Connect with us


Prepare data from Snowflake for machine learning with Amazon SageMaker Data Wrangler

Data preparation remains a major challenge in the machine learning (ML) space. Data scientists and engineers need to write queries and code to get data from source data stores, and then write the queries to transform this data, to create features to be used in model development and training. All of this data pipeline development…



Data preparation remains a major challenge in the machine learning (ML) space. Data scientists and engineers need to write queries and code to get data from source data stores, and then write the queries to transform this data, to create features to be used in model development and training. All of this data pipeline development work doesn’t really focus on the building of ML models, but focuses on the building of data pipelines necessary to make the data available to the models. Amazon SageMaker Data Wrangler makes it easier for data scientists and engineers to prepare data in the early phase of developing ML applications by using a visual interface.

Data Wrangler simplifies the process of data preparation and feature engineering using a single visual interface. Data Wrangler comes with over 300 built-in data transformations to help normalize, transform, and combine features without writing any code. You can now use Snowflake as a data source in Data Wrangler to easily prepare data in Snowflake for ML.

In this post, we use a simulated dataset that represents loans from a financial services provider, which has been provided by Snowflake. This dataset contains lender data about loans granted to individuals. We use Data Wrangler to transform and prepare the data for later use in ML models, first building a data flow in Data Wrangler, then exporting it to Amazon SageMaker Pipelines. First, we walk through setting up Snowflake as the data source, then explore and transform the data using Data Wrangler.


This post assumes you have the following:

Set up permissions for Data Wrangler

In this section, we cover the permissions required to set up Snowflake as a data source for Data Wrangler. This section requires you to perform steps in both the AWS Management Console and Snowflake. The user in each environment should have permission to create policies, roles, and secrets in AWS, and the ability to create storage integrations in Snowflake.

All permissions for AWS resources are managed via your IAM role attached to your Amazon SageMaker Studio instance. Snowflake-specific permissions are managed by the Snowflake admin; they can grant granular permissions and privileges to each Snowflake user. This includes databases, schemas, tables, warehouses, and storage integration objects. Make sure that the correct permissions are set up outside of Data Wrangler.

AWS access requirements

Snowflake requires the following permissions on your output S3 bucket and prefix to be able to access objects in the prefix:

  • s3:GetObject
  • s3:GetObjectVersion
  • s3:ListBucket

You can add a bucket policy to ensure that Snowflake only communicates with your bucket over HTTPS. For instructions, see What S3 bucket policy should I use to comply with the AWS Config rule s3-bucket-ssl-requests-only?

Create an IAM policy allowing Amazon S3 access

In this section, we cover creating the policy required for Snowflake to access data in an S3 bucket of your choosing. If you already have a policy and role that allows access to the S3 bucket you plan to use for the Data Wrangler output, you can skip this section and the next section, and start creating your storage integration in Snowflake.

  1. On the IAM console, choose Policies in the navigation pane.
  2. Choose Create policy.
  3. On the JSON tab, enter the following JSON snippet, substituting your bucket and prefix name for the placeholders:

# Example policy for S3 write access # This needs to be updated # Be sure to remove the angle brackets around and # Then replace with your own bucket and prefix names (eg: MY-SAGEMAKER-BUCKET/MY-PREFIX) { “Version”:”2012-10-17″, “Statement”:[ { “Effect”:”Allow”, “Action”: [ “s3:PutObject”, “s3:GetObject”, “s3:GetObjectVersion”, “s3:DeleteObject”, “s3:DeleteObjectVersion” ], “Resource”:[“arn:aws:s3::://*”] }, { “Effect”:”Allow”, “Action”: [ “s3:ListBucket” ], “Resource”:[“arn:aws:s3:::“], “Condition”: { “StringLike”: { “s3:prefix”: [“/*”] } } } ] }

  1. Choose Next: Tags.
  2. Choose Next: Review.
  3. For Name, enter a name for your policy (for example, snowflake_datawrangler_s3_access).
  4. Choose Create policy.

Create an IAM role

In this section, we create an IAM role and attach it to the policy we created.

  1. On the IAM console, choose Roles in the navigation pane.
  2. Choose Create role.
  3. Select Another AWS account as the trusted entity type
  4. For Account ID field, enter your own AWS account ID.

You modify the trusted relationship and grant access to Snowflake later.

  1. Select the Require External ID
  2. Enter a dummy ID such as your own account ID.

Later, we modify the trust relationship and specify the external ID for your Snowflake stage. An external ID is required to grant access to your AWS resources (such as Amazon  S3) to a third party (Snowflake).

  1. Choose Next.
  2. Locate the policy you created previously for the S3 bucket and choose this policy.
  3. Choose Next.
  4. Enter a name and description for the role, then choose Create role.

You now have an IAM policy created for an IAM role, and the policy is attached to the role.

  1. Record the role ARN value located on the role summary page.

In the next step, you create a Snowflake integration that references this role.

Create a storage integration in Snowflake

A storage integration in Snowflake stores a generated IAM entity for external cloud storage, with an optional set of allowed or blocked locations, in Amazon S3. An AWS administrator in your organization grants permissions on the storage location to the generated IAM entity. With this feature, users don’t need to supply credentials when creating stages or when loading or unloading data.

Create the storage integration with the following code:


Retrieve the IAM user for your Snowflake account

Run the following DESCRIBE INTEGRATION command to retrieve the ARN for the IAM user that was created automatically for your Snowflake account:


Record the following values from the output:

  • STORAGE_AWS_IAM_USER_ARN – The IAM user created for your Snowflake account
  • STORAGE_AWS_EXTERNAL_ID– The external ID needed to establish a trust relationship

Update the IAM role trust policy

Now we update the trust policy.

  1. On the IAM console, choose Roles in the navigation pane.
  2. Choose the role you created.
  3. On the Trust relationship tab, choose Edit trust relationship.
  4. Modify the policy document as shown in the following code with the DESC STORAGE INTEGRATION output values you recorded in the previous step:

{ “Version”: “2012-10-17”, “Statement”: [ { “Sid”: “”, “Effect”: “Allow”, “Principal”: { “AWS”: “” }, “Action”: “sts:AssumeRole”, “Condition”: { “StringEquals”: { “sts:ExternalId”: “” } } } ] }

  1. Choose Update trust policy.

Create an external stage in Snowflake

We use an external stage within Snowflake for loading data from an S3 bucket in your own account into Snowflake. In this step, we create an external (Amazon S3) stage that references the storage integration you created. For more information, see Creating an S3 Stage.

This requires a role that has the CREATE_STAGE privilege for the schema as well as the USAGE privilege on the storage integration. You can grant these privileges to the role as shown in the code in the next step.

Create the stage using the CREATE_STAGE command with placeholders for the external stage and S3 bucket and prefix. The stage also references a named file format object called my_csv_format:

grant create stage on schema public to role ; grant usage on integration SAGEMAKE_DATAWRANGLER_INTEGRATION to role ; create stage storage_integration = SAGEMAKE_DATAWRANGLER_INTEGRATION url = ‘/‘ file_format = my_csv_format;

Create a secret for Snowflake credentials (Optional)

Data Wrangler allows users to use the ARN of an AWS Secrets Manager secret or a Snowflake account name, user name, and password to access Snowflake. If you intend to use the Snowflake account name, user name, and password option, skip to the next section, which covers adding the data source. By default, Data Wrangler creates a Secrets Manager secret on your behalf, when using the second option.

To create a Secrets Manager secret manually, complete the following steps:

  1. On the Secrets Manager console, choose Store a new secret.
  2. For Select secret type¸ select Other types of secrets.
  3. Specify the details of your secret as key-value pairs.

