similar_song.py

def similar_songs():
    import csv

    vector = ['acousticness', 'danceability', 'energy', 
                'instrumentalness', 'liveness', 'speechiness',
                'valence']  # minus 'bpm & 'key'

    underworld = 'underworld.txt'
    mbm = 'mbm.txt'
    orbital = 'orbital.txt'
    cut_copy = 'cut_copy.txt'

    all = []
    for fileName in [cut_copy, mbm, orbital]:
        with open(fileName) as f:
            reader = csv.DictReader(f, dialect=csv.excel_tab)
            all.extend(list(reader))
    tree = KDTree.fromTable(all, vector, ['title', 'artist'])

    with open(underworld) as f:
        reader = csv.DictReader(f, dialect=csv.excel_tab)
        for song in reader:
            feature = [float(song[v]) if v in song else 0. for v in vector]
            points, labels, distance = tree.nearest_neighbor(feature)
            s = '{0} -> {1}\n  {2}\n  {3}\n'.format(song['title'], labels, feature, points)
            print(s)