68c9bab4a5c6821c2a4395763c676ba796406c49,dask_ml/preprocessing/_encoders.py,OneHotEncoder,_transform,#OneHotEncoder#Any#Any#,220

Before Change

            import dask.dataframe as dd

            // Validate that all are categorical.
            if not (X.dtypes == "category").all():
                raise ValueError("Must be all categorical.")

            if not len(X.columns) == len(self.categories_):
                raise ValueError(
                    "Number of columns ({}) does not match number "
                    "of categories_ ({})".format(len(X.columns), len(self.categories_))

After Change

            for i, (col, dtype) in enumerate(zip(X.columns, self.dtypes_)):
                Xi = X.iloc[:, i]
                if not pd.api.types.is_categorical_dtype(Xi.dtype):
                    Xi = Xi.astype(dtype)
                    X[col] = Xi

                if Xi.dtype != dtype:
                    raise ValueError(
                        "Different CategoricalDtype for fit and transform. "

Instances