The names of the key are case-sensitive and must be lowercase. If you enter any of these incorrectly, Data Wrangler raises an error.

If you prefer, you can use the plaintext option and enter the secret values as JSON:

{ “username”: ““, “password”: ““, “accountid”: “” }

  1. Choose Next.
  2. For Secret name, add the prefix AmazonSageMaker (for example, our secret is AmazonSageMaker-DataWranglerSnowflakeCreds).
  3. In the Tags section, add a tag with the key SageMaker and value true.

  1. Choose Next.
  2. The rest of the fields are optional; choose Next until you have the option to choose Store to store the secret.

After you store the secret, you’re returned to the Secrets Manager console.

  1. Choose the secret you just created, then retrieve the secret ARN.
  2. Store this in the text editor of your choice for use later when you create the Data Wrangler data source.

Set up the data source in Data Wrangler

In this section, we cover setting up Snowflake as a data source in Data Wrangler. This post assumes that you have access to SageMaker, an instance of Studio, and a user for Studio. For more information about prerequisites, see Get Started with Data Wrangler.

Create a new data flow

To create your data flow, complete the following steps:

  1. On the SageMaker console, choose Amazon SageMaker Studio in the navigation pane.
  2. Choose Open Studio.
  3. In the Launcher, choose New data flow.

Alternatively, on the File drop-down, choose New, then choose Data Wrangler Flow.

Creating a new flow can take a few minutes. After the flow has created, you see the Import data page.

Add Snowflake as a data source in Data Wrangler

Next, we add Snowflake as a data source.

  1. On the Add data source menu, choose Snowflake.

  1. Add your Snowflake connection details.

Data Wrangler uses HTTPS to connect to Snowflake.

  1. If you created a Secrets Manager secret manually, choose the Authentication method drop-down menu and choose ARN.

  1. Choose Connect.

You’re redirected to the import menu.

Run a query

Now that Snowflake is set up as a data source, you can access your data in Snowflake directly from the Data Wrangler query editor. The query we write in the editor is what Data Wrangler uses to import data from Snowflake to start our data flow.

  1. On the drop-down menus, choose the data warehouse, database, and schema you want to use for your query.

For this post, our dataset is in the database FIN_LOANS, the schema is DEV, and the table is LOAN_INT_HV. My data warehouse is called MOONMAXW_DEV_WH; depending on your setup, these will likely differ.

Alternatively, you can specify the full path to the dataset in the query editor. Make sure you still choose the database and schema on the drop-down menus.

  1. In the query editor, enter a query and preview the results.

For this post, we retrieve all columns from 1,000 rows.

  1. Choose Import.

  1. Enter a dataset name when prompted (for this post, we use snowflake_loan_int_hv).
  2. Choose Add.

You’re taken to the Prepare page, where you can add transformations and analyses to the data.

Add transformations to the data

Data Wrangler has over 300 built-in transformations. In this section, we use some of these transformations to prepare the dataset for an ML model.

On the Data Wrangler flow page, make sure you have chosen the Prepare tab. If you’re following the steps in the post, you’re directed here automatically after adding your dataset.

Convert data types

The first step we want to perform is to check that the correct data type was inferred on ingest for each column.

  1. Next to Data types, choose the plus sign.
  2. Choose Edit data types.

Looking through the columns, we identify that MNTHS_SINCE_LAST_DELINQ and MNTHS_SINCE_LAST_RECORD should most likely be represented as a number type, rather than string.

  1. On the right-hand menu, scroll down until you find MNTHS_SINCE_LAST_DELINQ and MNTHS_SINCE_LAST_RECORD.
  2. On the drop-down menu, choose Float.

Looking through the dataset, we can confirm that the rest of the columns appear to have been correctly inferred.

  1. Choose Preview to preview the changes.
  2. Choose Apply to apply the changes.
  3. Choose Back to data flow to see the current state of the flow.

Manage columns

The dataset we’re using has several columns that likely aren’t beneficial to future models, so we start our transformation process by dropping the columns that aren’t useful.

  1. Next to Data types, choose the plus sign.
  2. Choose Add transformation.

The transformation console opens. Here you can preview your dataset, select from the available transformations, and preview the transformations.

Looking through the data, we can see that the fields EMP_TITLE, URL, DESCRIPTION, and TITLE will likely not provide value to our model in our use case, so we drop them.

  1. On the Transform menu, choose Manage columns.
  2. On the Transform drop-down menu, leave Drop column
  3. Enter EMP_TITLE for Column to drop.
  4. Choose Preview to review the changes.
  5. Choose Add to add the step.
  6. If you want to see the step you added and previous steps, choose Previous steps on the Transform

  1. Repeat these steps for the remaining columns (URL, DESCRIPTION, and TITLE).
  2. Choose Back to data flow to see the current state of the flow.

In the data flow view, we can see that this node in the flow has four steps, which represent the four columns we’re dropping for this part of the flow.

Format string

Next, we look for columns that are string data that can be formatted to be more beneficial to use later. Looking through our dataset, we can see that INT_RATE might be useful in a future model as float, but has a trailing character of %. Before we can use another built-in transformation (parse as type) to convert this to a float, we must strip the trailing character.

  1. Next to Steps, choose the plus sign.
  2. Choose Add transform.
  3. Choose Format string.
  4. On the Transform drop-down, choose Remove Symbols.
  5. On the Input column drop-down, choose the INT_RATE column.
  6. For Symbols, enter %.
  7. Optionally, in the Output field, enter the name of a column that this data is written to.

For this post, we keep the original column and set the output column to INT_RATE_PERCENTAGE to denote to future users of this data that this column is the interest rate as a percentage. Later, we convert this to a float.

  1. Choose Preview.

When Data Wrangler adds a new column, it’s automatically added as the rightmost column.

  1. Review the change to ensure accuracy.
  2. Choose Add.

Parse column as type

Continuing with the preceding example, we’ve identified that INT_RATE_PERCENTAGE should be converted to a float type.

  1. Next to Steps, choose the plus sign.
  2. Choose Add transform.
  3. Choose Parse Column as Type.
  4. On the Column drop-down, choose INT_RATE_PERCENTAGE.

The From field is automatically populated.

  1. On the to drop-down, choose Float.
  2. Choose Preview.
  3. Choose Add.
  4. Choose Back to data flow.

As you can see, we now have six steps in this portion of the flow, four that represent columns being dropped, one that represents string formatting, and one that represents parse column as type.

Encode categorical data

Next, we want to look for categorical data in our dataset. Data Wrangler has a built-in functionality to encode categorical data using both ordinal and one-hot encodings. Looking at our dataset, we can see that the TERM, HOME_OWNERSHIP, and PURPOSE columns all appear to be categorical in nature.

  1. Next to Steps, choose the plus sign.
  2. Choose Add transform.

The first column in our list TERM has two possible values: 60 months and 36 months. Perhaps our future model would benefit from having these values one-hot encoded and placed into new columns.

  1. Choose Encode Categorical.
  2. On the Transform drop-down, choose One-hot encode.
  3. For Input column, choose TERM.
  4. On the Output style drop-down, choose Columns.
  5. Leave all other fields and check boxes as is.
  6. Choose Preview.

We can now see two columns, TERM_36 months and TERM_60 months, are one-hot encoded to represent the corresponding value in the TERM column.

  1. Choose Add.

The HOME_OWNERSHIP column has  four possible values: RENT, MORTGAGE, OWN, and other.

  1. Repeat the preceding steps to apply a one-hot encoding approach on these values.

Lastly, the PURPOSE column has several possible values. For this data, we use a one-hot encoding approach as well, but we set the output to a vector, rather than columns.

