search

traindb-project / traindb-ml

Remote ML Model Serving Component for TrainDB
Apache License 2.0
6 stars 2 forks source link

AQP Error: Exception: Node type unknown: <class 'rspn.structure.leaves.Categorical'> #41

Closed kihyuk-nam closed 2 years ago

kihyuk-nam commented 2 years ago

INPUT

SELECT SUM(order_dow) FROM orders

RESULT

2022-08-24 14:09:58,714 [INFO ]  ESTIMATE Aggregations: SELECT SUM(order_dow) FROM orders 
2022-08-24 14:09:58,714 [INFO ]   - Query: SELECT SUM(order_dow) FROM orders , Model: ['model/instances/ensemble_single_instacart_10000000.pkl']
2022-08-24 14:09:58,715 [INFO ]   - Show Confidence Intervals: True
2022-08-24 14:09:58,715 [INFO ]   Read the ensemble in ['model/instances/ensemble_single_instacart_10000000.pkl']
2022-08-24 14:09:58,717 [DEBUG]   - Including SPN with table_set {'orders'} with sampling ratio(3421084 / 9853060.949424399)
2022-08-24 14:09:58,717 [DEBUG]  Stats: (---Structure Statistics---
# nodes             63
    # sum nodes     0
    # prod nodes    19
    # leaf nodes    42
# params            42
# edges             43
# layers            5)
2022-08-24 14:09:58,718 [INFO ]   : <train.ensemble_compilation.spn_ensemble.SPNEnsemble object at 0x7fde78e0f970>
2022-08-24 14:09:58,720 [INFO ]   Evaluate 'SELECT SUM(order_dow) FROM orders :<train.ensemble_compilation.graph_representation.Query object at 0x7fde78e0faf0>'
2022-08-24 14:09:58,720 [DEBUG]   In evaluate_query
2022-08-24 14:09:58,720 [DEBUG]   query.query_type = QueryType.AQP
2022-08-24 14:09:58,721 [DEBUG]         predicted cardinality: 9853060.949424399
2022-08-24 14:09:58,721 [DEBUG]         computed prototypical cardinality in 0.0009669910650700331 secs.
2022-08-24 14:09:58,721 [DEBUG]   if len(query.group_bys) == 0 and confidence_intervals
2022-08-24 14:09:58,722 [DEBUG]   query.query_type = QueryType.AQP
2022-08-24 14:09:58,722 [DEBUG]   aggregation_operation_type = AggregationOperationType.AGGREGATION
2022-08-24 14:09:58,722 [DEBUG]   aggregation_type = AggregationType.SUM
2022-08-24 14:09:58,722 [DEBUG]   factors = [('orders', 'order_dow')]
2022-08-24 14:09:58,722 [DEBUG]   expectation_spn: <train.aqp_spn.aqp_spn.AQPSPN object at 0x7fde78e0fac0>
2022-08-24 14:09:58,722 [DEBUG]   expectation:  * E(orders.order_dow| orders.orders_nn IS NOT NULL)
INFO:     127.0.0.1:34034 - "GET /estimate/?query=SELECT%20SUM%28order_dow%29%20FROM%20orders%20&dataset=instacart&ensemble_location=model%2Finstances%2Fensemble_single_instacart_10000000.pkl&show_confidence_intervals=true HTTP/1.1" 500 Internal Server Error

...

  File "main.py", line 53, in aqp_read
    value = estimate(schema, dataset, query, ensemble_location, show_confidence_intervals)
  File "main.py", line 211, in estimate
    result = evaluate_an_aqp_query(ensemble_location, query, schema, show_confidence_intervals)
  File "/home/nam/Projects/traindb/traindb-ml/evaluation/aqp_evaluation.py", line 111, in evaluate_an_aqp_query
    spn_ensemble.evaluate_query(query,
  File "/home/nam/Projects/traindb/traindb-ml/train/ensemble_compilation/spn_ensemble.py", line 890, in evaluate_query
    current_stds, aggregation_result = expectation_spn.evaluate_expectation_batch(
  File "/home/nam/Projects/traindb/traindb-ml/train/aqp_spn/aqp_spn.py", line 161, in evaluate_expectation_batch
    self._normalized_conditional_expectation(features, inverted_features=inverted_features,
  File "/home/nam/Projects/traindb/traindb-ml/rspn/rspn.py", line 320, in _normalized_conditional_expectation
    return self._unnormalized_conditional_expectation_with_std(feature_scope,
  File "/home/nam/Projects/traindb/traindb-ml/rspn/rspn.py", line 282, in _unnormalized_conditional_expectation_with_std
    e_x_sq = self._indicator_expectation(feature_scope,
  File "/home/nam/Projects/traindb/traindb-ml/rspn/rspn.py", line 183, in _indicator_expectation
    full_result = expectation(self.mspn, feature_scope, inverted_features, range_conditions,
  File "/home/nam/Projects/traindb/traindb-ml/rspn/algorithms/expectations.py", line 64, in expectation
    [[expectation_recursive(spn, feature_scope, inverted_features, relevant_scope, evidence,
  File "/home/nam/Projects/traindb/traindb-ml/rspn/algorithms/expectations.py", line 146, in expectation_recursive
    llchildren = [expectation_recursive(child, feature_scope, inverted_features, relevant_scope, evidence,
  File "/home/nam/Projects/traindb/traindb-ml/rspn/algorithms/expectations.py", line 146, in <listcomp>
    llchildren = [expectation_recursive(child, feature_scope, inverted_features, relevant_scope, evidence,
  File "/home/nam/Projects/traindb/traindb-ml/rspn/algorithms/expectations.py", line 137, in expectation_recursive
    factor = expectation_recursive(child, feature_scope, inverted_features, relevant_scope, evidence,
  File "/home/nam/Projects/traindb/traindb-ml/rspn/algorithms/expectations.py", line 170, in expectation_recursive
    raise Exception('Node type unknown: ' + str(t_node))
Exception: Node type unknown: <class 'rspn.structure.leaves.Categorical'>

SUSPECTED CAUSE