RADACAD run professional training on Data Science and Advanced Analytics. Our trainer is a world-class speaker and mentor for Advanced Analytics, Dr. Leila Etaati. This course run both in-person and online. Online courses cover major time zones. RADACAD Also provide custom training for organizations. For custom training options please email us (training@radacad.com).

Power BI Training Modules:

all of the modules below are available in-person and live-online instructor-led. We do offer training as onsite private training sessions all around the world, and in some selected cities as public.

Upcoming Public Training Courses

If you can’t find your city or timezone here, contact us for an onsite private training session.

[add_eventon_el cal_id=”eventlist” el_title=”Upcoming Courses” number_of_months=”12″ etop_month=”yes” show_et_ft_img=”yes” event_type_2=”324″]

Video Training:

If you want to learn Power BI and AI at your own pace, check out our video courses below:

Course Title: Data Science and Advanced Analytics with Microsoft Technologies

 

Length:

From 1 to 7 days (Lecture + Labs): depends on the modules you enroll.

Delivery method:

In-Person or Online: Check the schedule of upcoming courses.

Type of training:

Public or private (contact us for more details)

 

The well-known worldwide training in Microsoft Advanced Analytics field on the planet from one to seven days of training delivered by the well-known experts and MVPs, authors of books, and speakers of many conferences themselves. In this training course, you will learn some basic concepts for Machine Learning, Predictive and Descriptive analytics. You learn how to write R codes for the aim of data wrangling, data modeling, data visualization, and machine learning.  Moreover, you will learn how to use custom AI tools like Azure Machine learning for creating your desire model, deploy it and use it as web service in other applications and scenarios like the Internet of Things (IoT). You will learn about how to use R in a dashboard, how to R in the cloud and on-premises storage. You will learn how to use pre-build AI tools like Bot and cognitive services to create smart report and applications. Expect learning best practices with great scenarios in this course. This course is designed in separate modules based on the type of audience. If you are a data scientist, data analyst, business intelligence developer, or data architect, this course has many things to teach you all.

This course is delivered to thousands of people all around the world, check out only a few of the recommendations at the bottom of this page, and check some of our clients.

 

 

Instructor: Dr. Leila Etaati

 

Our trainer is the world well-known name in the Microsoft Data Science field. Leila Etaati is Microsoft AI, and Data Platform (Most Valuable Professional) focused on AI and BI Microsoft technologies; Microsoft has awarded her MVP because of her dedication and expertise in Microsoft BI technologies from 2016 till now, she is one of two AI MVP in Australia and New Zealand. She is a speaker in world’s best and biggest Microsoft Data Platform, BI and Power BI, AI conferences such as Microsoft Ignite, Microsoft Business Applications Summit, Microsoft Data Insight Summit, PASS Summits, PASS Rallys, SQLBits, TechEds, and so on.  She is the author of some books on this topic, and she has more than 11 years’ experience in the Microsoft BI technologies and Data science. Leila is the co-founder of RADACAD and a consultant for more than seven years.

 

Advanced Analytics with Microsoft Technologies

This is the most comprehensive course for Microsoft Advanced Analytics and Data Science on the planet which split into modules. You can enroll in any of these modules separately or take the whole course. Modules designed independently, which means each module can be taken regardless of the order of modules. Here are a list and detailed agenda of each module:

• Module 1: Power BI for Data Scientists (2 days)
• Module 2: Data Science with Microsoft Cloud (2-days)
• Module 3: Advanced Data Science with Microsoft Services (2-days)
• Module 4: AI and Cognitive Services in Applications (1-day)

 

Module 1: Power BI for Data Scientists – 2 days course

 

This training is designed for people who want to do Machine Learning (ML) inside Power BI. In this training, you will learn different ways to use R languages for the aim of machine learning, visualization, data cleaning in Power BI.

In this two days training, you will learn some main concepts of machine learning.  You will learn some basics of R language and How to use it in Power BI visualization, Power Query (data wrangler part of Power BI), and how to use it for creating custom visual. Also, the training will cover some of the main algorithms for machine learning such as Predictive analytics (Decision-Tree, Decision Forest, KNN, SVM), Descriptive analysis (Clustering, Market Basket Analysis) and Forecasting (Time Series). Finally the pre-build advanced analytics visual in Power BI Marketplace will be explained and how to use them will be clarified.

