html_url,issue_url,id,node_id,user,created_at,updated_at,author_association,body,reactions,performed_via_github_app,issue
https://github.com/pydata/xarray/issues/729#issuecomment-184390218,https://api.github.com/repos/pydata/xarray/issues/729,184390218,MDEyOklzc3VlQ29tbWVudDE4NDM5MDIxOA==,1217238,2016-02-15T20:57:35Z,2016-02-15T20:57:35Z,MEMBER,"I just downloaded the data, too, and will see if can simply the task graph into something understandable by humans :).
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",,129150619
https://github.com/pydata/xarray/issues/729#issuecomment-178661780,https://api.github.com/repos/pydata/xarray/issues/729,178661780,MDEyOklzc3VlQ29tbWVudDE3ODY2MTc4MA==,1217238,2016-02-02T16:14:24Z,2016-02-02T16:14:24Z,MEMBER,"Something like `einsum` or a broadcasting matrix multiplication could help a little bit here, by replacing `(M * FLUX).sum('Paliers')` with `M.dot(FLUX, dim='Paliers')` and thereby reducing peak memory consumption, but even there I'm calculating peak chunk size at 950000 elements. This should be totally fine on most machines.

@mrocklin Unfortunately, I don't know an easy way to create a copy of a netCDF file with random data, but that's a good idea for a little project....
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",,129150619
https://github.com/pydata/xarray/issues/729#issuecomment-176362189,https://api.github.com/repos/pydata/xarray/issues/729,176362189,MDEyOklzc3VlQ29tbWVudDE3NjM2MjE4OQ==,1217238,2016-01-28T19:37:17Z,2016-01-28T19:37:17Z,MEMBER,"This is almost certainly an issue with dask's scheduler. cc @mrocklin

Could you share a summary of how you create this dataset? Is it something that should be possible to calculate in a single pass over the data?
","{""total_count"": 0, ""+1"": 0, ""-1"": 0, ""laugh"": 0, ""hooray"": 0, ""confused"": 0, ""heart"": 0, ""rocket"": 0, ""eyes"": 0}",,129150619