validation_queries.save('data/MQ2007/Fold1/validation')
test_queries.save('data/MQ2007/Fold1/test')
# ... because loading them will be then faster.
training_queries = Queries.load('data/MQ2007/Fold1/training')
validation_queries = Queries.load('data/MQ2007/Fold1/validation')
test_queries = Queries.load('data/MQ2007/Fold1/test')
logging.info('=' * 80)
# Set this to True in order to remove queries containing all documents
# of the same relevance score -- these are useless for LambdaMART.
remove_useless_queries = False
# Find constant query-document features.
cfs = find_constant_features(
[training_queries, validation_queries, test_queries])
# Get rid of constant features and (possibly) remove useless queries.
training_queries.adjust(remove_features=cfs, purge=remove_useless_queries)
validation_queries.adjust(remove_features=cfs, purge=remove_useless_queries)
test_queries.adjust(remove_features=cfs)
# Print basic info about query datasets.
logging.info('Train queries: %s' % training_queries)
logging.info('Valid queries: %s' % validation_queries)
logging.info('Test queries: %s' % test_queries)
logging.info('=' * 80)
param_grid = {
'metric': ['nDCG@10'],
test_queries.save('data/MQ2007/Fold1/test')
# ... because loading them will be then faster.
training_queries = Queries.load('data/MQ2007/Fold1/training')
validation_queries = Queries.load('data/MQ2007/Fold1/validation')
test_queries = Queries.load('data/MQ2007/Fold1/test')
logging.info('=' * 80)
# Set this to True in order to remove queries containing all documents
# of the same relevance score -- these are useless for LambdaMART.
remove_useless_queries = False
# Find constant query-document features.
cfs = find_constant_features([training_queries,
validation_queries,
test_queries])
# Get rid of constant features and (possibly) remove useless queries.
training_queries.adjust(remove_features=cfs, purge=remove_useless_queries)
validation_queries.adjust(remove_features=cfs, purge=remove_useless_queries)
test_queries.adjust(remove_features=cfs)
# Print basic info about query datasets.
logging.info('Train queries: %s' % training_queries)
logging.info('Valid queries: %s' % validation_queries)
logging.info('Test queries: %s' % test_queries)
logging.info('=' * 80)
param_grid = {'metric': ['NDCG@10'],