Hamilton + AWS

examples/aws/lambda/Dockerfile

@@ -0,0 +1,10 @@
+FROM public.ecr.aws/lambda/python:3.11
+
+COPY requirements.txt ./
+RUN pip install -r requirements.txt
+
+ENV HAMILTON_TELEMETRY_ENABLED=false
+
+COPY app ./app
+
+CMD ["app.lambda_handler.lambda_handler"]

examples/aws/lambda/README.md

@@ -0,0 +1,67 @@
+# Deploy Hamilton in AWS Lambda
+
+[AWS Lambda](https://aws.amazon.com/lambda/) - serverless computation service in AWS.
+
+Here we have an example how to deploy "hello-world" AWS Lambda with Hamilton functions.
+This example is based on the official instruction: https://docs.aws.amazon.com/lambda/latest/dg/python-image.html#python-image-instructions
+
+0. Set up AWS CLI: https://docs.aws.amazon.com/cli/latest/userguide/getting-started-quickstart.html
+
+1. Docker image build:
+
+```shell
+docker build --platform linux/amd64 -t aws-lambda-hamilton .
+```
+
+2. Local tests:
+
+```shell
+docker run -p 9000:8080 aws-lambda-hamilton
+```
+
+```shell
+curl -XPOST "http://localhost:9000/2015-03-31/functions/function/invocations" -d '{"body": {"columns":["signups","spend"],"index":[0,1,2,3,4,5],"data":[[1,10],[10,10],[50,20],[100,40],[200,40],[400,50]]}}'
+```
+
+3. Create AWS ECR repository:
+
+
+```shell
+aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 111122223333.dkr.ecr.us-east-1.amazonaws.com
+```
+
+```shell
+aws ecr create-repository --repository-name aws-lambda-hamilton --region us-east-1 --image-scanning-configuration scanOnPush=true --image-tag-mutability MUTABLE
+```
+
+4. Deploy image to AWS ECR:
+
+```shell
+docker tag aws-lambda-hamilton 111122223333.dkr.ecr.us-east-1.amazonaws.com/aws-lambda-hamilton:latest
+```
+
+```shell
+docker push 111122223333.dkr.ecr.us-east-1.amazonaws.com/aws-lambda-hamilton:latest
+```
+
+4.5. Create simple AWS Lambda role (if needed):
+
+```shell
+aws iam create-role --role-name lambda-ex --assume-role-policy-document '{"Version": "2012-10-17","Statement": [{ "Effect": "Allow", "Principal": {"Service": "lambda.amazonaws.com"}, "Action": "sts:AssumeRole"}]}'
+```
+
+5. Create AWS Lambda
+
+```shell
+aws lambda create-function \
+ --function-name aws-lambda-hamilton \
+ --package-type Image \
+ --code ImageUri=111122223333.dkr.ecr.us-east-1.amazonaws.com/aws-lambda-hamilton:latest \
+ --role arn:aws:iam::111122223333:role/lambda-ex
+```
+
+6. Test AWS Lambda
+
+```shell
+aws lambda invoke --function-name aws-lambda-hamilton --cli-binary-format raw-in-base64-out --payload '{"body": {"columns":["signups","spend"],"index":[0,1,2,3,4,5],"data":[[1,10],[10,10],[50,20],[100,40],[200,40],[400,50]]}}' response.json
+```

examples/aws/lambda/app/functions.py

@@ -0,0 +1,38 @@
+import pandas as pd
+
+from hamilton.function_modifiers import extract_columns
+
+
+@extract_columns("spend", "signups")
+def raw_table(input_table: pd.DataFrame) -> pd.DataFrame:
+ return input_table
+
+
+def avg_3wk_spend(spend: pd.Series) -> pd.Series:
+ """Rolling 3 week average spend."""
+ return spend.rolling(3).mean()
+
+
+def spend_per_signup(spend: pd.Series, signups: pd.Series) -> pd.Series:
+ """The cost per signup in relation to spend."""
+ return spend / signups
+
+
+def spend_mean(spend: pd.Series) -> float:
+ """Shows function creating a scalar. In this case it computes the mean of the entire column."""
+ return spend.mean()
+
+
+def spend_zero_mean(spend: pd.Series, spend_mean: float) -> pd.Series:
+ """Shows function that takes a scalar. In this case to zero mean spend."""
+ return spend - spend_mean
+
+
+def spend_std_dev(spend: pd.Series) -> float:
+ """Function that computes the standard deviation of the spend column."""
+ return spend.std()
+
+
+def spend_zero_mean_unit_variance(spend_zero_mean: pd.Series, spend_std_dev: float) -> pd.Series:
+ """Function showing one way to make spend have zero mean and unit variance."""
+ return spend_zero_mean / spend_std_dev

examples/aws/lambda/app/lambda_handler.py

@@ -0,0 +1,24 @@
+import pandas as pd
+
+from hamilton import driver
+
+from . import functions
+
+
+def lambda_handler(event, context):
+
+ df = pd.DataFrame(**event["body"])
+
+ dr = driver.Driver({}, functions)
+
+ output_columns = [
+ "spend",
+ "signups",
+ "avg_3wk_spend",
+ "spend_per_signup",
+ "spend_zero_mean_unit_variance",
+ ]
+
+ df_result = dr.execute(output_columns, inputs={"input_table": df})
+
+ return {"statusCode": 200, "body": df_result.to_json(orient="split")}

examples/aws/lambda/requirements.txt

@@ -0,0 +1,2 @@
+pandas
+sf-hamilton