{ "id": 232753, "title": "Any R scripts out there ?", "url": "/competitions/coleridgeinitiative-show-us-the-data/discussion/232753", "author_name": "", "post_date": "2021-04-15T08:15:18.268614700Z", "votes": 1, "comment_count": 4, "views": 0, "content": "

Since more than one week I try to build a simple submission with R. I always can commit and get a submission file. When I try to submit I always get errors, actually:
\nNotebook Threw Exception
\nHere is my submission:
\nhttps://www.kaggle.com/pehahn/simple-bigram-matching-in-r
\nI can't find any R-notebooks. Nobody using R out there?
\nThanks. Peter

", "messages": [ { "id": "1274352", "postDate": "04/15/2021 08:15:18", "content": "

Since more than one week I try to build a simple submission with R. I always can commit and get a submission file. When I try to submit I always get errors, actually:
\nNotebook Threw Exception
\nHere is my submission:
\nhttps://www.kaggle.com/pehahn/simple-bigram-matching-in-r
\nI can't find any R-notebooks. Nobody using R out there?
\nThanks. Peter

", "rawMarkdown": "Since more than one week I try to build a simple submission with R. I always can commit and get a submission file. When I try to submit I always get errors, actually:\n**Notebook Threw Exception**\nHere is my submission:\nhttps://www.kaggle.com/pehahn/simple-bigram-matching-in-r \nI can't find any R-notebooks. Nobody using R out there?\nThanks. Peter", "votes": null }, { "id": "1274476", "postDate": "04/15/2021 10:31:44", "content": "

Using R for textual data is generally not a great idea.
\nBut here you go: https://www.kaggle.com/rohanrao/coleridge-string-matching-benchmark-in-r

\n

This is a simple string matching benchmark in R scoring 0.532 (after rescoring) on LB, similar to the Python benchmarks.

", "rawMarkdown": "Using R for textual data is generally not a great idea.\nBut here you go: https://www.kaggle.com/rohanrao/coleridge-string-matching-benchmark-in-r\n\nThis is a simple string matching benchmark in R scoring ~~0.699~~ 0.532 (after rescoring) on LB, similar to the Python benchmarks.", "votes": null }, { "id": "1277508", "postDate": "04/18/2021 20:33:27", "content": "

It seems that the winning model would be some kind of NN, and R still doesn't have a decent DL framework.

", "rawMarkdown": "It seems that the winning model would be some kind of NN, and R still doesn't have a decent DL framework.", "votes": null }, { "id": "1278173", "postDate": "04/19/2021 15:58:08", "content": "

I remember this competition - my R script had been holding the best score for quite a long time using only textual data.

", "rawMarkdown": "I remember [this](https://www.kaggle.com/c/avito-demand-prediction/overview) competition - [my R script](https://www.kaggle.com/kailex/xgb-text2vec-tfidf-0-2237) had been holding the best score for quite a long time using only textual data.", "votes": null }, { "id": "1278294", "postDate": "04/19/2021 18:04:26", "content": "

Interesting link. Thank you

", "rawMarkdown": "Interesting link. Thank you", "votes": null } ], "comments": [ { "id": 1274476, "author_name": "rohanrao", "author_url": "", "post_date": "04/15/2021 10:31:44", "content": "

Using R for textual data is generally not a great idea.
\nBut here you go: https://www.kaggle.com/rohanrao/coleridge-string-matching-benchmark-in-r

\n

This is a simple string matching benchmark in R scoring 0.532 (after rescoring) on LB, similar to the Python benchmarks.

", "votes": null, "replies": [ { "id": 1278173, "author_name": "kailex", "author_url": "", "post_date": "04/19/2021 15:58:08", "content": "

I remember this competition - my R script had been holding the best score for quite a long time using only textual data.

", "votes": null, "replies": [] }, { "id": 1278294, "author_name": "pehahn", "author_url": "", "post_date": "04/19/2021 18:04:26", "content": "

Interesting link. Thank you

", "votes": null, "replies": [] } ] }, { "id": 1277508, "author_name": "kailex", "author_url": "", "post_date": "04/18/2021 20:33:27", "content": "

It seems that the winning model would be some kind of NN, and R still doesn't have a decent DL framework.

", "votes": null, "replies": [] } ], "raw_markdown_by_id": { "1274352": "Since more than one week I try to build a simple submission with R. I always can commit and get a submission file. When I try to submit I always get errors, actually:\n**Notebook Threw Exception**\nHere is my submission:\nhttps://www.kaggle.com/pehahn/simple-bigram-matching-in-r \nI can't find any R-notebooks. Nobody using R out there?\nThanks. Peter", "1274476": "Using R for textual data is generally not a great idea.\nBut here you go: https://www.kaggle.com/rohanrao/coleridge-string-matching-benchmark-in-r\n\nThis is a simple string matching benchmark in R scoring ~~0.699~~ 0.532 (after rescoring) on LB, similar to the Python benchmarks.", "1277508": "It seems that the winning model would be some kind of NN, and R still doesn't have a decent DL framework.", "1278173": "I remember [this](https://www.kaggle.com/c/avito-demand-prediction/overview) competition - [my R script](https://www.kaggle.com/kailex/xgb-text2vec-tfidf-0-2237) had been holding the best score for quite a long time using only textual data.", "1278294": "Interesting link. Thank you" }, "source": "meta" }