Data processing API

This section is dedicated to the API documentation of the data processing module of UDAO. The data processing module is responsible for processing the raw data in view of:

• training a machine learning model to describe the objective function

• process the raw data to be used as input for the optimization module along with the trained model.

It contains the following submodules:

• Containers
  • Base Container
  • Query Structure Container
  • Dataframe Container
• Extractors
  • Base Extractors
  • Query Plan Extractors
  • Tabular Extractor
• Preprocessors
  • Base preprocessors
  • Normalize preprocessor
• Iterators
  • Base Iterator
  • Query Plan Iterator
  • Tabular Iterator
• DataProcessor
  • DataProcessor
  • FeaturePipeline
  • create_data_processor()
• DataHandler
  • DataHandler
• Embedders
  • Base Predicate Embedder
  • Word2Vec Embedder
  • Doc2Vec Embedder
  • Utilities