Open tlienart opened 4 years ago
Basically we should just link to it. It would give more creds to original author + there's a fair bit of pre-proc code and it relies on a dataset that we can't serve.
it relies on a dataset that we can't serve.
Oh well.
A link would be good.
In general it would be nice to have a link to as many MLJ codes for ML datasets which are also featured on Kaggle:
-Note: many datasets below (Boston, Ames, MNIST etc) do not belong to Kaggle
-Some of these links are competitions, others just practice, some ongoing, some not
Boston: https://www.kaggle.com/c/boston-housing
Ames: https://www.kaggle.com/c/house-prices-advanced-regression-techniques
Titanic: https://www.kaggle.com/c/titanic
MNIST: https://www.kaggle.com/c/digit-recognizer
(ps: I don't think MLJ has @load MNIST
@ablaom @tlienart this could be helpful)
Iris: https://www.kaggle.com/uciml/iris Pima: https://www.kaggle.com/uciml/pima-indians-diabetes-database King County: https://www.kaggle.com/harlfoxem/housesalesprediction/kernels https://rdrr.io/cran/moderndive/man/house_prices.html
https://github.com/stefanjwojcik/mm2020/issues/1