evalml
evalml copied to clipboard
alteryx
EvalML is an AutoML library written in python.
- As a user, I wish I could use EvalML to quicky plot time series target data. - In particular, I would like to be able to create a plot...
In #3933, we ended up pinning the `category-encoders` dependency as it kept returning ~0.6 for the `TargetEncoder()` component when [tests are ran on main](https://github.com/alteryx/evalml/actions/runs/3939944955/jobs/6740422467). This issue tracks finding the root...
The following block of code will work for `pos_label_idx` equal to 1 but raise `ValueError: unknown format is not supported` when `pos_label_idx` is 0: ```python import woodwork as ww from...
Hello! I am testing EvalML for the first time. I was working with your [example](https://evalml.alteryx.com/en/stable/user_guide/timeseries.html) . Unfortunately I get this error and I can't complete the tutorial. Here is the...
Follow up to #3620 - this issue will track investigating why our pipelines raise `ParameterNotUsedWarnings` for our KIA pipelines. This can be seen [here](https://evalml.alteryx.com/en/v0.64.0/user_guide/timeseries.html#Known-in-advance-features).
If there are categories present in holdout data that weren't present in the training data, the OrdinalEncoder will not work unless `handle_unknown` and `unknown_value` are set correctly. This is problematic...
While attempting to split a dataset into multiple pandas dataframes, an error occurs when one column of binary data is marked as categorical through the infer_feature_types function while in its...
Woodwork updated their Boolean inference in [this](https://github.com/alteryx/woodwork/pull/1549) PR, with an additional update in [this](https://github.com/alteryx/woodwork/pull/1576) one. This issue covers two main areas of change: - Updating tests to be compatible -...
My application scenario is that there is more than one tag for a sample, that is, one sample corresponds to multiple tags. It seems that there is no support at...
- Currently, we explicitly pass along the origin and logical type when initializing woodwork on the updated partial dependence column. This means that if predictions ever become dependent on another...