An example of how to create a features container and model prediction pipeline

features_container_model_prediction_pipeline.py

import numpy as np
from pydantic import ValidationError

from some.path.features import AnimalFeatures, FeatureIsNoneError
from some.other.path.models import ML_MODEL
from some.logger import log


def create_features() -> np.ndarray:
    # instantiate the features container
    features = AnimalFeatures()
    
    # set the categorical feature values
    # this sets cat_1 = 1 and cat_2 = 0
    features.set_categorical_features("cat", 1)
    
    # set the continuous feature values
    features.dog = 1.7
    features.bird = -0.2
    # or, alternatively
    # features.set_bulk_features({"dog": 1.7, "bird": -0.2})
    
    # return the features as a numpy array
    return features.numpy_array


def make_predictions() -> float:
    # try to run the feature pipeline and get a prediction
    try:
        data = create_features()
        prediction = ML_MODEL.predict(data)
    # if one of the features container errors occur, set a default value and log a warning
    except (ValidationError, FeatureIsNoneError) as e:
        prediction = 0.0
        log.warn("there was a problem creating the features", exception=e)
    return prediction