Change a nicer key name in config and object names in code for prediction

[Lei Song, PhD]

Leave them as old for now. Need to update for next production season.

1. learner/run_it/run_geopyspark.py

   Line 529 in cfe2b77

    catalog_prefix_fix = params['image_catalog_fix'] 

   
   catalog_prefix_predict = params['image_catalog_predict']

And
2. All the fix here:

learner/run_it/run_geopyspark.py

Lines 721 to 753 in cfe2b77

 image_catalog_fix = spark.read \ 
     .option('inferScheme', True) \ 
     .option('header', True) \ 
     .csv('s3n://{}/{}'.format(s3_bucket, catalog_prefix_fix)) \ 
     .repartition('col', 'row') 
 all_image_uris_fix = image_catalog_fix \ 
     .filter(image_catalog_fix['season'] == 'GS') \ 
     .alias('gs') \ 
     .join(image_catalog_fix.filter(image_catalog_fix['season'] == 'OS').alias('os'), 
           (col('gs.col') == col('os.col')) & (col('gs.row') == col('os.row'))) \ 
     .select(col('gs.col'), col('gs.row'), col('gs.uri').alias('GS'), col('os.uri').alias('OS')) 
  
 #recollect all pixels for all testing images 
 compreh_names = f_pool.join(qs_in, ['name', 'col', 'row', 'name_col_row'], 'outer') 
 features_compreh = gather_data(all_image_uris_fix, 
                 compreh_names, 
                 master_metadata, 
                 feature_names, 
                 s3_bucket) 
 fitted_compreh = model.transform(features_compreh)\ 
      .select('spatial_key', 'column_index', 'row_index', 'probability', 'prediction') 
 grouped_compreh = fitted_compreh.groupBy('spatial_key') 
 # added to test sampling 
 assembled = grouped_compreh.agg( 
 assembleTile('column_index', 
              'row_index', 
              secondelement('probability'), 
              master_layout.tileLayout.tileCols, 
              master_layout.tileLayout.tileRows, 
              'float32' 
 ).alias('probability') 
 ) 
 layer = gps.TiledRasterLayer.from_rasterframe(assembled.asRF())