Challenge: Steps in Parallel
Requirements
Continue to update the code to introduce the Random Forest model by performing the following updates.
[Import Random Forest]
from sklearn.ensemble import RandomForestClassifier
Add Random Forest Function
@step(name="random_forest")
def train_random_forest(x, x_test, y, n_estimators):
"""Train a Random Forest ensemble model."""
n_estimators = int(n_estimators)
model = RandomForestClassifier(n_estimators=n_estimators)
model.fit(x, y)
print(model.predict(x_test))
Add Random Forest Function to Pipeline
train_random_forest(x, x_test, y, n_estimators)
[Updated
ml_pipeline
Function Arguments
]{style=“font-family: ‘Open Sans’, Verdana, Arial, Helvetica, sans-serif; font-weight: 600;”}
[n_estimators=100]{face=“monospace, serif” style=“font-family: monospace, serif;”}
[Updated
ml_pipeline
Function Call
]{style=“font-family: ‘Open Sans’, Verdana, Arial, Helvetica, sans-serif; font-weight: 600;”}
[ml_pipeline(rs=42, iters=100, n_estimators=100)]{face=“monospace, serif” style=“font-family: monospace, serif;”}
[Run the Pipeline
]{style=“font-family: ‘Open Sans’, Verdana, Arial, Helvetica, sans-serif; font-weight: 600;”}
python3 -m kale kale_sdk_parallel_steps.py --kfp
SOLUTION
When you are finished, compare your notebook to the solution and make any necessary changes so that your notebook matches the solution in the next unit.