At the end of this training, you will able to write R code in Power BI report and Power Query, create custom visual with the help of JSON codes and R scripts,

The training includes but not limited to topics below:

1.1: Introduction to R

R is a statistical language that has been used for many years for the aim of machine learning, statistical analytics, data wrangling, data visualization and so forth. There is a possibility to embed R codes inside Power BI to create more smart applications. In this module, we will go through the basics of R language and introduce some of the main R functions and commands such as statistical summary, package concepts, read data from SQL Server, Azure and so forth, visualization command, loop, and so forth. You will see some demos and introduction about:

• Introduction to R Language: What is R?
• RStudio; The First Experience
  • Install Rstudio
  • RStudio Environment
• R basic Command
  • Data Structure such as Data Frame, Vector, and Lists
  • Import Data from the local machine, SQL Server, Azure Data Lake and so forth.
  • Check the Statistical Summary of data
  • Check the Structure Summary of Data
  • Use existing Package and how to Install New Packages
  •  Create Basic Chart such as Histogram and Box Plot for better Understanding data
  • And some other useful commands

1.2: Introduction to Machine Learning

In this section, some introduction to Machine learning will be provided. The audience will learn what Artificial Intelligence is, what is Machine Learning, who is Data Scientists, who is data Analyst, and What is Deep learning.  Also, some explanations on what descriptive and predictive analytics are will be provided.  In this module audience will learn:

• What is Descriptive Analytics
• What is Predictive Analytics
• What is Forecasting
• What Languages exist for Machine Learning and what is the main difference

 

1.3: Use R in Power BI Report for Visualization

Power BI consists of different components such as Power BI visualization, Power Query, Power BI services and so forth. Power BI visualization has lots of interesting and useful chart to visual data and creates business reports. However, customer need can be varied; each customer may need different visual that not available in Power BI visualization pan. In this module

• How to set up R in Power BI visualization will be explained
• How to use R visual in Power BI will be shown
• R editor in Power BI will be explained, and all feature such as setting, how to debug code in RStudio, and how to run will be explained.
• How to draw some basic charts like Histogram, Boxplot, table (gride) will be shown.
• The audience will see how to use the ggplot2 package for drawing the more complex visualization
• They will learn how to create a table chart with four, and five dimensions
• The audience will learn how to create different bar chart, polar chart by writing simple R codes
• How to create a colorful chart in Power BI using R will be explained

 

1.4: Use R in Power Query

Power Query is one of the main important components in Power BI that is used for data cleaning and wrangling. Power Query is a comprehensive component for extracting data from different locations, clean the data and load it (ETL). The main language behind the scene of Power Query is M. In this module, you will see how we can use R scripts in Power query for storing data in local machine or other devices, creating loops, normalizing the data, and Machine Learning.

The content that you will learn in this module includes but not limited to;

• How to access the R editor and how to use it
• How to store the dataset from Power Query in a local machine
• How to access the R editor in Power query and how to run the R scripts
• How to use R to apply a loop on a dataset/column
• How to expand the regular expression language
• How to access the R codes in Power query advanced editor

 

1.5: Predictive Analytics in Power BI

Some explanation on what predictive analytics is will be provided. The main algorithms for classification and regression will be introduced. The main concepts of some algorithms for classification and regression such as Decision tree, KNN, linear and non-linear regression will be explained.

The content that you will learn in this module includes but not limited to;

• What is predictive analytics and what algorithms we use for predictive analytics
• Main concepts for the decision tree, SVM, regression, and KNN will be provided
• How to use decision tree algorithms (with related R codes) for the aim of classification in Power Query will be explained
• How to use regression algorithm for predicting a value in power Query will be shown
• How to parametrize the algorithm in Power Query for future use will be explained

 

1.6: Descriptive Analytics in Power BI

In this module, a brief explanation of what is descriptive analytics, what is clustering, what is market basket analytics will be provided. Audience will learn

• Basic concepts for clustering and market basket analytics
• How to write R scripts and what function has been used
• How to do Clustering in Power BI visualization and Power Query

 

1.7: Time series with R in Power BI

Forecasting is a popular and useful trend in many industries. Time series is an algorithm that has been used for forecasting the trend, pattern and future value for their sales, profit and so forth. In this module below item will be presented

• What is Time series and what are the main concepts behind it
• How to write R scripts for time series decomposition, forecasting using exponential smoothing and so forth.
• How to do forecasting in Power BI report and Power Query

1.8: Pre-build Advanced Analytics Visualization

Microsoft provides lots of interesting advanced analytics chart in the marketplace for Power BI users. This charts able end user to use them for analytics without writing any R scripts.

