This task is about natural language processing. It is based on a data set of 1,000 sentences in English, sampled from the Harry Potter book series, by J. K. Rowling. Your job is to find any sentences that might be similar to a reference sentence with the id "1140".
The data is available at a Github repository: https://github.com/lassehjorthmadsen/data-science-assignment. It it located it the data folder in a csv-file called harry.csv.
The repository contains an R-project that you can fork if you like, or you can download the data directly. The repository also contains an R folder with a three-line script, read_data.R that will load the data and identify the reference sentence.
It is entirely up to you what tools you use to process the data, and how you would like to meassure similarity to our reference sentence.
There is no right or wrong answers; we would like to use this as a starting point for a discussion on how you might approach a task like this: Workflow, tools, metrics and data considerations. However you chose to work with the data, we ask that you share any code you write along with suggested similar sentences.