Data science BootcampUsing Azure ML, orange and R for Data science

We’re very excited to have you join us to learn how to build predictive analytics solutions with Azure Machine Learning, orange and R.  we hope you have an enriching and engaging learning experience.

During which we will fresh up some fundamentals of data science and statistical analysis methods, do code with R throughout various examples of the data science process. And then we will start building machine learning model in Azure machine learning and orange.

By the end of this boot camp workshop you will be oriented to azure machine learning and orange, know how to use machine learning algorithms and for which cases. Do your own R analysis and beautiful visualizations.

  • Module 1: Learn what is the data science process.
  • Module 2: Building classification models.
  • Module 3: Building Regression Models.
  • Module 4: Building decision trees and tree forests.
  • Module 5: Neural networks and support vector machine learning.

First session:

The first session will be an introduction about The Data science process.

Followed by lab sessions for each module.we will learn how to build logistic regression models, do data manipulation and cleansing.

  • Module 1
  • Module 2

Second session:

In the second session,we will understand the mechanism of the decision tree, tree forests, we will also learn how to compare several models against each other and select the best model.

  1. Module 3
  2. Module 4

Third session:

In the third and final session, we will work on unsupervised learning techniques such as clustering using K-Means and KNN.

We will work on a movie rating example, We will also learn how to deploy our models as a web service.

  • Module 5
  • Module 6

Module 1 :  Importing and cleaning Data with R.

Module 2 : Manipulation and Transformation with R.

Module 3 : Visualization of Data with ggplot.

Module 4 : unsupervised clustering with R .

Day 2 is where all the hard work begins, we will start with the basics of importing and cleaning data, then with the process of manipulation and transformation of data to adjust for business needs, we will also learn why need to transform data for better intuition and understanding about our business.

Finally we will learn how to build and compare machine learning models using R and the caret Package.

Throughout day 2, we will use only R and various popular datasets for data science. Some of the packages that will be used inside R are readr,tidyverse,stringr,ggplot2,caret and dplyr.

Day three will be practical case studies where participants will implement machine learning algorithms to real case studies , compare several models and deploy a model for implementation.

Requirements:

Participants are kindly requested to install the free version of these software on their devices (Mac or windows) before attending the workshop.

  • Orange (http://orange.biolab.si)
  • Sign up for free to azure machine learning (https://azure.microsoft.com/en-us/services/machine-learning/)
  • Install r studio from http://rstudio.com/