metric = NormalizedDiscountedCumulativeGain(
38, queries=[train_queries, valid_queries, test_queries])
# Initialize LambdaMART model and train it.
# model = LambdaMART(n_estimators=10000, max_depth=2, shrinkage=0.07,
# estopping=100, n_jobs=-1)
# model.fit(metric, train_queries) # , validation=valid_queries)
model = LambdaMART(
metric='NDCG@38',
max_leaf_nodes=7,
shrinkage=0.07,
estopping=100,
n_jobs=-1,
random_state=42,
use_pines=True,
pines_kwargs=dict(
switch_criterion=ObliviousCartSwitchCriterionType.OBLIVIOUS_WHILE_CAN,
tree_type=TreeType.OBLIVIOUS_CART,
max_n_splits=10,
min_samples_leaf=50,
max_depth=2,
))
model.fit(train_queries, validation_queries=valid_queries)
logging.info('===============================================================')
# Save the model to files
# os.mkdir(MODELLER_DIR)
# logging.info('New folder is created: %s' % MODELLER_DIR)
# joblib.dump(model, MODELLER_DIR + model_name + '.pkl')
# logging.info('Model is saves as: %s' % MODELLER_DIR + model_name + '.pkl')
#parameters
metric = 'nDCG@10'
max_leaf_nodes = 7
min_samples_split = 2
estopping = 10
#TODO change these to the optimal ones found from the grid search
n_estimators = 1000
max_features = None
min_samples_leaf = 50
learn_rate = 0.2
model = LambdaMART(metric=metric,
max_leaf_nodes=max_leaf_nodes,
min_samples_split=min_samples_split,
estopping=estopping,
n_estimators=n_estimators,
max_features=max_features,
min_samples_leaf=min_samples_leaf,
shrinkage=learn_rate,
n_jobs=-1,
random_state=42)
model.fit(training_queries, validation_queries=validation_queries)
logging.info(
'================================================================================'
)
test_ranks = model.predict_rankings(test_queries)
dcg_score = NDCG(test_queries, test_ranks).mean_ndcg()
map_score = MAP(test_queries, test_ranks).mean_average_precision()
dcg_folds_scores.append(dcg_score)
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)
model = LambdaMART(metric='NDCG@10',
max_leaf_nodes=7,
shrinkage=0.1,
estopping=50,
n_jobs=-1,
min_samples_leaf=50,
random_state=42)
model.fit(training_queries, validation_queries=validation_queries)
logging.info('=' * 80)
logging.info('%s on the test queries: %.8f' %
(model.metric, model.evaluate(test_queries, n_jobs=-1)))
model.save('LambdaMART_L7_S0.1_E50_' + model.metric)
#train_queries.save('../data/train_bin')
#valid_queries.save('../data/validation_bin')
#test_queries.save('../data/test_bin')
# ... because loading them will be then faster.
#train_queries = Queries.load('../data/train_bin')
#valid_queries = Queries.load('../data/validation_bin')
#test_queries = Queries.load('../data/test_bin')
logging.info('================================================================================')
# Print basic info about query datasets.
logging.info('Train queries: %s' % train_queries)
logging.info('Valid queries: %s' % valid_queries)
logging.info('Test queries: %s' %test_queries)
logging.info('================================================================================')
# Prepare metric for this set of queries.
metric = NormalizedDiscountedCumulativeGain(38, queries=[train_queries, valid_queries, test_queries])
# Initialize LambdaMART model and train it.
model = LambdaMART(n_estimators=10000, max_depth=4, shrinkage=0.08, estopping=100, n_jobs=-1)
model.fit(metric, train_queries, validation=valid_queries)
logging.info('================================================================================')
# Print out the performance on the test set.
logging.info('%s on the test queries: %.8f' % (metric, metric.evaluate_queries(test_queries, model.predict(test_queries, n_jobs=-1))))
valid_queries = Queries.load_from_text('../data/svmlight_val.txt')
test_queries = Queries.load_from_text('../data/svmlight_test.txt')
logging.info(
'================================================================================'
)
logging.info('train LambdaMart')
# Prepare metric for this set of queries.
metric = NormalizedDiscountedCumulativeGain(
38, queries=[train_queries, valid_queries, test_queries])
# Initialize LambdaMART model and train it.
model = LambdaMART(n_estimators=10000,
max_depth=5,
shrinkage=0.08,
estopping=100,
n_jobs=-1,
n_iterations=100)
model.fit(metric, train_queries, validation=valid_queries)
logging.info(
'================================================================================'
)
logging.info('test')
# Print out the performance on the test set.
logging.info('%s on the test queries: %.8f' %
(metric,
metric.evaluate_queries(test_queries,
model.predict(test_queries, n_jobs=-1))))
'================================================================================'
)
metrics = {}
# Prepare metric for this set of queries.
metrics[0] = NormalizedDiscountedCumulativeGain(
10, queries=[train_queries, valid_queries, test_queries])
# metrics[1] = SeznamRank(10, queries=[train_queries, valid_queries, test_queries])
metrics[1] = DiscountedCumulativeGain(
10, queries=[train_queries, valid_queries, test_queries])
metrics[2] = WinnerTakesAll(
10, queries=[train_queries, valid_queries, test_queries])
# metrics[4] = ExpectedReciprocalRank(10, queries=[train_queries, valid_queries, test_queries])
# Initialize LambdaMART model and train it.
model = LambdaMART(n_estimators=50000,
max_depth=4,
shrinkage=0.1,
estopping=args.iter,
n_jobs=4)
metric = metrics[args.metric]
model.fit(metric, train_queries, validation=valid_queries)
logging.info(
'================================================================================'
)
# Print out the performance on the test set.
logging.info('%s on the test queries: %.8f' %
(metric,
metric.evaluate_queries(test_queries,
model.predict(test_queries, n_jobs=-1))))
#EOF
