Methods, systems, and articles of manufacture to autonomously select data structures

A non-transitory computer readable storage medium comprising instructions that, when executed by a processor, cause the processor to at least:

• assign training code operations to respective first ordered values;
• cause the training code operations to be performed on a statistically distributed data set of data structure application programming interface (API) calls to the respective first ordered values;
• assign candidate data structure types to respective second ordered values;
• generate, for a first data structure API call of the training code operations, a Bloom filter bit vector pattern based on (a) one of the first ordered values corresponding to the first data structure API, (b) one of the second ordered values corresponding to a first one of the assigned candidate data structure types, and (c) a size of the first data structure API that represents a quantity of operations associated with modification of a data structure of the first one of the assigned candidate data structure types;
• generate a first model training input feature vector based on the Bloom filter bit vector pattern, data corresponding to the first data structure API, and a performance metric of the first one of the candidate data structure types for the first data structure API;
• and
• train a data structure selection model with the first model training input feature vector.

A method to train a data structure selection model, the method comprising:

• assigning, by executing an instruction with processor circuitry, training code operations to respective first ordered values;
• perform, by executing an instruction with the processor circuitry, the operations on a statistically distributed data set of data structure application programming interface (API) calls to the respective first ordered values;
• assigning, by executing an instruction with the processor circuitry, candidate data structure types to respective second ordered values;
• generating, by executing an instruction with the processor circuitry, for a first data structure API call of the training code operations, a Bloom filter bit vector pattern based on (a) one of the first ordered values corresponding to the first data structure API, (b) one of the second ordered values corresponding to a first one of the assigned candidate data structure types, and (c) a size of the first data structure API that represents a quantity of operations associated with modification of a data structure of the first one of the assigned candidate data structure types;
• generating, by executing an instruction with the processor circuitry, a first model training input feature vector based on the Bloom filter bit vector pattern, data corresponding to the first data structure API, and a performance metric of the first one of the candidate data structure types;
• and
• training, by executing an instruction with the processor circuitry, the data structure selection model with the first model training input feature vector.

An apparatus to train a data structure selection model, the apparatus comprising:

• means for assigning ordinals to:
• assign training code operations to respective first ordered values;
• cause the operations to be performed on a statistically distributed data set of data structure application programming interface (API) calls to the respective first ordered values;
• and
• assign candidate data structure types to respective second ordered values;
• means for filter generating to, for a first data structure API call of the training code operations, generate a Bloom filter bit vector pattern based on (a) one of the first ordered values corresponding to the first data structure API, (b) one of the second ordered values corresponding to a first one of the assigned candidate data structure types, and (c) a size of the first data structure API that represents a quantity of operations associated with modification of a data structure of the first one of the assigned candidate data structure types;
• means for label generating to generate a first model training input feature vector based on the Bloom filter bit vector pattern, data corresponding to the first data structure API, and a performance metric of the first one of the candidate data structure types for the first data structure API;
• and
• means for neural network managing to train the data structure selection model with the first model training input feature vector.