Are we allowed to import data as a list or dictionary (copy-paste the data that we need)? In that case ensembling must not be done in single kernel as specified from closing instructions kernel?\nclosing instructions
", "messages": [ { "id": "463061", "postDate": "01/29/2019 10:32:16", "content": "Are we allowed to import data as a list or dictionary (copy-paste the data that we need)? In that case ensembling must not be done in single kernel as specified from closing instructions kernel?\nclosing instructions
", "rawMarkdown": "Are we allowed to import data as a list or dictionary (copy-paste the data that we need)? In that case ensembling must not be done in single kernel as specified from closing instructions kernel?\n[closing instructions][1]\n\n\n [1]: https://www.kaggle.com/c/quora-insincere-questions-classification/discussion/77029", "votes": null }, { "id": "463342", "postDate": "01/29/2019 20:45:11", "content": "As is stated in the Overview tab of this competition \"This competition does not allow external data.\" So while you may be technically able to upload external data to your kernel in whichever format you chose, your kernel's \"Submit to Competition\" button will be deactivated. I believe this is primarily to prevent you from scraping Quora's website to find which questions still exist and which have been taken down, as well as all related 'cheating' shenanigans. The exceptions to this are a number of whitelisted pre-trained models available on the kernels data page.
\n\nNow depending on the data you're talking about, there may be ways around this. If you're talking about... say, a list of 30 words which are \"profanity\", you can likely copy-paste them directly into your kernel as a list without triggering the submission blocker or violating the spirit of the rules of the competition. If it's a dictionary with thousands of entries, you might be out of luck as it might crash your kernel.
", "rawMarkdown": "As is stated in the [Overview tab](https://www.kaggle.com/c/quora-insincere-questions-classification#Kernels-FAQ) of this competition \"This competition does not allow external data.\" So while you may be technically able to upload external data to your kernel in whichever format you chose, your kernel's \"Submit to Competition\" button will be deactivated. I believe this is primarily to prevent you from scraping Quora's website to find which questions still exist and which have been taken down, as well as all related 'cheating' shenanigans. The exceptions to this are a number of whitelisted pre-trained models available on the kernels data page. \n\nNow depending on the data you're talking about, there may be ways around this. If you're talking about... say, a list of 30 words which are \"profanity\", you can likely copy-paste them directly into your kernel as a list without triggering the submission blocker or violating the spirit of the rules of the competition. If it's a dictionary with thousands of entries, you might be out of luck as it might crash your kernel.", "votes": null } ], "comments": [ { "id": 463342, "author_name": "alecthekulak", "author_url": "", "post_date": "01/29/2019 20:45:11", "content": "As is stated in the Overview tab of this competition \"This competition does not allow external data.\" So while you may be technically able to upload external data to your kernel in whichever format you chose, your kernel's \"Submit to Competition\" button will be deactivated. I believe this is primarily to prevent you from scraping Quora's website to find which questions still exist and which have been taken down, as well as all related 'cheating' shenanigans. The exceptions to this are a number of whitelisted pre-trained models available on the kernels data page.
\n\nNow depending on the data you're talking about, there may be ways around this. If you're talking about... say, a list of 30 words which are \"profanity\", you can likely copy-paste them directly into your kernel as a list without triggering the submission blocker or violating the spirit of the rules of the competition. If it's a dictionary with thousands of entries, you might be out of luck as it might crash your kernel.
", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "463061": "Are we allowed to import data as a list or dictionary (copy-paste the data that we need)? In that case ensembling must not be done in single kernel as specified from closing instructions kernel?\n[closing instructions][1]\n\n\n [1]: https://www.kaggle.com/c/quora-insincere-questions-classification/discussion/77029", "463342": "As is stated in the [Overview tab](https://www.kaggle.com/c/quora-insincere-questions-classification#Kernels-FAQ) of this competition \"This competition does not allow external data.\" So while you may be technically able to upload external data to your kernel in whichever format you chose, your kernel's \"Submit to Competition\" button will be deactivated. I believe this is primarily to prevent you from scraping Quora's website to find which questions still exist and which have been taken down, as well as all related 'cheating' shenanigans. The exceptions to this are a number of whitelisted pre-trained models available on the kernels data page. \n\nNow depending on the data you're talking about, there may be ways around this. If you're talking about... say, a list of 30 words which are \"profanity\", you can likely copy-paste them directly into your kernel as a list without triggering the submission blocker or violating the spirit of the rules of the competition. If it's a dictionary with thousands of entries, you might be out of luck as it might crash your kernel." }, "source": "meta" }