├── .gitignore
├── terraform
    ├── .gitignore
    ├── plan.out
    ├── outputs.tf
    ├── terraform_backend.tf.template
    ├── terraform.tfvars.template
    ├── main.tf
    ├── template
    │   └── sagemaker_instance_init.sh
    ├── steps.txt
    ├── kinesis.tf
    ├── s3_kinesis.tf
    ├── cloudwatch_event.tf
    ├── lambda.tf
    ├── sagemaker.tf
    ├── variables.tf
    ├── s3_sagemaker.tf
    ├── s3_function.tf
    ├── s3_lambda.tf
    ├── iam_kinesis.tf
    ├── iam_lambda.tf
    ├── iam_sagemaker.tf
    ├── plan.txt
    └── terraform.tfstate.backup
├── .github
    └── PULL_REQUEST_TEMPLATE.md
├── cloudformation
    ├── run-unit-tests.sh
    ├── resources.txt
    ├── build-s3-dist.sh
    └── fraud-detection-using-machine-learning.template
├── README.md
├── source
    ├── fraud_detection
    │   └── index.py
    └── notebooks
    │   └── sagemaker_fraud_detection.ipynb
└── LICENSE


/.gitignore:
--------------------------------------------------------------------------------
1 | dist/
2 | 


--------------------------------------------------------------------------------
/terraform/.gitignore:
--------------------------------------------------------------------------------
1 | .terraform/
2 | terraform.tfvars
3 | tfplan
4 | terraform.tfstate
5 | terraform_backend.tf


--------------------------------------------------------------------------------
/terraform/plan.out:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/qtangs/tf-fraud-detection-using-machine-learning/HEAD/terraform/plan.out


--------------------------------------------------------------------------------
/terraform/outputs.tf:
--------------------------------------------------------------------------------
1 | output "basic_notebook_instance_id" {
2 |   value = "${aws_sagemaker_notebook_instance.basic.id}"
3 | }
4 | 
5 | 


--------------------------------------------------------------------------------
/terraform/terraform_backend.tf.template:
--------------------------------------------------------------------------------
1 | terraform {
2 |   backend "s3" {
3 |     bucket = "<bucket-name>"
4 |     key    = "fraud-detection/terraform.tfstate"
5 |     region = "<region>"
6 |   }
7 | }
8 | 


--------------------------------------------------------------------------------
/terraform/terraform.tfvars.template:
--------------------------------------------------------------------------------
1 | aws_region="<region>"
2 | aws_profile="<profile>"
3 | function_bucket_name="<bucket-for-lambda-function>"
4 | function_version="<version>"
5 | s3_bucket_name_1="<bucket-1>"
6 | s3_bucket_name_2="<bucket-2>"


--------------------------------------------------------------------------------
/.github/PULL_REQUEST_TEMPLATE.md:
--------------------------------------------------------------------------------
1 | *Issue #, if available:*
2 | 
3 | *Description of changes:*
4 | 
5 | 
6 | By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.
7 | 


--------------------------------------------------------------------------------
/terraform/main.tf:
--------------------------------------------------------------------------------
 1 | provider "aws" {
 2 |   region  = var.aws_region
 3 |   profile = var.aws_profile
 4 |   version = "~> 2.21"
 5 | }
 6 | 
 7 | provider "template" {
 8 |   version = "~> 2.1"
 9 | }
10 | 
11 | provider "archive" {
12 |   version = "~> 1.2"
13 | }
14 | 
15 | data "aws_caller_identity" "current" {}
16 | 


--------------------------------------------------------------------------------
/terraform/template/sagemaker_instance_init.sh:
--------------------------------------------------------------------------------
1 | cd /home/ec2-user/SageMaker
2 | aws s3 cp s3://${function_bucket_name}-${aws_region}/fraud-detection-using-machine-learning/${function_version}/notebooks/sagemaker_fraud_detection.ipynb .
3 | sed -i 's/fraud-detection-end-to-end-demo/${s3_bucket_name_1}/g' sagemaker_fraud_detection.ipynb


--------------------------------------------------------------------------------
/cloudformation/run-unit-tests.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/bash
 2 | 
 3 | # This script should be run from the repo's deployment directory
 4 | # cd deployment
 5 | # ./run-unit-tests.sh
 6 | 
 7 | # Run unit tests
 8 | echo "Running unit tests"
 9 | echo "cd ../source"
10 | cd ../source
11 | echo "No unit tests to run, so sad ..."
12 | echo "Completed unit tests"
13 | 


--------------------------------------------------------------------------------
/terraform/steps.txt:
--------------------------------------------------------------------------------
 1 | 
 2 | terraform_backend.tf.template -> terraform_backend.tf
 3 | terraform.tfvars.template -> terraform.tfvars
 4 | 
 5 | export AWS_PROFILE=<your desired profile>
 6 | 
 7 | terraform init
 8 | terraform validate
 9 | terraform plan -out=tfplan
10 | terraform apply --auto-approve tfplan
11 | 
12 | 
13 | 
14 | terraform plan -destroy -out=tfplan
15 | terraform apply tfplan
16 | 


--------------------------------------------------------------------------------
/terraform/kinesis.tf:
--------------------------------------------------------------------------------
 1 | resource "aws_kinesis_firehose_delivery_stream" "fraud_detection_firehose_stream" {
 2 |   name        = "fraud-detection-firehose-stream"
 3 |   destination = "s3"
 4 | 
 5 |   s3_configuration {
 6 |     bucket_arn         = aws_s3_bucket.s3_bucket_2.arn
 7 |     prefix             = var.kinesis_firehose_prefix
 8 |     buffer_interval    = 60
 9 |     buffer_size        = 100
10 |     compression_format = "GZIP"
11 |     role_arn           = aws_iam_role.fraud_detection_firehose_role.arn
12 |   }
13 | 
14 |   tags = {
15 |     Group     = var.default_resource_group
16 |     CreatedBy = var.default_created_by
17 |   }
18 | }
19 | 


--------------------------------------------------------------------------------
/terraform/s3_kinesis.tf:
--------------------------------------------------------------------------------
 1 | resource "aws_s3_bucket" "s3_bucket_2" {
 2 |   bucket        = "${var.s3_bucket_name_2}-${var.aws_region}"
 3 |   acl           = "private"
 4 |   force_destroy = true                                        # delete all data from this bucket before destroy
 5 | 
 6 |   server_side_encryption_configuration {
 7 |     rule {
 8 |       apply_server_side_encryption_by_default {
 9 |         sse_algorithm = "AES256"
10 |       }
11 |     }
12 |   }
13 | 
14 |   tags = {
15 |     Description = "Bucket for storing processed events for visualization features."
16 |     Group       = "${var.default_resource_group}"
17 |     CreatedBy   = "${var.default_created_by}"
18 |   }
19 | }
20 | 


--------------------------------------------------------------------------------
/terraform/cloudwatch_event.tf:
--------------------------------------------------------------------------------
 1 | resource "aws_cloudwatch_event_rule" "fraud_detection_scheduled_rule" {
 2 |   name                = "fraud-detection-scheduled-rule"
 3 |   description         = "ScheduledRule"
 4 |   schedule_expression = "rate(1 minute)"
 5 |   is_enabled          = false
 6 | 
 7 |   tags = {
 8 |     Group     = "${var.default_resource_group}"
 9 |     CreatedBy = "${var.default_created_by}"
10 |   }
11 | }
12 | 
13 | resource "aws_cloudwatch_event_target" "fraud_detection" {
14 |   target_id = "TargetFunctionV1"
15 |   rule      = aws_cloudwatch_event_rule.fraud_detection_scheduled_rule.name
16 |   arn       = aws_lambda_function.fraud_detection_event_processor.arn
17 | }
18 | 
19 | resource "aws_lambda_permission" "fraud_detection" {
20 |   action        = "lambda:InvokeFunction"
21 |   function_name = aws_lambda_function.fraud_detection_event_processor.function_name
22 |   principal     = "events.amazonaws.com"
23 |   source_arn    = aws_cloudwatch_event_rule.fraud_detection_scheduled_rule.arn
24 | }
25 | 


--------------------------------------------------------------------------------
/terraform/lambda.tf:
--------------------------------------------------------------------------------
 1 | resource "aws_lambda_function" "fraud_detection_event_processor" {
 2 |   handler       = "index.lambda_handler"
 3 |   function_name = "fraud-detection-event-processor"
 4 |   role          = aws_iam_role.fraud_detection_lambda_role.arn
 5 |   s3_bucket     = aws_s3_bucket.fraud_detection_function_bucket.id
 6 |   s3_key        = "fraud-detection-using-machine-learning/${var.function_version}/fraud_detection.zip"
 7 | 
 8 |   # The filebase64sha256() function is available in Terraform 0.11.12 and later
 9 |   # For Terraform 0.11.11 and earlier, use the base64sha256() function and the file() function:
10 |   # source_code_hash = "${base64sha256(file("lambda_function_payload.zip"))}"
11 |   source_code_hash = filebase64sha256(data.archive_file.fraud_detection_archive.output_path)
12 | 
13 |   runtime = "python3.6"
14 | 
15 |   tags = {
16 |     Group     = var.default_resource_group
17 |     CreatedBy = var.default_created_by
18 |   }
19 | 
20 |   depends_on = [aws_s3_bucket_object.s3_fraud_detection_archive]
21 | }
22 | 


--------------------------------------------------------------------------------
/terraform/sagemaker.tf:
--------------------------------------------------------------------------------
 1 | resource "aws_sagemaker_notebook_instance" "basic" {
 2 |   name                  = "FraudDetectionNotebookInstance"
 3 |   role_arn              = aws_iam_role.sm_notebook_instance_role.arn
 4 |   instance_type         = "ml.t2.medium"
 5 |   lifecycle_config_name = aws_sagemaker_notebook_instance_lifecycle_configuration.basic_lifecycle.name
 6 | 
 7 |   tags = {
 8 |     Group     = var.default_resource_group
 9 |     CreatedBy = var.default_created_by
10 |   }
11 | 
12 |   depends_on = [aws_s3_bucket_object.s3_fraud_detection_notebook ]
13 | }
14 | 
15 | data "template_file" "instance_init" {
16 |   template = file("${path.module}/template/sagemaker_instance_init.sh")
17 | 
18 |   vars = {
19 |     s3_bucket_name_1     = aws_s3_bucket.s3_bucket_1.id
20 |     aws_region           = var.aws_region
21 |     function_bucket_name = var.function_bucket_name
22 |     function_version     = var.function_version
23 |   }
24 | }
25 | 
26 | resource "aws_sagemaker_notebook_instance_lifecycle_configuration" "basic_lifecycle" {
27 |   name     = "BasicNotebookInstanceLifecycleConfig"
28 |   on_start = base64encode(data.template_file.instance_init.rendered)
29 | 
30 |   depends_on = [aws_s3_bucket.s3_bucket_1]
31 | }
32 | 


--------------------------------------------------------------------------------
/terraform/variables.tf:
--------------------------------------------------------------------------------
 1 | # Default Tags
 2 | variable "default_resource_group" {
 3 |   description = "Default value to be used in resources' Group tag."
 4 |   default     = "fraud-detection"
 5 | }
 6 | 
 7 | variable "default_created_by" {
 8 |   description = "Default value to be used in resources' CreatedBy tag."
 9 |   default     = "terraform"
10 | }
11 | 
12 | # AWS Settings
13 | variable "aws_region" {
14 |   default = "eu-west-2"
15 | }
16 | 
17 | variable "aws_profile" {
18 |   default = "default"
19 | }
20 | 
21 | # Parameters
22 | variable "function_bucket_name" {
23 |   description = "Name of the S3 bucket hosting the code for fraud_detection Lambda function."
24 | }
25 | 
26 | variable "function_version" {
27 |   description = "Version of the fraud_detection Lambda function to use."
28 | }
29 | 
30 | variable "s3_bucket_name_1" {
31 |   description = "New bucket for storing the Amazon SageMaker model and training data."
32 | }
33 | 
34 | variable "s3_bucket_name_2" {
35 |   description = "New bucket for storing processed events for visualization features."
36 | }
37 | 
38 | variable "kinesis_firehose_prefix" {
39 |   description = "Kinesis Firehose prefix for delivery of processed events."
40 |   default     = "fraud-detection/firehose/"
41 | }
42 | 


--------------------------------------------------------------------------------
/terraform/s3_sagemaker.tf:
--------------------------------------------------------------------------------
 1 | resource "aws_s3_bucket" "s3_bucket_1" {
 2 |   bucket        = "${var.s3_bucket_name_1}-${var.aws_region}"
 3 |   acl           = "private"
 4 |   force_destroy = true                                        # delete all data from this bucket before destroy
 5 | 
 6 |   server_side_encryption_configuration {
 7 |     rule {
 8 |       apply_server_side_encryption_by_default {
 9 |         sse_algorithm = "AES256"
10 |       }
11 |     }
12 |   }
13 | 
14 |   tags = {
15 |     Description = "Bucket for storing the Amazon SageMaker model and training data."
16 |     Group       = "${var.default_resource_group}"
17 |     CreatedBy   = "${var.default_created_by}"
18 |   }
19 | }
20 | 
21 | resource "aws_s3_bucket_object" "s3_fraud_detection_notebook" {
22 |   bucket = aws_s3_bucket.fraud_detection_function_bucket.id
23 |   key    = "fraud-detection-using-machine-learning/${var.function_version}/notebooks/sagemaker_fraud_detection.ipynb"
24 |   source = "${path.module}/../source/notebooks/sagemaker_fraud_detection.ipynb"
25 | 
26 |   # The filemd5() function is available in Terraform 0.11.12 and later
27 |   # For Terraform 0.11.11 and earlier, use the md5() function and the file() function:
28 |   # etag = "${md5(file("path/to/file"))}"
29 |   etag = filemd5("${path.module}/../source/notebooks/sagemaker_fraud_detection.ipynb")
30 | }
31 | 


--------------------------------------------------------------------------------
/terraform/s3_function.tf:
--------------------------------------------------------------------------------
 1 | resource "aws_s3_bucket" "fraud_detection_function_bucket" {
 2 |   bucket = "${var.function_bucket_name}-${var.aws_region}"
 3 |   acl    = "private"
 4 | 
 5 |   server_side_encryption_configuration {
 6 |     rule {
 7 |       apply_server_side_encryption_by_default {
 8 |         sse_algorithm = "AES256"
 9 |       }
10 |     }
11 |   }
12 | 
13 |   tags = {
14 |     Description = "Bucket hosting the code for fraud_detection Lambda function."
15 |     Group       = var.default_resource_group
16 |     CreatedBy   = var.default_created_by
17 |   }
18 | }
19 | 
20 | data "archive_file" "fraud_detection_archive" {
21 |   type        = "zip"
22 |   source_file = "${path.module}/../source/fraud_detection/index.py"
23 |   output_path = "${path.module}/../dist/fraud_detection.zip"
24 | }
25 | 
26 | resource "aws_s3_bucket_object" "s3_fraud_detection_archive" {
27 |   bucket = aws_s3_bucket.fraud_detection_function_bucket.id
28 |   key    = "fraud-detection-using-machine-learning/${var.function_version}/fraud_detection.zip"
29 |   source = data.archive_file.fraud_detection_archive.output_path
30 | 
31 |   # The filemd5() function is available in Terraform 0.11.12 and later
32 |   # For Terraform 0.11.11 and earlier, use the md5() function and the file() function:
33 |   # etag = "${md5(file("path/to/file"))}"
34 |   etag = filemd5(data.archive_file.fraud_detection_archive.output_path) # use md5 of index.py to detect changes in the function
35 | }
36 | 


