DeepGabani
DeepGabani
Due to project level restriction on creating a private JSON key for service account, testing the authentication with private JSON key is pending. Suggestion: Use a personal account (not @google.com...
Fixes #206 .
For weather-mv ee (especially feature collection assets), when converting the dataset in a dataframe can run out of memory if the dataset is too large.
By providing accuracy, we ensure that data is matching if it was fetched directly in the same grid. User can pass their accuracy as per data, but the data we...
For ECMWF hres eu nowcasting data, **weather-mv rg** regridded the data which has data shifted horizontally by 180 degree longitudes. Below is a plot of the data that we are...
**The story / Current behavior** In the last step of weather-mv pipeline, the ingestion transform, each worker is ingesting its particular feature-collection. Our logic ensures that there is a room...
Currently, **weather-sp** provides an option to set the filename of the splitted file. For example, for the input file `--input-pattern 'gs://bucket-name/2017-1-sp-10u-10v-2t-2d-tp-ptype.gb'`, I provided `--output-template 'gs://bucket-name/monthly-splitted/{date}{time}/{step}/{date}{time}_FH-{step}.gb'` and it created splitted files...
A source data with multiple times in dimension needs to be ingested per-time in the earth engine. Currently, `weather-mv ee` assumes that the source data will have only one time...