Monthly Archives: June 2022

Organizations moving towards a data-driven culture embrace the use of data and machine learning (ML) in decision-making. To make ML-based decisions from data, you need your data available, accessible, clean, and in the right format to train ML models. Organizations with a multi-account architecture want to avoid situations where they must extract data from one account and load it into another for data preparation activities. Manually building and maintaining the different extract, transform, and load (ETL) jobs in different accounts adds complexity and cost, and makes it more difficult to maintain the governance, compliance, and security best practices to keep your data safe.

Amazon Redshift is a fast, fully managed cloud data warehouse. The Amazon Redshift cross-account data sharing feature provides a simple and secure way to share fresh, complete, and consistent data in your Amazon Redshift data warehouse with any number of stakeholders in different AWS accounts. Amazon SageMaker Data Wrangler is a capability of Amazon SageMaker that makes it faster for data scientists and engineers to prepare data for ML applications by using a visual interface. Data Wrangler allows you to explore and transform data for ML by connecting to Amazon Redshift datashares.

In this post, we walk through setting up a cross-account integration using an Amazon Redshift datashare and preparing data using Data Wrangler.

Solution overview

We start with two AWS accounts: a producer account with the Amazon Redshift data warehouse, and a consumer account for SageMaker ML use cases. For this post, we use the banking dataset. To follow along, download the dataset to your local machine. The following is a high-level overview of the workflow:

1. Instantiate an Amazon Redshift RA3 cluster in the producer account and load the dataset.
2. Create an Amazon Redshift datashare in the producer account and allow the consumer account to access the data.
3. Access the Amazon Redshift datashare in the consumer account.
4. Analyze and process data with Data Wrangler in the consumer account and build your data preparation workflows.
   

Be aware of the considerations for working with Amazon Redshift data sharing:

• Multiple AWS accounts – You need at least two AWS accounts: a producer account and a consumer account.
• Cluster type – Data sharing is supported in the RA3 cluster type. When instantiating an Amazon Redshift cluster, make sure to choose the RA3 cluster type.
• Encryption – For data sharing to work, both the producer and consumer clusters must be encrypted and should be in the same AWS Region.
• Regions – Cross-account data sharing is available for all Amazon Redshift RA3 node types in US East (N. Virginia), US East (Ohio), US West (N. California), US West (Oregon), Asia Pacific (Mumbai), Asia Pacific (Seoul), Asia Pacific (Singapore), Asia Pacific (Sydney), Asia Pacific (Tokyo), Canada (Central), Europe (Frankfurt), Europe (Ireland), Europe (London), Europe (Paris), Europe (Stockholm), and South America (São Paulo).
• Pricing – Cross-account data sharing is available across clusters that are in the same Region. There is no cost to share data. You just pay for the Amazon Redshift clusters that participate in sharing.

Cross-account data sharing is a two-step process. First, a producer cluster administrator creates a datashare, adds objects, and gives access to the consumer account. Then the producer account administrator authorizes sharing data for the specified consumer. You can do this from the Amazon Redshift console.

Create an Amazon Redshift datashare in the producer account

To create your datashare, complete the following steps:

1. On the Amazon Redshift console, create an Amazon Redshift cluster.
2. Specify Production and choose the RA3 node type.
3. Under Additional configurations, deselect Use defaults.
4. Under Database configurations, set up encryption for your cluster.
   
5. After you create the cluster, import the direct marketing bank dataset. You can download from the following URL: https://sagemaker-sample-data-us-west-2.s3-us-west-2.amazonaws.com/autopilot/direct_marketing/bank-additional.zip.
6. Upload bank-additional-full.csv to an Amazon Simple Storage Service (Amazon S3) bucket your cluster has access to.
7. Use the Amazon Redshift query editor and run the following SQL query to copy the data into Amazon Redshift:

   create table bank_additional_full (
     age char(40),
     job char(40),
     marital char(40),
     education char(40),
     default_history varchar(40),
     housing char(40),
     loan char(40),
     contact char(40),
     month char(40),
     day_of_week char(40),
     duration char(40),
     campaign char(40),
     pdays char(40),
     previous char(40),
     poutcome char(40),
     emp_var_rate char(40),
     cons_price_idx char(40),
     cons_conf_idx char(40),
     euribor3m char(40),
     nr_employed char(40),
     y char(40));
   copy bank_additional_full
   from <S3 LOCATION OF THE CSV FILE>
   credentials <CLUSTER ROLE ARN>
   region 'us-east-1'
   format csv
   IGNOREBLANKLINES
   IGNOREHEADER 1