--------------------------------------------------------------------------------
/terraform/s3_lambda.tf:
--------------------------------------------------------------------------------
 1 | resource "aws_s3_bucket" "fraud_detection_function_bucket" {
 2 |   bucket = "${var.function_bucket_name}-${var.aws_region}"
 3 |   acl    = "private"
 4 | 
 5 |   server_side_encryption_configuration {
 6 |     rule {
 7 |       apply_server_side_encryption_by_default {
 8 |         sse_algorithm = "AES256"
 9 |       }
10 |     }
11 |   }
12 | 
13 |   tags = {
14 |     Description = "Bucket hosting the code for fraud_detection Lambda function."
15 |     Group       = var.default_resource_group
16 |     CreatedBy   = var.default_created_by
17 |   }
18 | }
19 | 
20 | data "archive_file" "fraud_detection_archive" {
21 |   type        = "zip"
22 |   source_file = "${path.module}/../source/fraud_detection/index.py"
23 |   output_path = "${path.module}/../dist/fraud_detection.zip"
24 | }
25 | 
26 | resource "aws_s3_bucket_object" "s3_fraud_detection_archive" {
27 |   bucket = aws_s3_bucket.fraud_detection_function_bucket.id
28 |   key    = "fraud-detection-using-machine-learning/${var.function_version}/fraud_detection.zip"
29 |   source = data.archive_file.fraud_detection_archive.output_path
30 | 
31 |   # The filemd5() function is available in Terraform 0.11.12 and later
32 |   # For Terraform 0.11.11 and earlier, use the md5() function and the file() function:
33 |   # etag = "${md5(file("path/to/file"))}"
34 |   etag = filemd5(data.archive_file.fraud_detection_archive.output_path) # use md5 of index.py to detect changes in the function
35 | }
36 | 


--------------------------------------------------------------------------------
/cloudformation/resources.txt:
--------------------------------------------------------------------------------
 1 | Logical ID  Physical ID Type    Status  Status reason
 2 | BasicNotebookInstance	arn:aws:sagemaker:us-east-1:989069432549:notebook-instance/frauddetectionnotebookinstance	AWS::SageMaker::NotebookInstance	CREATE_COMPLETE	-
 3 | BasicNotebookInstanceLifecycleConfig	arn:aws:sagemaker:us-east-1:989069432549:notebook-instance-lifecycle-config/basicnotebookinstancelifecycleconfig-nbtnsfov4xei	AWS::SageMaker::NotebookInstanceLifecycleConfig	CREATE_COMPLETE	-
 4 | FirehoseDeliveryIAMPolicy	aws-f-Fire-1OAVA6HNY7OCK	AWS::IAM::Policy	CREATE_COMPLETE	-
 5 | FirehoseDeliveryIAMRole	aws-fraud-detection-using-FirehoseDeliveryIAMRole-AOTARKHYRERQ	AWS::IAM::Role	CREATE_COMPLETE	-
 6 | KinesisFirehoseDeliveryStream	fraud-detection-firehose-stream	AWS::KinesisFirehose::DeliveryStream	CREATE_COMPLETE	-
 7 | LambdaExecutionRole	aws-fraud-detection-using-mach-LambdaExecutionRole-1GQPB8RU28LAN	AWS::IAM::Role	CREATE_COMPLETE	-
 8 | LambdaFunction	fraud-detection-event-processor	AWS::Lambda::Function	CREATE_COMPLETE	-
 9 | NotebookInstanceExecutionRole	aws-fraud-detection-using-NotebookInstanceExecutio-XYJKAT5HT62K	AWS::IAM::Role	CREATE_COMPLETE	-
10 | NotebookInstanceIAMPolicy	aws-f-Note-1XD0QCDLFYVMY	AWS::IAM::Policy	CREATE_COMPLETE	-
11 | PermissionForEventsToInvokeLambda	aws-fraud-detection-using-machine-learning-PermissionForEventsToInvokeLambda-1BYURKUXUSOPL	AWS::Lambda::Permission	CREATE_COMPLETE	-
12 | S3Bucket1	aws-fraud-detection-model-data	AWS::S3::Bucket	CREATE_COMPLETE	-
13 | S3Bucket2	aws-fraud-detection-processed-events	AWS::S3::Bucket	CREATE_COMPLETE	-
14 | ScheduledRule	aws-fraud-detection-using-machine-le-ScheduledRule-KMHPLMNKWI32	AWS::Events::Rule	CREATE_COMPLETE	-


--------------------------------------------------------------------------------
/terraform/iam_kinesis.tf:
--------------------------------------------------------------------------------
 1 | resource "aws_iam_role" "fraud_detection_firehose_role" {
 2 |   name = "fraud-detection-firehose-role"
 3 | 
 4 |   tags = {
 5 |     Group     = "${var.default_resource_group}"
 6 |     CreatedBy = "${var.default_created_by}"
 7 |   }
 8 | 
 9 |   assume_role_policy = <<EOF
10 | {
11 |     "Version": "2012-10-17",
12 |     "Statement": [
13 |         {
14 |             "Effect": "Allow",
15 |             "Principal": {
16 |                 "Service": "firehose.amazonaws.com"
17 |             },
18 |             "Action": "sts:AssumeRole"
19 |         }
20 |     ]
21 | }
22 | EOF
23 | }
24 | 
25 | resource "aws_iam_role_policy_attachment" "fraud_detection_firehose" {
26 |   role       = aws_iam_role.fraud_detection_firehose_role.name
27 |   policy_arn = aws_iam_policy.fraud_detection_firehose_policy.arn
28 | }
29 | 
30 | resource "aws_iam_policy" "fraud_detection_firehose_policy" {
31 |   name        = "fraud-detection-firehose-policy"
32 |   description = "Policy for the Amazon Kinesis Data Firehose to save data to S3 bucket"
33 |   path        = "/"
34 | 
35 |   policy = <<EOF
36 | {
37 |     "Version": "2012-10-17",
38 |     "Statement": [
39 |         {
40 |             "Effect": "Allow",
41 |             "Action": [
42 |                 "s3:AbortMultipartUpload",
43 |                 "s3:GetBucketLocation",
44 |                 "s3:GetObject",
45 |                 "s3:ListBucket",
46 |                 "s3:ListBucketMultipartUploads",
47 |                 "s3:PutObject"
48 |             ],
49 |             "Resource": [
50 |                 "arn:aws:s3:::${aws_s3_bucket.s3_bucket_2.id}",
51 |                 "arn:aws:s3:::${aws_s3_bucket.s3_bucket_2.id}/${var.kinesis_firehose_prefix}*"
52 |             ]
53 |         }
54 |     ]
55 | }
56 | EOF
57 | }
58 | 


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | ## Fraud Detection Using Machine Learning
 2 | 
 3 | Setup end to end demo architecture for predicting fraud events with Machine Learning using `Amazon SageMaker` and `Terraform`.
 4 | This repo supports the original article posted on [Medium](https://medium.com/@qtangs/machine-learning-infrastructure-with-amazon-sagemaker-and-terraform-a-case-of-fraud-detection-ab6896144781).
 5 | 
 6 | ## Terraform version
 7 | 
 8 | Ensure your `Terraform` version is as follows (some modifications would be required if you run other `Terraform` versions):
 9 | ```sh
10 | $ terraform --version
11 | Terraform v0.11.14
12 | + provider.archive v1.2.2
13 | + provider.aws v2.21.1
14 | + provider.template v2.1.2
15 | ```
16 | To download `Terraform`, visit https://releases.hashicorp.com/terraform/
17 | 
18 | ## Setup steps
19 | 
20 | From `terraform` folder:
21 | 1. Copy `terraform_backend.tf.template` to `terraform_backend.tf` and modify values accordingly. You need to manually create an S3 bucket or use an existing one to store the Terraform state file.
22 | 2. Copy `terraform.tfvars.template` to `terraform.tfvars` and modify values accordingly. You don't need to create any buckets specified in here, they're to be created by terraform apply.
23 | 3. Run the followings:
24 | ```sh
25 | export AWS_PROFILE=<your desired profile>
26 | 
27 | terraform init
28 | terraform validate
29 | terraform plan -out=tfplan
30 | terraform apply --auto-approve tfplan
31 | ```
32 | 
33 | 
34 | ## Clean up
35 | 
36 | ```
37 | terraform plan -destroy -out=tfplan
38 | terraform apply tfplan
39 | ```
40 | 
41 | ## Original source
42 | https://github.com/awslabs/fraud-detection-using-machine-learning
43 | 
44 | Original CloudFormation script can be found at `cloudformation` folder (renamed from `deployment`).
45 | 
46 | 
47 | ## License
48 | 
49 | This library is licensed under the Apache 2.0 License. 
50 | 


--------------------------------------------------------------------------------
/terraform/iam_lambda.tf:
--------------------------------------------------------------------------------
 1 | resource "aws_iam_role" "fraud_detection_lambda_role" {
 2 |   name = "fraud-detection-lambda-role"
 3 | 
 4 |   tags = {
 5 |     Group     = "${var.default_resource_group}"
 6 |     CreatedBy = "${var.default_created_by}"
 7 |   }
 8 | 
 9 |   assume_role_policy = <<EOF
10 | {
11 |     "Version": "2012-10-17",
12 |     "Statement": [
13 |         {
14 |             "Effect": "Allow",
15 |             "Principal": {
16 |                 "Service": "lambda.amazonaws.com"
17 |             },
18 |             "Action": "sts:AssumeRole"
19 |         }
20 |     ]
21 | }
22 | EOF
23 | }
24 | 
25 | resource "aws_iam_role_policy_attachment" "fraud_detection_lambda" {
26 |   role       = aws_iam_role.fraud_detection_lambda_role.name
27 |   policy_arn = aws_iam_policy.fraud_detection_lambda_policy.arn
28 | }
29 | 
30 | resource "aws_iam_policy" "fraud_detection_lambda_policy" {
31 |   name        = "fraud-detection-lambda-policy"
32 |   description = "Policy for the fraud detection function to put records into the Amazon Kinesis Data Firehose"
33 |   path        = "/"
34 | 
35 |   policy = <<EOF
36 | {
37 |     "Version": "2012-10-17",
38 |     "Statement": [
39 |         {
40 |             "Effect": "Allow",
41 |             "Action": [
42 |                 "logs:CreateLogGroup",
43 |                 "logs:CreateLogStream",
44 |                 "logs:PutLogEvents"
45 |             ],
46 |             "Resource": "arn:aws:logs:${var.aws_region}:${data.aws_caller_identity.current.account_id}:log-group:/aws/lambda/*"
47 |         },
48 |         {
49 |             "Effect": "Allow",
50 |             "Action": [
51 |                 "sagemaker:InvokeEndpoint"
52 |             ],
53 |             "Resource": [
54 |                 "arn:aws:sagemaker:*:*:endpoint/*"
55 |             ]
56 |         },
57 |         {
58 |             "Effect": "Allow",
59 |             "Action": [
60 |                 "firehose:PutRecord",
61 |                 "firehose:PutRecordBatch"
62 |             ],
63 |             "Resource":  [
64 |                 "${aws_kinesis_firehose_delivery_stream.fraud_detection_firehose_stream.arn}"
65 |             ]
66 |         }
67 |     ]
68 | }
69 | EOF
70 | }
71 | 


--------------------------------------------------------------------------------
/cloudformation/build-s3-dist.sh:
--------------------------------------------------------------------------------
 1 | #!/bin/bash
 2 | 
 3 | # This script should be run from the repo's deployment directory
 4 | # cd deployment
 5 | # ./build-s3-dist.sh source-bucket-base-name
 6 | # source-bucket-base-name should be the base name for the S3 bucket location where the template will source the Lambda code from.
 7 | # The template will append '-[region_name]' to this bucket name.
 8 | # For example: ./build-s3-dist.sh solutions
 9 | # The template will then expect the source code to be located in the solutions-[region_name] bucket
10 | 
11 | # Check to see if input has been provided:
12 | if [ -z "$2" ]; then
13 |     echo "Please provide the base source bucket name and version where the lambda code will eventually reside."
14 |     echo "For example: ./build-s3-dist.sh solutions v1.0"
15 |     exit 1
16 | fi
17 | 
18 | # Build source
19 | echo "Staring to build distribution"
20 | # Create variable for deployment directory to use as a reference for builds
21 | echo "export deployment_dir=`pwd`"
22 | export deployment_dir=`pwd`
23 | 
24 | # Make deployment/dist folder for containing the built solution
25 | echo "mkdir -p $deployment_dir/dist"
26 | mkdir -p $deployment_dir/dist
27 | 
28 | # Copy project CFN template(s) to "dist" folder and replace bucket name with arg $1
29 | echo "cp -f fraud-detection-using-machine-learning.template $deployment_dir/dist"
30 | cp -f fraud-detection-using-machine-learning.template $deployment_dir/dist
31 | echo "Updating code source bucket in template with $1"
32 | replace="s/%%BUCKET_NAME%%/$1/g"
33 | echo "sed -i '' -e $replace $deployment_dir/dist/fraud-detection-using-machine-learning.template"
34 | sed -i '' -e $replace $deployment_dir/dist/fraud-detection-using-machine-learning.template
35 | echo "Updating code source bucket in template with $2"
36 | replace="s/%%VERSION%%/$2/g"
37 | echo "sed -i '' -e $replace $deployment_dir/dist/fraud-detection-using-machine-learning.template"
38 | sed -i '' -e $replace $deployment_dir/dist/fraud-detection-using-machine-learning.template
39 | 
40 | # Copy website files to $deployment_dir/dist
41 | echo "Copying notebooks to $deployment_dir/dist"
42 | cp -r $deployment_dir/../source/notebooks $deployment_dir/dist/
43 | 
44 | # Package fraud_detection Lambda function
45 | echo "Packaging fraud_detection lambda"
46 | cd $deployment_dir/../source/fraud_detection/
47 | zip -q -r9 $deployment_dir/dist/fraud_detection.zip *
48 | 
49 | # Done, so go back to deployment_dir
50 | echo "Completed building distribution"
51 | cd $deployment_dir
52 | 


