Machine Learning Using Azureml

  1. Home
  2. Machine-learning
  3. Machine Learning Using Azureml

Tags: Machine Learning

Microsoft Azure DP-100: Designing and Implementing a Data Science Solution Exam Covered. Learn Azure Machine Learning

Last updated 2022-01-10 | 4.5

- Prepare for and Pass the Azure DP-100 Exam
- Master Data Science and Machine Learning Models using Azure ML.
- Data Processing using Python and Pandas

What you'll learn

Prepare for and Pass the Azure DP-100 Exam
Master Data Science and Machine Learning Models using Azure ML.
Data Processing using Python and Pandas
AzureML SDK for Python for complete Machine Learning Lifecycle.
Azure Automated Machine Learning for faster and efficient Machine Learning model development and deployment
Understand the concepts and intuition of Machine Learning algorithms
Build Machine Learning models within minutes
Deploy production grade Machine Learning algorithms
Deploy Machine Learning webservices in the simplest manner

* Requirements

* Basic Math is good enough. This course does not require background in Data Science. Will be great if you have one.
* Free or paid subscription to Microsoft Azure is required. It may ask for Phone and/or Credit Card for verification

Description

This course will help you and your team to build skills required to pass the most in demand and challenging, Azure DP-100 Certification exam. It will earn you one of the most in-demand certificate of Microsoft Certified: Azure Data Scientist Associate.

DP-100 is designed for Data Scientists. This exam tests your knowledge of Data Science and Machine learning to implement machine learning models on Azure. So you must know right from Machine Learning fundamentals, Python, planning and creating suitable environments in Azure, creating machine learning models as well as deploying them in production.

Why should you go for DP-100 Certification?

  • One of the very few certifications in the field of Data Science and Machine Learning.

  • You can successfully demonstrate your knowledge and abilities in the field of Data Science and Machine Learning.

  • You will improve your job prospects substantially in the field of Data Science and Machine Learning.

Key points about this course

  • Covers the most current syllabus as on May, 2021.

  • 100% syllabus of DP-100 Exam is covered.

  • Very detailed and comprehensive coverage with more than 200 lectures and 25 Hours of content

  • Crash courses on Python and Azure Fundamentals for those who are new to the world of Data Science

Machine Learning is one of the hottest and top paying skills. It's also one of the most interesting field to work on.

In this course of Machine Learning using Azure Machine Learning, we will make it even more exciting and fun to learn, create and deploy machine learning models using Azure Machine Learning Service as well as the Azure Machine Learning Studio. We will go through every concept in depth. This course not only teaches basic but also the advance techniques of Data processing, Feature Selection and Parameter Tuning which an experienced and seasoned Data Science expert typically deploys. Armed with these techniques, in a very short time, you will be able to match the results that an experienced data scientist can achieve.

This course will help you prepare for the entry to this hot career path of Machine Learning as well as the Azure DP-100: Azure Data Scientist Associate exam.

----- Exam Syllabus for DP-100 Exam -----

1. Set up an Azure Machine Learning Workspace (30-35%)

Create an Azure Machine Learning workspace

  • Create an Azure Machine Learning workspaceConfigure workspace settings

  • Manage a workspace by using Azure Machine Learning studio

Manage data objects in an Azure Machine Learning workspace

  • Register and maintain datastores

  • Create and manage datasets

Manage experiment compute contexts

  • Create a compute instance

  • Determine appropriate compute specifications for a training workload

  • Create compute targets for experiments and training


Run Experiments and Train Models (25-30%)

Create models by using Azure Machine Learning Designer

  • Create a training pipeline by using Azure Machine Learning designer

  • Ingest data in a designer pipeline

  • Use designer modules to define a pipeline data flow

  • Use custom code modules in designer

Run training scripts in an Azure Machine Learning workspace

  • Create and run an experiment by using the Azure Machine Learning SDK

  • Configure run settings for a script

  • Consume data from a dataset in an experiment by using the Azure Machine Learning SDK