  1. On the Transform drop-down, choose One-hot encode.
  2. For Input column, choose PURPOSE.
  3. On the Output style drop-down, choose Vector.
  4. For Output Column, we call this column PURPOSE_VCTR.

This keeps the original PURPOSE column, if we decide to use it later.

  1. Leave all other fields and check boxes as is.
  2. Choose Preview.

  1. Choose Add.
  2. Choose Back to data flow.

We can now see nine different transformations in this flow, and we still haven’t written a single line of code.

Handle outliers

As our last step in this flow, we want to handle outliers in our dataset. As part of the data exploration process, we can create an analysis (which we cover in the next section). In the following example scatter plot, I explored if I could gain insights from looking at the relationship between annual income, interest rate, and employment length by observing the dataset on a scatter plot. On the graph, we have the loan receivers INT_RATE_PERCENTAGE on the X axis, ANNUAL_INC on the Y axis, and the data is color-coded by EMP_LENGTH. The dataset has some outliers that might skew the result of our model later. To address this, we use Data Wrangler’s built-in transformation for handling outliers.

  1. Next to Steps, choose the plus sign.
  2. Choose Add transform.
  3. Choose Handle outliers.
  4. On the Transform drop-down, choose Standard deviation numeric outliers.
  5. For Input column, enter ANNUAL_INC.
  6. For Output column, enter ANNUAL_INC_NO_OUTLIERS.

This is optional, but it’s good practice to notate that a column has been transformed for later consumers.

  1. On the Fix method drop-down, leave Clip

This option automatically clips values to the corresponding outlier detection bound, which we set next.

  1. For Standard deviations, leave the default of 4 to start.

This allows values within four standard deviations of the mean to be considered valid (and therefore not clipped). Values outside of this bound are clipped.

  1. Choose Preview.
  2. Choose Add.

The output includes an object type. We need to convert this to a float for it to be valid within our dataset and visualization.

  1. Follow the steps as when parsing a column as type, this time using the ANNUAL_INC_NO_OUTLIERS columns.
  2. Choose Back to data flow to see the current state of the flow.

Add analyses to the data

In this section, we walk through adding analyses to dataset. We focus on visualizations, but there are several other options, including detecting target leakage, generating a bias report, or adding your own custom visualizations using the Altair library.

Scatter plot

To create a scatter plot, complete the following steps:

  1. On the data flow page, next to Steps, choose the plus sign.
  2. Choose Add analysis.
  3. For Analysis type¸ choose Scatter plot.
  4. Using the preceding example, we name this analysis EmpLengthAnnualIncIntRate.
  5. For X Axis, enter INT_RATE_PERCENTAGE.
  6. For Y Axis, enter ANNUAL_INC_NO_OUTLIERS.
  7. For Color by, enter EMP_LENGTH.
  8. Choose Preview.

The following screenshot shows our scatter plot.

We can compare this to the old version, before the anomalies were removed.

So far this is looking good, but let’s add a facet to break out each category in the Grade column into its own graph.

  1. For Facet by, choose GRADE.
  2. Choose Preview.

The following screenshot has been trimmed down for display purposes. The Y axis still represents ANNUAL_INC. For faceted plots, this is displayed on the bottommost plot.

  1. Choose Save to save the analysis.

Export the data flow

Finally, we export this whole data flow as a pipeline, which creates a Jupyter notebook with the code pre-populated. With Data Wrangler, you can also export your data to a Jupyter notebook as a SageMaker processing job, SageMaker feature store, or export directly to Python code.

  1. On the Data Flow console, choose the Export
  2. Choose the steps to export. For our use case, we choose each box that represents a step.

  1. Choose Export step, then choose Pipeline.

The pre-populated Jupyter notebook loads and opens automatically, displaying all the generated steps and code for your data flow. The following screenshot shows the input section that defines the data source.

Clean up

If your work with Data Wrangler is complete, shut down your Data Wrangler instance to avoid incurring additional fees.


In this post, we covered setting up Snowflake as a data source for Data Wrangler, adding transformations and analyses to a dataset, then exporting to the data flow for further use in a Jupyter notebook. We further improved our data flow after visualizing our dataset using the Data Wrangler built-in analysis functionality. Most notably, we built a data preparation pipeline without having to write a single line of code.

To get started with Data Wrangler, see Prepare ML Data with Amazon SageMaker Data Wrangler, and see the latest information on the Data Wrangler product page.

Data Wrangler makes it easy to ingest data and perform data preparation tasks such as exploratory data analysis, feature selection, feature engineering. We’ve only covered a few of the capabilities of Data Wrangler in this post on data preparation; you can use Data Wrangler for more advanced data analysis such as feature importance, target leakage, and model explainability using an easy and intuitive user interface.

About the Authors

Maxwell Moon is a Senior Solutions Architect at AWS working with Independent Software Vendors (ISVs) to design and scale their applications on AWS. Outside of work, Maxwell is a dad to two cats, is an avid supporter of the Wolverhampton Wanderers Football Club, and tries to spend as much time playing music as possible.



Bosco Albuquerque is a Sr Partner Solutions Architect at AWS and has over 20 years of experience in working with database and analytics products from enterprise database vendors, and cloud providers and has helped large technology companies in designing data analytics solutions as well as led engineering teams is designing and implementing data analytics platforms and data products.


Continue Reading
Click to comment

Leave a Reply

Your email address will not be published.


Build a risk management machine learning workflow on Amazon SageMaker with no code

Since the global financial crisis, risk management has taken a major role in shaping decision-making for banks, including predicting loan status for potential customers. This is often a data-intensive exercise that requires machine learning (ML). However, not all organizations have the data science resources and expertise to build a risk management ML workflow. Amazon SageMaker…




Since the global financial crisis, risk management has taken a major role in shaping decision-making for banks, including predicting loan status for potential customers. This is often a data-intensive exercise that requires machine learning (ML). However, not all organizations have the data science resources and expertise to build a risk management ML workflow.

Amazon SageMaker is a fully managed ML platform that allows data engineers and business analysts to quickly and easily build, train, and deploy ML models. Data engineers and business analysts can collaborate using the no-code/low-code capabilities of SageMaker. Data engineers can use Amazon SageMaker Data Wrangler to quickly aggregate and prepare data for model building without writing code. Then business analysts can use the visual point-and-click interface of Amazon SageMaker Canvas to generate accurate ML predictions on their own.

In this post, we show how simple it is for data engineers and business analysts to collaborate to build an ML workflow involving data preparation, model building, and inference without writing code.

Solution overview

Although ML development is a complex and iterative process, you can generalize an ML workflow into the data preparation, model development, and model deployment stages.

Data Wrangler and Canvas abstract the complexities of data preparation and model development, so you can focus on delivering value to your business by drawing insights from your data without being an expert in code development. The following architecture diagram highlights the components in a no-code/low-code solution.

Amazon Simple Storage Service (Amazon S3) acts as our data repository for raw data, engineered data, and model artifacts. You can also choose to import data from Amazon Redshift, Amazon Athena, Databricks, and Snowflake.

As data scientists, we then use Data Wrangler for exploratory data analysis and feature engineering. Although Canvas can run feature engineering tasks, feature engineering usually requires some statistical and domain knowledge to enrich a dataset into the right form for model development. Therefore, we give this responsibility to data engineers so they can transform data without writing code with Data Wrangler.

After data preparation, we pass model building responsibilities to data analysts, who can use Canvas to train a model without having to write any code.

Finally, we make single and batch predictions directly within Canvas from the resulting model without having to deploy model endpoints ourselves.

Dataset overview

We use SageMaker features to predict the status of a loan using a modified version of Lending Club’s publicly available loan analysis dataset. The dataset contains loan data for loans issued through 2007–2011. The columns describing the loan and the borrower are our features. The column loan_status is the target variable, which is what we’re trying to predict.

