Chapter 3 Data transformation

We extracted most of the data by scraping NASDAQ marketplace, publicly available graphs and free-data available for financial data of the cryptocurrencies.

All of the data was rendered into csv files before treating them - as we were looking at a static data frame.

Date formats were corrected to make them uniform in R and missing values were dropped. The only case where we encountered missing values were in the file containing ethereum prices, but entire rows were empty instead of values. Hence the decision was made to drop them.

Tweet count was obtained from charts into a csv, and index prices were scraped from NASDAQ into a csv.