8. Navigate to the cluster details page and on the Datashares tab, choose Create datashare.
   
9. For Datashare name, enter a name.
10. For Database name, choose a database.
    
11. In the Add datashare objects section, choose the objects from the database you want to include in the datashare.
    You have granular control of what you choose to share with others. For simplicity, we share all the tables. In practice, you might choose one or more tables, views, or user-defined functions.
12. Choose Add.
    
13. To add data consumers, select Add AWS accounts to the datashare and add your secondary AWS account ID.
14. Choose Create datashare.
    
15. To authorize the data consumer you just created, go to the Datashares page on the Amazon Redshift console and choose the new datashare.
    
16. Select the data consumer and choose Authorize.

The consumer status changes from Pending authorization to Authorized.

Access the Amazon Redshift cross-account datashare in the consumer AWS account

Now that the datashare is set up, switch to your consumer AWS account to consume the datashare. Make sure you have at least one Amazon Redshift cluster created in your consumer account. The cluster has to be encrypted and in the same Region as the source.

1. On the Amazon Redshift console, choose Datashares in the navigation pane.
2. On the From other accounts tab, select the datashare you created and choose Associate.
   
3. You can associate the datashare with one or more clusters in this account or associate the datashare to the entire account so that the current and future clusters in the consumer account get access to this share.
   
4. Specify your connection details and choose Connect.
   
5. Choose Create database from datashare and enter a name for your new database.
   
6. To test the datashare, go to query editor and run queries against the new database to make sure all the objects are available as part of the datashare.
   

Analyze and process data with Data Wrangler

You can now use Data Wrangler to access the cross-account data created as a datashare in Amazon Redshift.

1. Open Amazon SageMaker Studio.
2. On the File menu, choose New and Data Wrangler Flow.
   
3. On the Import tab, choose Add data source and Amazon Redshift.
   
4. Enter the connection details of the Amazon Redshift cluster you just created in the consumer account for the datashare.
5. Choose Connect.
6. Use the AWS Identity and Access Management (IAM) role you used for your Amazon Redshift cluster.

Note that even though the datashare is a new database in the Amazon Redshift cluster, you can’t connect to it directly from Data Wrangler.

The correct way is to connect to the default cluster database first, and then use SQL to query the datashare database. Provide the required information for connecting to the default cluster database. Note that an AWS Key Management Service (AWS KMS) key ID is not required in order to connect.

Data Wrangler is now connected to the Amazon Redshift instance.

7. Query the data in the Amazon Redshift datashare database using a SQL editor.
   
8. Choose Import to import the dataset to Data Wrangler.
9. Enter a name for the dataset and choose Add.
   

You can now see the flow on the Data Flow tab of Data Wrangler.

After you have loaded the data into Data Wrangler, you can do exploratory data analysis and prepare data for ML.

10. Choose the plus sign and choose Add analysis.

Data Wrangler provides built-in analyses. These include but aren’t limited to a data quality and insights report, data correlation, a pre-training bias report, a summary of your dataset, and visualizations (such as histograms and scatter plots). You can also create your own custom visualization.

You can use the Data Quality and Insights Report to automatically generate visualizations and analyses to identify data quality issues, and recommend the right transformation required for your dataset.

11. Choose Data Quality and Insights Report, and choose the Target column as y.
12. Because this is a classification problem statement, for Problem type, select Classification.
13. Choose Create.
    

Data Wrangler creates a detailed report on your dataset. You can also download the report to your local machine.

14. For data preparation, choose the plus sign and choose Add analysis.
15. Choose Add step to start building your transformations.
    