To demonstrate in Data Wrangler, we split the dataset in two CSV files: part one and part two. We’ve removed some columns from Lending Club’s original dataset to simplify the demo. Our dataset contains over 37,000 rows and 21 feature columns, as described in the following table.

Column name Description
loan_status Current status of the loan (target variable).
loan_amount The listed amount of the loan applied for by the borrower. If the credit department reduces the loan amount, it’s reflected in this value.
funded_amount_by_investors The total amount committed by investors for that loan at that time.
term The number of payments on the loan. Values are in months and can be either 36 or 60.
interest_rate Interest rate on the loan.
installment The monthly payment owed by the borrower if the loan originates.
grade LC assigned loan grade.
sub_grade LC assigned loan subgrade.
employment_length Employment length in years. Possible values are between 0–10, where 0 means less than one year and 10 means ten or more years.
home_ownership The home ownership status provided by the borrower during registration. Our values are RENT, OWN, MORTGAGE, and OTHER.
annual_income The self-reported annual income provided by the borrower during registration.
verification_status Indicates if income was verified or not by the LC.
issued_amount The month at which the loan was funded.
purpose A category provided by the borrower for the loan request.
dti A ratio calculated using the borrower’s total monthly debt payments on the total debt obligations, excluding mortgage and the requested LC loan, divided by the borrower’s self-reported monthly income.
earliest_credit_line The month the borrower’s earliest reported credit line was opened.
inquiries_last_6_months The number of inquiries in the past 6 months (excluding auto and mortgage inquiries).
open_credit_lines The number of open credit lines in the borrower’s credit file.
derogatory_public_records The number of derogatory public records.
revolving_line_utilization_rate Revolving line utilization rate, or the amount of credit the borrower is using relative to all available revolving credit.
total_credit_lines The total number of credit lines currently in the borrower’s credit file.

We use this dataset for our data preparation and model training.


Complete the following prerequisite steps:

  1. Upload both loan files to an S3 bucket of your choice.
  2. Make sure you have the necessary permissions. For more information, refer to Get Started with Data Wrangler.
  3. Set up a SageMaker domain configured to use Data Wrangler. For instructions, refer to Onboard to Amazon SageMaker Domain.

Import the data

Create a new Data Wrangler data flow from the Amazon SageMaker Studio UI.

Import data from Amazon S3 by selecting the CSV files from the S3 bucket where you placed your dataset. After you import both files, you can see two separate workflows in the Data flow view.

You can choose several sampling options when importing your data in a Data Wrangler flow. Sampling can help when you have a dataset that is too large to prepare interactively, or when you want to preserve the proportion of rare events in your sampled dataset. Because our dataset is small, we don’t use sampling.

Prepare the data

For our use case, we have two datasets with a common column: id. As a first step in data preparation, we want to combine these files by joining them. For instructions, refer to Transform Data.

We use the Join data transformation step and use the Inner join type on the id column.

As a result of our join transformation, Data Wrangler creates two additional columns: id_0 and id_1. However, these columns are unnecessary for our model building purposes. We drop these redundant columns using the Manage columns transform step.

We’ve imported our datasets, joined them, and removed unnecessary columns. We’re now ready to enrich our data through feature engineering and prepare for model building.

Perform feature engineering

We used Data Wrangler for preparing data. You can also use the Data Quality and Insights Report feature within Data Wrangler to verify your data quality and detect abnormalities in your data. Data scientists often need to use these data insights to efficiently apply the right domain knowledge to engineering features. For this post, we assume we’ve completed these quality assessments and can move on to feature engineering.

In this step, we apply a few transformations to numeric, categorical, and text columns.

We first normalize the interest rate to scale the values between 0–1. We do this using the Process numeric transform to scale the interest_rate column using a min-max scaler. The purpose for normalization (or standardization) is to eliminate bias from our model. Variables that are measured at different scales won’t contribute equally to the model learning process. Therefore, a transformation function like a min-max scaler transform helps normalize features.

To convert a categorial variable into a numeric value, we use one-hot encoding. We choose the Encode categorical transform, then choose One-hot encode. One-hot encoding improves an ML model’s predictive ability. This process converts a categorical value into a new feature by assigning a binary value of 1 or 0 to the feature. As a simple example, if you had one column that held either a value of yes or no, one-hot encoding would convert that column to two columns: a Yes column and a No column. A yes value would have 1 in the Yes column and a 0 in the No column. One-hot encoding makes our data more useful because numeric values can more easily determine a probability for our predictions.

Finally, we featurize the employer_title column to transform its string values into a numerical vector. We apply the Count Vectorizer and a standard tokenizer within the Vectorize transform. Tokenization breaks down a sentence or series of text into words, whereas a vectorizer converts text data into a machine-readable form. These words are represented as vectors.

With all feature engineering steps complete, we can export the data and output the results into our S3 bucket. Alternatively, you can export your flow as Python code, or a Jupyter notebook to create a pipeline with your view using Amazon SageMaker Pipelines. Consider this when you want to run your feature engineering steps at scale or as part of an ML pipeline.

We can now use the Data Wrangler output file as our input for Canvas. We reference this as a dataset in Canvas to build our ML model.

In our case, we exported our prepared dataset to the default Studio bucket with an output prefix. We reference this dataset location when loading the data into Canvas for model building next.

Build and train your ML model with Canvas

On the SageMaker console, launch the Canvas application. To build an ML model from the prepared data in the previous section, we perform the following steps:

  1. Import the prepared dataset to Canvas from the S3 bucket.

We reference the same S3 path where we exported the Data Wrangler results from the previous section.

  1. Create new model in Canvas and name it loan_prediction_model.
  2. Select the imported dataset and add it to the model object.

To have Canvas build a model, we must select the target column.

  1. Because our goal is to predict the probability of a lender’s ability to repay a loan, we choose the loan_status column.

Canvas automatically identifies the type of ML problem statement. At the time of writing, Canvas supports regression, classification, and time series forecasting problems. You can specify the type of problem or have Canvas automatically infer the problem from your data.

  1. Choose your option to start the model building process: Quick build or Standard build.

The Quick build option uses your dataset to train a model within 2–15 minutes. This is useful when you’re experimenting with a new dataset to determine if the dataset you have will be sufficient to make predictions. We use this option for this post.

The Standard build option choses accuracy over speed and uses approximately 250 model candidates to train the model. The process usually takes 1–2 hours.

After the model is built, you can review the results of the model. Canvas estimates that your model is able to predict the right outcome 82.9% of the time. Your own results may vary due to the variability in training models.

In addition, you can dive deep into details analysis of the model to learn more about the model.

Feature importance represents the estimated importance of each feature in predicting the target column. In this case, the credit line column has the most significant impact in predicting if a customer will pay back the loan amount, followed by interest rate and annual income.

The confusion matrix in the Advanced metrics section contains information for users that want a deeper understanding of their model performance.

Before you can deploy your model for production workloads, use Canvas to test the model. Canvas manages our model endpoint and allows us to make predictions directly in the Canvas user interface.

  1. Choose Predict and review the findings on either the Batch prediction or Single prediction tab.

In the following example, we make a single prediction by modifying values to predict our target variable loan_status in real time

We can also select a larger dataset and have Canvas generate batch predictions on our behalf.


End-to-end machine learning is complex and iterative, and often involves multiple personas, technologies, and processes. Data Wrangler and Canvas enable collaboration between teams without requiring these teams to write any code.

A data engineer can easily prepare data using Data Wrangler without writing any code and pass the prepared dataset to a business analyst. A business analyst can then easily build accurate ML models with just a few click using Canvas and get accurate predictions in real time or in batch.

