In [1]:
from ggplot import *
import pandas as pd

In [116]:
with open('bach-chordsequence.txt', 'r') as f:
    BACH = [piece.strip('[]\n').split(', ') for piece in f.readlines()]
with open('beethoven-chordsequence.txt', 'r') as f:
    BEETHOVEN = [piece.strip('[]\n').split(', ') for piece in f.readlines()]
with open('debussy-chordsequence.txt', 'r') as f:
    DEBUSSY = [piece.strip('[]\n').split(', ') for piece in f.readlines()]
with open('scarlatti-chordsequence.txt', 'r') as f:
    SCARLATTI = [piece.strip('[]\n').split(', ') for piece in f.readlines()]
with open('victoria-chordsequence.txt', 'r') as f:
    VICTORIA = [piece.strip('[]\n').split(', ') for piece in f.readlines()]

In [119]:
labels = ['composer','length']
df = pd.DataFrame.from_records([('bach', len(piece)) for piece in BACH] +
                               [('beethoven', len(piece)) for piece in BEETHOVEN] +
                               [('debussy', len(piece)) for piece in DEBUSSY] +
                               [('scarlatti', len(piece)) for piece in SCARLATTI] +
                               [('victoria', len(piece)) for piece in VICTORIA], columns = labels)
df.describe(percentiles=[.1, .25, .5, .75, .90])


Out[119]:
length
count 4042.000000
mean 435.916378
std 590.176691
min 4.000000
10% 66.000000
25% 140.000000
50% 264.000000
75% 482.250000
90% 937.800000
max 8966.000000

In [3]:
from collections import Counter
flatten = lambda l: [item for sublist in l for item in sublist]

In [122]:
bach_chords = flatten(BACH)
beethoven_chords = flatten(BEETHOVEN)
debussy_chords = flatten(DEBUSSY)
scarlatti_chords = flatten(SCARLATTI)
victoria_chords = flatten(VICTORIA)

for cnt in [Counter(bach_chords),Counter(beethoven_chords),Counter(debussy_chords),Counter(scarlatti_chords),Counter(victoria_chords)]:
    print(pd.DataFrame.from_dict(cnt.most_common())[1].describe())


count      179.000000
mean      4282.296089
std       8649.457527
min          4.000000
25%        365.500000
50%       1400.000000
75%       4667.500000
max      83691.000000
Name: 1, dtype: float64
count      173.000000
mean      3653.150289
std       5626.847864
min         17.000000
25%        820.000000
50%       1837.000000
75%       4581.000000
max      52747.000000
Name: 1, dtype: float64
count     172.000000
mean      478.848837
std       532.832803
min         5.000000
25%       146.750000
50%       331.000000
75%       569.250000
max      3002.000000
Name: 1, dtype: float64
count     173.000000
mean      965.930636
std      1406.654668
min         1.000000
25%       165.000000
50%       446.000000
75%      1210.000000
max      9483.000000
Name: 1, dtype: float64
count     146.000000
mean      780.684932
std      1532.897818
min         1.000000
25%        19.750000
50%       191.500000
75%       814.000000
max      9265.000000
Name: 1, dtype: float64

In [ ]:


In [135]:
with open('mxl-list.txt', 'r') as f:
    files = [line.replace('-', '_').split('_')[0].strip('()') for line in f.readlines()]

In [140]:
Counter(files).most_common()