--------------------------------------------------------------------------------
/source/fraud_detection/index.py:
--------------------------------------------------------------------------------
 1 | ##############################################################################
 2 | #  Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.   #
 3 | #                                                                            #
 4 | #  Licensed under the Amazon Software License (the "License"). You may not   #
 5 | #  use this file except in compliance with the License. A copy of the        #
 6 | #  License is located at                                                     #
 7 | #                                                                            #
 8 | #      http://aws.amazon.com/asl/                                            #
 9 | #                                                                            #
10 | #  or in the "license" file accompanying this file. This file is distributed #
11 | #  on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND,        #
12 | #  express or implied. See the License for the specific language governing   #
13 | #  permissions and limitations under the License.                            #
14 | ##############################################################################
15 | import json
16 | import os
17 | import boto3
18 | import random
19 | import datetime
20 | import re
21 | 
22 | def lambda_handler(event, context):
23 |     data_payload = get_data(event, context)
24 |     if not data_payload:
25 |         return
26 |     pred = get_fraud_prediction(data_payload)
27 |     transformed_data = postprocess_event(event, pred)
28 |     response = store_data_prediction(transformed_data)
29 |     print(response)
30 | 
31 | def get_data(event, context):
32 |     if random.random() < 0.15:
33 |         return
34 |     non_fraud_example = [1.00000000e+00, -9.66271698e-01, -1.85226008e-01, 1.79299331e+00, -8.63291264e-01, -1.03088794e-02, 1.24720311e+00, 2.37608939e-01,
35 |                          3.77435863e-01, -1.38702404e+00, -5.49519211e-02, -2.26487264e-01, 1.78228229e-01, 5.07756889e-01, -2.87923753e-01, -6.31418109e-01,
36 |                          -1.05964720e+00, -6.84092760e-01, 1.96577501e+00, -1.23262203e+00, -2.08037779e-01, -1.08300455e-01, 5.27359685e-03, -1.90320522e-01,
37 |                          -1.17557538e+00, 6.47376060e-01, -2.21928850e-01, 6.27228469e-02, 6.14576302e-02, 1.23500000e+02]
38 |     fraud_example = [4.0600000e+02, -2.3122265e+00, 1.9519920e+00, -1.6098508e+00, 3.9979055e+00, -5.2218789e-01, -1.4265453e+00, -2.5373874e+00,
39 |                      1.3916572e+00, -2.7700894e+00, -2.7722721e+00, 3.2020333e+00, -2.8999074e+00, -5.9522188e-01, -4.2892537e+00, 3.8972411e-01, -1.1407472e+00,
40 |                      -2.8300557e+00, -1.6822468e-02, 4.1695571e-01, 1.2691055e-01, 5.1723236e-01, -3.5049368e-02, -4.6521106e-01, 3.2019821e-01, 4.4519167e-02,
41 |                      1.7783980e-01, 2.6114500e-01, -1.4327587e-01, 0.0000000e+00]
42 |     examples = [fraud_example, non_fraud_example]
43 |     idx = 1
44 |     if random.random() < 0.05:
45 |         idx = 0
46 |     return ','.join(map(str, examples[idx]))
47 | 
48 | def get_fraud_prediction(data):
49 |     sagemaker_endpoint_name = 'fraud-detection-endpoint'
50 |     sagemaker_runtime = boto3.client('sagemaker-runtime')
51 |     response = sagemaker_runtime.invoke_endpoint(EndpointName=sagemaker_endpoint_name, ContentType='text/csv',
52 |                                                  Body=data)
53 |     print(response)
54 |     result = json.loads(response['Body'].read().decode())
55 |     print(result)
56 |     pred = int(result['predictions'][0]['predicted_label'])
57 |     return pred
58 | 
59 | def postprocess_event(event, pred):
60 |     millisecond_regex = r'\\.\\d+'
61 |     timestamp = re.sub(millisecond_regex, '', str(datetime.datetime.now()))
62 |     source = random.choice(['Mobile', 'Web', 'Store'])
63 |     return [timestamp, 'random_id', source, str(pred)]
64 | 
65 | def store_data_prediction(data):
66 |     firehose_delivery_stream = 'fraud-detection-firehose-stream'
67 |     firehose = boto3.client('firehose', region_name=os.environ['AWS_REGION'])
68 |     record = ','.join(data) + '\\n'
69 |     response = firehose.put_record(DeliveryStreamName=firehose_delivery_stream, Record={'Data': record})
70 |     return response
71 | 


--------------------------------------------------------------------------------
/terraform/iam_sagemaker.tf:
--------------------------------------------------------------------------------
  1 | resource "aws_iam_role_policy_attachment" "data_scientist_attach" {
  2 |     role = "switch-role-custom"
  3 |     policy_arn = "arn:aws:iam::aws:policy/job-function/DataScientist"
  4 | }
  5 | 
  6 | resource "aws_iam_role" "sm_notebook_instance_role" {
  7 |   name = "sm-notebook-instance-role"
  8 | 
  9 |   tags = {
 10 |     Group     = "${var.default_resource_group}"
 11 |     CreatedBy = "${var.default_created_by}"
 12 |   }
 13 | 
 14 |   assume_role_policy = <<EOF
 15 | {
 16 |     "Version": "2012-10-17",
 17 |     "Statement": [
 18 |         {
 19 |             "Effect": "Allow",
 20 |             "Principal": {
 21 |                 "Service": "sagemaker.amazonaws.com"
 22 |             },
 23 |             "Action": "sts:AssumeRole"
 24 |         }
 25 |     ]
 26 | }
 27 | EOF
 28 | }
 29 | 
 30 | resource "aws_iam_role_policy_attachment" "sm_notebook_instance" {
 31 |   role       = aws_iam_role.sm_notebook_instance_role.name
 32 |   policy_arn = aws_iam_policy.sm_notebook_instance_policy.arn
 33 | }
 34 | 
 35 | resource "aws_iam_policy" "sm_notebook_instance_policy" {
 36 |   name        = "sm-notebook-instance-policy"
 37 |   description = "Policy for the Notebook Instance to manage training jobs, models and endpoints"
 38 |   path        = "/"
 39 | 
 40 |   policy = <<EOF
 41 | {
 42 |     "Version": "2012-10-17",
 43 |     "Statement": [
 44 |         {
 45 |             "Effect": "Allow",
 46 |             "Action": [
 47 |                 "s3:GetBucketLocation",
 48 |                 "s3:ListBucket",
 49 |                 "s3:GetObject",
 50 |                 "s3:PutObject",
 51 |                 "s3:DeleteObject"
 52 |             ],
 53 |             "Resource": [
 54 |                 "arn:aws:s3:::${aws_s3_bucket.s3_bucket_1.id}",
 55 |                 "arn:aws:s3:::${aws_s3_bucket.s3_bucket_1.id}/*",
 56 |                 "arn:aws:s3:::${aws_s3_bucket.fraud_detection_function_bucket.id}/*"
 57 |             ]
 58 |         },
 59 |         {
 60 |             "Effect": "Allow",
 61 |             "Action": [
 62 |                 "sagemaker:CreateTrainingJob",
 63 |                 "sagemaker:DescribeTrainingJob",
 64 |                 "sagemaker:CreateModel",
 65 |                 "sagemaker:DescribeModel",
 66 |                 "sagemaker:DeleteModel",
 67 |                 "sagemaker:CreateEndpoint",
 68 |                 "sagemaker:CreateEndpointConfig",
 69 |                 "sagemaker:DescribeEndpoint",
 70 |                 "sagemaker:DescribeEndpointConfig",
 71 |                 "sagemaker:DeleteEndpoint"
 72 |             ],
 73 |             "Resource": [
 74 |                 "arn:aws:sagemaker:${var.aws_region}:${data.aws_caller_identity.current.account_id}:*"
 75 |             ]
 76 |         },
 77 |         {
 78 |             "Effect": "Allow",
 79 |             "Action": [
 80 |                 "ecr:GetDownloadUrlForLayer",
 81 |                 "ecr:BatchGetImage",
 82 |                 "ecr:BatchCheckLayerAvailability"
 83 |             ],
 84 |             "Resource": [
 85 |                 "arn:aws:ecr:${var.aws_region}:${data.aws_caller_identity.current.account_id}:repository/*"
 86 |             ]
 87 |         },
 88 |         {
 89 |             "Effect": "Allow",
 90 |             "Action": [
 91 |                 "ec2:CreateVpcEndpoint",
 92 |                 "ec2:DescribeRouteTables"
 93 |             ],
 94 |             "Resource": "*"
 95 |         },
 96 |           {
 97 |             "Sid": "EnforceInstanceType",
 98 |             "Effect": "Allow",
 99 |             "Action": [
100 |                 "sagemaker:CreateTrainingJob",
101 |                 "sagemaker:CreateHyperParameterTuningJob"
102 |             ],
103 |             "Resource": "*",
104 |             "Condition": {
105 |                 "ForAllValues:StringLike": {
106 |                     "sagemaker:InstanceTypes": ["ml.t2.large"]
107 |                 }
108 |             }
109 |         },
110 |         {
111 |             "Effect": "Allow",
112 |             "Action": [
113 |                 "cloudwatch:PutMetricData",
114 |                 "cloudwatch:GetMetricData",
115 |                 "cloudwatch:GetMetricStatistics",
116 |                 "cloudwatch:ListMetrics"
117 |             ],
118 |             "Resource": [
119 |                 "arn:aws:cloudwatch:${var.aws_region}:${data.aws_caller_identity.current.account_id}:*"
120 |             ]
121 |         },
122 |         {
123 |             "Effect": "Allow",
124 |             "Action": [
125 |                 "logs:CreateLogGroup",
126 |                 "logs:CreateLogStream",
127 |                 "logs:DescribeLogStreams",
128 |                 "logs:GetLogEvents",
129 |                 "logs:PutLogEvents"
130 |             ],
131 |             "Resource": [
132 |                 "arn:aws:logs:${var.aws_region}:${data.aws_caller_identity.current.account_id}:log-group:/aws/sagemaker/*"
133 |             ]
134 |         },
135 |         {
136 |             "Effect": "Allow",
137 |             "Action": [
138 |                 "iam:PassRole"
139 |             ],
140 |             "Resource": [
141 |                 "${aws_iam_role.sm_notebook_instance_role.arn}"
142 |             ],
143 |             "Condition": {
144 |                 "StringEquals": {
145 |                     "iam:PassedToService": "sagemaker.amazonaws.com"
146 |                 }
147 |             }
148 |         },
149 |         {
150 |             "Effect": "Allow",
151 |             "Action": [
152 |                 "iam:GetRole"
153 |             ],
154 |             "Resource": [
155 |                 "${aws_iam_role.sm_notebook_instance_role.arn}"
156 |             ]
157 |         }
158 |     ]
159 | }
160 | EOF
161 | }
162 | 


--------------------------------------------------------------------------------
/LICENSE:
--------------------------------------------------------------------------------
  1 | 
  2 |                                  Apache License
  3 |                            Version 2.0, January 2004
  4 |                         http://www.apache.org/licenses/
  5 | 
  6 |    TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
  7 | 
  8 |    1. Definitions.
  9 | 
 10 |       "License" shall mean the terms and conditions for use, reproduction,
 11 |       and distribution as defined by Sections 1 through 9 of this document.
 12 | 
 13 |       "Licensor" shall mean the copyright owner or entity authorized by
 14 |       the copyright owner that is granting the License.
 15 | 
 16 |       "Legal Entity" shall mean the union of the acting entity and all
 17 |       other entities that control, are controlled by, or are under common
 18 |       control with that entity. For the purposes of this definition,
 19 |       "control" means (i) the power, direct or indirect, to cause the
 20 |       direction or management of such entity, whether by contract or
 21 |       otherwise, or (ii) ownership of fifty percent (50%) or more of the
 22 |       outstanding shares, or (iii) beneficial ownership of such entity.
 23 | 
 24 |       "You" (or "Your") shall mean an individual or Legal Entity
 25 |       exercising permissions granted by this License.
 26 | 
 27 |       "Source" form shall mean the preferred form for making modifications,
 28 |       including but not limited to software source code, documentation
 29 |       source, and configuration files.
 30 | 
 31 |       "Object" form shall mean any form resulting from mechanical
 32 |       transformation or translation of a Source form, including but
 33 |       not limited to compiled object code, generated documentation,
 34 |       and conversions to other media types.
 35 | 
 36 |       "Work" shall mean the work of authorship, whether in Source or
 37 |       Object form, made available under the License, as indicated by a
 38 |       copyright notice that is included in or attached to the work
 39 |       (an example is provided in the Appendix below).
 40 | 
 41 |       "Derivative Works" shall mean any work, whether in Source or Object
 42 |       form, that is based on (or derived from) the Work and for which the
 43 |       editorial revisions, annotations, elaborations, or other modifications
 44 |       represent, as a whole, an original work of authorship. For the purposes
 45 |       of this License, Derivative Works shall not include works that remain
 46 |       separable from, or merely link (or bind by name) to the interfaces of,
 47 |       the Work and Derivative Works thereof.
 48 | 
 49 |       "Contribution" shall mean any work of authorship, including
 50 |       the original version of the Work and any modifications or additions
 51 |       to that Work or Derivative Works thereof, that is intentionally
 52 |       submitted to Licensor for inclusion in the Work by the copyright owner
 53 |       or by an individual or Legal Entity authorized to submit on behalf of
 54 |       the copyright owner. For the purposes of this definition, "submitted"
 55 |       means any form of electronic, verbal, or written communication sent
 56 |       to the Licensor or its representatives, including but not limited to
 57 |       communication on electronic mailing lists, source code control systems,
 58 |       and issue tracking systems that are managed by, or on behalf of, the
 59 |       Licensor for the purpose of discussing and improving the Work, but
 60 |       excluding communication that is conspicuously marked or otherwise
 61 |       designated in writing by the copyright owner as "Not a Contribution."
 62 | 
 63 |       "Contributor" shall mean Licensor and any individual or Legal Entity
 64 |       on behalf of whom a Contribution has been received by Licensor and
 65 |       subsequently incorporated within the Work.
 66 | 
 67 |    2. Grant of Copyright License. Subject to the terms and conditions of
 68 |       this License, each Contributor hereby grants to You a perpetual,
 69 |       worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 70 |       copyright license to reproduce, prepare Derivative Works of,
 71 |       publicly display, publicly perform, sublicense, and distribute the
 72 |       Work and such Derivative Works in Source or Object form.
 73 | 
 74 |    3. Grant of Patent License. Subject to the terms and conditions of
 75 |       this License, each Contributor hereby grants to You a perpetual,
 76 |       worldwide, non-exclusive, no-charge, royalty-free, irrevocable
 77 |       (except as stated in this section) patent license to make, have made,
 78 |       use, offer to sell, sell, import, and otherwise transfer the Work,
 79 |       where such license applies only to those patent claims licensable
 80 |       by such Contributor that are necessarily infringed by their
 81 |       Contribution(s) alone or by combination of their Contribution(s)
 82 |       with the Work to which such Contribution(s) was submitted. If You
 83 |       institute patent litigation against any entity (including a
 84 |       cross-claim or counterclaim in a lawsuit) alleging that the Work
 85 |       or a Contribution incorporated within the Work constitutes direct
 86 |       or contributory patent infringement, then any patent licenses
 87 |       granted to You under this License for that Work shall terminate
 88 |       as of the date such litigation is filed.
 89 | 
 90 |    4. Redistribution. You may reproduce and distribute copies of the
 91 |       Work or Derivative Works thereof in any medium, with or without
 92 |       modifications, and in Source or Object form, provided that You
 93 |       meet the following conditions:
 94 | 
 95 |       (a) You must give any other recipients of the Work or
 96 |           Derivative Works a copy of this License; and
 97 | 
 98 |       (b) You must cause any modified files to carry prominent notices
 99 |           stating that You changed the files; and
100 | 
101 |       (c) You must retain, in the Source form of any Derivative Works
102 |           that You distribute, all copyright, patent, trademark, and
103 |           attribution notices from the Source form of the Work,
104 |           excluding those notices that do not pertain to any part of
105 |           the Derivative Works; and
106 | 
107 |       (d) If the Work includes a "NOTICE" text file as part of its
108 |           distribution, then any Derivative Works that You distribute must
109 |           include a readable copy of the attribution notices contained
110 |           within such NOTICE file, excluding those notices that do not
111 |           pertain to any part of the Derivative Works, in at least one
112 |           of the following places: within a NOTICE text file distributed
113 |           as part of the Derivative Works; within the Source form or
114 |           documentation, if provided along with the Derivative Works; or,
115 |           within a display generated by the Derivative Works, if and
116 |           wherever such third-party notices normally appear. The contents
117 |           of the NOTICE file are for informational purposes only and
118 |           do not modify the License. You may add Your own attribution
119 |           notices within Derivative Works that You distribute, alongside
120 |           or as an addendum to the NOTICE text from the Work, provided
121 |           that such additional attribution notices cannot be construed
122 |           as modifying the License.
123 | 
124 |       You may add Your own copyright statement to Your modifications and
125 |       may provide additional or different license terms and conditions
126 |       for use, reproduction, or distribution of Your modifications, or
127 |       for any such Derivative Works as a whole, provided Your use,
128 |       reproduction, and distribution of the Work otherwise complies with
129 |       the conditions stated in this License.
130 | 
131 |    5. Submission of Contributions. Unless You explicitly state otherwise,
132 |       any Contribution intentionally submitted for inclusion in the Work
133 |       by You to the Licensor shall be under the terms and conditions of
134 |       this License, without any additional terms or conditions.
135 |       Notwithstanding the above, nothing herein shall supersede or modify
136 |       the terms of any separate license agreement you may have executed
137 |       with Licensor regarding such Contributions.
138 | 
139 |    6. Trademarks. This License does not grant permission to use the trade
140 |       names, trademarks, service marks, or product names of the Licensor,
141 |       except as required for reasonable and customary use in describing the
142 |       origin of the Work and reproducing the content of the NOTICE file.
143 | 
144 |    7. Disclaimer of Warranty. Unless required by applicable law or
145 |       agreed to in writing, Licensor provides the Work (and each
146 |       Contributor provides its Contributions) on an "AS IS" BASIS,
147 |       WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
148 |       implied, including, without limitation, any warranties or conditions
149 |       of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
150 |       PARTICULAR PURPOSE. You are solely responsible for determining the
151 |       appropriateness of using or redistributing the Work and assume any
152 |       risks associated with Your exercise of permissions under this License.
153 | 
154 |    8. Limitation of Liability. In no event and under no legal theory,
155 |       whether in tort (including negligence), contract, or otherwise,
156 |       unless required by applicable law (such as deliberate and grossly
157 |       negligent acts) or agreed to in writing, shall any Contributor be
158 |       liable to You for damages, including any direct, indirect, special,
159 |       incidental, or consequential damages of any character arising as a
160 |       result of this License or out of the use or inability to use the
161 |       Work (including but not limited to damages for loss of goodwill,
162 |       work stoppage, computer failure or malfunction, or any and all
163 |       other commercial damages or losses), even if such Contributor
164 |       has been advised of the possibility of such damages.
165 | 
166 |    9. Accepting Warranty or Additional Liability. While redistributing
167 |       the Work or Derivative Works thereof, You may choose to offer,
168 |       and charge a fee for, acceptance of support, warranty, indemnity,
169 |       or other liability obligations and/or rights consistent with this
170 |       License. However, in accepting such obligations, You may act only
171 |       on Your own behalf and on Your sole responsibility, not on behalf
172 |       of any other Contributor, and only if You agree to indemnify,
173 |       defend, and hold each Contributor harmless for any liability
174 |       incurred by, or claims asserted against, such Contributor by reason
175 |       of your accepting any such warranty or additional liability.
176 | 


