Use Amazon Personalize & Data in the Raw for Real-Time Recommendations:

{
	"type": "record",
	"name": "Interactions",
	"namespace": "com.amazonaws.personalize.schema",
	"fields": [
		{
			"name": "USER_ID",
			"type": "string"
		},
		{
			"name": "ITEM_ID",
			"type": "string"
		},
		{
			"name": "TIMESTAMP",
			"type": "long"
		},
		{
			"name": "EVENT_TYPE",
			"type": "string"
		}
	],
	"version": "1.0"
}      

# Here we are just importing some standard Python packages. 
# Not all of these are used in this tutorial but as you explore more 
# will be very handy so we went ahead and packaged them for you.  
 
import json
import boto3
import time
import os
import csv
 
# Here we are starting to build our standard Lambda function.
# AWS provides multiple tutorials on how to build Lambda functions 
# so we will only cover the highest level here. 
 
def lambda_handler(event, context):
 
    count=0
 
# We will define boto3 resource to access your S3 bucket 
# and we will define a boto3 client to access the Personalize endpoint.
# You will see several environment variables defined with the os.environ syntax. 
# We will talk about these variables in the how to.
 
    s3 = boto3.resource(
        's3',
        aws_access_key_id = os.environ['aws_access_key_id'],
        aws_secret_access_key = os.environ['aws_secret_access_key'],
        region_name='us-west-2'
    )
 
 
    personalize_events = boto3.client(
        service_name='personalize-events',
        aws_access_key_id = os.environ['aws_access_key_id'],
        aws_secret_access_key = os.environ['aws_secret_access_key'],
        region_name='us-west-2'
    )
 
# Here we are providing two S3 objects. 
# The first is the one you will use to automate your data stream when using the S3 
# file created trigger.
# The second is one you can use to test your function if you want to specify an S3 file.
# If you are not familiar with the Lambda os.environ variables the first S3 object allows 
# us to capture the file location and name of the file that was created and triggered our 
# Lambda (the data we want to process to send).
# Finally, we read the data into an object to process and send to Amazon Personalize.
 
 
    content_object = s3.Object(os.environ['bucket_id'],event['Records'][0]['s3']['object']['key'])
    #content_object = s3.Object(os.environ['bucket_id'], 'bucket/file')
 
    file_content = content_object.get()['Body'].read().decode('utf-8')
 
# This is a simple data format string to ensure we send data to Personalize 
# in the format we specified.
 
    p='%Y-%m-%d %H:%M:%S.%f'
 
# This is the Python function that we define to send data to Amazon Personalize.
# As you continue to build out the data you send you will be looking to add
# data points to the properties.
 
    def put_e(u,s,e,sA,eT,iI):
        personalize_events.put_events(
            trackingId = os.environ['trackingId'],
            userId= u,
            sessionId = s,
            eventList = [{
                'eventId': e,
                'sentAt': sA,
                'eventType': eT,
                'properties': json.dumps({'itemId': iI})
            }]
        )
 
# The following section is where most edits to make the Lambda 
# work for your instance will be done. 
# In this example we assume you have fully integrated Data in the Raw
# and only want to send product interactions where you have authenticated the user.
# data is a simple helper that loads and formats the JSON object we loaded from the S3 object
 
    data = json.loads("[" + file_content.replace("}\n{", "},\n{") + "]")
 
    for d in data:
        if  d["type"]=="pageload" and d["pageType"]=="product" and d["pageLabel"]!="not set" and "user" in d :
            put_e(d["user"],d["sessionId"],d["id"],int(time.mktime(time.strptime(d["createdAt"],p))),'viewed',d["pageLabel"])
            count=count+1
 
# Finally, in cases when you are manually testing the Lambda
# This will return a count of the lines you sent to Personalize
 
    return {'data_sent':str(count)}