Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Analyzing the Evolution of Linkin Park's Music with Pandas

kvsingh.github.io

Post reply on HN
Print view View original

1–10 of 17 posts

Re: Analyzing the Evolution of Linkin Park's Music with Pandas

#2

Post by data_8301 »

Hi, author of the post here. I thought it'd be nice to post some information about the analysis.

I got some audio features (loudness, energy and valence) for Linkin Park's songs using the Spotify API. In the post, I do an album-wise analysis of these features, and how they vary across and within the albums using the Python Data Analysis Library, Pandas.

I try to articulate the general progression in style through the average change in these features, as well as the change in variation of these features.

If you're a Linkin Park fan, I would love to know how your experience of listening to LP matches with my analysis :)

Re: Analyzing the Evolution of Linkin Park's Music with Pandas

#3

Post by kelsolaar »

data_8301 wrote: post #2

Hi, author of the post here. I thought it'd be nice to post some information about the analysis. I got some audio features (loudness, energy and valence) for Linkin Park's songs using the Spotify API. In the post, I do an album-wise analysis of these features, and how they vary across and within the albums using the Python Data Analysis Library, Pandas. I try to articulate the general progression in style through the…

Excellent work! I'm not a Linkin Park fan although I listened a lot to their albums especially the two first ones. I slowly stopped listening when they released their subsequent albums which correlates with the "energy" loss your data analysis depicts!

Re: Analyzing the Evolution of Linkin Park's Music with Pandas

#4

Post by jamesb93 »

data_8301 wrote: post #2

Hi, author of the post here. I thought it'd be nice to post some information about the analysis. I got some audio features (loudness, energy and valence) for Linkin Park's songs using the Spotify API. In the post, I do an album-wise analysis of these features, and how they vary across and within the albums using the Python Data Analysis Library, Pandas. I try to articulate the general progression in style through the…

Perceptual loudness or just some measure or the rms/foote/peakamp? It's proven that these kinds of audio descriptors are frought when trying to attribute them to any human perception.

Re: Analyzing the Evolution of Linkin Park's Music with Pandas

#5

Post by ac130kz »

jamesb93 wrote: post #4
data_8301 wrote: post #2

Hi, author of the post here. I thought it'd be nice to post some information about the analysis. I got some audio features (loudness, energy and valence) for Linkin Park's songs using the Spotify API. In the post, I do an album-wise analysis of these features, and how they vary across and within the albums using the Python Data Analysis Library, Pandas. I try to articulate the general progression in style through the…

Perceptual loudness or just some measure or the rms/foote/peakamp? It's proven that these kinds of audio descriptors are frought when trying to attribute them to any human perception.

There is also a "Loudness War" factor in any of popular modern recordings. The dynamic range standards are simply put terrible, despite studies claiming the importance and necessity of keeping the levels good enough.

Re: Analyzing the Evolution of Linkin Park's Music with Pandas

#7

Post by throwaway2016a »

Interesting to see this here...

One of the things I like about Linkin Park is that their style evolved so much over the years. Even when they got big they were not afraid to completely change up their style almost completely.

I think the author knows this and tries to point it out in the commentary but I don't know if the graphs tell a compelling story.

One thing I'd like to point out from a data perspective is that a bar graph might not be the best tool for this. An album consists of many songs and there are graphs that can convey more information while maintaining readability. Perhaps a scatter plot or candlestick graph? If you use point size for song duration you can even display duration and energy of all the songs on each album in a scatter plot and I think it would be readable still.

Re: Analyzing the Evolution of Linkin Park's Music with Pandas

#8

Post by Jaruzel »

catiguana wrote: post #6

I didn't know the framework, I seriously hoped it included actual pandas.

Me too. Quite disappointed to be honest.

Was hoping for "We put headphones on 7 pandas and analysed their reaction to Linkin Park's best known songs. 5 out of 7 pandas agreed that the 'Living Things' album wasn't very good."

Post reply on HN