At the time of this writing, Data Wrangler provides over 300 built-in transformations. You can also write your own transformations using Pandas or PySpark.

You can now start building your transforms and analysis based on your business requirement.

Conclusion

In this post, we explored sharing data across accounts using Amazon Redshift datashares without having to manually download and upload data. We walked through how to access the shared data using Data Wrangler and prepare the data for your ML use cases. This no-code/low-code capability of Amazon Redshift datashares and Data Wrangler accelerates training data preparation and increases the agility of data engineers and data scientists with faster iterative data preparation.

To learn more about Amazon Redshift and SageMaker, refer to the Amazon Redshift Database Developer Guide and Amazon SageMaker Documentation.

About the Authors

 Meenakshisundaram Thandavarayan is a Senior AI/ML specialist with AWS. He helps hi-tech strategic accounts on their AI and ML journey. He is very passionate about data-driven AI.

James Wu is a Senior AI/ML Specialist Solution Architect at AWS. helping customers design and build AI/ML solutions. James’s work covers a wide range of ML use cases, with a primary interest in computer vision, deep learning, and scaling ML across the enterprise. Prior to joining AWS, James was an architect, developer, and technology leader for over 10 years, including 6 years in engineering and 4 years in marketing & advertising industries.

Read More

Predicting common machine failure types is critical in manufacturing industries. Given a set of characteristics of a product that is tied to a given type of failure, you can develop a model that can predict the failure type when you feed those attributes to a machine learning (ML) model. ML can help with insights, but up until now you needed ML experts to build models to predict machine failure types, the lack of which could delay any corrective actions that businesses need for efficiencies or improvement.

In this post, we show you how business analysts can build a machine failure type prediction ML model with Amazon SageMaker Canvas. Canvas provides you with a visual point-and-click interface that allows you to build models and generate accurate ML predictions on your own—without requiring any ML experience or having to write a single line of code.

Solution overview

Let’s assume you’re a business analyst assigned to a maintenance team of a large manufacturing organization. Your maintenance team has asked you to assist in predicting common failures. They have provided you with a historical dataset that contains characteristics tied to a given type of failure and would like you to predict which failure will occur in the future. The failure types include No Failure, Overstrain, and Power Failures. The data schema is listed in the following table.

After the failure type is identified, businesses can take any corrective actions. To do this, you use the data you have in a CSV file, which contains certain characteristics of a product as outlined in the table. You use Canvas to perform the following steps:

1. Import the maintenance dataset.
2. Train and build the predictive machine maintenance model.
3. Analyze the model results.
4. Test predictions against the model.

Prerequisites

A cloud admin with an AWS account with appropriate permissions is required to complete the following prerequisites:

1. Deploy an Amazon SageMaker domain For instructions, see Onboard to Amazon SageMaker Domain.
2. Launch Canvas. For instructions, see Setting up and managing Amazon SageMaker Canvas (for IT administrators).
3. Configure cross-origin resource sharing (CORS) policies for Canvas. For instructions, see Give your users the ability to upload local files.

Import the dataset

First, download the maintenance dataset and review the file to make sure all the data is there.

Canvas provides several sample datasets in your application to help you get started. To learn more about the SageMaker-provided sample datasets you can experiment with, see Use sample datasets. If you use the sample dataset (canvas-sample-maintenance.csv) available within Canvas, you don’t have to import the maintenance dataset.

You can import data from different data sources into Canvas. If you plan to use your own dataset, follow the steps in Importing data in Amazon SageMaker Canvas.

For this post, we use the full maintenance dataset that we downloaded.

1. Sign in to the AWS Management Console, using an account with the appropriate permissions to access Canvas.
2. Log in to the Canvas console.
3. Choose Import.
4. Choose Upload and select the maintenance_dataset.csv file.
5. Choose Import data to upload it to Canvas.

The import process takes approximately 10 seconds (this can vary depending on dataset size). When it’s complete, you can see the dataset is in Ready status.

After you confirm that the imported dataset is ready, you can create your model.

