Deploy
MLOps and deployment related functions in PyCaret
predict_model
This function generates the label using a trained model. When data
is None, it predicts label and score on the holdout set.
Hold-out predictions
Unseen data predictions
Probability by class
NOTE: This is only applicable for the Classification use-cases.
Setting probability threshold
NOTE: This is only applicable for the Classification use-cases (binary only).
The threshold for converting predicted probability to the class labels. Unless this parameter is set, it will default to the value set during model creation. If that wasn’t set, the default will be 0.5 for all classifiers. Only applicable for binary classification.
Comparison between different thresholds on the hold-out data
finalize_model
This function trains a given model on the entire dataset including the hold-out set.
This function doesn't change any parameter of the model. It only refits on the entire dataset including the hold-out set.
deploy_model
This function deploys the entire ML pipeline on the cloud.
AWS
Before deploying a model to an AWS S3 (‘aws’), environment variables must be configured using the command-line interface. To configure AWS environment variables, type aws configure in your python command line. The following information is required which can be generated using the Identity and Access Management (IAM) portal of your amazon console account:
AWS Access Key ID
AWS Secret Key Access
Default Region Name (can be seen under Global settings on your AWS console)
Default output format (must be left blank)
GCP
To deploy a model on Google Cloud Platform ('gcp'), the project must be created using the command-line or GCP console. Once the project is created, you must create a service account and download the service account key as a JSON file to set environment variables in your local environment.
Learn more about it: https://cloud.google.com/docs/authentication/production
Azure
To deploy a model on Microsoft Azure ('azure'), environment variables for the connection string must be set in your local environment. Go to settings of storage account on Azure portal to access the connection string required.
AZURE_STORAGE_CONNECTION_STRING (required as environment variable)
Learn more about it: https://docs.microsoft.com/en-us/azure/storage/blobs/storage-quickstart-blobs-python?toc=%2Fpython%2Fazure%2FTOC.json
save_model
This function saves the transformation pipeline and a trained model object into the current working directory as a pickle file for later use.
load_model
This function loads a previously saved pipeline.
save_experiment
The save_experiment
function saves the experiment to a pickle file. The experiment is saved using cloudpickle to deal with lambda functions. The data or test data is NOT saved with the experiment and will need to be specified again when loading using load_experiment
.
load_experiment
The load_experiment
function loads an experiment from the path or a file. The data
(and test_data
) is not saved with the experiment and will need to be specified again at the time of loading.
check_drift
The check_drift
function generates a drift report file using the evidently library.
It will generate a HTML report locally.
convert_model
This function transpiles the trained machine learning model's decision function in different programming languages such as Python, C, Java, Go, C#, etc. It is very useful if you want to deploy models into environments where you can't install your normal Python stack to support model inference.
Video:
create_api
This function takes an input model and creates a POST API for inference. It only creates the API and doesn't run it automatically. To run the API, you must run the Python file using !python
.
Once you initialize API with the !python
command. You can see the server on localhost:8000/docs.
Video:
create_docker
This function creates a Dockerfile
and requirements.txt
for productionalizing API end-point.
You can see two files are created for you.
Video:
create_app
This function creates a basic gradio
app for inference. It will later be expanded for other app types such Streamlit
.
Video:
Last updated