--------------------------------------------------------------------------------
/source/notebooks/sagemaker_fraud_detection.ipynb:
--------------------------------------------------------------------------------
  1 | {
  2 |  "cells": [
  3 |   {
  4 |    "cell_type": "markdown",
  5 |    "metadata": {},
  6 |    "source": [
  7 |     "# Credit card fraud detector"
  8 |    ]
  9 |   },
 10 |   {
 11 |    "cell_type": "markdown",
 12 |    "metadata": {},
 13 |    "source": [
 14 |     "## Investigate and process the data"
 15 |    ]
 16 |   },
 17 |   {
 18 |    "cell_type": "markdown",
 19 |    "metadata": {},
 20 |    "source": [
 21 |     "Let's start by downloading and reading in the credit card fraud data set."
 22 |    ]
 23 |   },
 24 |   {
 25 |    "cell_type": "code",
 26 |    "execution_count": null,
 27 |    "metadata": {},
 28 |    "outputs": [],
 29 |    "source": [
 30 |     "%%bash\n",
 31 |     "wget https://s3-us-west-2.amazonaws.com/sagemaker-e2e-solutions/fraud-detection/creditcardfraud.zip\n",
 32 |     "unzip creditcardfraud.zip"
 33 |    ]
 34 |   },
 35 |   {
 36 |    "cell_type": "code",
 37 |    "execution_count": null,
 38 |    "metadata": {},
 39 |    "outputs": [],
 40 |    "source": [
 41 |     "import numpy as np \n",
 42 |     "import pandas as pd\n",
 43 |     "\n",
 44 |     "data = pd.read_csv('creditcard.csv', delimiter=',')"
 45 |    ]
 46 |   },
 47 |   {
 48 |    "cell_type": "markdown",
 49 |    "metadata": {},
 50 |    "source": [
 51 |     "Let's take a peek at our data (we only show a subset of the columns in the table):"
 52 |    ]
 53 |   },
 54 |   {
 55 |    "cell_type": "code",
 56 |    "execution_count": null,
 57 |    "metadata": {},
 58 |    "outputs": [],
 59 |    "source": [
 60 |     "print(data.columns)\n",
 61 |     "data[['Time', 'V1', 'V2', 'V27', 'V28', 'Amount', 'Class']].describe()"
 62 |    ]
 63 |   },
 64 |   {
 65 |    "cell_type": "markdown",
 66 |    "metadata": {},
 67 |    "source": [
 68 |     "The class column corresponds to whether or not a transaction is fradulent. We see that the majority of data is non-fraudulant with only $492$ ($.173\\%$) of the data corresponding to fraudulant examples."
 69 |    ]
 70 |   },
 71 |   {
 72 |    "cell_type": "code",
 73 |    "execution_count": null,
 74 |    "metadata": {},
 75 |    "outputs": [],
 76 |    "source": [
 77 |     "nonfrauds, frauds = data.groupby('Class').size()\n",
 78 |     "print('Number of frauds: ', frauds)\n",
 79 |     "print('Number of non-frauds: ', nonfrauds)\n",
 80 |     "print('Percentage of fradulent data:', 100.*frauds/(frauds + nonfrauds))"
 81 |    ]
 82 |   },
 83 |   {
 84 |    "cell_type": "markdown",
 85 |    "metadata": {},
 86 |    "source": [
 87 |     "This dataset has 28 columns, $V_i$ for $i=1..28$ of anonymized features along with columns for time, amount, and class. We already know that the columns $V_i$ have been normalized to have $0$ mean and unit standard deviation as the result of a PCA. You can read more about PCA here:. \n",
 88 |     "\n",
 89 |     "Tip: For our dataset this amount of preprocessing will give us reasonable accuracy, but it's important to note that there are more preprocessing steps one can use to improve accuracy . For unbalanced data sets like ours where the positive (fraudulent) examples occur much less frequently than the negative (legitimate) examples, we may try “over-sampling” the minority dataset by generating synthetic data (read about SMOTE in Data Mining for Imbalanced Datasets: An Overview (https://link.springer.com/chapter/10.1007%2F0-387-25465-X_40) or undersampling the majority class by using ensemble methods (see http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.68.6858&rep=rep1&type=pdfor)."
 90 |    ]
 91 |   },
 92 |   {
 93 |    "cell_type": "code",
 94 |    "execution_count": null,
 95 |    "metadata": {},
 96 |    "outputs": [],
 97 |    "source": [
 98 |     "feature_columns = data.columns[:-1]\n",
 99 |     "label_column = data.columns[-1]\n",
100 |     "\n",
101 |     "features = data[feature_columns].values.astype('float32')\n",
102 |     "labels = (data[label_column].values).astype('float32')"
103 |    ]
104 |   },
105 |   {
106 |    "cell_type": "markdown",
107 |    "metadata": {},
108 |    "source": [
109 |     "Let's do some analysis and discuss different ways we can preprocess our data. Let's discuss the way in which this data was preprocessed."
110 |    ]
111 |   },
112 |   {
113 |    "cell_type": "markdown",
114 |    "metadata": {},
115 |    "source": [
116 |     "## SageMaker Linear Learner"
117 |    ]
118 |   },
119 |   {
120 |    "cell_type": "markdown",
121 |    "metadata": {},
122 |    "source": [
123 |     "### Prepare Data and Upload to S3"
124 |    ]
125 |   },
126 |   {
127 |    "cell_type": "markdown",
128 |    "metadata": {},
129 |    "source": [
130 |     "The Amazon common libraries provide utilities to convert NumPy n-dimensional arrays into a the Record-IO format which SageMaker uses for a concise representation of features and labels. The Record-IO format is implemented via protocol buffer so the serialization is very efficient."
131 |    ]
132 |   },
133 |   {
134 |    "cell_type": "code",
135 |    "execution_count": null,
136 |    "metadata": {},
137 |    "outputs": [],
138 |    "source": [
139 |     "import io\n",
140 |     "import sagemaker.amazon.common as smac\n",
141 |     "\n",
142 |     "buf = io.BytesIO()\n",
143 |     "smac.write_numpy_to_dense_tensor(buf, features, labels)\n",
144 |     "buf.seek(0);"
145 |    ]
146 |   },
147 |   {
148 |    "cell_type": "markdown",
149 |    "metadata": {},
150 |    "source": [
151 |     "Now we upload the data to S3 using boto3."
152 |    ]
153 |   },
154 |   {
155 |    "cell_type": "code",
156 |    "execution_count": null,
157 |    "metadata": {},
158 |    "outputs": [],
159 |    "source": [
160 |     "import boto3\n",
161 |     "import os\n",
162 |     "import sagemaker\n",
163 |     "\n",
164 |     "session = sagemaker.Session()\n",
165 |     "bucket = \"fraud-detection-end-to-end-demo\"\n",
166 |     "\n",
167 |     "prefix = 'linear-learner'\n",
168 |     "key = 'recordio-pb-data'\n",
169 |     "boto3.resource('s3').Bucket(bucket).Object(os.path.join(prefix, 'train', key)).upload_fileobj(buf)\n",
170 |     "\n",
171 |     "s3_train_data = 's3://{}/{}/train/{}'.format(bucket, prefix, key)\n",
172 |     "print('Uploaded training data location: {}'.format(s3_train_data))\n",
173 |     "\n",
174 |     "output_location = 's3://{}/{}/output'.format(bucket, prefix)\n",
175 |     "print('Training artifacts will be uploaded to: {}'.format(output_location))"
176 |    ]
177 |   },
178 |   {
179 |    "cell_type": "markdown",
180 |    "metadata": {},
181 |    "source": [
182 |     "Now we train a Linear Learner using SageMaker's built-in algorithm. To specify the Linear Learner algorithm, we use a utility function to obtain it's URI. A complete list of build-in algorithms is found here: https://docs.aws.amazon.com/sagemaker/latest/dg/algos.html"
183 |    ]
184 |   },
185 |   {
186 |    "cell_type": "code",
187 |    "execution_count": null,
188 |    "metadata": {},
189 |    "outputs": [],
190 |    "source": [
191 |     "from sagemaker.amazon.amazon_estimator import get_image_uri\n",
192 |     "\n",
193 |     "container = get_image_uri(boto3.Session().region_name, 'linear-learner')"
194 |    ]
195 |   },
196 |   {
197 |    "cell_type": "markdown",
198 |    "metadata": {},
199 |    "source": [
200 |     "SageMaker abstracts training with Estimators. We can pass container, and all parameters to the estimator, as well as the hyperparameters for the linear learner and fit the estimator to the data in S3."
201 |    ]
202 |   },
203 |   {
204 |    "cell_type": "code",
205 |    "execution_count": null,
206 |    "metadata": {},
207 |    "outputs": [],
208 |    "source": [
209 |     "from sagemaker import get_execution_role\n",
210 |     "\n",
211 |     "linear = sagemaker.estimator.Estimator(container,\n",
212 |     "                                       get_execution_role(), \n",
213 |     "                                       train_instance_count=1, \n",
214 |     "                                       train_instance_type='ml.c4.xlarge',\n",
215 |     "                                       output_path=output_location,\n",
216 |     "                                       sagemaker_session=session)\n",
217 |     "linear.set_hyperparameters(feature_dim=features.shape[1],\n",
218 |     "                           predictor_type='binary_classifier',\n",
219 |     "                           mini_batch_size=200)\n",
220 |     "\n",
221 |     "linear.fit({'train': s3_train_data})"
222 |    ]
223 |   },
224 |   {
225 |    "cell_type": "markdown",
226 |    "metadata": {},
227 |    "source": [
228 |     "### Host Linear Classifier"
229 |    ]
230 |   },
231 |   {
232 |    "cell_type": "markdown",
233 |    "metadata": {},
234 |    "source": [
235 |     "Now we deploy the estimator to and endpoint."
236 |    ]
237 |   },
238 |   {
239 |    "cell_type": "code",
240 |    "execution_count": null,
241 |    "metadata": {},
242 |    "outputs": [],
243 |    "source": [
244 |     "from sagemaker.predictor import csv_serializer, json_deserializer\n",
245 |     "\n",
246 |     "linear_predictor = linear.deploy(initial_instance_count=1,\n",
247 |     "                                 endpoint_name=\"fraud-detection-endpoint\",\n",
248 |     "                                 instance_type='ml.m4.xlarge')\n",
249 |     "# Specify input and output formats.\n",
250 |     "linear_predictor.content_type = 'text/csv'\n",
251 |     "linear_predictor.serializer = csv_serializer\n",
252 |     "linear_predictor.deserializer = json_deserializer"
253 |    ]
254 |   },
255 |   {
256 |    "cell_type": "markdown",
257 |    "metadata": {},
258 |    "source": [
259 |     "## Clean up\n",
260 |     "\n",
261 |     "We will leave the prediction endpoint running at the end of this notebook so we can handle incoming event streams. However, don't forget to delete the prediction endpoint when you're done. You can do that at the Amazon SageMaker console in the Endpoints page. Or you can run `linear_predictor.delete_endpoint()`"
262 |    ]
263 |   },
264 |   {
265 |    "attachments": {},
266 |    "cell_type": "markdown",
267 |    "metadata": {},
268 |    "source": [
269 |     "\n",
270 |     "## Data Acknowledgements\n",
271 |     "\n",
272 |     "The dataset used to demonstrated the fraud detection solution has been collected and analysed during a research collaboration of Worldline and the Machine Learning Group (http://mlg.ulb.ac.be) of ULB (Université Libre de Bruxelles) on big data mining and fraud detection. More details on current and past projects on related topics are available on https://www.researchgate.net/project/Fraud-detection-5 and the page of the [DefeatFraud](https://mlg.ulb.ac.be/wordpress/portfolio_page/defeatfraud-assessment-and-validation-of-deep-feature-engineering-and-learning-solutions-for-fraud-detection/) project\n",
273 |     "We cite the following works:\n",
274 |     "* Andrea Dal Pozzolo, Olivier Caelen, Reid A. Johnson and Gianluca Bontempi. Calibrating Probability with Undersampling for Unbalanced Classification. In Symposium on Computational Intelligence and Data Mining (CIDM), IEEE, 2015\n",
275 |     "* Dal Pozzolo, Andrea; Caelen, Olivier; Le Borgne, Yann-Ael; Waterschoot, Serge; Bontempi, Gianluca. Learned lessons in credit card fraud detection from a practitioner perspective, Expert systems with applications,41,10,4915-4928,2014, Pergamon\n",
276 |     "* Dal Pozzolo, Andrea; Boracchi, Giacomo; Caelen, Olivier; Alippi, Cesare; Bontempi, Gianluca. Credit card fraud detection: a realistic modeling and a novel learning strategy, IEEE transactions on neural networks and learning systems,29,8,3784-3797,2018,IEEE\n",
277 |     "* Dal Pozzolo, Andrea Adaptive Machine learning for credit card fraud detection ULB MLG PhD thesis (supervised by G. Bontempi)\n",
278 |     "* Carcillo, Fabrizio; Dal Pozzolo, Andrea; Le Borgne, Yann-Aël; Caelen, Olivier; Mazzer, Yannis; Bontempi, Gianluca. Scarff: a scalable framework for streaming credit card fraud detection with Spark, Information fusion,41, 182-194,2018,Elsevier\n",
279 |     "* Carcillo, Fabrizio; Le Borgne, Yann-Aël; Caelen, Olivier; Bontempi, Gianluca. Streaming active learning strategies for real-life credit card fraud detection: assessment and visualization, International Journal of Data Science and Analytics, 5,4,285-300,2018,Springer International Publishing"
280 |    ]
281 |   }
282 |  ],
283 |  "metadata": {
284 |   "kernelspec": {
285 |    "display_name": "Python 2",
286 |    "language": "python",
287 |    "name": "python2"
288 |   },
289 |   "language_info": {
290 |    "codemirror_mode": {
291 |     "name": "ipython",
292 |     "version": 2
293 |    },
294 |    "file_extension": ".py",
295 |    "mimetype": "text/x-python",
296 |    "name": "python",
297 |    "nbconvert_exporter": "python",
298 |    "pygments_lexer": "ipython2",
299 |    "version": "2.7.15"
300 |   }
301 |  },
302 |  "nbformat": 4,
303 |  "nbformat_minor": 2
304 | }
305 | 