Build and train the model

To create and train your model, complete the following steps:

1. Choose New model, and provide a name for your model.
2. Choose Create.
3. Select the maintenance_dataset.csv dataset and choose Select dataset.
   In the model view, you can see four tabs, which correspond to the four steps to create a model and use it to generate predictions: Select, Build, Analyze, and Predict.
4. On the Select tab, select the maintenance_dataset.csv dataset you uploaded previously and choose Select dataset.
   This dataset includes 9 columns and 10,000 rows. Canvas automatically moves to the Build phase.
5. On this tab, choose the target column, in our case Failure Type.The maintenance team has informed you that this column indicates the type of failures typically seen based off of historical data from their existing machines. This is what you want to train your model to predict. Canvas automatically detects that this is a 3 Category problem (also known as multi-class classification). If the wrong model type is detected, you can change it manually with the Change type option.
   It should be noted that this dataset is highly unbalanced towards the No Failure class, which can be seen by viewing the column named Failure Type. Although Canvas and the underlying AutoML capabilities can partly handle dataset imbalance, this may result in some skewed performances. As an additional next step, refer to Balance your data for machine learning with Amazon SageMaker Data Wrangler. Following the steps in the shared link, you can launch an Amazon SageMaker Studio app from the SageMaker console and import this dataset within Amazon SageMaker Data Wrangler and use the Balance data transformation, then take the balanced dataset back to Canvas and continue the following steps. We are proceeding with the imbalanced dataset in this post to show that Canvas can handle imbalanced datasets as well.
   In the bottom half of the page, you can look at some of the statistics of the dataset, including missing and mismatched values, unique vales, and mean and median values. You can also drop some of the columns if you don’t want to use them for the prediction by simply deselecting them.
   After you’ve explored this section, it’s time to train the model! Before building a complete model, it’s a good practice to have a general idea about the model performance by training a Quick Model. A quick model trains fewer combinations of models and hyperparameters in order to prioritize speed over accuracy, especially in cases where you want to prove the value of training an ML model for your use case. Note that the quick build option isn’t available for models bigger than 50,000 rows.
6. Choose Quick build.

Now you wait anywhere from 2–15 minutes. Once done, Canvas automatically moves to the Analyze tab to show you the results of quick training. The analysis performed using quick build estimates that your model is able to predict the right failure type (outcome) 99.2% of the time. You may experience slightly different values. This is expected.

Let’s focus on the first tab, Overview. This is the tab that shows you the Column impact, or the estimated importance of each column in predicting the target column. In this example, the Torque [Nm] and Rotational speed [rpm] columns have the most significant impact in predicting what type of failure will occur.

Evaluate model performance

When you move to the Scoring portion of your analysis, you can see a plot representing the distribution of our predicted values with respect to the actual values. Notice that most failures will be within the No Failure category. To learn more about how Canvas uses SHAP baselines to bring explainability to ML, refer to Evaluating Your Model’s Performance in Amazon SageMaker Canvas, as well as SHAP Baselines for Explainability.

Canvas splits the original dataset into train and validation sets before the training. The scoring is a result of Canvas running the validation set against the model. This is an interactive interface where you can select the failure type. If you choose Overstrain Failure in the graphic, you can see that model identifies these 84% of time. This is good enough to take action on—perhaps have an operator or engineer check further. You can choose Power Failure in the graphic to see the respective scoring for further interpretation and actions.

You may be interested in failure types and how well the model predicts failure types based on a series of inputs. To take a closer look at the results, choose Advanced metrics. This displays a matrix that allows you to more closely examine the results. In ML, this is referred to as a confusion matrix.

This matrix defaults to the dominate class, No Failure. On the Class menu, you can choose to view advanced metrics of the other two failure types of Overstrain Failure and Power Failure.

In ML, the accuracy of the model is defined as the number of correct predictions divided over the total number of predictions. The blue boxes represent correct predictions that the model made against a subset of test data where there was a known outcome. Here we are interested in what percentage of the time the model predicted a particular machine failure type (lets say No Failure) when its actually that failure type (No Failure). In ML, a ratio used to measure this is TP / (TP + FN). This is referred to as recall. In the default case, No Failure, there were 1,923 correct predictions out of 1,926 overall records, which resulted in 99% recall. Alternatively, in the class of Overstrain Failure, there were 32 out of 38, which results in 84% recall. Lastly, in the class of Power Failure, there were 16 out of 19, which results in 84% recall.