Generate metrics from an experiment run

  • Log metrics from an experiment run

  • Retrieve and view experiment outputs

  • Use logs to troubleshoot experiment run errors

Automate the model training process

  • Create a pipeline by using the SDK

  • Pass data between steps in a pipeline

  • Run a pipeline

  • Monitor pipeline runs


Optimize and Manage Models (20-25%)

Use Automated ML to create optimal models

  • Use the Automated ML interface in Azure Machine Learning studio

  • Use Automated ML from the Azure Machine Learning SDK

  • Select pre-processing options

  • Determine algorithms to be searched

  • Define a primary metric

  • Get data for an Automated ML run

  • Retrieve the best model

Use Hyperdrive to tune hyperparameters

  • Select a sampling method

  • Define the search space

  • Define the primary metric

  • Define early termination options

  • Find the model that has optimal hyperparameter values

Use model explainers to interpret models

  • Select a model interpreter

  • Generate feature importance data

Manage models

  • Register a trained model

  • Monitor model usage

  • Monitor data drift


Deploy and Consume Models (20-25%)

Create production compute targets

  • Consider security for deployed services

  • Evaluate compute options for deployment

Deploy a model as a service

  • Configure deployment settings

  • Consume a deployed service

  • Troubleshoot deployment container issues

Create a pipeline for batch inferencing

  • Publish a batch inferencing pipeline

  • Run a batch inferencing pipeline and obtain outputs

Publish a designer pipeline as a web service

  • Create a target compute resource

  • Configure an Inference pipeline

  • Consume a deployed endpoint


Some feedback from previous students,

  1. "The instructor explained every concept smoothly and clearly. I'm an acountant without tech background nor excellent statistical knowledge. I do really appreciate these helpful on-hand labs and lectures. Passed the DP-100 in Dec 2020. This course really help."


  2. "Cleared DP-100 today with the help of this course. I would say this is the one of the best course to get in depth knowledge about Azure machine learning and clear the DP-100 with ease. Thank you Jitesh and team for this wonderful tutorial which helped me clear the certification."


  3. "The instructor explained math concept clearly. These math concepts are necessary as fundation of machine learning, and also are very helpful for studying DP-100 exam concepts. Passed DP-100."


I am committed to and invested in your success. I have always provided answers to all the questions and not a single question remains unanswered for more than a few days. The course is also regularly updated with newer features.

Learning data science and then further deploying Machine Learning Models have been difficult in the past. To make it easier, I have explained the concepts using very simple and day-to-day examples. Azure ML is Microsoft's way of democratizing Machine Learning. We will use this revolutionary tool to implement our models. Once learnt, you will be able to create and deploy machine learning models in less than an hour using Azure Machine Learning Studio.

Azure Machine Learning Studio is a great tool to learn to build advance models without writing a single line of code using simple drag and drop functionality. Azure Machine Learning (AzureML) is considered as a game changer in the domain of Data Science and Machine Learning.

This course has been designed keeping in mind entry level Data Scientists or no background in programming. This course will also help the data scientists to learn the AzureML tool. You can skip some of the initial lectures or run them at 2x speed, if you are already familiar with the concepts or basics of Machine Learning.

The course is very hands on and you will be able to develop your own advance models while learning,

  • Advance Data Processing methods

  • Statistical Analysis of the data using Azure Machine Learning Modules

  • MICE or Multiple Imputation By Chained Equation

  • SMOTE or Synthetic Minority Oversampling Technique

  • PCA; Principal Component Analysis

  • Two class and multiclass classifications

  • Logistic Regression

  • Decision Trees

  • Linear Regression

  • Support Vector Machine (SVM)

  • Understanding how to evaluate and score models

  • Detailed Explanation of input parameters to the models

  • How to choose the best model using Hyperparameter Tuning

  • Deploy your models as a webservice using Azure Machine Learning Studio

  • Cluster Analysis

  • K-Means Clustering

  • Feature selection using Filter-based as well as Fisher LDA of AzureML Studio

  • Recommendation system using one of the most powerful recommender of Azure Machine Learning

  • All the slides and reference material for offline reading

You will learn and master, all of the above even if you do not have any prior knowledge of programming.