--------------------------------------------------------------------------------
/terraform/plan.txt:
--------------------------------------------------------------------------------
  1 | ❯ terraform plan
  2 | Refreshing Terraform state in-memory prior to plan...
  3 | The refreshed state will be used to calculate this plan, but will not be
  4 | persisted to local or remote state storage.
  5 | 
  6 | data.archive_file.fraud_detection_archive: Refreshing state...
  7 | data.aws_caller_identity.current: Refreshing state...
  8 | 
  9 | ------------------------------------------------------------------------
 10 | 
 11 | An execution plan has been generated and is shown below.
 12 | Resource actions are indicated with the following symbols:
 13 |   + create
 14 |  <= read (data resources)
 15 | 
 16 | Terraform will perform the following actions:
 17 | 
 18 |   # data.template_file.instance_init will be read during apply
 19 |   # (config refers to values not yet known)
 20 |  <= data "template_file" "instance_init"  {
 21 |       + id       = (known after apply)
 22 |       + rendered = (known after apply)
 23 |       + template = <<~EOT
 24 |             cd /home/ec2-user/SageMaker
 25 |             aws s3 cp s3://${function_bucket_name}-${aws_region}/fraud-detection-using-machine-learning/${function_version}/notebooks/sagemaker_fraud_detection.ipynb .
 26 |             sed -i 's/fraud-detection-end-to-end-demo/${s3_bucket_name_1}/g' sagemaker_fraud_detection.ipynb
 27 |         EOT
 28 |       + vars     = {
 29 |           + "aws_region"           = "eu-west-2"
 30 |           + "function_bucket_name" = "lamda-bucket"
 31 |           + "function_version"     = "1"
 32 |           + "s3_bucket_name_1"     = (known after apply)
 33 |         }
 34 |     }
 35 | 
 36 |   # aws_cloudwatch_event_rule.fraud_detection_scheduled_rule will be created
 37 |   + resource "aws_cloudwatch_event_rule" "fraud_detection_scheduled_rule" {
 38 |       + arn                 = (known after apply)
 39 |       + description         = "ScheduledRule"
 40 |       + id                  = (known after apply)
 41 |       + is_enabled          = false
 42 |       + name                = "fraud-detection-scheduled-rule"
 43 |       + schedule_expression = "rate(1 minute)"
 44 |       + tags                = {
 45 |           + "CreatedBy" = "terraform"
 46 |           + "Group"     = "fraud-detection"
 47 |         }
 48 |     }
 49 | 
 50 |   # aws_cloudwatch_event_target.fraud_detection will be created
 51 |   + resource "aws_cloudwatch_event_target" "fraud_detection" {
 52 |       + arn       = (known after apply)
 53 |       + id        = (known after apply)
 54 |       + rule      = "fraud-detection-scheduled-rule"
 55 |       + target_id = "TargetFunctionV1"
 56 |     }
 57 | 
 58 |   # aws_iam_policy.fraud_detection_firehose_policy will be created
 59 |   + resource "aws_iam_policy" "fraud_detection_firehose_policy" {
 60 |       + arn         = (known after apply)
 61 |       + description = "Policy for the Amazon Kinesis Data Firehose to save data to S3 bucket"
 62 |       + id          = (known after apply)
 63 |       + name        = "fraud-detection-firehose-policy"
 64 |       + path        = "/"
 65 |       + policy      = (known after apply)
 66 |     }
 67 | 
 68 |   # aws_iam_policy.fraud_detection_lambda_policy will be created
 69 |   + resource "aws_iam_policy" "fraud_detection_lambda_policy" {
 70 |       + arn         = (known after apply)
 71 |       + description = "Policy for the fraud detection function to put records into the Amazon Kinesis Data Firehose"
 72 |       + id          = (known after apply)
 73 |       + name        = "fraud-detection-lambda-policy"
 74 |       + path        = "/"
 75 |       + policy      = (known after apply)
 76 |     }
 77 | 
 78 |   # aws_iam_policy.sm_notebook_instance_policy will be created
 79 |   + resource "aws_iam_policy" "sm_notebook_instance_policy" {
 80 |       + arn         = (known after apply)
 81 |       + description = "Policy for the Notebook Instance to manage training jobs, models and endpoints"
 82 |       + id          = (known after apply)
 83 |       + name        = "sm-notebook-instance-policy"
 84 |       + path        = "/"
 85 |       + policy      = (known after apply)
 86 |     }
 87 | 
 88 |   # aws_iam_role.fraud_detection_firehose_role will be created
 89 |   + resource "aws_iam_role" "fraud_detection_firehose_role" {
 90 |       + arn                   = (known after apply)
 91 |       + assume_role_policy    = jsonencode(
 92 |             {
 93 |               + Statement = [
 94 |                   + {
 95 |                       + Action    = "sts:AssumeRole"
 96 |                       + Effect    = "Allow"
 97 |                       + Principal = {
 98 |                           + Service = "firehose.amazonaws.com"
 99 |                         }
100 |                     },
101 |                 ]
102 |               + Version   = "2012-10-17"
103 |             }
104 |         )
105 |       + create_date           = (known after apply)
106 |       + force_detach_policies = false
107 |       + id                    = (known after apply)
108 |       + max_session_duration  = 3600
109 |       + name                  = "fraud-detection-firehose-role"
110 |       + path                  = "/"
111 |       + tags                  = {
112 |           + "CreatedBy" = "terraform"
113 |           + "Group"     = "fraud-detection"
114 |         }
115 |       + unique_id             = (known after apply)
116 |     }
117 | 
118 |   # aws_iam_role.fraud_detection_lambda_role will be created
119 |   + resource "aws_iam_role" "fraud_detection_lambda_role" {
120 |       + arn                   = (known after apply)
121 |       + assume_role_policy    = jsonencode(
122 |             {
123 |               + Statement = [
124 |                   + {
125 |                       + Action    = "sts:AssumeRole"
126 |                       + Effect    = "Allow"
127 |                       + Principal = {
128 |                           + Service = "lambda.amazonaws.com"
129 |                         }
130 |                     },
131 |                 ]
132 |               + Version   = "2012-10-17"
133 |             }
134 |         )
135 |       + create_date           = (known after apply)
136 |       + force_detach_policies = false
137 |       + id                    = (known after apply)
138 |       + max_session_duration  = 3600
139 |       + name                  = "fraud-detection-lambda-role"
140 |       + path                  = "/"
141 |       + tags                  = {
142 |           + "CreatedBy" = "terraform"
143 |           + "Group"     = "fraud-detection"
144 |         }
145 |       + unique_id             = (known after apply)
146 |     }
147 | 
148 |   # aws_iam_role.sm_notebook_instance_role will be created
149 |   + resource "aws_iam_role" "sm_notebook_instance_role" {
150 |       + arn                   = (known after apply)
151 |       + assume_role_policy    = jsonencode(
152 |             {
153 |               + Statement = [
154 |                   + {
155 |                       + Action    = "sts:AssumeRole"
156 |                       + Effect    = "Allow"
157 |                       + Principal = {
158 |                           + Service = "sagemaker.amazonaws.com"
159 |                         }
160 |                     },
161 |                 ]
162 |               + Version   = "2012-10-17"
163 |             }
164 |         )
165 |       + create_date           = (known after apply)
166 |       + force_detach_policies = false
167 |       + id                    = (known after apply)
168 |       + max_session_duration  = 3600
169 |       + name                  = "sm-notebook-instance-role"
170 |       + path                  = "/"
171 |       + tags                  = {
172 |           + "CreatedBy" = "terraform"
173 |           + "Group"     = "fraud-detection"
174 |         }
175 |       + unique_id             = (known after apply)
176 |     }
177 | 
178 |   # aws_iam_role_policy_attachment.fraud_detection_firehose will be created
179 |   + resource "aws_iam_role_policy_attachment" "fraud_detection_firehose" {
180 |       + id         = (known after apply)
181 |       + policy_arn = (known after apply)
182 |       + role       = "fraud-detection-firehose-role"
183 |     }
184 | 
185 |   # aws_iam_role_policy_attachment.fraud_detection_lambda will be created
186 |   + resource "aws_iam_role_policy_attachment" "fraud_detection_lambda" {
187 |       + id         = (known after apply)
188 |       + policy_arn = (known after apply)
189 |       + role       = "fraud-detection-lambda-role"
190 |     }
191 | 
192 |   # aws_iam_role_policy_attachment.sm_notebook_instance will be created
193 |   + resource "aws_iam_role_policy_attachment" "sm_notebook_instance" {
194 |       + id         = (known after apply)
195 |       + policy_arn = (known after apply)
196 |       + role       = "sm-notebook-instance-role"
197 |     }
198 | 
199 |   # aws_kinesis_firehose_delivery_stream.fraud_detection_firehose_stream will be created
200 |   + resource "aws_kinesis_firehose_delivery_stream" "fraud_detection_firehose_stream" {
201 |       + arn            = (known after apply)
202 |       + destination    = "s3"
203 |       + destination_id = (known after apply)
204 |       + id             = (known after apply)
205 |       + name           = "fraud-detection-firehose-stream"
206 |       + tags           = {
207 |           + "CreatedBy" = "terraform"
208 |           + "Group"     = "fraud-detection"
209 |         }
210 |       + version_id     = (known after apply)
211 | 
212 |       + s3_configuration {
213 |           + bucket_arn         = (known after apply)
214 |           + buffer_interval    = 60
215 |           + buffer_size        = 100
216 |           + compression_format = "GZIP"
217 |           + prefix             = "fraud-detection/firehose/"
218 |           + role_arn           = (known after apply)
219 | 
220 |           + cloudwatch_logging_options {
221 |               + enabled         = (known after apply)
222 |               + log_group_name  = (known after apply)
223 |               + log_stream_name = (known after apply)
224 |             }
225 |         }
226 |     }
227 | 
228 |   # aws_lambda_function.fraud_detection_event_processor will be created
229 |   + resource "aws_lambda_function" "fraud_detection_event_processor" {
230 |       + arn                            = (known after apply)
231 |       + function_name                  = "fraud-detection-event-processor"
232 |       + handler                        = "index.lambda_handler"
233 |       + id                             = (known after apply)
234 |       + invoke_arn                     = (known after apply)
235 |       + last_modified                  = (known after apply)
236 |       + memory_size                    = 128
237 |       + publish                        = false
238 |       + qualified_arn                  = (known after apply)
239 |       + reserved_concurrent_executions = -1
240 |       + role                           = (known after apply)
241 |       + runtime                        = "python3.6"
242 |       + s3_bucket                      = (known after apply)
243 |       + s3_key                         = "fraud-detection-using-machine-learning/1/fraud_detection.zip"
244 |       + source_code_hash               = "drsFUujtfxWaaAyLLL8F3YTco0RyOGpAo72FGtbW+L4="
245 |       + source_code_size               = (known after apply)
246 |       + tags                           = {
247 |           + "CreatedBy" = "terraform"
248 |           + "Group"     = "fraud-detection"
249 |         }
250 |       + timeout                        = 3
251 |       + version                        = (known after apply)
252 | 
253 |       + tracing_config {
254 |           + mode = (known after apply)
255 |         }
256 |     }
257 | 
258 |   # aws_lambda_permission.fraud_detection will be created
259 |   + resource "aws_lambda_permission" "fraud_detection" {
260 |       + action        = "lambda:InvokeFunction"
261 |       + function_name = "fraud-detection-event-processor"
262 |       + id            = (known after apply)
263 |       + principal     = "events.amazonaws.com"
264 |       + source_arn    = (known after apply)
265 |       + statement_id  = (known after apply)
266 |     }
267 | 
268 |   # aws_s3_bucket.fraud_detection_function_bucket will be created
269 |   + resource "aws_s3_bucket" "fraud_detection_function_bucket" {
270 |       + acceleration_status         = (known after apply)
271 |       + acl                         = "private"
272 |       + arn                         = (known after apply)
273 |       + bucket                      = "lamda-bucket-eu-west-2"
274 |       + bucket_domain_name          = (known after apply)
275 |       + bucket_regional_domain_name = (known after apply)
276 |       + force_destroy               = false
277 |       + hosted_zone_id              = (known after apply)
278 |       + id                          = (known after apply)
279 |       + region                      = (known after apply)
280 |       + request_payer               = (known after apply)
281 |       + tags                        = {
282 |           + "CreatedBy"   = "terraform"
283 |           + "Description" = "Bucket hosting the code for fraud_detection Lambda function."
284 |           + "Group"       = "fraud-detection"
285 |         }
286 |       + website_domain              = (known after apply)
287 |       + website_endpoint            = (known after apply)
288 | 
289 |       + server_side_encryption_configuration {
290 |           + rule {
291 |               + apply_server_side_encryption_by_default {
292 |                   + sse_algorithm = "AES256"
293 |                 }
294 |             }
295 |         }
296 | 
297 |       + versioning {
298 |           + enabled    = (known after apply)
299 |           + mfa_delete = (known after apply)
300 |         }
301 |     }
302 | 
303 |   # aws_s3_bucket.s3_bucket_1 will be created
304 |   + resource "aws_s3_bucket" "s3_bucket_1" {
305 |       + acceleration_status         = (known after apply)
306 |       + acl                         = "private"
307 |       + arn                         = (known after apply)
308 |       + bucket                      = "bucket-1-eu-west-2"
309 |       + bucket_domain_name          = (known after apply)
310 |       + bucket_regional_domain_name = (known after apply)
311 |       + force_destroy               = true
312 |       + hosted_zone_id              = (known after apply)
313 |       + id                          = (known after apply)
314 |       + region                      = (known after apply)
315 |       + request_payer               = (known after apply)
316 |       + tags                        = {
317 |           + "CreatedBy"   = "terraform"
318 |           + "Description" = "Bucket for storing the Amazon SageMaker model and training data."
319 |           + "Group"       = "fraud-detection"
320 |         }
321 |       + website_domain              = (known after apply)
322 |       + website_endpoint            = (known after apply)
323 | 
324 |       + server_side_encryption_configuration {
325 |           + rule {
326 |               + apply_server_side_encryption_by_default {
327 |                   + sse_algorithm = "AES256"
328 |                 }
329 |             }
330 |         }
331 | 
332 |       + versioning {
333 |           + enabled    = (known after apply)
334 |           + mfa_delete = (known after apply)
335 |         }
336 |     }
337 | 
338 |   # aws_s3_bucket.s3_bucket_2 will be created
339 |   + resource "aws_s3_bucket" "s3_bucket_2" {
340 |       + acceleration_status         = (known after apply)
341 |       + acl                         = "private"
342 |       + arn                         = (known after apply)
343 |       + bucket                      = "bucket-2-eu-west-2"
344 |       + bucket_domain_name          = (known after apply)
345 |       + bucket_regional_domain_name = (known after apply)
346 |       + force_destroy               = true
347 |       + hosted_zone_id              = (known after apply)
348 |       + id                          = (known after apply)
349 |       + region                      = (known after apply)
350 |       + request_payer               = (known after apply)
351 |       + tags                        = {
352 |           + "CreatedBy"   = "terraform"
353 |           + "Description" = "Bucket for storing processed events for visualization features."
354 |           + "Group"       = "fraud-detection"
355 |         }
356 |       + website_domain              = (known after apply)
357 |       + website_endpoint            = (known after apply)
358 | 
359 |       + server_side_encryption_configuration {
360 |           + rule {
361 |               + apply_server_side_encryption_by_default {
362 |                   + sse_algorithm = "AES256"
363 |                 }
364 |             }
365 |         }
366 | 
367 |       + versioning {
368 |           + enabled    = (known after apply)
369 |           + mfa_delete = (known after apply)
370 |         }
371 |     }
372 | 
373 |   # aws_s3_bucket_object.s3_fraud_detection_archive will be created
374 |   + resource "aws_s3_bucket_object" "s3_fraud_detection_archive" {
375 |       + acl                    = "private"
376 |       + bucket                 = (known after apply)
377 |       + content_type           = (known after apply)
378 |       + etag                   = "45ac1e0db8aba0472ac7a2e44a8af99a"
379 |       + force_destroy          = false
380 |       + id                     = (known after apply)
381 |       + key                    = "fraud-detection-using-machine-learning/1/fraud_detection.zip"
382 |       + server_side_encryption = (known after apply)
383 |       + source                 = "./../dist/fraud_detection.zip"
384 |       + storage_class          = (known after apply)
385 |       + version_id             = (known after apply)
386 |     }
387 | 
388 |   # aws_s3_bucket_object.s3_fraud_detection_notebook will be created
389 |   + resource "aws_s3_bucket_object" "s3_fraud_detection_notebook" {
390 |       + acl                    = "private"
391 |       + bucket                 = (known after apply)
392 |       + content_type           = (known after apply)
393 |       + etag                   = "807555ee32ce7a9cb0b1d6073c6673c0"
394 |       + force_destroy          = false
395 |       + id                     = (known after apply)
396 |       + key                    = "fraud-detection-using-machine-learning/1/notebooks/sagemaker_fraud_detection.ipynb"
397 |       + server_side_encryption = (known after apply)
398 |       + source                 = "./../source/notebooks/sagemaker_fraud_detection.ipynb"
399 |       + storage_class          = (known after apply)
400 |       + version_id             = (known after apply)
401 |     }
402 | 
403 |   # aws_sagemaker_notebook_instance.basic will be created
404 |   + resource "aws_sagemaker_notebook_instance" "basic" {
405 |       + arn                    = (known after apply)
406 |       + direct_internet_access = "Enabled"
407 |       + id                     = (known after apply)
408 |       + instance_type          = "ml.t2.medium"
409 |       + lifecycle_config_name  = "BasicNotebookInstanceLifecycleConfig"
410 |       + name                   = "FraudDetectionNotebookInstance"
411 |       + role_arn               = (known after apply)
412 |       + security_groups        = (known after apply)
413 |       + tags                   = {
414 |           + "CreatedBy" = "terraform"
415 |           + "Group"     = "fraud-detection"
416 |         }
417 |     }
418 | 
419 |   # aws_sagemaker_notebook_instance_lifecycle_configuration.basic_lifecycle will be created
420 |   + resource "aws_sagemaker_notebook_instance_lifecycle_configuration" "basic_lifecycle" {
421 |       + arn      = (known after apply)
422 |       + id       = (known after apply)
423 |       + name     = "BasicNotebookInstanceLifecycleConfig"
424 |       + on_start = (known after apply)
425 |     }
426 | 
427 | Plan: 21 to add, 0 to change, 0 to destroy.
428 | 
429 | ------------------------------------------------------------------------
430 | 
431 | Note: You didn't specify an "-out" parameter to save this plan, so Terraform
432 | can't guarantee that exactly these actions will be performed if
433 | "terraform apply" is subsequently run.
434 | 
435 | ❯ 
436 | ❯ 