Out[140]:
[('bach', 2328),
 ('mozart', 767),
 ('haydn', 746),
 ('beethoven', 674),
 ('scarlatti', 598),
 ('handel', 536),
 ('polish', 394),
 ('hymns', 362),
 ('victoria', 333),
 ('schubert', 289),
 ('chopin', 277),
 ('tchaikovsky', 243),
 ('alkan', 238),
 ('dandrieu', 211),
 ('debussy', 199),
 ('pachelbel', 185),
 ('liszt', 174),
 ('brahms', 162),
 ('couperin', 159),
 ('canadian', 156),
 ('dvorak', 149),
 ('scottish', 140),
 ('irish', 140),
 ('lully', 119),
 ('schumann', 118),
 ('frescobaldi', 115),
 ('byrd', 113),
 ('saint', 105),
 ('cocquiel', 104),
 ('shostakovich', 104),
 ('faure', 100),
 ('english', 95),
 ('brade', 95),
 ('buxtehude', 94),
 ('schuetz', 92),
 ('morales', 89),
 ('scriabin', 87),
 ('guerrero', 87),
 ('lasso', 84),
 ('schein', 83),
 ('rosenmueller', 79),
 ('anonymous', 78),
 ('palestrina', 72),
 ('holborne', 69),
 ('mendelssohn', 68),
 ('anglebert', 67),
 ('franck', 65),
 ('soler', 65),
 ('raff', 63),
 ('albeniz', 63),
 ('cima', 62),
 ('markull', 62),
 ('froberger', 60),
 ('telemann', 60),
 ('godowsky', 58),
 ('corelli', 55),
 ('raehs', 55),
 ('eccard', 53),
 ('maier', 52),
 ('albinoni', 49),
 ('fuellsack', 48),
 ('various', 48),
 ('boyvin', 48),
 ('chaumont', 47),
 ('fischer', 47),
 ('satie', 47),
 ('ravenscroft', 47),
 ('clementi', 46),
 ('american', 45),
 ('grieg', 44),
 ('downland', 42),
 ('busoni', 42),
 ('hammerschmidt', 42),
 ('krebs', 41),
 ('welsh', 41),
 ('lefebure', 41),
 ('vivaldi', 40),
 ('gottschalk', 40),
 ('uccellini', 40),
 ('ravel', 40),
 ('stravinsky', 39),
 ('corrette', 38),
 ('praetorius', 38),
 ('joplin', 37),
 ('gesualdo', 37),
 ('danzi', 36),
 ('lemmens', 35),
 ('becker', 34),
 ('mahler', 33),
 ('reger', 33),
 ('anonimo', 32),
 ('vecchi', 32),
 ('merula', 31),
 ('dornel', 31),
 ('simpson', 31),
 ('groh', 30),
 ('gabrieli', 30),
 ('pederson', 30),
 ('hummel', 30),
 ('bruckner', 30),
 ('young', 30),
 ('fuehrer', 29),
 ('cramer', 29),
 ('castelnuovo', 29),
 ('clerambault', 28),
 ('carols', 27),
 ('well', 27),
 ('rameau', 26),
 ('delibes', 26),
 ('paganini', 26),
 ('visee', 26),
 ('jacquest', 25),
 ('cazzati', 25),
 ('pozzoli', 24),
 ('offenbach', 24),
 ('donizetti', 24),
 ('reicha', 24),
 ('hindemith', 23),
 ('marcello', 23),
 ('buehler', 23),
 ('lecuona', 22),
 ('henry', 22),
 ('dowland', 22),
 ('janacek', 22),
 ('bizet', 21),
 ('roman', 21),
 ('gervaise', 21),
 ('adson', 21),
 ('monteverdi', 21),
 ('mainerio', 21),
 ('brachrogge', 21),
 ('lotti', 20),
 ('altenburg', 20),
 ('marini', 19),
 ('cannabich', 19),
 ('glazunov', 19),
 ('hassler', 19),
 ('lemko', 18),