This course is a complete Machine Learning course with basics covered. We will not only build the models but also explain various parameters of all those models and where we can apply them.

We would also look at

  • Steps for building an ML model.

  • Supervised and Unsupervised learning

  • Understanding the data and pre-processing

  • Different model types

  • The AzureML Cheat Sheet.

  • How to use Classification and Regression

  • What is clustering or cluster analysis

KDNuggets one of the leading forums on Data Science calls Azure Machine Learning as the next big thing in Machine Learning. It further goes on to say, "people without data science background can also build data models through drag-and-drop gestures and simple data flow diagrams."

Azure Machine Learning's library has many pre-built models that you can re-use as well as deploy them.

So, hit the enroll button and I will see you inside the course.

Best-

Who this course is for:

  • Developers who want to start a career in or wants to learn about the exciting domain of Data Science and Machine Learning
  • Existing Data Scientists who want to earn DP-100 Certification
  • Anyone who wants to learn Data Science and Machine Learning
  • Business Analysts who want to apply Data Science to solve business problems
  • Functional Experts who can take help of Machine Learning and build/test their hypothesis quickly
  • Students and non-technical professionals who want to start a career in Machine Learning
  • Data Engineers or Software Engineers who want to learn Data Science and Machine Learning

Course content

25 sections • 225 lectures

Course Introduction 4 lectures

Note on DP-100 Exam and New Studio Preview 05:07

Create Your Free Azure Account Preview 06:18

The course slides as well as Data Files for all sections Preview 00:16

Important Message About Udemy Reviews Preview 03:17

Basics of Machine Learning 7 lectures

What You Will Learn in This Section Preview 02:18

This lecture provides an overview of the section of Basics of Machine Learning and what is covered in this section.

Why Machine Learning is the Future? Preview 08:45

Why machine learning is the future? The Data explosion. We will also see some common examples of ML as well as discuss couple of case studies of Machine Learning.

What is Machine Learning? Preview 10:04

In this lecture we cover,

  • What is Machine Learning; definition and explanation
  • How machines learn? 
  • Examples of Machine Learning
  • Supervised, Unsupervised and Reinforcement Learning

Understanding various aspects of data - Type, Variables, Category Preview 08:14

In this lecture we will learn about reading and understanding the data 

  • Types of Variables 
  • Data Type and 
  • Category of the variables

Common Machine Learning Terms - Probability, Mean, Mode, Median, Range Preview 08:05

We will learn various basic terms such as Mean, Mode, Median, Range and their importance along with what is probability and how to calculate it for some simple example.

Types of Machine Learning Models - Classification, Regression, Clustering etc Preview 10:29

In this lecture, we are going to cover four fundamental model types that you would build and related algorithms. 

  • Classification
  • Regression
  • Cluster Analysis
  • Anomaly Detection

Basics of Machine Learning

Getting Started with Azure ML 5 lectures

What You Will Learn in This Section? Preview 02:08

Provides the section overview of Getting started with AzureML.

What is Azure ML and high level architecture. Preview 03:59

Overview of AzureML and its high level architecture.

Azure ML Experiment Workflow Preview 07:19

Workflow of Azure Machine Learning experiment. 

  • GET THE DATA
  • PREPARE THE DATA
  • FEATURE SELECTION
  • CHOOSE AND APPLY LEARNING ALGORITHMS
  • TRAIN AND EVALUATE THE MODEL

Azure ML Cheat Sheet for Model Selection Preview 06:01

In this lecture we will cover the Azure ML Cheat Sheet for model selection.

