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
# load dataset
from pycaret.datasets import get_data
diabetes = get_data('diabetes')
# init setup
from pycaret.classification import *
clf1 = setup(data = diabetes, target = 'Class variable')
# create a model
xgboost = create_model('xgboost')
# predict on hold-out
predict_model(xgboost)
Unseen data predictions
# load dataset
from pycaret.datasets import get_data
diabetes = get_data('diabetes')
# init setup
from pycaret.classification import *
clf1 = setup(data = diabetes, target = 'Class variable')
# create a model
xgboost = create_model('xgboost')
# predict on new data
new_data = diabetes.copy()
new_data.drop('Class variable', axis = 1, inplace = True)
predict_model(xgboost, data = new_data)
Probability by class
# load dataset
from pycaret.datasets import get_data
diabetes = get_data('diabetes')
# init setup
from pycaret.classification import *
clf1 = setup(data = diabetes, target = 'Class variable')
# create a model
xgboost = create_model('xgboost')
# predict on new data
new_data = diabetes.copy()
new_data.drop('Class variable', axis = 1, inplace = True)
predict_model(xgboost, raw_score = True, data = new_data)
Setting probability threshold
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.
# load dataset
from pycaret.datasets import get_data
diabetes = get_data('diabetes')
# init setup
from pycaret.classification import *
clf1 = setup(data = diabetes, target = 'Class variable')
# create a model
xgboost = create_model('xgboost')
# probability threshold 0.3
predict_model(xgboost, probability_threshold = 0.3)
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.
# load dataset
from pycaret.datasets import get_data
diabetes = get_data('diabetes')
# init setup
from pycaret.classification import *
clf1 = setup(data = diabetes, target = 'Class variable')
# create a model
rf = create_model('rf')
# finalize a model
finalize_model(rf)
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.
# load dataset
from pycaret.datasets import get_data
diabetes = get_data('diabetes')
# init setup
from pycaret.classification import *
clf1 = setup(data = diabetes, target = 'Class variable')
# create a model
lr = create_model('lr')
# finalize a model
final_lr = finalize_model(lr)
# deploy a model
deploy_model(final_lr, model_name = 'lr_aws', platform = 'aws', authentication = { 'bucket' : 'pycaret-test' })
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 dataset
from pycaret.datasets import get_data
diabetes = get_data('diabetes')
# init setup
from pycaret.classification import *
clf1 = setup(data = diabetes, target = 'Class variable')
# create a model
dt = create_model('dt')
# save pipeline
save_model(dt, 'dt_pipeline')
load_model
This function loads a previously saved pipeline.
# load dataset
from pycaret.datasets import get_data
diabetes = get_data('diabetes')
# init setup
from pycaret.classification import *
clf1 = setup(data = diabetes, target = 'Class variable')
# create a model
dt = create_model('dt')
# save pipeline
save_model(dt, 'dt_pipeline')
# load pipeline
load_model('dt_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 dataset
from pycaret.datasets import get_data
diabetes = get_data('diabetes')
# init setup
from pycaret.classification import *
clf1 = setup(data = diabetes, target = 'Class variable')
# save experiment
save_experiment('my_saved_experiment1')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.
# load data
data = get_data('diabetes')
# load experiment function
from pycaret.classification import load_experiment
clf2 = load_experiment('my_saved_experiment1', data = data)
check_drift
The check_drift function generates a drift report file using the evidently library.
# load dataset
from pycaret.datasets import get_data
data = get_data('insurance')
# generate drift report
check_drift(reference_data = data.head(500), current_data = data.tail(500), target = 'charges')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.
# load dataset
from pycaret.datasets import get_data
juice = get_data('juice')
# init setup
from pycaret.classification import *
exp_name = setup(data = juice, target = 'Purchase')
# train a model
lr = create_model('lr')
# convert a model
convert_model(lr, 'java')
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.
# load dataset
from pycaret.datasets import get_data
juice = get_data('juice')
# init setup
from pycaret.classification import *
exp_name = setup(data = juice, target = 'Purchase')
# train a model
lr = create_model('lr')
# create api
create_api(lr, 'lr_api')
# run api
!python lr_api.py
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.
# load dataset
from pycaret.datasets import get_data
juice = get_data('juice')
# init setup
from pycaret.classification import *
exp_name = setup(data = juice, target = 'Purchase')
# train a model
lr = create_model('lr')
# create api
create_api(lr, 'lr_api')
# create docker
create_docker('lr_api')
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.
# load dataset
from pycaret.datasets import get_data
juice = get_data('juice')
# init setup
from pycaret.classification import *
exp_name = setup(data = juice, target = 'Purchase')
# train a model
lr = create_model('lr')
# create app
create_app(lr)
Video:
Last updated
Was this helpful?