DATA SCIENCE &

MACHINE LEARNING
BY USING R-PROGRAMMING

CURRICULUM
FUNDAMENTAL OF STATISTICS.
Population and sample
Descriptive and Inferential Statistics
Statistical data analysis
Variables
Sample and Population Distributions
Interquartile range
Central Tendency
Normal Distribution
Skewness.
Boxplot
Five Number Summary
Standard deviation
Standard Error
Emperical Formula
central limit theorem
Estimation
Confidence interval
Hypothesis testing
p-value
Scatterplot and correlation coefficient
Standard Error
Scales of Measurements and Data Types
Data Summarization
Visual Summarization
Numerical Summarization
Outliers & Summary

Module 1- Introduction to Data Analytics

Objectives:
This module introduces you to some of the important keywords in R like Business
Intelligence, Business
Analytics, Data and Information. You can also learn how R can play an important role in
solving complex analytical problems.
This module tells you what is R and how it is used by the giants like Google, Facebook, etc.
Also, you will learn use of 'R' in the industry, this module also helps you compare R with other
software
in analytics, install R and its packages.

Topics:
Business Analytics, Data, Information
Understanding Business Analytics and R
Compare R with other software in analytics
Install R
Perform basic operations in R using command line
Module 2- Introduction to R programming
Starting and quitting R

Recording your work

Basic features of R.
Calculating with R
Named storage
Functions
R is case-sensitive
Listing the objects in the workspace
Vectors
Extracting elements from vectors
Vector arithmetic
Simple patterned vectors
Missing values and other special values
Character vectors Factors
More on extracting elements from vectors
Matrices and arrays
Data frames
Dates and times

Import and Export data in R

Importing data in to R
CSV File
Excel File
Import data from text table

Topics
Variables in R
Scalars
Vectors
R Matrices
List
R – Data Frames
Using c, Cbind, Rbind, attach and detach functions in R
R – Factors
R – CSV Files
R – Excel File

NOTE-:
Assignments
Business Scenerio/Group Discussion.

R Nuts and Bolts-:

Entering Input. – Evaluation- R Objects- Numbers- Attributes- Creating Vectors- Mixing Objects-
Explicit Coercion- Summary- Names- Data Frames.

Module 3- Managing Data Frames with the dplyr package

The dplyr Package
Installing the dplyr package
select()
filter()
arrange()
rename()
mutate()
group_by()
%>%

NOTE-:
Assignments
Business Scenerio/Group Discussion.
Module 4- Loop Functions
Looping on the Command Line
lapply()
sapply()
tapply()
apply()

NOTE-:
Assignments
Business Scenerio/Group Discussion.

Module 5- Data Manipulation in R Objectives:

In this module, we start with a sample of a dirty data set and perform Data Cleaning on it, resulting
in a data set, which is ready for any analysis.
Thus using and exploring the popular functions required to clean data in R.

Topics
Data sorting
Find and remove duplicates record
Cleaning data
Merging data

Statistical Plotting-:
Bar charts and dot charts
Pie charts
Histograms
Box plots
Scatterplots
QQ plots

Objectives:
Control Structure Programming with R
The for() loop
The if() statement
The while() loop
The repeat loop, and the break and next statements
Apply
Sapply
Lapply

Factors
Using Factors
Manipulating Factors
Numeric Factors
Creating Factors from Continuous Variables
Convert the variables in factors or in others.

Reshaping
Data Modifying
Data Frame Variables
Recoding Variables
The recode Function
Reshaping Data Frames
The reshape Package

Module 6- Statistical Learning-:

What Is Statistical Learning?
Why Estimate f?
How Do We Estimate f?
The Trade-Off Between Prediction Accuracy and Model Interpretability

Supervised Versus Unsupervised Learning

Regression Versus Classification Problems
Assessing Model Accuracy
Module 7- Basics of Statistics & Linear & Multiple Regression
This module touches the base of Descriptive and Inferential Statistics and Probabilities &
'Regression Techniques'.
Linear and logistic regression is explained from the basics with the examples and it is
implemented in R using two case studies dedicated to each type of Regression discussed.
Assessing the Accuracy of the Coefficient Estimates.

Assessing the Accuracy of the Model.

Estimating the Regression Coefficients.
Some Important Questions
Lab: Linear Regression.
Libraries .
Simple Linear Regression
Multiple Linear Regression
Interaction Terms
Qualitative Predictors
Writing Functions

NOTE-:
Assignments with Different Datasets.
Business Scenerio/Group Discussion

Module 8- Classification-:
An Overview of Classification.
Why Not Linear Regression?
Logistic Regression
The Logistic Model
Estimating the Regression Coefficients

Making Predictions
Logistic Regression for >2 Response Classes
Lab: Logistic Regression.
The Stock Market Data
Logistic Regression

NOTE-:
Assignments with Different Datasets.
Business Scenerio/Group Discussion.

