Creating reference and analysis set
After your data is split into train, test, and production sets, you can build and deploy your model. The testing and production data will later be used to create the reference and analysis set.
In this exercise, you will go through this process. You have all of your X_train/test/prod, and y_train/test/prod datasets created in the previous exercise already loaded here.
For this exercise, pandas has been imported as pd and is ready for use.
This exercise is part of the course
Monitoring Machine Learning in Python
Hands-on interactive exercise
Have a go at this exercise by completing this sample code.
from lightgbm import LGBMRegressor
# Fit the model
model = LGBMRegressor(random_state=111, n_estimators=50, n_jobs=1)
model.____(____, ____)
# Make predictions
y_pred_train = model.predict(____)
y_pred_test = model.predict(____)
# Deploy the model
y_pred_prod = model.predict(____)