Now, you have two options:

1. You can use this model to run some predictions by choosing Predict.
2. You can create a new version of this model to train with the Standard build option. This will take much longer—about 1–2 hours—but provides a more robust model because it goes through a full AutoML review of data, algorithms, and tuning iterations.

Because you’re trying to predict failures, and the model predicts failures correctly 84% of time, you can confidently use the model to identify possible failures. So, you can proceed to option 1. If you weren’t confident, then you could have a data scientist review the modeling Canvas did and offer potential improvements via option 2.

Generate predictions

Now that the model is trained, you can start generating predictions.

1. Choose Predict at the bottom of the Analyze page, or choose the Predict tab.
2. Choose Select dataset, and choose the maintenance_dataset.csv file.
3. Choose Generate predictions.

Canvas uses this dataset to generate our predictions. Although it’s generally a good idea to not use the same dataset for both training and testing, you can use the same dataset for the sake of simplicity in this case. Alternatively, you can remove some records from your original dataset that you use for training and use those records in a CSV file and feed it to the batch prediction here so you don’t use the same dataset for testing post-training.

After a few seconds, the prediction is complete. Canvas returns a prediction for each row of data and the probability of the prediction being correct. You can choose Preview to view the predictions, or choose Download to download a CSV file containing the full output.

You can also choose to predict one by one values by choosing Single prediction instead of Batch prediction. Canvas shows you a view where you can provide the values for each feature manually and generate a prediction. This is ideal for situations like what-if scenarios, for example: How does the tool wear impact the failure type? What if process temperature increases or decreases? What if rotational speed changes?

Standard build

The Standard build option chooses accuracy over speed. If you want to share the artifacts of the model with your data scientist and ML engineers, you can create a standard build next.

1. Choose Add version
   
   
2. Choose a new version and choose Standard build.
3. After you create a standard build, you can share the model with data scientists and ML engineers for further evaluation and iteration.

Clean up

To avoid incurring future session charges, log out of Canvas.

Conclusion

In this post, we showed how a business analyst can create a machine failure type prediction model with Canvas using maintenance data. Canvas allows business analysts such as reliability engineers to create accurate ML models and generate predictions using a no-code, visual, point-and-click interface. Analysts can take this to the next level by sharing their models with data scientist colleagues. Data scientists can view the Canvas model in Studio, where they can explore the choices Canvas made, validate model results, and even take the model to production with a few clicks. This can accelerate ML-based value creation and help scale improved outcomes faster.

To learn more about using Canvas, see Build, Share, Deploy: how business analysts and data scientists achieve faster time-to-market using no-code ML and Amazon SageMaker Canvas. For more information about creating ML models with a no-code solution, see Announcing Amazon SageMaker Canvas – a Visual, No Code Machine Learning Capability for Business Analysts.

About the Authors

Rajakumar Sampathkumar is a Principal Technical Account Manager at AWS, providing customers guidance on business-technology alignment and supporting the reinvention of their cloud operation models and processes. He is passionate about cloud and machine learning. Raj is also a machine learning specialist and works with AWS customers to design, deploy, and manage their AWS workloads and architectures.

Twann Atkins is a Senior Solutions Architect for Amazon Web Services. He is responsible for working with Agriculture, Retail, and Manufacturing customers to identify business problems and working backwards to identify viable and scalable technical solutions. Twann has been helping customers plan and migrate critical workloads for more than 10 years with a recent focus on democratizing analytics, artificial intelligence and machine learning for customers and builders of tomorrow.

Omkar Mukadam is a Edge Specialist Solution Architecture at Amazon Web Services. He currently focuses on solutions which enables commercial customers to effectively design, build and scale with AWS Edge service offerings which includes but not limited to AWS Snow Family.

Read More