• How to access the Power BI advanced analytics visualization in Marketplace
• What is decision tree visualization and how to use it
• What is time series visualizations?
• How to use clustering and correlation analytics visualization

1.9: Create Custom Visual with R and JSON Scripts

There is a possibility to expand the visualization in Power BI with creating custom visual. These visuals have some difference from what we have in section 1-3. These custom visuals can be shared with others easily without disclosing the code behind them. These visualizations can be put in a list of visual for other people in the company. In this section.

• How to create custom visual with R
• How to use the Power BI template for it
• How to create a proper setting and so forth

 

 

Module 2: Data Science with Microsoft Cloud – 2 days course

 

This training is designed for data scientists, data developer or data architecture, who have the data in the cloud or thinking about using Microsoft machine learning tools in cloud scale. In this training, you will get familiar with machine learning cloud possibilities.

In this course, you will learn how to Azure ML Studio as the first tool for machine learning cloud that introduced in 2014. The detail on how to create a model, how to enhance machine learning algorithms, how to import data and so forth will be explained. Then, you will get familiar with Azure Data Science Virtual Machine as a comprehensive tool for machine learning, some of the tools in it like the Tensor flow and Azure ML workbench will be explained. Then, how to do machine learning in Azure Data Lake store will be explained. Finally, Azure Data Bricks and how to use it for the aim of machine learning will be explained too.  This training has many hands-on labs, and all the required scenario will be explained step by step.

At the end of this training, the audience will learn how to define a machine learning problem and how to use Azure ML Studio for cloud machine learning, and also how to use Azure data Lake Analytics, Azure Data Bricks and so forth for machine learning.

The training includes but not limited to topics below:

2.1: Azure Machine Learning (ML) Studio

In this section, you will learn some basic of machine learning and how it works. Then some introduction to Azure ML Studio will be provided.

• Import data: The main component for importing data from local PC, how to import data from another workspace, how to import data from HTML website, how to import data from cloud such as Azure SQL DB.
• Data Cleaning: data cleaning is the main process that we should do before any machine learning process. I will explain the available component in Azure ML. How to clean missing values, remove duplicate data, select column, clip value (remove outliers), group data into bins, and create an indicator for data. You will learn how to normalize the data, how to use SQL Statement for data transformation, how to use enter data manually, how to edit the data type, change the column name with edit metadata component, how to join data from different data resource , how to increase the number of low incidence in a dataset which unbalanced.
• Feature Selection Data Sampling: the process of feature selection will be explained, how to split data, how to partition data using a sampling approach, how to create different folds for the aim of cross-validation.
• Models: a bit talk about the available models in Azure mL for predictive, descriptive, prescriptive and anomaly detection. An example of a prediction of a group, a value, clustering data and anomaly detection will be shown. For each scenario, an example will be presented; different algorithms will apply to a problem. The main concepts of k-mean, how to use elbow chart to identify the number of the cluster will be discussed, the PCA chart will be explained. The trained model for recommendation “match box recommender” will be explained through a scenario. The main concepts of collaborative filtering and content-based filtering and hybrid approach for recommendation will be discussed.
• Training and Scoring models: how to choose algorithms and how to train model and test model, what is cross-validation, how to do cross-validation to apply a model to different folds of data, how to check the different values for each parameter and see the related accuracy to that.
• Evaluate: how to evaluate a classification problem concepts of Accuracy, Recall, Precision, AUC will be discussed, the evaluation criteria for regression algorithm MAE, RMSE and so on will be shown. How to evaluate and see the result of more than three algorithms on one dataset will be shown. Using different evaluate the model, enter data manually component and add row component.
• Publish to Web:  the process of creating a web service from a model will be discussed, how to check it in Excel will be shown, also how to use it in Stream Analytics as a function for data will be shown.
• Sharing workspace, create projects: the process of how to share the workspace with others will be discussed, how to create a project for each experiment, how to create a trained model component for reuse, and a data transformed dataset, how to export datasets to CSV, and other formats will be shown.
• Azure ML model in Power BI: Create a model in Azure ML Studio and use it in Power BI
• Azure ML Model in IoT: the process of how to create a model in Azure ML model studio and apply it on streamed data.