--------------------------------------------------------------------------------
/cloudformation/fraud-detection-using-machine-learning.template:
--------------------------------------------------------------------------------
  1 | {
  2 |     "AWSTemplateFormatVersion":"2010-09-09",
  3 |     "Description" : "(SO0056) - fraud-detection-using-machine-learning: Solution for predicting fraud events with ML using Amazon SageMaker. Version 1",
  4 |     "Parameters": {
  5 |         "S3BucketName1": {
  6 |             "Type": "String",
  7 |             "Description": "New bucket for storing the Amazon SageMaker model and training data."
  8 |         },
  9 |         "S3BucketName2": {
 10 |             "Type": "String",
 11 |             "Description": "New bucket for storing processed events for visualization features."
 12 |         },
 13 |         "KinesisFirehosePrefix": {
 14 |           "Type": "String",
 15 |           "Default": "fraud-detection/firehose/",
 16 |           "Description": "Kinesis Firehose prefix for delivery of processed events."
 17 |         }
 18 |     },
 19 |     "Metadata" : {
 20 |       "AWS::CloudFormation::Interface" : {
 21 |        "ParameterGroups" : [
 22 |         {
 23 |           "Label" : { "default":"Amazon S3 Bucket Configuration" },
 24 |           "Parameters" : [ "S3BucketName1", "S3BucketName2" ]
 25 |         },
 26 |         {
 27 |           "Label" : { "default":"Amazon Kinesis Firehose Configuration" },
 28 |           "Parameters" : [ "KinesisFirehosePrefix" ]
 29 |         }
 30 |        ],
 31 |        "ParameterLabels" : {
 32 |           "S3BucketName1" : { "default" : "Model and Data Bucket Name" },
 33 |           "S3BucketName2" : { "default" : "Results Bucket Name" },
 34 |           "KinesisFirehosePrefix" : { "default" : "Kinesis Firehose S3 Prefix" }
 35 |        }
 36 |       }
 37 |     },
 38 |     "Mappings": {
 39 |       "Function" : {
 40 |         "FraudDetection" : {
 41 |           "S3Bucket" : "%%BUCKET_NAME%%",
 42 |           "S3Key" : "fraud-detection-using-machine-learning/%%VERSION%%/fraud_detection.zip"
 43 |         }
 44 |       },
 45 |       "Notebook" : {
 46 |         "FraudDetection" : {
 47 |           "S3Bucket" : "%%BUCKET_NAME%%",
 48 |           "S3Key" : "/fraud-detection-using-machine-learning/%%VERSION%%/notebooks/sagemaker_fraud_detection.ipynb"
 49 |         }
 50 |       }
 51 |    },
 52 |    "Resources":{
 53 |       "S3Bucket1":{
 54 |          "Type":"AWS::S3::Bucket",
 55 |          "Properties":{
 56 |             "BucketName": { "Ref": "S3BucketName1"},
 57 |             "PublicAccessBlockConfiguration" : {
 58 |                 "BlockPublicAcls": true,
 59 |                 "BlockPublicPolicy": true,
 60 |                 "IgnorePublicAcls": true,
 61 |                 "RestrictPublicBuckets": true
 62 |             },
 63 |             "BucketEncryption": {
 64 |                 "ServerSideEncryptionConfiguration": [
 65 |                     "ServerSideEncryptionByDefault": {
 66 |                       "SSEAlgorithm": "AES256"
 67 |                     }
 68 |                 ]
 69 |             }
 70 |          }
 71 |       },
 72 |       "S3Bucket2":{
 73 |          "Type":"AWS::S3::Bucket",
 74 |          "Properties":{
 75 |             "BucketName": { "Ref": "S3BucketName2"},
 76 |             "PublicAccessBlockConfiguration" : {
 77 |                 "BlockPublicAcls": true,
 78 |                 "BlockPublicPolicy": true,
 79 |                 "IgnorePublicAcls": true,
 80 |                 "RestrictPublicBuckets": true
 81 |             },
 82 |             "BucketEncryption": {
 83 |                 "ServerSideEncryptionConfiguration": [
 84 |                     "ServerSideEncryptionByDefault": {
 85 |                       "SSEAlgorithm": "AES256"
 86 |                     }
 87 |                 ]
 88 |             }
 89 |          }
 90 |       },
 91 |       "BasicNotebookInstance":{
 92 |          "Type":"AWS::SageMaker::NotebookInstance",
 93 |          "Properties":{
 94 |             "InstanceType":"ml.t2.medium",
 95 |             "NotebookInstanceName":"FraudDetectionNotebookInstance",
 96 |             "RoleArn":{
 97 |                "Fn::GetAtt":[
 98 |                   "NotebookInstanceExecutionRole",
 99 |                   "Arn"
100 |                ]
101 |             },
102 |             "LifecycleConfigName":{
103 |                "Fn::GetAtt":[
104 |                   "BasicNotebookInstanceLifecycleConfig",
105 |                   "NotebookInstanceLifecycleConfigName"
106 |                ]
107 |             }
108 |          }
109 |       },
110 |       "BasicNotebookInstanceLifecycleConfig":{
111 |          "Type":"AWS::SageMaker::NotebookInstanceLifecycleConfig",
112 |          "DependsOn":[
113 |             "S3Bucket1"
114 |          ],
115 |          "Properties":{
116 |             "OnStart":[
117 |                {
118 |                   "Content":{
119 |                      "Fn::Base64": {"Fn::Join":[";",["cd /home/ec2-user/SageMaker",
120 |                                                      { "Fn::Join": ["", ["aws s3 cp s3://", { "Fn::Join": ["-", [ { "Fn::FindInMap" : [ "Notebook", "FraudDetection", "S3Bucket"]}, {"Ref": "AWS::Region"} ]] }, { "Fn::FindInMap" : [ "Notebook", "FraudDetection", "S3Key"]}, " ."]] },
121 |                                                      { "Fn::Join": ["", ["sed -i 's/fraud-detection-end-to-end-demo/", {"Ref" : "S3BucketName1"}, "/g' sagemaker_fraud_detection.ipynb"]]}
122 |                                                      ]]
123 |                      }
124 |                   }
125 |                }
126 |             ]
127 |          }
128 |       },
129 |       "NotebookInstanceExecutionRole":{
130 |          "Type":"AWS::IAM::Role",
131 |          "Properties":{
132 |             "AssumeRolePolicyDocument":{
133 |                "Version":"2012-10-17",
134 |                "Statement":[
135 |                   {
136 |                      "Effect":"Allow",
137 |                      "Principal":{
138 |                         "Service":[
139 |                            "sagemaker.amazonaws.com"
140 |                         ]
141 |                      },
142 |                      "Action":[
143 |                         "sts:AssumeRole"
144 |                      ]
145 |                   }
146 |                ]
147 |             }
148 |          }
149 |       },
150 |       "NotebookInstanceIAMPolicy":{
151 |          "Type":"AWS::IAM::Policy",
152 |          "Properties":{
153 |             "PolicyName":"sm-notebook-instance-policy",
154 |             "PolicyDocument":{
155 |                 "Version":"2012-10-17",
156 |                 "Statement":[
157 |                     {
158 |                         "Effect": "Allow",
159 |                         "Action": [
160 |                             "s3:GetBucketLocation",
161 |                             "s3:ListBucket",
162 |                             "s3:GetObject",
163 |                             "s3:PutObject",
164 |                             "s3:DeleteObject"
165 |                         ],
166 |                         "Resource": [
167 |                             { "Fn::Join": ["", ["arn:aws:s3:::", { "Ref": "S3BucketName1"}]]},
168 |                             { "Fn::Join": ["", ["arn:aws:s3:::", { "Ref": "S3BucketName1"}, "/*"]]},
169 |                             { "Fn::Join": ["", ["arn:aws:s3:::", { "Fn::Join": ["-", [ { "Fn::FindInMap" : [ "Notebook", "FraudDetection", "S3Bucket"]}, {"Ref": "AWS::Region"} ]] }, "/*"]]}
170 |                         ]
171 |                     },
172 |                     {
173 |                         "Effect": "Allow",
174 |                         "Action": [
175 |                             "sagemaker:CreateTrainingJob",
176 |                             "sagemaker:DescribeTrainingJob",
177 |                             "sagemaker:CreateModel",
178 |                             "sagemaker:DescribeModel",
179 |                             "sagemaker:DeleteModel",
180 |                             "sagemaker:CreateEndpoint",
181 |                             "sagemaker:CreateEndpointConfig",
182 |                             "sagemaker:DescribeEndpoint",
183 |                             "sagemaker:DescribeEndpointConfig",
184 |                             "sagemaker:DeleteEndpoint"
185 |                         ],
186 |                         "Resource": [
187 |                             { "Fn::Join" : ["", ["arn:aws:sagemaker:",{"Ref" : "AWS::Region"},":",{ "Ref" : "AWS::AccountId" }, ":*" ]]}
188 |                         ]
189 |                     },
190 |                     {
191 |                         "Effect": "Allow",
192 |                         "Action": [
193 |                             "ecr:GetDownloadUrlForLayer",
194 |                             "ecr:BatchGetImage",
195 |                             "ecr:BatchCheckLayerAvailability",
196 |                         ],
197 |                         "Resource": [
198 |                             { "Fn::Join" : ["", ["arn:aws:ecr:",{"Ref" : "AWS::Region"},":",{ "Ref" : "AWS::AccountId" }, ":repository/*" ]]}
199 |                         ]
200 |                     },
201 |                     {
202 |                         "Effect": "Allow",
203 |                         "Action": [
204 |                             "ec2:CreateVpcEndpoint",
205 |                             "ec2:DescribeRouteTables"
206 |                         ],
207 |                         "Resource": "*"
208 |                     },
209 |                     {
210 |                         "Effect": "Allow",
211 |                         "Action": [
212 |                             "cloudwatch:PutMetricData",
213 |                             "cloudwatch:GetMetricData",
214 |                             "cloudwatch:GetMetricStatistics",
215 |                             "cloudwatch:ListMetrics"
216 |                         ],
217 |                         "Resource": [
218 |                             { "Fn::Join" : ["", ["arn:aws:cloudwatch:",{"Ref" : "AWS::Region"},":",{ "Ref" : "AWS::AccountId" }, ":*" ]]},
219 |                         ]
220 |                     },
221 |                     {
222 |                       "Effect": "Allow",
223 |                       "Action": [
224 |                         "logs:CreateLogGroup",
225 |                         "logs:CreateLogStream",
226 |                         "logs:DescribeLogStreams",
227 |                         "logs:GetLogEvents",
228 |                         "logs:PutLogEvents"
229 |                       ],
230 |                       "Resource": { "Fn::Join" : ["", ["arn:aws:logs:",{"Ref" : "AWS::Region"},":",{ "Ref" : "AWS::AccountId" }, ":log-group:/aws/sagemaker/*" ]]}
231 |                     },
232 |                     {
233 |                         "Effect": "Allow",
234 |                         "Action": [
235 |                             "iam:PassRole"
236 |                         ],
237 |                         "Resource": [
238 |                             {"Fn::GetAtt":["NotebookInstanceExecutionRole","Arn"]}
239 | 
240 |                             ],
241 |                         "Condition": {
242 |                             "StringEquals": {
243 |                                 "iam:PassedToService": "sagemaker.amazonaws.com"
244 |                             }
245 |                         }
246 |                     },
247 |                     {
248 |                         "Effect": "Allow",
249 |                         "Action": [
250 |                             "iam:GetRole"
251 |                         ],
252 |                         "Resource": [
253 |                             {"Fn::GetAtt":["NotebookInstanceExecutionRole","Arn"]}
254 |                         ]
255 |                     }
256 |                  ]
257 |             },
258 |             "Roles":[
259 |                {
260 |                   "Ref":"NotebookInstanceExecutionRole"
261 |                }
262 |             ]
263 |          }
264 |       },
265 |       "LambdaFunction":{
266 |          "Type":"AWS::Lambda::Function",
267 |          "Properties":{
268 |             "Handler":"index.lambda_handler",
269 |             "FunctionName":"fraud-detection-event-processor",
270 |             "Role":{
271 |                "Fn::GetAtt":[
272 |                   "LambdaExecutionRole",
273 |                   "Arn"
274 |                ]
275 |             },
276 |             "Code": {
277 |               "S3Bucket": { "Fn::Join": ["-", [ { "Fn::FindInMap" : [ "Function", "FraudDetection", "S3Bucket"]}, {"Ref": "AWS::Region"} ]] },
278 |               "S3Key": { "Fn::FindInMap" : [ "Function", "FraudDetection", "S3Key"]}
279 |             },
280 |             "Runtime":"python3.6"
281 |          }
282 |       },
283 |       "ScheduledRule":{
284 |          "Type":"AWS::Events::Rule",
285 |          "Properties":{
286 |             "Description":"ScheduledRule",
287 |             "ScheduleExpression":"rate(1 minute)",
288 |             "State":"DISABLED",
289 |             "Targets":[
290 |                {
291 |                   "Arn":{
292 |                      "Fn::GetAtt":[
293 |                         "LambdaFunction",
294 |                         "Arn"
295 |                      ]
296 |                   },
297 |                   "Id":"TargetFunctionV1"
298 |                }
299 |             ]
300 |          }
301 |       },
302 |       "PermissionForEventsToInvokeLambda":{
303 |          "Type":"AWS::Lambda::Permission",
304 |          "Properties":{
305 |             "FunctionName":{
306 |                "Ref":"LambdaFunction"
307 |             },
308 |             "Action":"lambda:InvokeFunction",
309 |             "Principal":"events.amazonaws.com",
310 |             "SourceArn":{
311 |                "Fn::GetAtt":[
312 |                   "ScheduledRule",
313 |                   "Arn"
314 |                ]
315 |             }
316 |          }
317 |       },
318 |       "LambdaExecutionRole":{
319 |          "Type":"AWS::IAM::Role",
320 |          "Properties":{
321 |             "AssumeRolePolicyDocument":{
322 |                "Version":"2012-10-17",
323 |                "Statement":[
324 |                   {
325 |                      "Effect":"Allow",
326 |                      "Principal":{
327 |                         "Service":[
328 |                            "lambda.amazonaws.com"
329 |                         ]
330 |                      },
331 |                      "Action":[
332 |                         "sts:AssumeRole"
333 |                      ]
334 |                   }
335 |                ]
336 |             },
337 |             "Path":"/",
338 |             "Policies":[
339 |                {
340 |                   "PolicyName":"root",
341 |                   "PolicyDocument":{
342 |                      "Version":"2012-10-17",
343 |                      "Statement":[
344 |                         {
345 |                            "Effect":"Allow",
346 |                            "Action":[
347 |                               "logs:CreateLogGroup",
348 |                               "logs:CreateLogStream",
349 |                               "logs:PutLogEvents"
350 |                            ],
351 |                            "Resource": { "Fn::Join" : ["", ["arn:aws:logs:",{"Ref" : "AWS::Region"},":",{ "Ref" : "AWS::AccountId" }, ":log-group:/aws/lambda/*" ]]}
352 |                         },
353 |                         {
354 |                            "Effect":"Allow",
355 |                            "Action":[
356 |                               "sagemaker:InvokeEndpoint"
357 |                            ],
358 |                            "Resource":[
359 |                                 "arn:aws:sagemaker:*:*:endpoint/*"
360 |                             ]
361 |                         },
362 |                         {
363 |                            "Effect":"Allow",
364 |                            "Action":[
365 |                               "firehose:PutRecord",
366 |                               "firehose:PutRecordBatch"
367 |                            ],
368 |                            "Resource":{
369 |                              "Fn::GetAtt":[
370 |                                 "KinesisFirehoseDeliveryStream",
371 |                                 "Arn"
372 |                              ]
373 |                            }
374 |                         }
375 | 
376 |                      ]
377 |                   }
378 |                }
379 |             ]
380 |          }
381 |       },
382 |       "KinesisFirehoseDeliveryStream":{
383 |          "Type":"AWS::KinesisFirehose::DeliveryStream",
384 |          "Properties":{
385 |             "DeliveryStreamName":"fraud-detection-firehose-stream",
386 |             "DeliveryStreamType":"DirectPut",
387 |             "S3DestinationConfiguration":{
388 |                "BucketARN":{
389 |                  "Fn::GetAtt":[
390 |                     "S3Bucket2",
391 |                     "Arn"
392 |                  ]
393 |                },
394 |                "Prefix": {"Ref": "KinesisFirehosePrefix"},
395 |                "BufferingHints":{
396 |                   "IntervalInSeconds":60,
397 |                   "SizeInMBs":100
398 |                },
399 |                "CompressionFormat":"GZIP",
400 |                "EncryptionConfiguration":{
401 |                   "NoEncryptionConfig":"NoEncryption"
402 |                },
403 |                "RoleARN":{
404 |                   "Fn::GetAtt":[
405 |                      "FirehoseDeliveryIAMRole",
406 |                      "Arn"
407 |                   ]
408 |                }
409 |             }
410 |          },
411 |          "DependsOn":[
412 |             "FirehoseDeliveryIAMPolicy"
413 |          ]
414 |       },
415 |       "FirehoseDeliveryIAMRole":{
416 |          "Type":"AWS::IAM::Role",
417 |          "Properties":{
418 |             "AssumeRolePolicyDocument":{
419 |                "Version":"2012-10-17",
420 |                "Statement":[
421 |                   {
422 |                      "Sid":"",
423 |                      "Effect":"Allow",
424 |                      "Principal":{
425 |                         "Service":"firehose.amazonaws.com"
426 |                      },
427 |                      "Action":[
428 |                         "sts:AssumeRole"
429 |                      ]
430 |                   }
431 |                ]
432 |             }
433 |          }
434 |       },
435 |       "FirehoseDeliveryIAMPolicy":{
436 |          "Type":"AWS::IAM::Policy",
437 |          "Properties":{
438 |             "PolicyName":"fraud-detection-firehose-policy",
439 |             "PolicyDocument":{
440 |                "Version":"2012-10-17",
441 |                "Statement":[
442 |                   {
443 |                      "Effect":"Allow",
444 |                      "Action":[
445 |                         "s3:AbortMultipartUpload",
446 |                         "s3:GetBucketLocation",
447 |                         "s3:GetObject",
448 |                         "s3:ListBucket",
449 |                         "s3:ListBucketMultipartUploads",
450 |                         "s3:PutObject"
451 |                      ],
452 |                      "Resource": [{ "Fn::Join": ["", ["arn:aws:s3:::", { "Ref": "S3BucketName2"}]]},
453 |                                   { "Fn::Join": ["", ["arn:aws:s3:::", { "Ref": "S3BucketName2"}, "/",  { "Ref": "KinesisFirehosePrefix"}, "*"]]}]
454 |                   }
455 |                ]
456 |             },
457 |             "Roles":[
458 |                {
459 |                   "Ref":"FirehoseDeliveryIAMRole"
460 |                }
461 |             ]
462 |          }
463 |       }
464 |    },
465 |    "Outputs":{
466 |       "BasicNotebookInstanceId":{
467 |          "Value":{
468 |             "Ref":"BasicNotebookInstance"
469 |          }
470 |       },
471 |       "firehoseDeliveryStreamArn":{
472 |          "Description":"Firehose Delivery Stream ARN",
473 |          "Value":{
474 |             "Fn::GetAtt":[
475 |                "KinesisFirehoseDeliveryStream",
476 |                "Arn"
477 |             ]
478 |          }
479 |       },
480 |       "firehoseDeliveryRoleArn":{
481 |          "Description":"Firehose Delivery Role ARN",
482 |          "Value":{
483 |             "Fn::GetAtt":[
484 |                "FirehoseDeliveryIAMRole",
485 |                "Arn"
486 |             ]
487 |          }
488 |       }
489 |    }
490 | }
491 | 