Get started with Data Wrangler using these tools without having to manage any infrastructure. You can set up Canvas quickly and immediately start creating ML models to support your business needs.

About the Authors

Peter Chung is a Solutions Architect for AWS, and is passionate about helping customers uncover insights from their data. He has been building solutions to help organizations make data-driven decisions in both the public and private sectors. He holds all AWS certifications as well as two GCP certifications.

 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.

Dan Ferguson is a Solutions Architect at AWS, based in New York, USA. As a machine learning services expert, Dan works to support customers on their journey to integrating ML workflows efficiently, effectively, and sustainably.


Continue Reading


Optimize F1 aerodynamic geometries via Design of Experiments and machine learning

FORMULA 1 (F1) cars are the fastest regulated road-course racing vehicles in the world. Although these open-wheel automobiles are only 20–30 kilometers (or 12–18 miles) per-hour faster than top-of-the-line sports cars, they can speed around corners up to five times as fast due to the powerful aerodynamic downforce they create. Downforce is the vertical force…




FORMULA 1 (F1) cars are the fastest regulated road-course racing vehicles in the world. Although these open-wheel automobiles are only 20–30 kilometers (or 12–18 miles) per-hour faster than top-of-the-line sports cars, they can speed around corners up to five times as fast due to the powerful aerodynamic downforce they create. Downforce is the vertical force generated by the aerodynamic surfaces that presses the car towards the road, increasing the grip from the tires. F1 aerodynamicists must also monitor the air resistance or drag, which limits straight-line speed.

The F1 engineering team is in charge of designing the next generation of F1 cars and putting together the technical regulation for the sport. Over the last 3 years, they have been tasked with designing a car that maintains the current high levels of downforce and peak speeds, but is also not adversely affected by driving behind another car. This is important because the previous generation of cars can lose up to 50% of their downforce when racing closely behind another car due to the turbulent wake generated by wings and bodywork.

Instead of relying on time-consuming and costly track or wind tunnel tests, F1 uses Computational Fluid Dynamics (CFD), which provides a virtual environment to study the flow of fluids (in this case the air around the F1 car) without ever having to manufacture a single part. With CFD, F1 aerodynamicists test different geometry concepts, assess their aerodynamic impact, and iteratively optimize their designs. Over the past 3 years, the F1 engineering team has collaborated with AWS to set up a scalable and cost-efficient CFD workflow that has tripled the throughput of CFD runs and cut the turnaround time per run by half.

F1 is in the process of looking into AWS machine learning (ML) services such as Amazon SageMaker to help optimize the design and performance of the car by using the CFD simulation data to build models with additional insights. The aim is to uncover promising design directions and reduce the number of CFD simulations, thereby reducing the time taken to converge to optimal designs.

In this post, we explain how F1 collaborated with the AWS Professional Services team to develop a bespoke Design of Experiments (DoE) workflow powered by ML to advise F1 aerodynamicists on which design concepts to test in CFD to maximize learning and performance.

Problem statement

When exploring new aerodynamic concepts, F1 aerodynamicists sometimes employ a process called Design of Experiments (DoE). This process systematically studies the relationship between multiple factors. In the case of a rear wing, this might be wing chord, span, or camber, with respect to aerodynamic metrics such as downforce or drag. The goal of a DoE process is to efficiently sample the design space and minimize the number of candidates tested before converging to an optimal result. This is achieved by iteratively changing multiple design factors, measuring the aerodynamic response, studying the impact and relationship between factors, and then continuing testing in the most optimum or informative direction. In the following figure, we present an example rear wing geometry that F1 has kindly shared with us from their UNIFORM baseline. Four design parameters which F1 aerodynamicists could investigate in a DoE routine are labeled.

In this project, F1 worked with AWS Professional Services to investigate using ML to enhance DoE routines. Traditional DoE methods require a well-populated design space in order to understand the relationship between design parameters and therefore rely on a large number of upfront CFD simulations. ML regression models could use the results from previous CFD simulations to predict the aerodynamic response given the set of design parameters, as well as give you an indication of the relative importance of each design variable. You could use these insights to predict optimal designs and help designers converge to optimum solutions with fewer upfront CFD simulations. Secondly, you could use data science techniques to understand which regions in the design space haven’t been explored and could potentially hide optimal designs.

To illustrate the bespoke ML-powered DoE workflow, we walk through a real example of designing a front wing.

Designing a front wing

F1 cars rely on wings such as the front and rear wings to generate most of their downforce, which we refer to throughout this example by the coefficient Cz. Throughout this example, the downforce values have been normalized. In this example, F1 aerodynamicists used their domain expertise to parameterize the wing geometry as follows (refer to the following figure for a visual representation):

  • LE-Height – Leading edge height
  • Min-Z – Minimum ground clearance
  • Mid-LE-Angle – Leading edge angle of the third element
  • TE-Angle – Trailing edge angle
  • TE-Height – Trailing edge height

This front wing geometry was shared by F1 and is part of the UNIFORM baseline.

These parameters were selected because they are sufficient to describe the main aspects of the geometry efficiently and because in the past, aerodynamic performance has shown notable sensitivity with respect to these parameters. The goal of this DoE routine was to find the combination of the five design parameters that would maximize aerodynamic downforce (Cz). The design freedom is also limited by setting maximum and minimum values to the design parameters, as shown in the following table.

. Minimum Maximum
TE-Height 250.0 300.0
TE-Angle 145.0 165.0
Mid-LE-Angle 160.0 170.0
Min-Z 5.0 50.0
LE-Height 100.0 150.0

Having established the design parameters, the target output metric, and the bounds of our design space, we have all we need to get started with the DoE routine. A workflow diagram of our solution is presented in the following image. In the following section, we dive deep into the different stages.

Initial sampling of the design space

The first step of the DoE workflow is to run in CFD an initial set of candidates that efficiently sample the design space and allow us to build the first set of ML regression models to study the influence of each feature. First, we generate a pool of N samples using Latin Hypercube Sampling (LHS) or a regular grid method. Then, we select k candidates to test in CFD by means of a greedy inputs algorithm, which aims to maximize the exploration of the design space. Starting with a baseline candidate (the current design), we iteratively select candidates furthest away from all the previously tested candidates. Suppose that we already tested k designs; for the remaining design candidates, we find the minimum distance d with respect to the tested k designs:

The greedy inputs algorithm selects the candidate that maximizes the distance in the feature space to the previously tested candidates:

In this DoE, we selected three greedy inputs candidates and ran those in CFD to assess their aerodynamic downforce (Cz). The greedy inputs candidates explore the bounds of the design space and at this stage, none of them proved superior to the baseline candidate in terms of aerodynamic downforce (Cz). The results of this initial round of CFD testing together with the design parameters are displayed in the following table.

. TE-Height TE-Angle Mid-LE-Angle Min-Z LE-Height Normalized Cz
Baseline 292.25 154.86 166 5 130 0.975
GI 0 250 165 160 50 100 0.795
GI 1 300 145 170 50 100 0.909
GI 2 250 145 170 5 100 0.847

Initial ML regression models

The goal of the regression model is to predict Cz for any combination of the five design parameters. With such a small dataset, we prioritized simple models, applied model regularization to avoid overfitting, and combined the predictions of different models where possible. The following ML models were constructed:

  • Ordinary Least Squares (OLS)
  • Support Vector Regression (SVM) with an RBF kernel
  • Gaussian Process Regression (GP) with a Matérn kernel
  • XGBoost

In addition, a two-level stacked model was built, where the predictions of the GP, SVM, and XGBoost models are assimilated by a Lasso algorithm to produce the final response. This model is referred to throughout this post as the stacked model. To rank the predictive capabilities of the five models we described, a repeated k-fold cross validation routine was implemented.

