-
I came across this while using EvalML to solve a problem.
It would be useful to be able to get a repr of the automl object after it's been defined. Basically, printing it out would give you inform…
-
Expected behavior: `random_state` parameters support the same param types as `sklearn.utils.check_random_state` (which is how random state args are generally used by sklearn arguments):
- `int`s - us…
-
[Example](https://github.com/FeatureLabs/evalml/runs/646266037)
CircleCI on master sometimes runs tests under the `dep-update` branch but will fail as the `dep-update` branch is used and deleted by t…
-
Right now, we will one hot encode every unique category in a categorical variable. This leads to very high dimensionality and sparse outputs.
We should adopt the same behavior as `featuretools.en…
-
- We already calculate the confusion matrix for [classification problems](https://github.com/FeatureLabs/evalml/blob/6f23eea7c6c2696b5fa30c1165069ffd12a54fcd/evalml/objectives/standard_metrics.py#L326…
-
-
**Missing functionality**
There’s no easy way to define a list of custom pipelines to run in automl search. You’d have to override evalml.pipelines.utils.ALL_PIPELINES
**Proposed change**
The pipelin…
-
Currently we attach the Logger class to `AutoBase`, `PipelineBase` and `ComponentBase` as instance state:
```
from evalml.utils import Logger
...
class PipelineBase:
def __init__(self, ...):
…
-
We currently have at least one third-party library dependency (xgboost) and another on the way (catboost #247). This issue tracks figuring out how we present that to users.
Questions:
* What hap…
-
Some places in the code base require that arguments implement an interface. For example, the pipeline verifies that the last component is something that can predict, etc. Instead of checking that it…