Hi,
Thanks for the code provided and for your work.
Can you please provide the columns the code expects from the input data and also the geocell (after it has been generated).
Right now, I get a KeyError on this line in dataset_preprocessing.py when I pass in the generated geocell (geocells_yfcc.csv).
geocell_df['polygon'] = geocell_df['polygon'].apply(wkt.loads)
This makes sense because the geocells_yfcc.csv only has these columns name,admin_1,country,size,num_polygons,geometry. The polygon column is missing.
That makes me wonder if I've missed a step or if I'm doing something wrong.
Can you help? thanks!
Hi,
Thanks for the code provided and for your work.
Can you please provide the columns the code expects from the input data and also the geocell (after it has been generated).
Right now, I get a KeyError on this line in dataset_preprocessing.py when I pass in the generated geocell (geocells_yfcc.csv).
geocell_df['polygon'] = geocell_df['polygon'].apply(wkt.loads)This makes sense because the geocells_yfcc.csv only has these columns
name,admin_1,country,size,num_polygons,geometry. The polygon column is missing.That makes me wonder if I've missed a step or if I'm doing something wrong.
Can you help? thanks!