World Bank Data

In the next section, you'll find a series of exercises. These are relatively brief and focus on extracting, or in other words, reading in data from different sources. The goal is to familiarize yourself with different types of files and see how the same data can be formatted in different ways. This lesson assumes you have experience with pandas and basic programming skills.

This lesson uses data from the World Bank. The data comes from two sources:

1. World Bank Indicator Data - This data contains socio-economic indicators for countries around the world. A few example indicators include population, arable land, and central government debt.
2. World Bank Project Data - This data set contains information about World Bank project lending since 1947.

Both of these data sets are available in different formats including as a csv file, json, or xml. You can download the csv directly or you can use the World Bank APIs to extract data from the World Bank's servers. You'll be doing both in this lesson.

The end goal is to clean these data sets and bring them together into one table. As you'll see, it's not as easy as one might hope. By the end of the lesson, you'll have written an ETL pipeline to extract, transform, and load this data into a new database.

The goal of the lesson is to combine these data sets together so that you can run a linear regression model predicting World Bank Project total costs. You will not actually build the model; instead, you will get the data ready so that a data analyst or data scientist could more easily build the model.

QUIZ QUESTION::

Match the World Bank data set with the type of information it contains

ANSWER CHOICES: