model_data_1(df, grp)\n preds = []\n for q in range(a, b):\n model = models[q-1] \n pred = model.predict_proba(df)[0, 1]\n mask = sample_submission.session_id.str.contains(f'q{q}')\n sample_submission.loc[mask,'correct'] = int(pred > threshold[q-1]) \n env.predict(sample_submission)\n\nt2 = datetime.datetime.now()\nprint('Run in ', t2-t1)\nIts completely fine when i run inference for first time. But for 1+ times, i saw the data is being appended to the submission.csv
\n''
Thank you
", "rawMarkdown": "When i Submit my inference notebook, after completely running the notebook. I am getting \"submission scoring error\"\nI checked some discussion, nothing seems to be solving the issue.\n\nCan anyone help me in figuring out, why the submission scoring error is happening? & its solution\n\n\n\nCode :\n```\nlimits = {'0-4':(1,4), '5-12':(4,14), '13-22':(14,19)}\nt1 = datetime.datetime.now()\nfor (test, sample_submission) in iter_test:\n print\n test = test.sort_values(by='index')\n grp = test.level_group.values[0]\n session_id = test.session_id.values[0]\n df = (pl.from_pandas(test))\n df = feature_engineer(df)\n a,b = limits[grp]\n df = model_data_1(df, grp)\n preds = []\n for q in range(a, b):\n model = models[q-1] \n pred = model.predict_proba(df)[0, 1]\n mask = sample_submission.session_id.str.contains(f'q{q}')\n sample_submission.loc[mask,'correct'] = int(pred > threshold[q-1]) \n env.predict(sample_submission)\n \nt2 = datetime.datetime.now()\nprint('Run in ', t2-t1)\n```\n\nIts completely fine when i run inference for first time. But for 1+ times, i saw the data is being appended to the submission.csv\n\n''\n\nThank you", "votes": null }, { "id": "2273046", "postDate": "05/25/2023 01:28:28", "content": "I am new to Kaggle. I also got an error when submitting, but when I stopped reading \"test.csv\", the error disappeared.
", "rawMarkdown": "I am new to Kaggle. I also got an error when submitting, but when I stopped reading \"test.csv\", the error disappeared.", "votes": null }, { "id": "2273178", "postDate": "05/25/2023 03:56:25", "content": "Thanks for replying,
\nI am not reading test.csv file, i am using jo_wilder api to take prediction data.
\nCan you send me your prediction code, hidding the features, please.
A new jo_wilder_310 has been released. Please check.
\nhttps://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/412512
\nhttps://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/400313
These are old fixed bro. I don't know why, now i can't submit, any of my work
", "rawMarkdown": "These are old fixed bro. I don't know why, now i can't submit, any of my work", "votes": null }, { "id": "2277649", "postDate": "05/28/2023 00:18:49", "content": "I too struggled with debugging a \"Submission Scoring Error\". In my case, it turned out that it wasn't a submission scoring error, but rather \"Notebook Throw Exception\". Perhaps, when an error occurs during the runninig of the notebook, the execution is interrupted at that point, and the submission.csv up to that point is evaluated? If that's the case, it is possible of encountering a submission scoring error because of shortage of records.
", "rawMarkdown": "I too struggled with debugging a \"Submission Scoring Error\". In my case, it turned out that it wasn't a submission scoring error, but rather \"Notebook Throw Exception\". Perhaps, when an error occurs during the runninig of the notebook, the execution is interrupted at that point, and the submission.csv up to that point is evaluated? If that's the case, it is possible of encountering a submission scoring error because of shortage of records.", "votes": null }, { "id": "2277918", "postDate": "05/28/2023 07:19:15", "content": "How did you solved. Could you give me the sample code change u did to rectify the error, without the logic! Please
", "rawMarkdown": "How did you solved. Could you give me the sample code change u did to rectify the error, without the logic! Please", "votes": null }, { "id": "2280507", "postDate": "05/30/2023 06:31:04", "content": "I'm also facing the same error, did you solve this error?
", "rawMarkdown": "I'm also facing the same error, did you solve this error?", "votes": null }, { "id": "2280551", "postDate": "05/30/2023 07:14:30", "content": "No. But the error is not in API, it is the feature engineering technique that i couldn't figure it out
", "rawMarkdown": "No. But the error is not in API, it is the feature engineering technique that i couldn't figure it out", "votes": null } ], "comments": [ { "id": 2273046, "author_name": "mitsuyasuhoshino", "author_url": "", "post_date": "05/25/2023 01:28:28", "content": "I am new to Kaggle. I also got an error when submitting, but when I stopped reading \"test.csv\", the error disappeared.