Generating the next design candidate to test in CFD

Selecting which candidate to test next requires careful consideration. The F1 aerodynamicist must balance the benefit of exploiting options predicted by the ML model to provide high downforce with the cost of failing to explore uncharted regions of the design space, which may provide even higher downforce. For that reason, in this DoE routine, we propose three candidates: one performance-driven and two exploration-driven. The purpose of the exploration-driven candidates is also to provide additional data points to the ML algorithm in regions of the design space where the uncertainty around the prediction is highest. This in turn leads to more accurate predictions in the next round of design iteration.

Genetic algorithm optimization to maximize downforce

To obtain the candidate with the highest expected aerodynamic downforce, we could run a prediction over all possible design candidates. However, this wouldn’t be efficient. For this optimization problem, we use a genetic algorithm (GA). The goal is to efficiently search through a huge solution space (obtained via the ML prediction of Cz) and return the most optimal candidate. GAs are advantageous when the solution space is complex and non-convex, so that classical optimization methods such as gradient descent are an ineffective means to find a global solution. GA is a subset of evolutionary algorithms and inspired by concepts from natural selection, genetic crossover, and mutation to solve the search problem. Over a series of iterations (known as generations), the best candidates of an initially randomly selected set of design candidates are combined (much like reproduction). Eventually, this mechanism allows you to find the most optimal candidates in an efficient manner. For more information about GAs, refer to Using genetic algorithms on AWS for optimization problems.

Generating exploration-driven candidates

In generating what we term exploration-driven candidates, a good sampling strategy must be able to adapt to a situation of effect sparsity, where only a subset of the parameters significantly affects the solution. Therefore, the sampling strategy should spread out the candidates across the input design space but also avoid unnecessary CFD runs, changing variables that have little effect on performance. The sampling strategy must take into account the response surface predicted by the ML regressor. Two sampling strategies were employed to obtain exploration-driven candidates.

In the case of Gaussian Process Regressors (GP), the standard deviation of the predicted response surface can be used as an indication of the uncertainty of the model. The sampling strategy consists of selecting out of the pool of N samples , the candidate that maximizes . By doing so, we’re sampling in the region of the design space where the regressor is least confident about its prediction. In mathematical terms, we select the candidate that satisfies the following equation:

Alternatively, we employ a greedy inputs and outputs sampling strategy, which maximizes both the distances in the feature space and in the response space between the proposed candidate and the already tested designs. This tackles the effect sparsity situation because candidates that modify a design parameter of little relevance have a similar response, and therefore the distances in the response surface are minimal. In mathematical terms, we select the candidate that satisfies the following equation, where the function f is the ML regression model:

Candidate selection, CFD testing, and optimization loop

At this stage, the user is presented with both performance-driven and exploration-driven candidates. The next step consists of selecting a subset of the proposed candidates, running CFD simulations with those design parameters, and recording the aerodynamic downforce response.

After this, the DoE workflow retrains the ML regression models, runs the genetic algorithm optimization, and proposes a new set of performance-driven and exploration-driven candidates. The user runs a subset of the proposed candidates and continues iterating in this fashion until the stopping criteria is met. The stopping criteria is generally met when a candidate deemed optimum is obtained.


In the following figure, we record the normalized aerodynamic downforce (Cz) from the CFD simulation (blue) and the one predicted beforehand using the ML regression model of choice (pink) for each iteration of the DoE workflow. The goal was to maximize aerodynamic downforce (Cz). The first four runs (to the left of the red line) were the baseline and the three greedy inputs candidates outlined previously. From there on, a combination of performance-driven and exploration-driven candidates were tested. In particular, the candidates at iterations 6 and 8 were exploratory candidates, both showing lower levels of downforce than the baseline candidate (iteration 1). As expected, as we recorded more candidates, the ML prediction became increasingly accurate, as denoted by the decreasing distance between the predicted and actual Cz. At iteration 9, the DoE workflow managed to find a candidate with a similar performance to the baseline, and at iteration 12, the DoE workflow was concluded when the performance-driven candidate surpassed the baseline.

The final design parameters together with the resultant normalized downforce value is presented in the following table. The normalized downforce level for the baseline candidate was 0.975, whereas the optimum candidate for the DoE workflow recorded a normalized downforce level of 1.000. This is an important 2.5% relative increase.

For context, a traditional DoE approach with five variables would require 25 upfront CFD simulations before achieving a good enough fit to predict an optimum. On the other hand, this active learning approach converged to an optimum in 12 iterations.

. TE-Height TE-Angle Mid-LE-Angle Min-Z LE-Height Normalized Cz
Baseline 292.25 154.86 166 5 130 0.975
Optimal 299.97 156.79 166.27 5.01 135.26 1.000

Feature importance

Understanding the relative feature importance for a predictive model can provide a useful insight into the data. It can help feature selection with less important variables being removed, thereby reducing the dimensionality of the problem and potentially improving the predictive powers of the regression model, particularly in the small data regime. In this design problem, it provides F1 aerodynamicists an insight into which variables are the most sensitive and therefore require more careful tuning.

In this routine, we implemented a model-agnostic technique called permutation importance. The relative importance of each variable is measured by calculating the increase in the model’s prediction error after randomly shuffling the values for that variable alone. If a feature is important for the model, the prediction error increases greatly, and vice versa for lesser important features. In the following figure, we present the permutation importance for a Gaussian Process Regressor (GP) predicting aerodynamic downforce (Cz). The trailing edge height (TE-Height) was deemed the most important.


In this post, we explained how F1 aerodynamicists are using ML regression models in DoE workflows when designing novel aerodynamic geometries. The ML-powered DoE workflow developed by AWS Professional Services provides insights into which design parameters will maximize performance or explore uncharted regions in the design space. As opposed to iteratively testing candidates in CFD in a grid search fashion, the ML-powered DoE workflow is able to converge to optimal design parameters in fewer iterations. This saves both time and resources because fewer CFD simulations are required.

Whether you’re a pharmaceutical company looking to speed up chemical composition optimization or a manufacturing company looking to find the design dimensions for the most robust designs, DoE workflows can help reach optimal candidates more efficiently. AWS Professional Services is ready to supplement your team with specialized ML skills and experience to develop the tools to streamline DoE workflows and help you achieve better business outcomes. For more information, see AWS Professional Services, or reach out through your account manager to get in touch.

About the Authors

Pablo Hermoso Moreno is a Data Scientist in the AWS Professional Services Team. He works with clients across industries using Machine Learning to tell stories with data and reach more informed engineering decisions faster. Pablo’s background is in Aerospace Engineering and having worked in the motorsport industry he has an interest in bridging physics and domain expertise with ML. In his spare time, he enjoys rowing and playing guitar.


Continue Reading


Detect social media fake news using graph machine learning with Amazon Neptune ML

In recent years, social media has become a common means for sharing and consuming news. However, the spread of misinformation and fake news on these platforms has posed a major challenge to the well-being of individuals and societies. Therefore, it is imperative that we develop robust and automated solutions for early detection of fake news…




In recent years, social media has become a common means for sharing and consuming news. However, the spread of misinformation and fake news on these platforms has posed a major challenge to the well-being of individuals and societies. Therefore, it is imperative that we develop robust and automated solutions for early detection of fake news on social media. Traditional approaches rely purely on the news content (using natural language processing) to mark information as real or fake. However, the social context in which the news is published and shared can provide additional insights into the nature of fake news on social media and improve the predictive capabilities of fake news detection tools. In this post, we demonstrate how to use Amazon Neptune ML to detect fake news based on the content and social context of the news on social media.

