Problem B
Haydn Seek

A lot of people have used the music recognition software "Shazam" (the app that tells you the name of a song by listening to it), most people think it’s some smart algorithm like Fast Fourier Transform that makes it be able to recognize what song is being played. But as it turns out, Shazam has - like all smart companies - outsourced this work to Iceland instead. So everytime you want the name of a song, it goes through a number of experts in a certain field that will listen and then tell you the song name.
Hordigordur has recently been employed by Shazam and wrote on his CV that he knows everything about knowing which classical composer is which by only listening to a small bit of a piece. However, this is a lie, Hordigordur doesn’t know anything about classical composers, he has however gotten some data from his company that he can "polish his skills with". Instead of actually learning all the material, Hordigordur does the unthinkable: he outsources it back to you. He asks you to create an algorithm that will listen to a bit of music and determine which composer wrote it.

Indata

Download the zip-file with training data and test data, this can be found at the bottom of the page where it says "attachments". The data contains an interval of 100 notes in a piece of music. Every note can be described by its starting time (in the column "start"), its duration (in the column "duration"), its pitch (in the column "pitch") and its velocity (in the column "velocity"). The training data will also include what composer wrote the piece in the column "composer".

Output

For all test cases, you should print one row that contains a string: the composer’s name.
Note that some name can be spelled in a way you might not expect, so make sure to copy the names from the training data.

Scoring

If $x$ is how many percent you guess correctly of the composer, your final score is:

At the end of the competition, all solutions will be retested on the remaining 70% of the data. Your final score at the end of the competition will only be based on the remaining 70% of the data; the 30% tested during the competition will have no effect. It is guaranteed that the 30% tested during the competition were chosen uniformly at random and are entirely disjoint from the 70% tested at the end. Therefore, the results on the 30% tested during the competition should be seen as a strong indicator of how well your solution performs. At the same time, it is detrimental to overfit your solution to the test data.