Hey there! Thanks to some highly productive sessions of work, I am a whole week ahead on my research schedule.
I planned on spending two weeks (last week and this week) on completing all of the database manipulation and graphing of the data I had collected for analysis, most likely due to my unfamiliarity with the topic. However, things ended up going much smoother than I had anticipated, and I created 24 graphs that depict the various relationships within my data.
I started off by first transferring all of the data from my simple spreadsheet into a local database using PostgreSQL and pgAdmin.
I then transferred all of my data from the spreadsheet into a basic CSV (Comma-Separated Value) file, which I could then copy into my database.
From there, I wrote a simple script that would extract the data I needed for each different graph. Essentially, I needed to graph data on every value returned by the API against the measures of success (MV Views, Music Show Wins, Downloads). There were 8 different API values I used, meaning that I ended up with 24 total graphs.
Unfortunately, I was disappointed to find that the R2 values for my graphs were fairly low, meaning that the data didn’t closely match the trend lines I found. This prevents me from making precise predictions about the different values in terms of success, but I can still identify general trends and patterns.
Aside from my research, at my internship, things have continued nicely, and I’m still working on the projects I was assigned. I’m really grateful for the SQL I learned, and how I was able to use it to streamline the process and manipulating all my data and graphing it.
For the upcoming week, I plan on starting to work on typing up my method and results section for my paper. I also would like to perform additional analysis on the graphs I drew.