Speaker: Manos Antoniou
SoftOne, Data Scientist | PyData Piraeus, Co-Organizer
This 3-hour course will provide an overview of using R & tidyverse, for solving real-word business problems. The session will step through the process of using the R tidyverse packages for data wrangling, transform data, grouping, summarizing, visualizing & develop machine learning models. The tidyverse is a collection of R packages designed for data science. All packages share an underlying design philosophy, grammar, and data structures. The goal of the course is to provide a thorough workflow in R & tidyverse that can be used with many different business problems. Case studies on real data will be used to illustrate the functionality.
Level:
Beginner / Intermediate
Target audience:
Students, Data analysts, Data scientists
Prerequisites on Audience:
a) SW/HW:
All attendees should bring a laptop with the following system requirements (i3 CPU or better, at least 4GB of RAM, at least 1 GB of free disk space, OS Windows 10/8/7 or MacOS 10.12+ or Ubuntu 14/16/18, R latest version & R studio latest version installed).
b) Know-how:
No prerequisite knowledge needed in R Programming, Statistics, Data Science, or Machine Learning. Although a basic understanding of statistical analysis & R language will help.
Deliverables:
R notebooks containing all code generated during the 3 parts of the workshop & presentations used will be delivered to all participants.
Schedule:
1st PART – Introduction to R & Tidyverse
- Introduction to R
- Training in tidyverse libraries (dplyr, tidyr, ggplot2, readr, purr, tibble, stringr, forcats)
- Data wrangling
- Tidy data
- Grouping & summarizing
- Visualize data
- Modelling
2nd PART – Customer segmentation case study
- ETL
- Exploratory analysis
- Modelling
- Visualization
3rd PART – Churn prediction case study
- ETL
- Exploratory analysis
- Modelling
- Visualization