Module 9- Variance Inflation Factor-:

Introduction
Multicolinearity.
How we can detect the multicolinearity.
Effects of multicolinearity
Lab: VIF
Mutiple Datasets.
Applications.
Applications.Reduce the features.

NOTE-:
Assignments with Different Datasets.
Business Scenerio/Group Discussion.

Correlation
Types of Correlation
Properties of Correlation
Methods of Calculating Correlation

Module 10- Best Model Selection-:

Subset Selection
Best Subset Selection
Stepwise Selection
 Choosing the Optimal Model
Lab 1: Subset Selection Methods
Best Subset Selection
Forward and Backward Stepwise Selection
Choosing Among Models Using the Validation Set Approach and Cross-Validation

NOTE-:
Assignments with Different Datasets.
Business Scenerio/Group Discussion.

Explore many algorithms and models:

Popular algorithms: Classification, Regression, Clustering, and Dimensional Reduction.
Popular models: Train/Test Split, Root Mean Squared Error, and Random Forests. Get ready to
do more learning than your machine!

Module-11-Machine Learning vs Statistical Modeling & Supervised vs Unsupervised Learning

Machine Learning Languages, Types, and Examples
Machine Learning vs Statistical Modelling
Supervised vs Unsupervised Learning
Supervised Learning Classification
Unsupervised Learning

Module 12 - Supervised Learning I

K-Nearest Neighbors
Decision Trees
Random Forests
Reliability of Random Forests
Advantages & Disadvantages of Decision Trees

Module 13 - Supervised Learning II

Regression Algorithms
Model Evaluation
Model Evaluation: Overfitting & Underfitting
Understanding Different Evaluation Models

Module 14 - Unsupervised Learning

K-Means Clustering plus Advantages & Disadvantages
Hierarchical Clustering plus Advantages & Disadvantages
Measuring the Distances Between Clusters - Single Linkage Clustering
Measuring the Distances Between Clusters - Algorithms for Hierarchy Clustering
Density-Based Clustering

Module 15 - Dimensionality Reduction & Collaborative Filtering

Dimensionality Reduction: Feature Extraction & Selection
Collaborative Filtering & Its Challenges

Module 16- Tree-Based Methods-:

The Basics of Decision Trees
Regression Trees
Classification Trees
Trees Versus Linear Models
Advantages and Disadvantages of Trees
Bagging, Random Forests, Boosting
Bagging
Random Forests
Lab: Decision Trees
Fitting Classification Trees
Fitting Regression Trees

NOTE-:
Assignments with Different Datasets.
Business Scenerio/Group Discussion.
 Module 17- Time Series & Forcasting-:
Time series
Estimating and Eliminating the Deterministic Components if they are present in the Model.
Estimating and Eliminating Seasonality if it is present in the Model
Modeling the Remainder using Auto Regressive Moving Average (ARMA) Models
Identify 'order' of the ARMA model
'Forecast' or Predict for Future Values
Practise on R

NOTE-:
Assignments with Different Datasets.
Business Scenerio/Group Discussion.

Module-18-:Support Vector Machines – Outline

Understand when the Support Vector family of methods are an appropriate method of analysis.
Understand what a hyperplane is and how they are used with the Support Vector methods.
Identify the differences between Maximal Margin Classifiers, Support Vector Classifiers, and Support
Vector Machines.
Know how each of the algorithms determines the best separating hyperplane.
Distinguish between hard and soft margins and when each is to be used.
Know how to extend the method for nonlinear cases.

NOTE-:
Assignments with Different Datasets.
Business Scenerio/Group Discussion.

Module-19-Principal Component Analysis – Outline

Understand what principal components are and when principal component analysis is appropriate.
Describe eigenvalues and eigenvectors and how they are used to calculate principal components.
Understand loading and loading vectors.
Know how to decide how many principal components to use in the analysis.
Be able to use principal component analysis for regression.

NOTE-:
Assignments with Different Datasets.
Business Scenerio/Group Discussion.

Partners : Java
NOIDA GREATER NOIDA GHAZIABAD FARIDABAD
A-43 & A-52, Sector-16, F 205 Neelkanth Plaza Alpha 1 1, Anand Industrial Estate, SCO-32, 1st Floor, Sec.-16,
Noida - 201301, (U.P.) INDIA commercial Belt Opposite to Alpha Near ITS College, Mohan Nagar, Faridabad (HARYANA)
Ph. : 0120-4646464 Metro Station Greater Noida Ghaziabad (U.P.) Ph. : 0129-4150605-09
Mb. : 09871055180 Ph. : 0120-4345190-91-92 to 97 Ph.: 0120-4835400...98-99 Mb. : 09811612707
Mb. :09899909738, 09899913475 Mb. : 09810831363 / 9818106660
: 08802288258 - 59-60
GURGAON
1808/2, 2nd floor old DLF,
Near Honda Showroom,
Sec.-14, Gurgaon (Haryana)
Ph. : 0124-4219095-96-97-98
Mb. : 09873477222-333
www.facebook.com/ducateducation