Dylan Stewart

**Author of Proposal: Dylan Stewart** ## Reason or Problem A common issue with multi-dimensional raster image processing (at the extremes, hyperspectral imagery with hundreds of features) is significant redundancy within...

Update k-means|| description. Previous description was incomplete/incorrect.

[FEA] Write data to parquet

2

**Is your feature request related to a problem? Please describe.** I wish I could use cuSpatial to write data to GeoParquet. I have several GBs of census data with various...

memory usage does not reflect size on disk

5

This may be the expected behavior? I discovered this issue because I thought that setting the partition size manually `ddf.repartition(partition_size="100MB")` to try and balance these partitions would also be reflected...

landcover.ipynb predictions misalignment?

1

 It seems that there might be some misalignment of imagery within the landcover example? Looking at this output, the labels don't appear...

[BUG] unable to pickle trained cuml dask KNeighborsClassifier

1

**Describe the bug** After fitting a cuml dask KNeighborsClassifier, the `get_combined_model()` method returns None **Code to reproduce bug** ```python import cudf import cuml import dask import dask_cudf from cuml.dask.datasets import...

Several changes have been made (e.g., now available on conda forge, there are 3 output parquet files that have various features in each) and the ReadMe doesn't reflect these changes.