Neptune ML is a new capability of Amazon Neptune that uses graph neural networks (GNNs), a machine learning (ML) technique purpose-built for graphs, to make easy, fast, and accurate predictions using graph data. Making accurate predictions on graphs with billions of relationships requires expertise. Existing ML approaches such as XGBoost can’t operate effectively on graphs because they’re designed for tabular data. As a result, using these methods on graphs can take time, require specialized skills, and produce suboptimal predictions.

Neptune ML uses the Deep Graph Library (DGL), an open-source library to which AWS contributes, and Amazon SageMaker to build and train GNNs, including Relational Graph Convolutional Networks (R-GCNs) for tasks such as node classification, node regression, link prediction, or edge classification.

The DGL makes it easy to apply deep learning to graph data, and Neptune ML automates the heavy lifting of selecting and training the best ML model for graph data. It provides fast and memory-efficient message passing primitives for training GNNs. Neptune ML uses the DGL to automatically choose and train the best ML model for your workload. This enables you to make ML-based predictions on graph data in hours instead of weeks. For more information, see Amazon Neptune ML for machine learning on graphs.

Amazon SageMaker is a fully managed service that provides every developer and data scientist with the ability to prepare, build, train, and deploy ML models quickly.

Overview of GNNs

GNNs are neural networks that take graphs as input. These models operate on the relational information in data to produce insights not possible in other neural network architectures and algorithms. A graph (sometimes called a network) is a data structure that highlights the relationships between components in the data. It consists of nodes (or vertices) and edges (or links) that act as connections between the nodes. Such a data structure has an advantage when dealing with entities that have multiple relationships. Graph data structures have been around for centuries, with a wide variety of modern use cases.

GNNs are emerging as an important class of deep learning (DL) models. GNNs learn embeddings on nodes, edges, and graphs. GNNs have been around for about 20 years, but interest in them has dramatically increased in the last 5 years. In this time, we’ve seen new architectures emerge, novel applications realized, and new platforms and libraries enter the scene. There are several potential research and industry use cases for GNNs, including the following:

  • Computer vision – Generating scene graphs
  • Forecasting – Predicting traffic volume
  • Node classification – Implementing targeted campaigns, detecting fake news
  • Graph classification – Predicting the properties of a chemical compound
  • Link prediction – Building recommendation systems
  • Other – Predicting adversarial attacks


For this post, we use the BuzzFeed dataset from the 2018 version of FakeNewsNet. The BuzzFeed dataset consists of a sample of news articles shared on Facebook from nine news agencies over 1 week leading up to the 2016 US election. Every post and the corresponding news article have been fact-checked by BuzzFeed journalists. The following table summarizes key statistics about the BuzzFeed dataset from FakeNewsNet.

Category Amount
Users 15,257
Authors 126
Publishers 28
Social Links 634,750
Engagements 25,240
News Articles 182
Fake News 91
Real News 91

To get the raw data, you can complete the following steps:

  1. Clone the FakeNewsNet repository from GitHub.
  2. Check out the old version branch.
  3. Change the directory to Data/BuzzFeed.

Each row in the Users.txt file provides a UUID for the corresponding user.

Each row in the News.txt file provides a name and ID for the corresponding news in the dataset.

In the BuzzFeedNewsUser.txt file, the news_id in the first column is posted or shared by the user_id in the second column n times, where n is the value in the third column.

In the BuzzFeedUserUser.txt file, the user_id in the first column follows the user_id in the second column.

User features such as age, gender, and historical social media activities (109,626 features for each user) are made available in UserFeature.mat file. Sample news content files, shown in the following screenshot, contain information such as news title, news text, author name, and publisher web address.

We processed the raw data from the FakeNewsNet repository and converted it into CSV format for vertices and edges in a heterogeneous property graph that can be readily loaded into a Neptune database with Apache TinkerPop Gremlin. The constructed property graph is composed of four vertex types and five edge types, as demonstrated in the following schematic, which together describe the social context in which each news item is published and shared. The News vertices have two properties: news_title and news_type (Fake or Real). The edges connecting News and User vertices have a weight property describing how many times the user has shared the news. The User vertices have a 100-dimension property representing user features such as age, gender, and historical social media activities (reduced from 109,626 to 100 using principal coordinate analysis).

The following screenshot shows the first 10 rows of the processed nodes.csv file.

The following screenshot shows the first 10 rows of the processed edges.csv file.

To follow along with this post, start by using the following AWS CloudFormation quick-start template to quickly spin up an associated Neptune cluster and AWS graph notebook, and set up all the configurations needed to work with Neptune ML in a graph notebook. You then need to download and save the sample dataset in the default Amazon Simple Storage Service (Amazon S3) bucket associated with your SageMaker session, or in an S3 bucket of your choice. For rapid experimentation and initial data exploration, you can save a copy of the dataset under the home directory of the local volume attached to your SageMaker notebook instance, and follow the create_graph_dataset.ipynb Jupyter notebook. After you generate the processed nodes and edges files, you can run the following commands to upload the transformed graph data to Amazon S3:

bucket = ‘‘ prefix = ‘fake-news-detection/data’ s3_client = boto3.client(‘s3’) resp = s3_client.upload_file(‘./Data/upload/nodes.csv’, bucket, f”{prefix}/nodes.csv”) resp = s3_client.upload_file(‘./Data/upload/edges.csv’, bucket, f”{prefix}/edges.csv”)

You can use the %load magic command, which is available as part of the AWS graph notebook, to bulk load data to Neptune:

%load -s {s3_uri} -f csv -p OVERSUBSCRIBE –run

You can use the %graph_notebook_config magic command to see information about the Neptune cluster associated with your graph notebook. You can also use the %status magic command to see the status of your Neptune cluster, as shown in the following screenshot.

Solution overview

Neptune ML uses graph neural network technology to automatically create, train, and deploy ML models on your graph data. Neptune ML supports common graph prediction tasks, such as node classification and regression, edge classification and regression, and link prediction. In our solution, we use node classification to classify news nodes according to the news_type property.

The following diagram illustrates the high-level process flow to develop the best model for fake news detection.

Graph ML with Neptune ML involves five main steps:

  1. Export and configure the data – The data export step uses the Neptune-Export service to export data from Neptune into Amazon S3 in CSV format. A configuration file named training-data-configuration.json is automatically generated, which specifies how the exported data can be loaded into a trainable graph.
  2. Preprocess the data – The exported dataset is preprocessed using standard techniques to prepare it for model training. Feature normalization can be performed for numeric data, and text features can be encoded using word2vec. At the end of this step, a DGL graph is generated from the exported dataset for the model training step. This step is implemented using a SageMaker processing job, and the resulting data is stored in an Amazon S3 location that you have specified.
  3. Train the model – This step trains the ML model that will be used for predictions. Model training is done in two stages:
    1. The first stage uses a SageMaker processing job to generate a model training strategy configuration set that specifies what type of model and model hyperparameter ranges are used for the model training.
    2. The second stage uses a SageMaker model tuning job to try different hyperparameter configurations and select the training job that produced the best-performing model. The tuning job runs a pre-specified number of model training job trials on the processed data. At the end of this stage, the trained model parameters of the best training job are used to generate model artifacts for inference.
  4. Create an inference endpoint in SageMaker – The inference endpoint is a SageMaker endpoint instance that is launched with the model artifacts produced by the best training job. The endpoint is able to accept incoming requests from the graph database and return the model predictions for inputs in the requests.
  5. Query the ML model using Gremlin – You can use extensions to the Gremlin query language to query predictions from the inference endpoint.

