Analysis

Building reports and dashboards to Share Analysis. Power BI Microsoft’s business analytics platform allows users connect, visualize and share data.

This session focuses on:

• How to get started with Power BI
• How to create reports and dashboards in Power BI
• How to share your power BI reports and dashboards

Materials here

In this session, participants learn how to work with geospatial data in R to generate meaningful insights. We move from understanding spatial data structures to producing clean, reproducible maps and spatial outputs.

The session covers:

• An introduction to spatial data types and common geospatial file formats
• How to read, clean, and manipulate spatial data
• Performing spatial joins, overlays, and basic spatial analysis
• Creating clear, publication-ready static maps in R

Materials here

Text analysis is the process of extracting meaningful information from text data, enabling programmers to uncover patterns and insights that would otherwise remain buried under text corpora. This hands-on session introduces the fundamentals of text analysis using popular Python text analysis libraries. Participants will learn essential techniques such as text data preprocessing, word and n-gram frequency analysis, and basic text classification, applied in examples for development research. The session provides foundational skills to participants so they can pursue further specialization in text analysis and natural language processing independently.

Materials here

Data pipelines are essential for efficiently collecting, processing, and analyzing data. They enable automation, reproducibility, scalability, and more importantly, reliability in data workflows, ensuring data is clean, structured, and ready for analysis. In this hands-on session, participants explore the fundamentals of data pipelines, including their structure, key components, and practical applications. Using a public finance dataset, users walk through an end-to-end example, introducing the Medallion architecture—a framework for organizing data in Bronze, Silver, and Gold layers. Instructors demonstrate how to execute different stages of the pipeline using workflow orchestration to automate tasks within a Databricks environment. 

In this 1.5-hour session, instructors introduce R Shiny, a tool that lets users build web-based applications using R. The session cover the core theory behind how Shiny apps work, including the structure of a Shiny app and the basics of reactive programming, followed by a hands-on, step-by-step walkthrough. Users follow along on their own machine and leave the session with a basic, fully functional Shiny app.

Materials here

When datasets bulk up, data.table steps up. Scale up your data analysis with the data.table package in R. Known for being up to 30 times faster compared to conventional tools like Tidyverse, data.table turns extensive data grouping from a chore into a breeze. This workshop is designed for R enthusiasts keen to enhance their efficiency, offering hands-on learning with clear, easy-to-grasp examples. Users discover a syntax that's not just fast but also a cinch to pick up. If you're already versed in Dplyr/Tidyverse, consider this workshop your bridge to quicker, smoother data analysis. Get results that are both speedy and reliable. By the close of our session, you'll be primed to conquer large data with ease and confidence.

Materials here

Improve and refine your data analysis skills with the “Data Analysis with Tidyverse" workshop. Designed for those eager to leverage the full capabilities of the Tidyverse in R, this session offers a rich introduction to the Tidyverse ecosystem and its collection of packages that streamline data analytics. You will learn to establish a clean and organized workflow, starting with data importation and advancing through transformative operations using the "pipe" syntax. The workshop emphasizes practical skills, with interactive exercises. 

Materials here

This seminar provides guidance for World Bank staff on how to overcome a common reasons papers fail to reproduce: a non-automated workflow. Specifically, the focus will be on automating output creation using Stata and R, coupled with the implementation of a systematic workflow to ensure that results remain consistently up-to-date.

Materials here