 

2.2: Data science Virtual Machine

The Data Science Virtual Machine (DSVM) is a customized VM image on Microsoft’s Azure cloud built specifically for doing data science. It has much popular data science and other tools pre-installed and pre-configured to jump-start building intelligent applications for advanced analytics. It is available on Windows Server and Linux. In this session, the audience will learn

• How to set it up
  • Environment needs
  • What parameter needs to be set up
• What software and tools can be used
  • visual studio and how to access R and Python
  • Azure ML workbench
  • SQL Server and Power BI
• Deep learning introduction
• Deep learning tools such as Tensor flow and so forth.
  • Tensorflow
  • Weka

 

2.3: Azure Data Lake Analytics

Azure Data Lake Analytics is a distributed, cloud-based data processing architecture offered by Microsoft in the Azure cloud. It is an on-demand analytics job service that simplifies big data. Instead of deploying, configuring, and tuning hardware, you write queries to transform your data and extract valuable insights. The analytics service can handle jobs of any scale instantly by setting the dial for how much power you need. You only pay for your job when it is running, making it cost-effective. In this section, you will learn

• How to set up Azure Data Lake Store gen1 and Azure Data Lake Analytics
  • Th main process of how to set them up will be explained
  • How to access Azure Data Lake Analytics via visual studio also will be explained
• How to use an existing sample of U-SQL
  • An introduction into USQL
  • How to run USQL in the cloud and how to run it
• How to write R codes inside USQL
  • How embed the R or Python code
  • How to pass parameters and access the data
• What is the best practice to create a machine learning project in data Lake
  • How to create a model
  • Store model
  • And use the model for production

 

2.4: Azure Data Bricks

Azure Databricks is an Apache Spark-based analytics platform optimized for the Microsoft Azure cloud services platform. Designed with the founders of Apache Spark, Databricks is integrated with Azure to provide one-click setup, streamlined workflows, and an interactive workspace that enables collaboration between data scientists, data engineers, and business analysts. Azure data bricks are one of the main platforms for the aim machine learning in this part audience will get familiar with

• What is data bricks and how to set it up
• The environment of data bricks and explain how they work
• How to able to write R, Python, Scala, and SQL at the same time
• Visualization of Databricks
• Workspace and clusters
• How to get information from Azure Data Lake store
• How to get data from event Hub
• What is notebook
• How to pass data from one cell to other
• How to use Databricks for a machine learning scenario storage model in Azure Data lake and show the result in Power BI

 

 

Module 3: Advanced Data Science with Microsoft Services – 2 days course

 

This training is designed for data science, data analysis and who want to do machine learning by writing R or Python code. This course will start with some explanation of different machine learning algorithms and approaches.  Then, some discussion on basic statistical analysis will be provided such as probability, factor analysis, hypothesis testing and so forth. Then the process of machine learning from business understanding, data cleaning, feature selection, model selection, split data for testing and training, evaluating the created model and finally developing and visual the trained model and analyzing the result will be presented.

For predict analysis algorithms such as decision tree, boosted decision tree, decision forest will be explained. The concept and how they work will be explained. Then how to set parameters for each of them will be illustrated. Also, the process of data preparation for each of these algorithms will be discussed. Finally, the related code for writing this algorithm in the cloud will be explained. The same process will be done for the descriptive algorithms such as clustering.

In this two days training, the audience will learn some deep concepts for machine learning, data analysis, main algorithms for predictive, descriptive and statistical analysis using R, R in Power BI and SQL Server.

The training includes but not limited to topics below:

3.1: Machine Learning Basics

The main concepts, life cycle and best practice of doing machine learning with Microsoft product will be explained.