Before we proceed with the first step of machine learning, let’s verify that the graph dataset is loaded in the Neptune cluster. Run the following Gremlin traversal to see the count of nodes by label:

%%gremlin g.V().groupCount().by(label).unfold().order().by(keys)

If nodes are loaded correctly, the output is as follows:

  • 126 author nodes
  • 182 news nodes
  • 28 publisher nodes
  • 15,257 user nodes

Use the following code to see the count edges by label:

%%gremlin g.E().groupCount().by(label).unfold().order().by(keys)

If edges are loaded correctly, the output is as follows:

  • 634,750 follows edges
  • 174 published edges
  • 250 wrote edges
  • 250 wrote_for edges

Now let’s go through the ML development process in detail.

Export and configure the data

The export process is triggered by calling to the Neptune-Export service endpoint. This call contains a configuration object that specifies the type of ML model to build, in our case node classification, as well as any feature configurations required.

The configuration options provided to the Neptune-Export service are broken into two main sections: selecting the target and configuring features. Here we want to classify news nodes according to the news_type property.

The second section of the configuration, configuring features, is where we specify details about the types of data stored in our graph and how the ML model should interpret that data. When data is exported from Neptune, all properties of all nodes are included. Each property is treated as a separate feature for the ML model. Neptune ML does its best to infer the correct type of feature for a property, but in many cases, the accuracy of the model can be improved by specifying information about the property used for a feature. We use word2vec to encode the news_title property of news nodes, and the numerical type for user_features property of user nodes. See the following code:

export_params={ “command”: “export-pg”, “params”: { “endpoint”: neptune_ml.get_host(), “profile”: “neptune_ml”, “useIamAuth”: neptune_ml.get_iam(), “cloneCluster”: False }, “outputS3Path”: f”{s3_uri}/neptune-export”, “additionalParams”: { “neptune_ml”: { “version”: “v2.0”, “targets”: [ { “node”: “news”, “property”: “news_type”, “type”: “classification” } ], “features”: [ { “node”: “news”, “property”: “news_title”, “type”: “text_word2vec” }, { “node”: “user”, “property”: “user_features”, “type”: “numerical” } ] } }, “jobSize”: “medium”}

Start the export process by running the following command:

%%neptune_ml export start –export-url {neptune_ml.get_export_service_host()} –export-iam –wait –store-to export_results ${export_params}

Preprocess the data

When the export job is complete, we’re ready to train our ML model. There are three machine learning steps in Neptune ML. The first step (data processing) processes the exported graph dataset using standard feature preprocessing techniques to prepare it for use by the DGL. This step performs functions such as feature normalization for numeric data and encoding text features using word2vec. At the conclusion of this step, the dataset is formatted for model training. This step is implemented using a SageMaker processing job, and data artifacts are stored in a pre-specified Amazon S3 location when the job is complete. Run the following code to create the data processing configuration and begin the processing job:

# The training_job_name can be set to a unique value below, otherwise one will be auto generated training_job_name=neptune_ml.get_training_job_name(‘fake-news-detection’) processing_params = f””” –config-file-name training-data-configuration.json –job-id {training_job_name} –s3-input-uri {export_results[‘outputS3Uri’]} –s3-processed-uri {str(s3_uri)}/preloading “””

Train the model

Now that you have the data processed in the desired format, this step trains the ML model that is used for predictions. The model training is done in two stages. The first stage uses a SageMaker processing job to generate a model training strategy. A model training strategy is a configuration set that specifies what type of model and model hyperparameter ranges are used for the model training. After the first stage is complete, the SageMaker processing job launches a SageMaker hyperparameter tuning job. The hyperparameter tuning job runs a pre-specified number of model training job trials on the processed data, and stores the model artifacts generated by the training in the output Amazon S3 location. When all the training jobs are complete, the hyperparameter tuning job also notes the training job that produced the best performing model.

We use the following training parameters:

training_params=f””” –job-id {training_job_name} –data-processing-id {training_job_name} –instance-type ml.c5.18xlarge –s3-output-uri {str(s3_uri)}/training –max-hpo-number 20 –max-hpo-parallel 4 “””

The hyperparameter tuning finds the best version of a model by running many training jobs on the dataset. You can summarize hyperparameters of the five best training jobs and their respective model performance as follows:

tuning_job_name = training_results[‘hpoJob’][‘name’] tuner = sagemaker.HyperparameterTuningJobAnalytics(tuning_job_name) full_df = tuner.dataframe() if len(full_df) > 0: df = full_df[full_df[“FinalObjectiveValue”] > -float(“inf”)] if len(df) > 0: df = df.sort_values(“FinalObjectiveValue”, ascending=False) print(“Number of training jobs with valid objective: %d” % len(df)) print({“lowest”: min(df[“FinalObjectiveValue”]), “highest”: max(df[“FinalObjectiveValue”])}) pd.set_option(“display.max_colwidth”, None) # Don’t truncate TrainingJobName else: print(“No training jobs have reported valid results yet.”)

We can see that the best performing training job achieved an accuracy of approximately 94%. This training job will be automatically selected by Neptune ML for creating an endpoint in the next step.

Create an endpoint

The final step of machine learning is to create an inference endpoint, which is a SageMaker endpoint instance that is launched with the model artifacts produced by the best training job. We use this endpoint in our graph queries to return the model predictions for the inputs in the request. After the endpoint is created, it stays active until it’s manually deleted. Create the endpoint with the following code:

endpoint_params=f””” –id {training_job_name} –model-training-job-id {training_job_name} “”” #Create endpoint %neptune_ml endpoint create –wait –store-to endpoint_results {endpoint_params}

Our new endpoint is now up and running.

Query the ML model

Now let’s query your trained graph to see how the model predicts news_type for one unseen news node:

# Random fake news: test node: Actual %%gremlin g.V().has(‘news_title’, ‘BREAKING: Steps to FORCE FBI Director Comey to Resign In Process – Hearing Decides His Fate Sept 28’).properties(“news_type”).value() # Random fake news: test node: Predicted %%gremlin g.with(“Neptune#ml.endpoint”, “${endpoint}”). V().has(‘news_title’, “BREAKING: Steps to FORCE FBI Director Comey to Resign In Process – Hearing Decides His Fate Sept 28”).properties(“news_type”).with(“Neptune#ml.classification”).value()

If your graph is continuously changing, you may need to update ML predictions frequently using the newest data. Although you can do this simply by rerunning the earlier steps (from data export and configuration to creating your inference endpoint), Neptune ML supports simpler ways to update your ML predictions using new data. See Workflows for handling evolving graph data for more details.


In this post, we showed how Neptune ML and GNNs can help detect social media fake news using node classification on graph data by combining information from the complex interaction patterns in the graph. For instructions on implementing this solution, see the GitHub repo. You can also clone and extend this solution with additional data sources for model retraining and tuning. We encourage you to reach out and discuss your use cases with the authors via your AWS account manager.

Additional references

For more information related to Neptune ML and detecting fake news in social media, see the following resources:

About the Authors

Hasan Shojaei is a Data Scientist with AWS Professional Services, where he helps customers across different industries such as sports, insurance, and financial services solve their business challenges through the use of big data, machine learning, and cloud technologies. Prior to this role, Hasan led multiple initiatives to develop novel physics-based and data-driven modeling techniques for top energy companies. Outside of work, Hasan is passionate about books, hiking, photography, and ancient history.

Sarita Joshi is a Senior Data Science Manager with the AWS Professional Services Intelligence team. Together with her team, Sarita plays a strategic role for our customers and partners by helping them achieve their business outcomes through machine learning and artificial intelligence solutions at scale. She has several years of experience as a consultant advising clients across many industries and technical domains, including AI, ML, analytics, and SAP. She holds a master’s degree in Computer Science, Specialty Data Science from Northeastern University.


Continue Reading


Copyright © 2021 Today's Digital.