Group 4 Data Prep
Group 4 Project - A Tale of Bitcoin
|
|
|
|
|
|
|
|
Data source and preparation
The following are the data used
- Per minute bitcoin price data, extracted from Kaggle: https://www.kaggle.com/mczielinski/bitcoin-historical-data
- Nasdaq index: https://finance.yahoo.com/quote/%5EIXIC/history?ltr=1
- S&P500: https://finance.yahoo.com/quote/%5EGSPC/history?p=%5EGSPC
- Gold Price: https://finance.yahoo.com/quote/%5EXAU/history?p=%5EXAU
Data was easily downloaded from the link above. The bitcoin data downloaded requires data type conversion from UNIX time stamp to the more common YYYY-MM-DD format. The function [as.POSIXct] in base R easily convert the timestamp into the right format. We have also selected to use data from 2012 onwards because there is only 1-month worth of data in 2011. Excluding this data will not substantially affect our analysis. Data date range is from 1st January 2012 to 20th October 2017 The following are screenshots of the original data imported
Summary of number of data rows and variables Bitcoin dataframe [Attach image]
Gold dataframe [Attach image]
Nasdaq dataframe [Attach image]
SP500 dataframe [Attach image]
