Data Science with R - Training

Module 1- Intro to Data Science

Learning Objectives: Get an idea of what is data science. Why data science is "Rosy" or "Handy" or "Fascinating"
Get acquainted with various analysis and visualization tools used in data science

Topics

• What is Data Science?
• Analytics Landscape
• Life Cycle of a Data Science Projects
• Data Science Tools & Technologies

Hands-on: No hands-on

Module 2- Mastering R

Learning Objectives:  Get an idea of what is R. Why R is so popular tool among Data Scientists.
Learn how to install R and its components.
Learn how to install and load libraries
Learn frequently used libraries
Learn about data structures in R
Learn all about loops and control statements in R
Learn how to write custom functions, nested functions and functions with arguments
Lean all about loop functions available in R which are efficient and can be written with single command
Learn all about string manipulations and regular expressions. The functions can be extremely useful for text or unstructured data manipulations
Learn how to import data from various sources in R. How to write files from R. How to connect to various databases from R
Learn visualization in R with base and ggplot libraries. Learn Grammar of Graphics in a very structured easy-to-understand manner
Hands-on session on a real-life case study

Topics

• Intro to R Programming
• Installing and Loading Libraries
• Data Structures in R
• Control & Loop Statements in R
• Functions in R
• Loop Functions in R
• String Manipulation & Regular Expression in R
• Working with Data in R
• Data Visualization in R
• Case Study
  

Hands-on:

• Know how to install R, R Studio
• and other libraries
• Write R Code to understand and implement
• R Data Structures
• Write R Code to implement loop and
• control structures in R
• Write R Code to read and write data from/to R.
• Read data not only from CSV files but also
• using direct connection to various databases
• Write R Code to implement ggplot
• for data visualization
• Complex Real-Life Data Manipulation, Preparation & Exploratory Data Analysis case study
  

Module 3- Probability & Statistics

Learning Objectives: Visit basics like mean (expected value), median and mode
Distribution of data in terms of variance, standard deviation and interquartile range
Basic summaries about the data and the measures. Together with simple graphics analysis
Basics of probability with daily life examples
Marginal probability and its importance with respective to datascience
Learn baye's theorem and conditional probability
Learn alternate and null hypothesis, Type1 error, Type2 error, power of the test, p-value

Topics

• Measures of Central Tendency
• Measures of Dispersion
• Descriptive Statistics
• Probability Basics
• Marginal Probability
• Bayes Theorem
• Probability Distributions
• Hypothesis Testing  

Module 4- Advanced Statistics & Predictive Modeling - I

Learning Objectives:  Analysis of Variance and its practical use
Linear Regression with Ordinary Least Square Estimate to predict a continuous variable. It covers strong concepts, model building, evaluating model parameters, measuring performance metrics on Test and Validation set. Further it covers enhancing model performance by means of various steps like feature engineering & regularization
Real Life Case Study with Linear Regression
Dimensionality Reduction Technique with Principal Component Analysis and Factor Analysis. Covers techniques to find the optimum number of components/factors using scree plot, one-eigenvalue criterion
Real-Life case study with PCA & FA

Topics

• ANOVA
• Linear Regression (OLS)
• Case Study: Linear Regression
• Principal Component Analysis
• Factor Analysis
• Case Study: PCA/FA
  

Hands-on:

• With attributes describing various aspect of residential homes, you are required to build a regression model to predict the property prices.
• Reduce Data Dimensionality for a House Attribute Dataset for more insights & better modeling

Module 5-  Advanced Statistics & Predictive Modeling - II

Learning Objectives:  Binomial Logistic Regression for Binomial Classification Problems. Covers evaluation of model parameters, model performance using various metrics like sensitivity, specificity, precision, recall, ROC Cuve, AUC, KS-Statistics, Kappa Value
Real Life Case Study with Binomial Logistic Regression
KNN Algorith for Classification Problem. Covers techniques that are used to find the optimum value for K
Real Life Case Study with KNN
Decision Trees - for regression & classification problem. Covers both Classification & regression problem. Candidates get knowledge on Entropy, Information Gain, Standard Deviation reduction, Gini Index, CHAID
Real Life Case Study with Decision Tree

Topics

• Logistic Regression
• Case Study: Logistic Regression
• K-Nearest Neighbor Algorithm
• Case Study: K-Nearest Neighbor Algorithm
• Decision Tree
• Case Study: Decision Tree

Hands-on:

• With various customer attributes describing customer charactarestics, build a classification model to predict which customer is likely to default a credit card payment next month. This can help the bank be proactive in collecting dues
• Predict if a patient is likely to get any chronic kidney disease depending on the health metrics
• Wine comes in various style. With the ingredient composition known, we can build a model to predict the the Wine Quality using Decision Tree (Regression Trees)
  

Module 6-  Time Series Forecasting

Learning Objectives: Understand Time Series Data and its components like Level Data, Trend Data and Seasonal Data
Understand Exponential Smoothing Model and when to use the same
Use Holt's model when your data has both Constant Data and Trend Data. How to select the right smooting constants.]
Use Holt's model when your data has Constant Data, Trend Data and Seasonal Data. How to select the right smooting constants.
Use Auto Regressive Integrated Moving Average Model for building Time Series Model
Real Life Case Study with ARIMA

Topics

• Understand Time Series Data
• Visualizing TIme Series Components
• Exponential Smoothing
• Holt's Model
• Holt-Winter's Model
• ARIMA
• Case Study: Time Series Modeling on Stock Price

Hands-on:

• Write R code to Understand Time Series
• Data and its components like Level Data,
• Trend Data and Seasonal Data
• Write R code to Use Holt's model when your
• data has Constant Data, Trend Data and
• Seasonal Data.How to select the right
• smooting constants.
• Write R code to Use Auto Regressive
• Integrated Moving Average Model for
• building Time Series Model
• Dataset including features such as symbol, date, close, adj_close, volume of a stock. This data will exhibit characteristics of a time series data. We will use ARIMA to predict the stock prices.
  

Module 7-  Capstone Project

Learning Objectives: An industry mentor guided group project to handle a real-life project. The same way you would execute a data science project in any business problem

Topics

• Industry relevant capstone project under experienced industry-expert mentor

Hands-on: Project to be selected by candidates.

Projects
Covers Exploratory Data Analysis, Linear Regression, Logistic Regression, Decision Tree, Time Series Forecasting, Recommender Engines, Text Mining, ANN, SVM, K means Clustering, Ensemble Machine Learning Techniques