• The main Predictive, descriptive and Prescriptive analysis will be explained
• What are the main stages of machine learning cycle will be illustrated
  • Business understanding
  • Data cleaning and feature selection
  • Model Selection
  • Data training and testing
  • Evaluating measures
  • Writing codes

 

3.2: Predictive Analytics

In this section, the audience will learn some of the algorithms such as Decision tree, Decision Forest, regression and SVM for the aim of predictive analytics. The main concepts of these algorithms will be explained, and the related R or Python code will be shown. How to analysis the trained model and set up the parameters also will be discussed. Finally, how to evaluate the result will be explained.

• What is classification and how to evaluate a classification result using confusion Matrix
• Decision Tree, Decision Forest, and Boosted decision tree
• SVM and KNN
• How to do classification using decision tree in SQL Server 2016
• How to classify by decision forest in Power BI
• The main code for SVM and KNN and how to compare the results by writing R codes

3.3: Descriptive Analytics

Descriptive analytics is an unsupervised learning approach. In this part, the audience will be familiar with some of the main algorithms for descriptive analytics from text mining, clustering and, Market basket analytics.

• The main concepts for clustering and k-mean clustering will be explained. Also, the process of identifying the number of clusters will be explained
• The main process for text mining for the aim of sentiment analytics, keyword extraction, and language detection
• How to do clustering in Power BI and how to use Power BI visual to analysis cluster
• What is market basket analysis and what is support, confidence and lift measure
• How to do Market basket analysis with R and rules package and how to show the result in Power BI visualization tools
• Text mining concepts and main concepts

3.4: Forecasting

Forecasting is one of the main approaches for time series. The main concepts of the time series will be explained and how to decompose time series, how to use exponential smoothing and ARIMA for forecasting the time series data. Audience will learn

• What is the forecasting
• How to decompose time series data
• What is Exponential smoothing and how to do it in RStudio and Power BI
• What is ARIMA and how to do it in Power BI

Module 4: AI and Cognitive Services in Applications -1-day course

 

In this one-day training, the audience will get familiar with some AI tools available in Microsoft such as cognitive services, Bot framework, AI websites and so forth.

The main specifications of these tools are that there is no need to write R or python codes for the aim of machine learning.

In this one-day training audience will learn how to set up these AI tools in Azure, and how to use some of the cool AI websites like custom vision, QnA and so forth.

The training includes but not limited to topics below:

 

4.1: Cognitive Services

Microsoft Cognitive Services (formerly Project Oxford) are a set of APIs, SDKs and services available to developers to make their applications more intelligent, engaging and discoverable. Microsoft Cognitive Services expands on Microsoft’s evolving portfolio of machine learning APIs and enables developers to easily add intelligent features – such as emotion and video detection; facial, speech and vision recognition; and speech and language understanding – into their applications. In this section, below item will be explained

• How to set up Cognitive services in Azure Portal
• Using cognitive services for text analytics such as sentiment analytics, keyword extraction and topic extraction in Power BI
• How to use cognitive services for handwriting detection and face recognition

 

4.2: Bot Framework

Azure Bot Service speeds up development by providing an integrated environment that’s purpose-built for bot development with the Microsoft Bot Framework connectors and BotBuilder SDKs. Developers can get started in seconds with out-of-the-box templates for scenarios including basic, form, language understanding, question and answer, and proactive bots.

• How to set up the bot framework
• How to use a bot for creating form and altering it in a .Net application
• How to create Bot for the Question and Answer and embed it in Power BI or website
• How to set up QnA

 

4.3: Application with Cognitive Service

There is a possibility to create an application in combination with Cognitive services. The audience will learn how to create a Face recognition API in .Net application for identifying the age, emotion, and so forth. Also, some more explanation of how to use Microsoft flow for creating a process to apply the cognitive services on the data. The process of how to set up the Flow using a template or to use a blank flow will be explained.

• How to set up cognitive services for face recognition
• Application C# for creating a web app
• What is Microsoft Flow and how to use it
• How to apply cognitive service on Twitter data

4.4: Create Model in Azure ML than in Power BI and Stream Analytics

There is a possibility to create a model in Azure, create an API out of it, then use it in Stream analytics for applying machine learning in live data will be explained. Moreover, how to use that model in Power BI also will be explained briefly.

• Create a model in Azure ML Studio and a web service out of that
• How to apply Azure ML API on a streamed data
• How to use the created API on a dataset in Power BI

 

 

 

 

Save

Save

Save

Save

Save

Save

Save

Save