 ('german', 18),
 ('morley', 18),
 ('senfl', 18),
 ('bartok', 18),
 ('daquin', 17),
 ('festa', 17),
 ('gershwin', 17),
 ('rubinstein', 17),
 ('kleber', 17),
 ('desprez', 17),
 ('castello', 16),
 ('balbastre', 16),
 ('jollage', 16),
 ('bertini', 16),
 ('beckwith', 15),
 ('jacchini', 15),
 ('carpentier', 15),
 ('cabanilles', 15),
 ('abel', 15),
 ('tchajkowsky', 14),
 ('mattheson', 14),
 ('campra', 14),
 ('mussorgsky', 14),
 ('walther', 14),
 ('dupre', 14),
 ('gade', 13),
 ('rachmaninov', 13),
 ('galilei', 13),
 ('dufay', 13),
 ('encina', 13),
 ('karg', 13),
 ('glinka', 13),
 ('isaac', 13),
 ('albrechtsberger', 13),
 ('wagner', 13),
 ('sousa', 13),
 ('strauss', 13),
 ('onslow', 12),
 ('respighi', 12),
 ('horak', 12),
 ('alexandra', 12),
 ('hertel', 12),
 ('chabrier', 12),
 ('pres', 11),
 ('poulenc', 11),
 ('sibelius', 11),
 ('tartini', 11),
 ('guilmant', 11),
 ('vitali', 11),
 ('brosig', 11),
 ('vierne', 11),
 ('cherubini', 10),
 ('rachmaninoff', 10),
 ('arcadelt', 10),
 ('asola', 10),
 ('weelkes', 10),
 ('gounod', 10),
 ('britten', 10),
 ('dunstable', 10),
 ('schoenberg', 10),
 ('laub', 10),
 ('sanz', 9),
 ('cambini', 9),
 ('zipoli', 9),
 ('messiaen', 9),
 ('morton', 9),
 ('ockeghem', 9),
 ('bustijin', 9),
 ('aiblinger', 9),
 ('mussorgskij', 9),
 ('fuherer', 9),
 ('agricola', 9),
 ('verdi', 8),
 ('spohr', 8),
 ('susato', 8),
 ('finger', 8),
 ('selma', 8),
 ('lalande', 8),
 ('boyce', 8),
 ('bernhard', 8),
 ('dumage', 8),
 ('medtner', 8),
 ('fontana', 8),
 ('sommer', 8),
 ('locke', 8),
 ('rossini', 8),
 ('widor', 8),
 ('scheidt', 8),
 ('russian', 8),
 ('berlioz', 8),
 ('falconieri', 7),
 ('marenzio', 7),
 ('chelleri', 7),
 ('arbeau', 7),
 ('machaut', 7),
 ('pezel', 7),
 ('foucquet', 7),
 ('gallus', 7),
 ('lemaigre', 7),
 ('leclair', 7),
 ('pasquini', 7),
 ('gigout', 7),
 ('rimsky', 7),
 ('soriano', 7),
 ('dutch', 7),
 ('josquin', 7),
 ('boismortier', 7),
 ('lebegue', 7),
 ('arriaga', 6),
 ('grigny', 6),
 ('drobisch', 6),
 ('merulo', 6),
 ('dussek', 6),
 ('reiche', 6),
 ('gibbons', 6),
 ('vazquez', 6),
 ('penalosa', 6),
 ('kreisler', 6),
 ('dieupart', 6),
 ('stehle', 6),
 ('puccini', 6),
 ('barber', 6),
 ('lechner', 6),
 ('hainlein', 6),
 ('reimann', 6),
 ('dubois', 6),
 ('kempter', 6),
 ('porpora', 6),
 ('garcia', 6),
 ('grossi', 6),
 ('viadana', 6),
 ('chausson', 6),
 ('fantini', 6),
 ('landini', 6),
 ('roberti', 6),
 ('prokofiev', 6),
 ('campion', 6),
 ('leo', 6),
 ('tallard', 5),
 ('geminiani', 5),
 ('forqueray', 5),
 ('scott', 5),
 ('mechelaere', 5),
 ('zangl', 5),
 ('rue', 5),
 ('gastoldi', 5),
 ('galuppi', 5),
