def save_model(self):
"""Save the model into a .joblib and upload it on Google Storage /models folder
HINTS : use sklearn.joblib (or jbolib) libraries and google-cloud-storage"""
joblib.dump(self.pipeline, 'model.joblib')
print(colored("model.joblib saved locally", "green"))
if self.upload:
storage_upload(model_version=MODEL_VERSION)
return self.mlflow_client.get_experiment_by_name(
self.experiment_name).experiment_id
@memoized_property
def mlflow_run(self):
return self.mlflow_client.create_run(self.mlflow_experiment_id)
def mlflow_log_param(self, key, value):
self.mlflow_client.log_param(self.mlflow_run.info.run_id, key, value)
def mlflow_log_metric(self, key, value):
self.mlflow_client.log_metric(self.mlflow_run.info.run_id, key, value)
if __name__ == "__main__":
# Get and clean data
N = 100
df = get_data_from_gcp(nrows=N)
df = clean_data(df)
y = df["fare_amount"]
X = df.drop("fare_amount", axis=1)
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3)
# Train and save model, locally and
trainer = Trainer(X=X_train, y=y_train)
trainer.set_experiment_name('xp2')
trainer.run()
rmse = trainer.evaluate(X_test, y_test)
print(f"rmse: {rmse}")
trainer.save_model_locally()
storage_upload()