--------------------------------------------------------------------------------
/terraform/terraform.tfstate.backup:
--------------------------------------------------------------------------------
  1 | {
  2 |   "version": 4,
  3 |   "terraform_version": "0.12.24",
  4 |   "serial": 180,
  5 |   "lineage": "bfd345ed-2c5f-6215-79ff-414bb50fa510",
  6 |   "outputs": {
  7 |     "basic_notebook_instance_id": {
  8 |       "value": "FraudDetectionNotebookInstance",
  9 |       "type": "string"
 10 |     }
 11 |   },
 12 |   "resources": [
 13 |     {
 14 |       "mode": "data",
 15 |       "type": "archive_file",
 16 |       "name": "fraud_detection_archive",
 17 |       "provider": "provider.archive",
 18 |       "instances": [
 19 |         {
 20 |           "schema_version": 0,
 21 |           "attributes": {
 22 |             "excludes": null,
 23 |             "id": "15c0d7a3b4dfba2084502adbee99d770a2a0dff6",
 24 |             "output_base64sha256": "drsFUujtfxWaaAyLLL8F3YTco0RyOGpAo72FGtbW+L4=",
 25 |             "output_md5": "45ac1e0db8aba0472ac7a2e44a8af99a",
 26 |             "output_path": "./../dist/fraud_detection.zip",
 27 |             "output_sha": "15c0d7a3b4dfba2084502adbee99d770a2a0dff6",
 28 |             "output_size": 1674,
 29 |             "source": [],
 30 |             "source_content": null,
 31 |             "source_content_filename": null,
 32 |             "source_dir": null,
 33 |             "source_file": "./../source/fraud_detection/index.py",
 34 |             "type": "zip"
 35 |           }
 36 |         }
 37 |       ]
 38 |     },
 39 |     {
 40 |       "mode": "data",
 41 |       "type": "aws_caller_identity",
 42 |       "name": "current",
 43 |       "provider": "provider.aws",
 44 |       "instances": [
 45 |         {
 46 |           "schema_version": 0,
 47 |           "attributes": {
 48 |             "account_id": "852204850242",
 49 |             "arn": "arn:aws:iam::852204850242:user/Build",
 50 |             "id": "2020-06-11 11:27:27.334709 +0000 UTC",
 51 |             "user_id": "AIDA4M226BRBENYEOT25Y"
 52 |           }
 53 |         }
 54 |       ]
 55 |     },
 56 |     {
 57 |       "mode": "data",
 58 |       "type": "template_file",
 59 |       "name": "instance_init",
 60 |       "provider": "provider.template",
 61 |       "instances": [
 62 |         {
 63 |           "schema_version": 0,
 64 |           "attributes": {
 65 |             "filename": null,
 66 |             "id": "0197965c90dbbe72ed9c9a54d1f369e4de6b35e26783cdac5711a3d243d374cd",
 67 |             "rendered": "cd /home/ec2-user/SageMaker\naws s3 cp s3://lamda-bucket-eu-west-2/fraud-detection-using-machine-learning/1/notebooks/sagemaker_fraud_detection.ipynb .\nsed -i 's/fraud-detection-end-to-end-demo/bucket-1-eu-west-2/g' sagemaker_fraud_detection.ipynb",
 68 |             "template": "cd /home/ec2-user/SageMaker\naws s3 cp s3://${function_bucket_name}-${aws_region}/fraud-detection-using-machine-learning/${function_version}/notebooks/sagemaker_fraud_detection.ipynb .\nsed -i 's/fraud-detection-end-to-end-demo/${s3_bucket_name_1}/g' sagemaker_fraud_detection.ipynb",
 69 |             "vars": {
 70 |               "aws_region": "eu-west-2",
 71 |               "function_bucket_name": "lamda-bucket",
 72 |               "function_version": "1",
 73 |               "s3_bucket_name_1": "bucket-1-eu-west-2"
 74 |             }
 75 |           }
 76 |         }
 77 |       ]
 78 |     },
 79 |     {
 80 |       "mode": "managed",
 81 |       "type": "aws_iam_policy",
 82 |       "name": "sm_notebook_instance_policy",
 83 |       "provider": "provider.aws",
 84 |       "instances": [
 85 |         {
 86 |           "schema_version": 0,
 87 |           "attributes": {
 88 |             "arn": "arn:aws:iam::852204850242:policy/sm-notebook-instance-policy",
 89 |             "description": "Policy for the Notebook Instance to manage training jobs, models and endpoints",
 90 |             "id": "arn:aws:iam::852204850242:policy/sm-notebook-instance-policy",
 91 |             "name": "sm-notebook-instance-policy",
 92 |             "name_prefix": null,
 93 |             "path": "/",
 94 |             "policy": "{\n    \"Version\": \"2012-10-17\",\n    \"Statement\": [\n        {\n            \"Effect\": \"Allow\",\n            \"Action\": [\n                \"s3:GetBucketLocation\",\n                \"s3:ListBucket\",\n                \"s3:GetObject\",\n                \"s3:PutObject\",\n                \"s3:DeleteObject\"\n            ],\n            \"Resource\": [\n                \"arn:aws:s3:::bucket-1-eu-west-2\",\n                \"arn:aws:s3:::bucket-1-eu-west-2/*\",\n                \"arn:aws:s3:::lamda-bucket-eu-west-2/*\"\n            ]\n        },\n        {\n            \"Effect\": \"Allow\",\n            \"Action\": [\n                \"sagemaker:CreateTrainingJob\",\n                \"sagemaker:DescribeTrainingJob\",\n                \"sagemaker:CreateModel\",\n                \"sagemaker:DescribeModel\",\n                \"sagemaker:DeleteModel\",\n                \"sagemaker:CreateEndpoint\",\n                \"sagemaker:CreateEndpointConfig\",\n                \"sagemaker:DescribeEndpoint\",\n                \"sagemaker:DescribeEndpointConfig\",\n                \"sagemaker:DeleteEndpoint\"\n            ],\n            \"Resource\": [\n                \"arn:aws:sagemaker:eu-west-2:852204850242:*\"\n            ]\n        },\n        {\n            \"Effect\": \"Allow\",\n            \"Action\": [\n                \"ecr:GetDownloadUrlForLayer\",\n                \"ecr:BatchGetImage\",\n                \"ecr:BatchCheckLayerAvailability\"\n            ],\n            \"Resource\": [\n                \"arn:aws:ecr:eu-west-2:852204850242:repository/*\"\n            ]\n        },\n        {\n            \"Effect\": \"Allow\",\n            \"Action\": [\n                \"ec2:CreateVpcEndpoint\",\n                \"ec2:DescribeRouteTables\"\n            ],\n            \"Resource\": \"*\"\n        },\n          {\n            \"Sid\": \"EnforceInstanceType\",\n            \"Effect\": \"Allow\",\n            \"Action\": [\n                \"sagemaker:CreateTrainingJob\",\n                \"sagemaker:CreateHyperParameterTuningJob\"\n            ],\n            \"Resource\": \"*\",\n            \"Condition\": {\n                \"ForAllValues:StringLike\": {\n                    \"sagemaker:InstanceTypes\": [\"ml.t2.large\"]\n                }\n            }\n        },\n        {\n            \"Effect\": \"Allow\",\n            \"Action\": [\n                \"cloudwatch:PutMetricData\",\n                \"cloudwatch:GetMetricData\",\n                \"cloudwatch:GetMetricStatistics\",\n                \"cloudwatch:ListMetrics\"\n            ],\n            \"Resource\": [\n                \"arn:aws:cloudwatch:eu-west-2:852204850242:*\"\n            ]\n        },\n        {\n            \"Effect\": \"Allow\",\n            \"Action\": [\n                \"logs:CreateLogGroup\",\n                \"logs:CreateLogStream\",\n                \"logs:DescribeLogStreams\",\n                \"logs:GetLogEvents\",\n                \"logs:PutLogEvents\"\n            ],\n            \"Resource\": [\n                \"arn:aws:logs:eu-west-2:852204850242:log-group:/aws/sagemaker/*\"\n            ]\n        },\n        {\n            \"Effect\": \"Allow\",\n            \"Action\": [\n                \"iam:PassRole\"\n            ],\n            \"Resource\": [\n                \"arn:aws:iam::852204850242:role/sm-notebook-instance-role\"\n            ],\n            \"Condition\": {\n                \"StringEquals\": {\n                    \"iam:PassedToService\": \"sagemaker.amazonaws.com\"\n                }\n            }\n        },\n        {\n            \"Effect\": \"Allow\",\n            \"Action\": [\n                \"iam:GetRole\"\n            ],\n            \"Resource\": [\n                \"arn:aws:iam::852204850242:role/sm-notebook-instance-role\"\n            ]\n        }\n    ]\n}\n"
 95 |           },
 96 |           "private": "bnVsbA==",
 97 |           "dependencies": [
 98 |             "aws_iam_role.sm_notebook_instance_role",
 99 |             "aws_s3_bucket.fraud_detection_function_bucket",
100 |             "aws_s3_bucket.s3_bucket_1"
101 |           ]
102 |         }
103 |       ]
104 |     },
105 |     {
106 |       "mode": "managed",
107 |       "type": "aws_iam_role",
108 |       "name": "sm_notebook_instance_role",
109 |       "provider": "provider.aws",
110 |       "instances": [
111 |         {
112 |           "schema_version": 0,
113 |           "attributes": {
114 |             "arn": "arn:aws:iam::852204850242:role/sm-notebook-instance-role",
115 |             "assume_role_policy": "{\"Version\":\"2012-10-17\",\"Statement\":[{\"Effect\":\"Allow\",\"Principal\":{\"Service\":\"sagemaker.amazonaws.com\"},\"Action\":\"sts:AssumeRole\"}]}",
116 |             "create_date": "2020-06-11T11:27:51Z",
117 |             "description": "",
118 |             "force_detach_policies": false,
119 |             "id": "sm-notebook-instance-role",
120 |             "max_session_duration": 3600,
121 |             "name": "sm-notebook-instance-role",
122 |             "name_prefix": null,
123 |             "path": "/",
124 |             "permissions_boundary": null,
125 |             "tags": {
126 |               "CreatedBy": "terraform",
127 |               "Group": "fraud-detection"
128 |             },
129 |             "unique_id": "AROA4M226BRBGZXTNFI3C"
130 |           },
131 |           "private": "bnVsbA=="
132 |         }
133 |       ]
134 |     },
135 |     {
136 |       "mode": "managed",
137 |       "type": "aws_iam_role_policy_attachment",
138 |       "name": "sm_notebook_instance",
139 |       "provider": "provider.aws",
140 |       "instances": [
141 |         {
142 |           "schema_version": 0,
143 |           "attributes": {
144 |             "id": "sm-notebook-instance-role-20200611112756083600000001",
145 |             "policy_arn": "arn:aws:iam::852204850242:policy/sm-notebook-instance-policy",
146 |             "role": "sm-notebook-instance-role"
147 |           },
148 |           "private": "bnVsbA==",
149 |           "dependencies": [
150 |             "aws_iam_policy.sm_notebook_instance_policy",
151 |             "aws_iam_role.sm_notebook_instance_role",
152 |             "aws_s3_bucket.fraud_detection_function_bucket",
153 |             "aws_s3_bucket.s3_bucket_1"
154 |           ]
155 |         }
156 |       ]
157 |     },
158 |     {
159 |       "mode": "managed",
160 |       "type": "aws_s3_bucket",
161 |       "name": "fraud_detection_function_bucket",
162 |       "provider": "provider.aws",