", "votes": null, "replies": [ { "id": 2273178, "author_name": "navinkumarmnk", "author_url": "", "post_date": "05/25/2023 03:56:25", "content": "Thanks for replying,
\nI am not reading test.csv file, i am using jo_wilder api to take prediction data.
\nCan you send me your prediction code, hidding the features, please.
A new jo_wilder_310 has been released. Please check.
\nhttps://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/412512
\nhttps://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/400313
These are old fixed bro. I don't know why, now i can't submit, any of my work
", "votes": null, "replies": [] } ] } ] } ] }, { "id": 2277649, "author_name": "ryotak12", "author_url": "", "post_date": "05/28/2023 00:18:49", "content": "I too struggled with debugging a \"Submission Scoring Error\". In my case, it turned out that it wasn't a submission scoring error, but rather \"Notebook Throw Exception\". Perhaps, when an error occurs during the runninig of the notebook, the execution is interrupted at that point, and the submission.csv up to that point is evaluated? If that's the case, it is possible of encountering a submission scoring error because of shortage of records.
", "votes": null, "replies": [ { "id": 2277918, "author_name": "navinkumarmnk", "author_url": "", "post_date": "05/28/2023 07:19:15", "content": "How did you solved. Could you give me the sample code change u did to rectify the error, without the logic! Please
", "votes": null, "replies": [] } ] }, { "id": 2280507, "author_name": "nabgesharvari", "author_url": "", "post_date": "05/30/2023 06:31:04", "content": "I'm also facing the same error, did you solve this error?
", "votes": null, "replies": [ { "id": 2280551, "author_name": "navinkumarmnk", "author_url": "", "post_date": "05/30/2023 07:14:30", "content": "No. But the error is not in API, it is the feature engineering technique that i couldn't figure it out
", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "2271832": "When i Submit my inference notebook, after completely running the notebook. I am getting \"submission scoring error\"\nI checked some discussion, nothing seems to be solving the issue.\n\nCan anyone help me in figuring out, why the submission scoring error is happening? & its solution\n\n\n\nCode :\n```\nlimits = {'0-4':(1,4), '5-12':(4,14), '13-22':(14,19)}\nt1 = datetime.datetime.now()\nfor (test, sample_submission) in iter_test:\n print\n test = test.sort_values(by='index')\n grp = test.level_group.values[0]\n session_id = test.session_id.values[0]\n df = (pl.from_pandas(test))\n df = feature_engineer(df)\n a,b = limits[grp]\n df = model_data_1(df, grp)\n preds = []\n for q in range(a, b):\n model = models[q-1] \n pred = model.predict_proba(df)[0, 1]\n mask = sample_submission.session_id.str.contains(f'q{q}')\n sample_submission.loc[mask,'correct'] = int(pred > threshold[q-1]) \n env.predict(sample_submission)\n \nt2 = datetime.datetime.now()\nprint('Run in ', t2-t1)\n```\n\nIts completely fine when i run inference for first time. But for 1+ times, i saw the data is being appended to the submission.csv\n\n''\n\nThank you", "2273046": "I am new to Kaggle. I also got an error when submitting, but when I stopped reading \"test.csv\", the error disappeared.", "2273178": "Thanks for replying,\nI am not reading test.csv file, i am using jo_wilder api to take prediction data.\nCan you send me your prediction code, hidding the features, please.", "2273193": "A new jo_wilder_310 has been released. Please check.\n\nhttps://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/412512\nhttps://www.kaggle.com/competitions/predict-student-performance-from-game-play/discussion/400313", "2273798": "These are old fixed bro. I don't know why, now i can't submit, any of my work", "2277649": "I too struggled with debugging a \"Submission Scoring Error\". In my case, it turned out that it wasn't a submission scoring error, but rather \"Notebook Throw Exception\". Perhaps, when an error occurs during the runninig of the notebook, the execution is interrupted at that point, and the submission.csv up to that point is evaluated? If that's the case, it is possible of encountering a submission scoring error because of shortage of records.", "2277918": "How did you solved. Could you give me the sample code change u did to rectify the error, without the logic! Please", "2280507": "I'm also facing the same error, did you solve this error?", "2280551": "No. But the error is not in API, it is the feature engineering technique that i couldn't figure it out" }, "source": "meta" }