Getting Started with AzureML

------- DP - 100 Certification Exam --------- 1 lectures

DP-100 Exam Curriculum Preview 09:33

Azure Machine Learning with Studio Designer 1 lectures

What this Section Covers? Preview 00:17

DP-100 - Set-up Azure Machine Learning Workspace 11 lectures

Understand the AzureMLService Architecture Preview 07:57

Create the AzureML Workspace Preview 09:58

View and Manage Workspace Settings Preview 05:12

Overview of New AzureML Studio Preview 10:32

DP-100 Exam Coverage So far. Preview 01:47

What is AzureML Datastore and Dataset? Preview 06:50

Create and Register a Datastore Preview 11:53

Create a Dataset Preview 12:24

Explore the AzureML Dataset Preview 03:22

Understanding the AzureML Compute Resources Preview 08:08

Create a Compute Cluster and Compute Instance Preview 06:55

DP-100 - Run Experiments and Train Models 3 lectures

What is an AzureML Pipeline? Preview 05:59

Create a Pipeline using AzureML Designer Preview 11:44

Submit the Designer Pipeline run Preview 11:55

DP-100 Deploy and consume the models 4 lectures

Create an Inference Pipeline Preview 08:41

Deploy a real-time endpoint using Designer Preview 09:53

Create a batch inference pipeline using Designer Preview 08:20

Run a Batch Inference Pipeline from Designer Preview 05:01

Data Processing using AzureML Designer 13 lectures

Get Data to the workspace Preview 08:20

Import Data to the workspace from external sources Preview 10:31

Edit Metadata - Column Names Preview 07:58

Understanding the Run Preview 05:00

Edit Metadata - Data Type Preview 08:02

Export Data to the Blob Storage Preview 11:51

Add Columns to the Dataset Preview 05:08

Add Rows to the Dataset Preview 04:09

Normalization of Data Part 1 Preview 08:21

Normalization of Data Part 2 Preview 08:45

Clean Missing Data Preview 09:43

Partition and Sample Data Part 1 Preview 06:02

Partition and Sample Data Part 2 Preview 08:46

Classification 13 lectures

What is Logistic Regression Preview 06:54

Two Class Logistic Regression - Problem Statement Preview 05:52

Data Preparation for Two Class Classification Preview 06:15

Train the Model for Logistic Regression Preview 07:27

Evaluate the Model Part 1 Preview 04:14

Evaluate the Model - Confusion Matrix Preview 10:41

Evaluate the Model - AUC ROC Preview 05:32

Parameters of Two Class Logistics Regression Preview 08:24

What is Decision Tree? Preview 07:45

Ensemble Learning in Decision Tree Preview 03:54

Bagging and Boosting in Decision Tree Preview 04:41

Hands On - Train the Two Class Boosted Decision Tree Preview 05:58

Evaluate and Compare Decision Tree output Preview 03:18

Regression using AzureML Designer 7 lectures

What is Linear Regression? Preview 07:31

Ordinary Least Square and Common Errors Preview 06:01

Hands On - Automobile Price Predictions Data Analysis Preview 05:40

Hands On - Automobile Price Predictions Data Processing Preview 05:38

Hands On - Automobile Price Predictions Train Model Preview 05:21

Hands On - Automobile Price Predictions Evaluate Preview 07:11

R-Squared or Coefficient of Determination Preview 04:28

Designer/Classic Studio Vs Pandas and Scikit-learn 20 lectures

A note on Anaconda and Spyder. Preview 00:27

What this section is about? Preview 02:08

Pandas - Import Data for Experiments Preview 07:36

Pandas - Import Data Part 2 Preview 05:16

Select Columns using Pandas Preview 07:42

Select Columns By drop method Preview 07:43

Add columns and rows Preview 07:01

Clean Missing Data Preview 07:06

Edit Metadata of columns using Pandas Preview 04:22

Create Summary Statistics using describe Preview 07:29

Clip Values - Remove Outliers using Constants Preview 05:52

Clip Values - Remove Outliers with Percentiles Preview 07:54

Convert and Save a delimited file using Pandas Preview 07:02

Data Normalization Preview 11:51

Label Encoding of String Categorical data Preview 09:48

Why Hot encoding is required? Preview 03:30

Hot Encoding using Pandas get_dummies Preview 04:09

Split The Data for training and testing Preview 11:23