163 |       "instances": [
164 |         {
165 |           "schema_version": 0,
166 |           "attributes": {
167 |             "acceleration_status": "",
168 |             "acl": "private",
169 |             "arn": "arn:aws:s3:::lamda-bucket-eu-west-2",
170 |             "bucket": "lamda-bucket-eu-west-2",
171 |             "bucket_domain_name": "lamda-bucket-eu-west-2.s3.amazonaws.com",
172 |             "bucket_prefix": null,
173 |             "bucket_regional_domain_name": "lamda-bucket-eu-west-2.s3.eu-west-2.amazonaws.com",
174 |             "cors_rule": [],
175 |             "force_destroy": false,
176 |             "grant": [],
177 |             "hosted_zone_id": "Z3GKZC51ZF0DB4",
178 |             "id": "lamda-bucket-eu-west-2",
179 |             "lifecycle_rule": [],
180 |             "logging": [],
181 |             "object_lock_configuration": [],
182 |             "policy": null,
183 |             "region": "eu-west-2",
184 |             "replication_configuration": [],
185 |             "request_payer": "BucketOwner",
186 |             "server_side_encryption_configuration": [
187 |               {
188 |                 "rule": [
189 |                   {
190 |                     "apply_server_side_encryption_by_default": [
191 |                       {
192 |                         "kms_master_key_id": "",
193 |                         "sse_algorithm": "AES256"
194 |                       }
195 |                     ]
196 |                   }
197 |                 ]
198 |               }
199 |             ],
200 |             "tags": {
201 |               "CreatedBy": "terraform",
202 |               "Description": "Bucket hosting the code for fraud_detection Lambda function.",
203 |               "Group": "fraud-detection"
204 |             },
205 |             "versioning": [
206 |               {
207 |                 "enabled": false,
208 |                 "mfa_delete": false
209 |               }
210 |             ],
211 |             "website": [],
212 |             "website_domain": null,
213 |             "website_endpoint": null
214 |           },
215 |           "private": "bnVsbA=="
216 |         }
217 |       ]
218 |     },
219 |     {
220 |       "mode": "managed",
221 |       "type": "aws_s3_bucket",
222 |       "name": "s3_bucket_1",
223 |       "provider": "provider.aws",
224 |       "instances": [
225 |         {
226 |           "schema_version": 0,
227 |           "attributes": {
228 |             "acceleration_status": "",
229 |             "acl": "private",
230 |             "arn": "arn:aws:s3:::bucket-1-eu-west-2",
231 |             "bucket": "bucket-1-eu-west-2",
232 |             "bucket_domain_name": "bucket-1-eu-west-2.s3.amazonaws.com",
233 |             "bucket_prefix": null,
234 |             "bucket_regional_domain_name": "bucket-1-eu-west-2.s3.eu-west-2.amazonaws.com",
235 |             "cors_rule": [],
236 |             "force_destroy": true,
237 |             "grant": [],
238 |             "hosted_zone_id": "Z3GKZC51ZF0DB4",
239 |             "id": "bucket-1-eu-west-2",
240 |             "lifecycle_rule": [],
241 |             "logging": [],
242 |             "object_lock_configuration": [],
243 |             "policy": null,
244 |             "region": "eu-west-2",
245 |             "replication_configuration": [],
246 |             "request_payer": "BucketOwner",
247 |             "server_side_encryption_configuration": [
248 |               {
249 |                 "rule": [
250 |                   {
251 |                     "apply_server_side_encryption_by_default": [
252 |                       {
253 |                         "kms_master_key_id": "",
254 |                         "sse_algorithm": "AES256"
255 |                       }
256 |                     ]
257 |                   }
258 |                 ]
259 |               }
260 |             ],
261 |             "tags": {
262 |               "CreatedBy": "terraform",
263 |               "Description": "Bucket for storing the Amazon SageMaker model and training data.",
264 |               "Group": "fraud-detection"
265 |             },
266 |             "versioning": [
267 |               {
268 |                 "enabled": false,
269 |                 "mfa_delete": false
270 |               }
271 |             ],
272 |             "website": [],
273 |             "website_domain": null,
274 |             "website_endpoint": null
275 |           },
276 |           "private": "bnVsbA=="
277 |         }
278 |       ]
279 |     },
280 |     {
281 |       "mode": "managed",
282 |       "type": "aws_s3_bucket_object",
283 |       "name": "s3_fraud_detection_archive",
284 |       "provider": "provider.aws",
285 |       "instances": [
286 |         {
287 |           "schema_version": 0,
288 |           "attributes": {
289 |             "acl": "private",
290 |             "bucket": "lamda-bucket-eu-west-2",
291 |             "cache_control": "",
292 |             "content": null,
293 |             "content_base64": null,
294 |             "content_disposition": "",
295 |             "content_encoding": "",
296 |             "content_language": "",
297 |             "content_type": "binary/octet-stream",
298 |             "etag": "45ac1e0db8aba0472ac7a2e44a8af99a",
299 |             "force_destroy": false,
300 |             "id": "fraud-detection-using-machine-learning/1/fraud_detection.zip",
301 |             "key": "fraud-detection-using-machine-learning/1/fraud_detection.zip",
302 |             "kms_key_id": null,
303 |             "metadata": null,
304 |             "object_lock_legal_hold_status": "",
305 |             "object_lock_mode": "",
306 |             "object_lock_retain_until_date": "",
307 |             "server_side_encryption": "AES256",
308 |             "source": "./../dist/fraud_detection.zip",
309 |             "storage_class": "STANDARD",
310 |             "tags": null,
311 |             "version_id": "",
312 |             "website_redirect": ""
313 |           },
314 |           "private": "bnVsbA==",
315 |           "dependencies": [
316 |             "aws_s3_bucket.fraud_detection_function_bucket"
317 |           ]
318 |         }
319 |       ]
320 |     },
321 |     {
322 |       "mode": "managed",
323 |       "type": "aws_s3_bucket_object",
324 |       "name": "s3_fraud_detection_notebook",
325 |       "provider": "provider.aws",
326 |       "instances": [
327 |         {
328 |           "schema_version": 0,
329 |           "attributes": {
330 |             "acl": "private",
331 |             "bucket": "lamda-bucket-eu-west-2",
332 |             "cache_control": "",
333 |             "content": null,
334 |             "content_base64": null,
335 |             "content_disposition": "",
336 |             "content_encoding": "",
337 |             "content_language": "",
338 |             "content_type": "binary/octet-stream",
339 |             "etag": "807555ee32ce7a9cb0b1d6073c6673c0",
340 |             "force_destroy": false,
341 |             "id": "fraud-detection-using-machine-learning/1/notebooks/sagemaker_fraud_detection.ipynb",
342 |             "key": "fraud-detection-using-machine-learning/1/notebooks/sagemaker_fraud_detection.ipynb",
343 |             "kms_key_id": null,
344 |             "metadata": null,
345 |             "object_lock_legal_hold_status": "",
346 |             "object_lock_mode": "",
347 |             "object_lock_retain_until_date": "",
348 |             "server_side_encryption": "AES256",
349 |             "source": "./../source/notebooks/sagemaker_fraud_detection.ipynb",
350 |             "storage_class": "STANDARD",
351 |             "tags": null,
352 |             "version_id": "",
353 |             "website_redirect": ""
354 |           },
355 |           "private": "bnVsbA==",
356 |           "dependencies": [
357 |             "aws_s3_bucket.fraud_detection_function_bucket"
358 |           ]
359 |         }
360 |       ]
361 |     },
362 |     {
363 |       "mode": "managed",
364 |       "type": "aws_sagemaker_notebook_instance",
365 |       "name": "basic",
366 |       "provider": "provider.aws",
367 |       "instances": [
368 |         {
369 |           "schema_version": 0,
370 |           "attributes": {
371 |             "arn": "arn:aws:sagemaker:eu-west-2:852204850242:notebook-instance/frauddetectionnotebookinstance",
372 |             "direct_internet_access": "Enabled",
373 |             "id": "FraudDetectionNotebookInstance",
374 |             "instance_type": "ml.t2.medium",
375 |             "kms_key_id": "",
376 |             "lifecycle_config_name": "BasicNotebookInstanceLifecycleConfig",
377 |             "name": "FraudDetectionNotebookInstance",
378 |             "role_arn": "arn:aws:iam::852204850242:role/sm-notebook-instance-role",
379 |             "security_groups": [],
380 |             "subnet_id": "",
381 |             "tags": {
382 |               "CreatedBy": "terraform",
383 |               "Group": "fraud-detection"
384 |             }
385 |           },
386 |           "private": "bnVsbA==",
387 |           "dependencies": [
388 |             "aws_iam_role.sm_notebook_instance_role",
389 |             "aws_s3_bucket.fraud_detection_function_bucket",
390 |             "aws_s3_bucket.s3_bucket_1",
391 |             "aws_s3_bucket_object.s3_fraud_detection_notebook",
392 |             "aws_sagemaker_notebook_instance_lifecycle_configuration.basic_lifecycle"
393 |           ]
394 |         }
395 |       ]
396 |     },
397 |     {
398 |       "mode": "managed",
399 |       "type": "aws_sagemaker_notebook_instance_lifecycle_configuration",
400 |       "name": "basic_lifecycle",
401 |       "provider": "provider.aws",
402 |       "instances": [
403 |         {
404 |           "schema_version": 0,
405 |           "attributes": {
406 |             "arn": "arn:aws:sagemaker:eu-west-2:852204850242:notebook-instance-lifecycle-config/basicnotebookinstancelifecycleconfig",
407 |             "id": "BasicNotebookInstanceLifecycleConfig",
408 |             "name": "BasicNotebookInstanceLifecycleConfig",
409 |             "on_create": null,
410 |             "on_start": "Y2QgL2hvbWUvZWMyLXVzZXIvU2FnZU1ha2VyCmF3cyBzMyBjcCBzMzovL2xhbWRhLWJ1Y2tldC1ldS13ZXN0LTIvZnJhdWQtZGV0ZWN0aW9uLXVzaW5nLW1hY2hpbmUtbGVhcm5pbmcvMS9ub3RlYm9va3Mvc2FnZW1ha2VyX2ZyYXVkX2RldGVjdGlvbi5pcHluYiAuCnNlZCAtaSAncy9mcmF1ZC1kZXRlY3Rpb24tZW5kLXRvLWVuZC1kZW1vL2J1Y2tldC0xLWV1LXdlc3QtMi9nJyBzYWdlbWFrZXJfZnJhdWRfZGV0ZWN0aW9uLmlweW5i"
411 |           },
412 |           "private": "bnVsbA==",
413 |           "dependencies": [
414 |             "aws_s3_bucket.s3_bucket_1"
415 |           ]
416 |         }
417 |       ]
418 |     }
419 |   ]
420 | }
421 | 


--------------------------------------------------------------------------------