Skip to content

MRMS precip_type handling #5

Description

@oznogr

When running CHIMP with 'mrms_w_type', the precip_type tensor is not handled properly.

In RefernceDataset.load_sample:

              if not np.issubdtype(y_t.dtype, np.floating):
                    y_t = y_t.astype(np.int64)

changes the precip_type y_t target to int64 and then:

            if invalid is not None:
                y_t[invalid] = np.nan

throws an error because y_t is int64 and np.nan is float.

Activity

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

      Milestone

      No milestone

      Relationships

      None yet

      Development

      No branches or pull requests

      Issue actions