 ('aguilera', 5),
 ('hofmann', 5),
 ('moskowsky', 5),
 ('lindeman', 5),
 ('miaskowskij', 5),
 ('flecha', 5),
 ('lazzari', 5),
 ('obrecht', 5),
 ('geoffry', 5),
 ('shakespearean', 5),
 ('italian', 5),
 ('french', 5),
 ('cavazzoni', 5),
 ('cabezon', 5),
 ('escobar', 5),
 ('skraup', 5),
 ('tchajkowski', 5),
 ('shostakovitch', 5),
 ('schiedermayr', 5),
 ('grapner', 5),
 ('ives', 5),
 ('tchaikowsky', 5),
 ('moussorgskij', 5),
 ('biber', 5),
 ('delaland', 5),
 ('sor', 5),
 ('ysaye', 5),
 ('lehar', 5),
 ('oltra', 5),
 ('gumpelzhaimer', 5),
 ('stolzer', 5),
 ('gombert', 4),
 ('redford', 4),
 ('eybler', 4),
 ('godard', 4),
 ('campos', 4),
 ('roeder', 4),
 ('arbo', 4),
 ('franáaix', 4),
 ('fosse', 4),
 ('lidner', 4),
 ('kittel', 4),
 ('herzogenberg', 4),
 ('loeillet', 4),
 ('othmayr', 4),
 ('goudimel', 4),
 ('sacchini', 4),
 ('cornysh', 4),
 ('schiedermaier', 4),
 ('muffat', 4),
 ('bloch', 4),
 ('borodin', 4),
 ('tallis', 4),
 ('hilton', 4),
 ('bruna', 4),
 ('bacewitz', 4),
 ('paderewsky', 4),
 ('charpentier', 4),
 ('lupo', 4),
 ('ghiselin', 4),
 ('ohnewald', 4),
 ('goedicke', 4),
 ('fasch', 4),
 ('rore', 4),
 ('guammi', 4),
 ('croce', 4),
 ('barsanti', 4),
 ('waldteufel', 4),
 ('fux', 3),
 ('busnois', 3),
 ('sammartini', 3),
 ('paradisi', 3),
 ('kuhlau', 3),
 ('bernstein', 3),
 ('poglietti', 3),
 ('tye', 3),
 ('madrid', 3),
 ('vulpius', 3),
 ('tejeda', 3),
 ('andreu', 3),
 ('cornelius', 3),
 ('hartmann', 3),
 ('indy', 3),
 ('happy', 3),
 ('distler', 3),
 ('falla', 3),
 ('est', 3),
 ('enrique', 3),
 ('bellasio', 3),
 ('bononcini', 3),
 ('ingegneri', 3),
 ('cato', 3),
 ('pinto', 3),
 ('haussmann', 3),
 ('haendel', 3),
 ('breton', 3),
 ('albert', 3),
 ('herzog', 3),
 ('bruhns', 3),
 ('boellmann', 3),
 ('beatles', 3),
 ('compere', 3),
 ('arne', 3),
 ('hickin', 3),
 ('casella', 3),
 ('beck', 3),
 ('alexandrov', 3),
 ('friml', 3),
 ('galynin', 3),
 ('neukomm', 3),
 ('purcell', 3),
 ('kabalevski', 3),
 ('bull', 3),
 ('bennet', 3),
 ('malvezzi', 3),
 ('kirnberger', 3),
 ('iglo', 3),
 ('reinecke', 3),
 ('sermisy', 3),
 ('cimarosa', 3),
 ('seixas', 3),
 ('lamb', 3),
 ('forster', 3),
 ('gheyn', 3),
 ('suppe', 3),
 ('piazzola', 3),
 ('casanovas', 3),
 ('rossi', 3),
 ('grecianinov', 3),
 ('emmerig', 3),
 ('prieto', 3),
 ('leybach', 3),
 ('speer', 3),
 ('barbiereau', 3),
 ('holst', 3),
 ('ugolino', 3),
 ('rheinberger', 3),
 ('galles', 3),
 ('gluck', 3),
 ('aldrovandini', 3),
 ('janequin', 3),
 ('elizabethan', 3),
 ('berlin', 3),
 ('barie', 2),
 ('willaert', 2),
 ('weiss', 2),
 ('eustachio', 2),
 ('cooper', 2),
 ('michl', 2),
