Methods and apparatus to provide machine assisted programming
Methods, apparatus, systems and articles of manufacture to provide machine assisted programming are disclosed. An example apparatus includes processor circuitry to execute computer readable instructions to: execute a machine learning model to generate a first code recommendation for programming code, the first code recommendation being associated with security of the programming code; cause output of the first code recommendation via a user interface; update the machine learning model based on feedback obtained via the user interface; determine a performance of the programming code; generate a second code recommendation, the second code recommendation being associated with the performance of the programming code; and cause output of the second code recommendation via the user interface.
1 . A non-transitory computer readable storage medium comprising instructions to cause processor circuitry to at least:
execute a machine learning model to generate a first code recommendation for programming code, the first code recommendation being associated with security of the programming code;
cause output of the first code recommendation via a user interface;
update the machine learning model by applying a weight to the machine learning model based on a user selection of the first code recommendation;
in response to updating the machine learning model, determine a performance of the programming code;
generate a second code recommendation by the machine learning model, the second code recommendation being associated with the performance of the programming code; and
cause output of the second code recommendation via the user interface.
2 . The non-transitory computer readable storage medium of claim 1 , wherein the performance of the programming code corresponds to at least one of an amount of processor resources to execute the programming code, an efficiency of the programming code, or a latency associated with the programming code.
3 . The non-transitory computer readable storage medium of claim 1 , wherein the instructions cause the one or more processors to convert the programming code into one or more feature vectors associated with the programming code, the machine learning model to generate the first code recommendation based on the one or more feature vectors.
4 . The non-transitory computer readable storage medium of claim 1 , wherein the instructions cause the one or more processors to cause code to be inserted into the programming code in response to user selection of the first code recommendation.
5 . The non-transitory computer readable storage medium of claim 1 , wherein a user provides feedback via the user interface.
6 . The non-transitory computer readable storage medium of claim 5 , wherein the feedback corresponds to user selection of the first code recommendation.
7 . An apparatus comprising:
memory;
computer readable instructions; and
processor circuitry to execute the computer readable instructions to:
execute a machine learning model to generate a first code recommendation for programming code, the first code recommendation being associated with security of the programming code;
cause output of the first code recommendation via a user interface;
update the machine learning model by applying a weight to the machine learning model based on a user selection of the first code recommendation;
in response to updating the machine learning model, determine a performance of the programming code;
generate a second code recommendation by the machine learning model, the second code recommendation being associated with the performance of the programming code; and
cause output of the second code recommendation via the user interface.
8 . The apparatus of claim 7 , wherein the performance of the programming code corresponds to at least one of an amount of processor resources to execute the programming code, an efficiency of the programming code, or a latency associated with the programming code.
9 . The apparatus of claim 7 , wherein the processor circuitry is to convert the programming code into one or more feature vectors associated with the programming code, the machine learning model to generate the first code recommendation based on the one or more feature vectors.
10 . The apparatus of claim 7 , wherein the processor circuitry is to cause code to be inserted into the programming code in response to user selection of the first code recommendation.
11 . The apparatus of claim 7 , wherein a user provides feedback via the user interface.
12 . The apparatus of claim 11 , wherein the feedback corresponds to user selection of the first code recommendation.
13 . A method comprising:
executing a machine learning model to generate a first code recommendation for programming code, the first code recommendation being associated with security of the programming code;
outputting of the first code recommendation via a user interface;
updating the machine learning model by applying a weight to the machine learning model based on a user selection of the first code recommendation;
in response to updating the machine learning model, determining a performance of the programming code;
generating a second code recommendation by the machine learning model, the second code recommendation being associated with the performance of the programming code; and
outputting of the second code recommendation via the user interface.
14 . The method of claim 13 , wherein the performance of the programming code corresponds to at least one of an amount of processor resources to execute the programming code, an efficiency of the programming code, or a latency associated with the programming code.
15 . The method of claim 13 , further including converting the programming code into one or more feature vectors associated with the programming code, the machine learning model to generate the first code recommendation based on the one or more feature vectors.
16 . The method of claim 13 , further including causing code to be inserted into the programming code in response to user selection of the first code recommendation.
17 . The method of claim 13 , wherein a user provides feedback via the user interface.
18 . The method of claim 17 , wherein the feedback corresponds to user selection of the first code recommendation.
19 . The non-transitory computer readable storage medium of claim 1 , wherein the weight is associated with a feature vector of the first code recommendation, the machine learning model trained using the feature vector.
20 . The non-transitory computer readable storage medium of claim 1 , wherein the instructions cause the one or more processors to update, based on user selection of the first code recommendation, a ranking of feature vectors associated with the first code recommendation.