sentiment_lambda_function.py

# We need to use the low-level library to interact with SageMaker since the SageMaker API
# is not available natively through Lambda.
import boto3

# And we need the regular expression library to do some of the data processing
import re

REPLACE_NO_SPACE = re.compile("(\.)|(\;)|(\:)|(\!)|(\')|(\?)|(\,)|(\")|(\()|(\))|(\[)|(\])")
REPLACE_WITH_SPACE = re.compile("(<br\s*/><br\s*/>)|(\-)|(\/)")


def review_to_words(review):
    words = REPLACE_NO_SPACE.sub("", review.lower())
    words = REPLACE_WITH_SPACE.sub(" ", words)
    return words


def bow_encoding(words, vocabulary):
    bow = [0] * len(vocabulary)  # Start by setting the count for each word in the vocabulary to zero.
    for word in words.split():  # For each word in the string
        if word in vocabulary:  # If the word is one that occurs in the vocabulary, increase its count.
            bow[vocabulary[word]] += 1
    return bow


def lambda_handler(event, context):
    vocab = "*** ACTUAL VOCABULARY GOES HERE ***"

    words = review_to_words(event['body'])
    bow = bow_encoding(words, vocab)

    # The SageMaker runtime is what allows us to invoke the endpoint that we've created.
    runtime = boto3.Session().client('sagemaker-runtime')

    # Now we use the SageMaker runtime to invoke our endpoint, sending the review we were given
    response = runtime.invoke_endpoint(EndpointName='***ENDPOINT NAME HERE***',  # The name of the endpoint we created
                                       ContentType='text/csv',  # The data format that is expected
                                       Body=','.join([str(val) for val in bow]).encode('utf-8'))  # The actual review

    # The response is an HTTP response whose body contains the result of our inference
    result = response['Body'].read().decode('utf-8')

    # Round the result so that our web app only gets '1' or '0' as a response.
    result = round(float(result))

    return {
        'statusCode': 200,
        'headers': {'Content-Type': 'text/plain', 'Access-Control-Allow-Origin': '*'},
        'body': str(result)
    }