Datails - StepUp Analytics

Kalyani University, Data Science Using R



Workshop Start Date: 14-09-2019

Workshop End Date: 20-10-2019

Venue: Kalyani University

Registration Ends: 08-09-2019

Fee: Rs.500

Duration: 30 hours


Pre-requisite:

This session is for Kalyani University students

Software: R programming (R Studio). The team will assist in all the installations.


Total Duration: 30 hours

Course Schedule: The second weekend of September 

3 hours on Saturday and Sunday each (total 5 weekends)


Additional Q&A session based on demands


Mode: Live Online session

Projects: One real-time project based on R, It Will be mentored by faculty.


Certification: Post-workshop completion and project submission, Candidates will be awarded a certificate


R Programming

Data structure

Vector: numeric, character, logical

Factor, Matrix, Data frame, List

Hands-on practice


Operation

Mathematical, Statistical, Logical

Relational, Conditional, ifelse

String Operation, Date operation, etc…

Hands-on practice


Exploratory Data Analysis

External data import & export

Data Summary, Transformation

A subset, Rename, Reshape, Sort, Merge, Append

Tabulation, Aggregation,

Handling missing values, etc…

Hands-on practice


Data Munging with ‘dplyr’

All kind of data manipulation with ‘dplyr’

Hands-on practice


Loop & User Defined Function

Control flow: if-else-if

for loop, while loop, next, break

User-defined function to build an algorithm

Hands-on practice


R Graphics & Statistics

Data Visualisation

Generating graphs/plots in R

Graphical parameters

Line, Bar, Pie, Histogram, Density plots

Saving/Exporting R plots

dev.off()

Hands-on practice


Advanced graphics with ‘ggplot2’

Advanced and fancy charting

Colour and theme manipulation

Hands-on practice


Statistical Science (Descriptive)

Central tendency: Mean, Median

Dispersion: variance, std.deviation

Quartiles, IQR, covariance, correlation

Different Distribution Analysis

Box-plot, Outlier treatment

Hands-on practice


Machine Learning & Modelling

Supervised Learning Models

Hands-on case study for the below algorithm


Multivariate Linear Regression

Univariate analysis & Variable Selection

Model Assumptions & Diagnostic Checks


Logistic Regression for Classification

Logit function, odds ratio,

Model Estimation, Confusion Matrix

Accuracy, Sensitivity, Specificity

ROC curve, AUC, Gini-Coefficient


Unsupervised Learning Models

Cluster Analysis

Anomaly Detection, Image Classification