diff --git a/autopilot/sagemaker_autopilot_neo4j_portfolio_churn.ipynb b/autopilot/sagemaker_autopilot_neo4j_portfolio_churn.ipynb index 21c3b887ab..3f8774acfe 100644 --- a/autopilot/sagemaker_autopilot_neo4j_portfolio_churn.ipynb +++ b/autopilot/sagemaker_autopilot_neo4j_portfolio_churn.ipynb @@ -470,7 +470,7 @@ "\n", "Our data is, in some sense a time series. We're going to window over three quarters. Q4 of 2021 is used to generate labels, so it's not present in the data set. That leaves Q3 as our validation data set. Q2 becomes test and Q1 is for training.\n", "\n", - "We take this approach random than generating random folds or similar to avoid time based leakage." + "We take this approach rather than generating random folds or similar to avoid time based leakage." ] }, { @@ -702,8 +702,7 @@ "cell_type": "markdown", "metadata": {}, "source": [ - "We can use batch inference through Amazon SageMaker batch transform. The same model can also be deployed to perform online inference using Amazon SageMaker hosting.\n", - "\n" + "We can use batch inference through Amazon SageMaker batch transform. The same model can also be deployed to perform online inference using Amazon SageMaker hosting." ] }, {