Literacy rates around the world
Data Pipeline Byte 2
Cleaning the Raw Data
The raw data file was downloaded in csv format.
There were a bunch of different indicators that I could have
chosen to look at, but I decided on literacy rates.
The data file was wide by years meaning there was one contry per indicator type,
however I wanted the data to be long by indicator type so I had to reshape my
data before I put it in google fusion tables. I was also interested in looking
at a countries income, so I had to merge the income data with the literacy rate data. I checked for completeness, correctness,
and coherency in a number of ways. Please look under the Data Quality Tab for more details.
After cleaning and reshaping the data I was able to put the results in google fusion tables.
Female Literacy Rates
The graph below is a histogram of the female literacy rate around the world by country in 2015. You can see that the data is highly skewed to the right, meaning more countries on average have higher rates of reading.
Male Literacy Rates
The graph below is a histogram of the male literacy rate around the world by country in 2015. You can see that the data is highly skewed to the right, even more so than for female literacy
Box Plot of Literacy Rates by Region
The box plot below illustrates the distribution of the data by region. The North American region has been left out, since none of the countries had data for 2015.
Sub Saharan Africa has the widest distribution, and Europe and Central Asian has the smallest.
Box Plot of Literacy Rates by Income
The box plot below illustrates the distribution of the data by income,
1 being low income and 5 being high income. The high income countries have
a very small distrubution, with literacy rates at nearly 100%. Low income contries
on the other hand vary significantly. Income groups 2 and 3 vary, but also contain some countries that are far below the distribution.
Map of Countries by Income
The map is a visulization of the countries and the respective income groups for reference.