NameError in Machine learning with Open Data Cube notebook code

Question

I am trying to run the "Machine learning with the Open Data Cube" using my own .shp file but seem to keep getting the same error. The only cell that I altered in the following link is number 3, and the error then comes up after cell 9: https://docs.dea.ga.gov.au/notebooks/Frequently_used_code/Machine_learning_with_ODC.html

The code works perfectly when I don't alter the shapefile path but as soon as I add my own shape file (available here) it doesn't work anymore. The format of the example .shp file and mine are the same.

The code in the original tutorial for cell 3 was:

path = '../Supplementary_data/Machine_learning_with_ODC/example_training_data.shp'
field = 'classnum'
time = ('2015')
zonal_stats = 'median'
resolution = (-25, 25)
output_crs = 'epsg:3577'

I then customised that using my own shape file in cell 3:

path = '../Supplementary_data/Machine_learning_with_ODC/Trainingv4.shp'
field = 'classnum'
time = ('2015')
zonal_stats = 'median'
resolution = (-25, 25)
output_crs = 'epsg:4326'

Every other cell remained the same and the preview of my shapefile had the same format as the example one (ie class column with integer and then geometry coordinates)

Any suggestions?

Answer 1

I am an author of the notebook and the classification tools library, I've fixed the issue you found. It was a missing import triggered in a particular edge case, in this instance some of your training labels fail to load data. You can access these changes by pulling down the latest develop branch or simply add import time to the classification.py file in DEA Tools. I noted that your data is in CRS EPSG:4326, I reprojected it to albers EPSG:3577 and was able to successfully run through the notebook and complete a classification.