Beginners Guide To AWS SageMaker - Create your first ML Model

In this video we take a look at AWS SageMaker and it's machine learning capabilities. I guide you through an AWS tutorial where we build an ML model using the XGBoost algorithm. This estimates the likelihood that a bank customer will take out a Credit Deposit with the Bank.

00:00 - Intro
00:22 - What Is AWS SageMaker?
00:48 - When Do We Use SageMaker?
01:12 - Why Use AWS SageMaker?
01:47 - What The Tutorial Will Cover
02:25 - Hands On SageMaker Tutorial

Git Hub

Website

Discourse Forum

AWS - Step by Step

What AWS Say
Amazon SageMaker is a fully managed machine learning service. With SageMaker, data scientists and developers can quickly and easily build and train machine learning models, and then directly deploy them into a production-ready hosted environment. It provides an integrated Jupyter authoring notebook instance for easy access to your data sources for exploration and analysis, so you don't have to manage servers. It also provides common machine learning algorithms that are optimized to run efficiently against extremely large data in a distributed environment. With native support for bring-your-own-algorithms and frameworks, SageMaker offers flexible distributed training options that adjust to your specific workflows. Deploy a model into a secure and scalable environment by launching it with a few clicks from SageMaker Studio or the SageMaker console. Training and hosting are billed by minutes of usage, with no minimum fees and no upfront commitments.

[DecafDave]

Johnny, what do the containers mean in step 1? Is that a specific container that only has a certain machine learning algorithm, i.e. xgboost? How can I find containers for different algorithms?

[שיטל-הצ]

.Hi Johnny, Could you make another video, and focus on the data, what comes in and how we prdedict, I mean real life example, thank you

[Borolad]

Step 1 doesn't work. It just gives you the following error message:

ImportError Traceback (most recent call last)
Cell In[1], line 11
9 from IPython.display import display
10 from time import gmtime, strftime
---> 11 from sagemaker.predictor import csv_serializer
13 # Define IAM role
14 role = get_execution_role()

ImportError: cannot import name 'csv_serializer' from 'sagemaker.predictor'

**EDIT: I managed to get it working. To anybody else doing this tutorial who runs into the same problem, prior to entering Johnny's step 1 code, run these 3 lines of code in the very first cell:


import sys
!{sys.executable} -m pip install sagemaker==1.72.0 -U
!{sys.executable} -m pip install sagemaker-experiments


Apparently v2 of Sagemaker altered the functionality somehow and the original code will not work without this modification.