Build Logistic Regression using Python - Part 1 Preview 04:22

Build Logistic Regression using Python - Part 2 Preview 12:09

Azure Machine Learning with AzureML SDK 1 lectures

Introduction to AzureML SDK Preview 04:40

DP-100 - Set-up Azure Machine Learning Workspace 7 lectures

Create AzureML Workspace using SDK Preview 08:23

Verify the Workspace and Write the Workspace Config File Preview 03:31

Create and Register a Datastore using AzureML SDK Preview 10:56

Create and Register a Dataset using SDK Preview 11:22

Access Workspace, Datastore and Datasets using SDK Preview 11:28

Pandas Dataframe and AzureML Dataset conversions Preview 09:50

Upload local data to storage account via datastore Preview 10:20

DP-100 - Run Experiments and Train Models 23 lectures

Problem Statement - Run a sample experiment and log values Preview 02:49

Run a sample experiment using AzureML SDK - Part 1 Preview 08:38

Run a sample experiment using AzureML SDK - Part 2 Preview 10:55

Run a script in Azureml environment - Part 1 Preview 04:32

Run a script in Azureml environment - Part 2 Preview 07:28

Run a script in Azureml environment - Part 3 Preview 08:29

Run a script in Azureml environment - Part 4 Preview 07:54

Run a script in Azureml environment - Part 5 Preview 06:26

DP-100 Exam Coverage So far. Preview 02:14

Train and Run a Model Script in AzureML Part 1 Preview 06:11

Train and Run a Model Script in AzureML Part 2 Preview 10:31

Train and Run a Model Script in AzureML Part 3 Preview 10:31

Train and Run a Model Script in AzureML Part 4 Preview 05:00

Train and Run a Model Script in AzureML Part 5 Preview 09:05

Provisioning Compute Cluster using SDK Preview 11:20

Automate Model Training using AzureML SDK Preview 07:52

Automate Model Training - Define Pipeline Steps Preview 14:21

Automate Model Training - Define Run Configuration Preview 08:04

Automate Model Training - Define Build and Run Preview 06:15

Detour - Command Line Arguments Preview 11:58

Automate Model Training - Create Dataprep Step Preview 14:01

Automate Model Training - Create Training Step Preview 03:39

Run the pipeline and see the results Preview 10:13

Using Python Scripts in AzureML Designer 3 lectures

Simple Python Script in Designer Preview 06:17

Execute Python Script using Zip Bundle Preview 03:30

Execute Python Script using Zip Bundle - Hands on Preview 07:58

DP-100 - Optimize and Manage Models 1 lectures

Section Coverage Preview 00:08

Use Automated ML to Create Optimal Models 6 lectures

What is Azure AutoML? Preview 05:44

Use the Automated ML interface in Azure Machine Learning studio Preview 09:52

View the AutoML Run Result Preview 08:53

Note on Normalized Macro Recall Preview 05:15

Use Automated ML from the Azure Machine Learning SDK Preview 13:34

Retrieve the Best Model and View results Preview 08:28

Use Azure Hyperdrive to Tune Hyperparameters 7 lectures

Introduction to Azure Hyperdrive Preview 01:23

Define the Hyperparameter Search Space Preview 03:02

Select a Sampling method Preview 03:44

Define Early Termination Options Preview 10:22

Configure the Hyperdrive run Preview 17:05

Create the Training Script for Hyperdrive run Preview 05:08

Retrieve the Best Model Preview 11:38

Use model explainers to interpret models 10 lectures

Why model explanation is important? Preview 05:36

Understanding Shapley Value Preview 12:08

Interpretability Techniques in Azure Preview 07:26

Implement Interpretability - Initial Set-up Preview 03:15

Implement Interpretability - Global Explanations Preview 10:29

Implement Interpretability - Local Explanations Preview 07:38

Implement Interpretability - Local Explanations Part 2 Preview 05:37

Run Interpret Model Script in Azure Workspace Preview 06:54

Visualize Explanations in AzureML Studio Preview 07:58

Retrieve/Download Feature Importance Values. Preview 04:01

Model Registration and Deployment using AzureML SDK 18 lectures

Model Deployment Steps Preview 02:50

Understanding Model/Object Serialization Preview 08:05

Hands on - Serialization using Joblib Preview 08:01

