evalml
evalml copied to clipboard
alteryx
EvalML is an AutoML library written in python.
Currently the `target_impute_strategy` is applied to any kind of target data, independent of whether or not the strategy makes sense for that kind of data. This is only problematic for...
SimpleImputer can raise `TypeConversionError` if `mean` or `median` strategy used with boolean data
The following code will attempt to use the `mean` and `median` strategies with boolean data, which converts the values to floats and then imputes whatever the mean and median of...
With the resolution of #3908, prophet is no longer a "special" dependency that can only be installed on some machines and needs explicit testing. We should remove our prophet-specific make...
- As a user of EvalML, I expect an estimator-ready dataframe when I call `transform_all_but_final()`. However, for time series problems, this dataframe includes the datetime column even if it is...
Once https://github.com/pandas-dev/pandas/issues/41565 has been implemented and released, we should upgrade pandas to that version, which will allow us to remove the nullable type handling put in place by https://github.com/alteryx/evalml/issues/4001.
- As a user, I wish I could pass any boolean column into the ARIMARegressor component. Currently, if you pass in a column with the `Boolean` logical type, we convert...
- With XGBoost 1.5.0, you can now use `enable_categorical` argument to pass categorical data (which avoids us needing to one-hot encode categorical columns) - https://xgboost.readthedocs.io/en/stable/python/examples/categorical.html#sphx-glr-python-examples-categorical-py ```python import xgboost as xgb...
```python import woodwork as ww X = pd.DataFrame({ "nullable bool col": [True, False, False, True, True] * 4, "nullable int col": [0, 1, 2, 0, 3] * 4, }) X.ww.init()...
From https://github.com/pandas-dev/pandas/issues/51074 using `apply(str)` can be used to set the float categories to be strings, and we can try to see if that lets us use the actual float categories....
actions_pipeline = make_pipeline_from_data_check_output(problem_type, messages) data_df, y = actions_pipeline.fit(data_df, target) ################################################# Error Message: File /anaconda/envs/azureml_py310_sdkv2/lib/python3.10/site-packages/woodwork/logical_types.py:475, in IntegerNullable.transform(self, series, null_invalid_values) 473 if null_invalid_values: 474 series = _coerce_integer(series) --> 475 return super().transform(series) File...
