Module I: Data Science Basics (4 classes)

1) Getting & Loading Your Data

  A. Mining Datasets

  B. Access Your Data Anywhere

  C. Big Data, EDW, CRM, ERP or Social Media

  D. Data formats: csv, xlsx, hive, spark, html, API      

  E. Load Data From local File or remote URL

2) Understand Your Data Using Descrip_ve Statistics

  A. Class Distribution

  B. Data Summary

  C. Standard Deviations

  D. Skewness

  E. Correlations

  F. Hands On Lab

3) Understand Your Data Using Data Visualization

A. Get Results with QPlot, GGPlot & GGViz

B. Univariate and Multivariate Visualization

C. Tips For Data Visualization

D. Hands On Lab

4) Prepare Data for Predictive Modeling

  A. Data Pre-Processing in R

  B. Scale, Center, Standardize and Normalize Data

  C. Box-Cox and Yeo-Johnson Transform

  D. Principal Component Analysis Transform

  E. Independent Component Analysis Transform

  F. Tips For Data Transforms

  G. Hands On Lab

5) Inferential Statistics

A. Frequentists vs Bayesians

B. Hypothesis Testing

C. Central Limit Theorem

D. CI, P Value, ANOVA & T-test

E. Common PiEalls of Hypothesis Testing

F. Model Selection

  

Module II: Predictive Modeling  (4 classes)

 

6) Resampling & Estimating Model Accuracy

  A. Estimating Model Accuracy

  B. Data Split

  C. Bootstrap & Bagging

  D. k-fold Cross Validation

  E. Tips For Evaluating Algorithms

  F. Hands On Lab

7) Statistical Modeling Algorithms

  A. Linear Regression

  B. Non-linear Regression

  C. Logistic Regression

  D. Hands On Lab

8 ) Compare Performance of Multiple Algorithms

  A. Pre-Processing Dataset

  B. Train, Tune and Test Models

  C. Comparison & Evaluation Metrics in R

  D. Accuracy, Kappa, RMSE and R2

  E. AUC, ROC Curve, and Logarithmic Loss

  F. Choose The Best Predictive Model

  G. Hands On Lab

9) Combine Prediction Models with Ensembles

  A. Increase The Accuracy Of Your Models

  B. Test Dataset

  C. Boosting Algorithms

  D. Bagging Algorithms

  E. Stacking Algorithms

  F. Hands On Lab

10) Moving Your Model to Production

  A. Finalize Your Machine Learning Model

  B. Make Predictions On New Data

  C. Create A Standalone Model

  D. Save and Load Your Model

  E. Hands On Lab

 

Capstone Project

Includes Motivation, Dataset Selection thru to Project Presentation, Peer Review & 1 on 1 with your Mentor 

In addition to the lectures and hands-on sessions , you will be guided with the selection of a business problem to solve, guidance and support in applying the lessons to your project, mentoring your approach to solve the challenges, 1-On-1 follow up with your Mentor, and deployment of your solution on Anova’s proprietary platform where you can showcase to your employers or colleagues

R Boot Camp Program Details

  • Pre-Requisites +

    • The R boot camp assumes you already have at least an intermediate understanding of R and sta tisti cs.  
    • Coding  –For the basic boot camp (the first 4 weeks), you need to have basic programming skills and have used R at a basic level, perhaps in an entry level MOOC or
  • Read More
  • What You'll Learn +

       

    Module I: Data Science Basics  (4 classes)

    1) Getting & Loading Your Data

      A. Mining Datasets

      B. Access Your Data Anywhere

      C. Big Data, EDW, CRM, ERP or Social Media

      D. Data formats: csv, xlsx, hive, spark, html, API      

      E. Load Data

    Read More
  • Course Logistics +

    Dates:  Every Saturday starting 19th of August 2017 (Excluding Holidays)

      - 2 Modules of 4 Saturday sessions of each, and a Capstone Project, 1 on 1 with Mentors

      - Each session is broken into 3-4 hours of topical concepts and presentations, followed by 1-2 hours of lab sessions. Financing may

    Read More
  • Other +

    INCLUDES : ( In addition to enhancing your skills & knowledge with real world data product experience )

    ♦  Access to a virtual machine  ready to use with R, R-Studio, all the data set files and all the packages

    you will need for the boot camp

    ♦ A generous  list of resources and instruc

    Read More
    • 1