Handling OneHotEncoding/Dummy Values in Production Preview 06:01

Hands on - Dummy Variables in Production Preview 11:54

Train the model for webservice deployment Preview 03:51

Register the Model using Run_ID Preview 09:40

Register the Model using local pkl file Preview 04:24

Retrieve all the registered models from the workspace Preview 03:08

Provisioning AKS Production Cluster using SDK Preview 07:42

Create the Inference and Deployment Configuration for Webservice Preview 08:15

Entry Script - Init Function Preview 05:59

Understanding Data processing using JSON, Dictionary and Dataframe Preview 07:01

Entry Script - run Function Preview 12:00

Create webservice deployment object Preview 05:50

Deploy a real-time endpoint using SDK Preview 06:35

Consume the web service from Python program Preview 04:37

Consume the web service as an End Point. Preview 07:08

Using Databricks with Azure Machine Learning 23 lectures

Databricks Update to DP-100 Preview 04:00

(Optional) What is Big Data? Preview 08:58

(Optional) What is Hadoop? Preview 07:33

What is Spark and Databricks? Preview 10:36

Create an Azure Databricks workspace Preview 09:15

Note on Deleting Databricks resource in Azure Portal Preview 02:46

Note on Increasing vCPU Quota Limits Preview 03:42

Create an Azure Databricks cluster Preview 08:06

Link AzureML Workspace with the Databricks Workspace Preview 04:42

Create and run notebooks in Azure Databricks Part-1 Preview 04:22

Create and run notebooks in Azure Databricks Part-2 Preview 07:43

Mount Blob storage to Databricks using dbutils Part-1 Preview 10:59

Mount Blob storage to Databricks using dbutils Part-2 Preview 07:18

Run an sklearn experiment with Databricks Notebook Preview 06:36

Overview to Run a Training script using DatabricksStep in a pipeline Preview 10:43

Saving data to Azure Blob storage from Databricks Preview 10:26

Passing parameters between Azure Databricks notebooks Preview 05:09

Attach a Databricks Cluster as an Attached Compute Target Preview 11:01

Verify Databricks Cluster as Attached Compute Preview 01:49

Databricks Pipeline - Initial Set-up Preview 06:18

Databricks Pipeline - Build DatabricksStep Preview 12:46

Databricks Pipeline - Databricks and Python notebook Preview 06:44

Databricks Pipeline - Submit the pipeline and verify the output Preview 08:30

Python Crash Course 28 lectures

An Important Note. Preview 00:14

Install Anaconda Preview 05:26

Hello World and Know your environment Preview 05:38

Variable Types in Python Preview 09:19

Conditional Statements in Python Preview 06:03

Python Loops explained. Preview 02:40

While Loops in Python Preview 05:35

For Loop in Python Preview 05:17

Python Lists Preview 01:57

Python Lists - Operations Part 1 Preview 04:09

Python Lists - Operations Part 2 Preview 02:32

Multidimensional Lists in Python Preview 04:32

Slicing a multidimensional list Preview 05:56

Python Tuples Preview 03:47

Python Dictionary Preview 03:40

Python Dictionary Hands on Part 1 Preview 04:55

Python Dictionary Hands on Part 2 Preview 04:21

Python Functions Preview 05:08

Python Functions - Hands on Preview 05:36

Global Vs Local Variables in Python Preview 08:39

Types of Function Arguments Preview 04:24

Function Arguments - Required Arguments Preview 07:49

Function Arguments - Default Arguments Preview 05:56

Function Arguments - Keyword Arguments Preview 07:49

Object Oriented Programming Preview 11:33

Define a Class and Create an Object Preview 14:54

Initialize the Class Attributes using __init__ Preview 08:56

Packages and Modules in Python Preview 05:58

Azure Fundamentals 7 lectures

What is Cloud Computing? Preview 08:03

What is Azure? Preview 04:11

Azure Basic Terms and Concepts Preview 05:09

Azure Storage and Data Resource Preview 09:33

Azure Storage hands on Preview 12:20

Azure Compute/Virtual Machines Preview 04:18

Dockers and Azure Container Registry Preview 05:47

Thank You and Bonus Lecture 2 lectures

Way Forward Preview 04:46

Bonus Lecture Preview 03:08