 ('gasparini', 2),
 ('taverner', 2),
 ('narvaez', 2),
 ('padilla', 2),
 ('martini', 2),
 ('cervera', 2),
 ('smetana', 2),
 ('white', 2),
 ('moore', 2),
 ('diabelli', 2),
 ('ferrabosco', 2),
 ('luebeck', 2),
 ('kodaly', 2),
 ('gippenbusch', 2),
 ('anonym', 2),
 ('macque', 2),
 ('sgambati', 2),
 ('destouches', 2),
 ('kuehnel', 2),
 ('hahn', 2),
 ('mico', 2),
 ('himmel', 2),
 ('luetkemann', 2),
 ('gesius', 2),
 ('stojowsky', 2),
 ('o', 2),
 ('bruck', 2),
 ('kostner', 2),
 ('gruber', 2),
 ('blow', 2),
 ('bassano', 2),
 ('loewe', 2),
 ('strozzi', 2),
 ('allwood', 2),
 ('clemens', 2),
 ('mac', 2),
 ('japonesa', 2),
 ('dykes', 2),
 ('tchajkowskij', 2),
 ('canon', 2),
 ('ganne', 2),
 ('fernandez', 2),
 ('echevarria', 2),
 ('de', 2),
 ('busto', 2),
 ('moussorgski', 2),
 ('giuliani', 2),
 ('clarke', 2),
 ('cara', 2),
 ('franzoni', 2),
 ('loret', 2),
 ('oxinagas', 2),
 ('attwood', 2),
 ('capirola', 2),
 ('schutt', 2),
 ('tchaikowski', 2),
 ('geissler', 2),
 ('beckmann', 2),
 ('bauer', 2),
 ('sole', 2),
 ('chapi', 2),
 ('klemm', 2),
 ('corteccia', 2),
 ('giorgi', 2),
 ('royer', 2),
 ('henselt', 2),
 ('chambers', 2),
 ('boely', 2),
 ('mingote', 2),
 ('schippers', 2),
 ('kirbye', 2),
 ('lidon', 2),
 ('kissin', 2),
 ('kullak', 2),
 ('khachaturian', 2),
 ('attaignant', 2),
 ('rembt', 2),
 ('gimenez', 2),
 ('kirkpatrick', 2),
 ('ett', 2),
 ('marais', 2),
 ('donato', 2),
 ('arauxo', 2),
 ('banchieri', 2),
 ('sweelinck', 2),
 ('cordier', 2),
 ('gelinek', 2),
 ('cornago', 2),
 ('cavaccio', 2),
 ('luther', 2),
 ('halle', 2),
 ('barbieri', 2),
 ('unknown', 2),
 ('mouton', 2),
 ('philips', 2),
 ('wieck', 2),
 ('benoit', 2),
 ('caccini', 2),
 ('gaultier', 2),
 ('lassus', 2),
 ('johnson', 2),
 ('pepusch', 2),
 ('altnikol', 2),
 ('geist', 2),
 ('koeler', 2),
 ('macdowell', 2),
 ('jackson', 1),
 ('bardos', 1),
 ('pino', 1),
 ('dufaut', 1),
 ('pescetti', 1),
 ('villalobos', 1),
 ('maschek', 1),
 ('rebikov', 1),
 ('picchi', 1),
 ('fielitz', 1),
 ('antegnati', 1),
 ('tosone', 1),
 ('alain', 1),
 ('kraus', 1),
 ('freundt', 1),
 ('altisent', 1),
 ('ancina', 1),
 ('berchem', 1),
 ('daggere', 1),
 ('dohnanyi', 1),
 ('balakirev', 1),
 ('schultz', 1),
 ('aichinger', 1),
 ('ascher', 1),
 ('adam', 1),
 ('danyel', 1),
 ('arditi', 1),
 ('bevin', 1),
 ('jomelli', 1),
 ('rampolini', 1),
 ('von', 1),
 ('ammann', 1),
 ('braun', 1),
 ('bargagni', 1),
 ('jeune', 1),
 ('barnhouse', 1),
 ('andlauer', 1),
 ('costeley', 1),
 ('patavino', 1),
 ('kothe', 1),
 ('moulu', 1),
 ('esquivel', 1),
 ('traditional', 1),
 ('heller', 1),
 ('alcock', 1),
 ('gersbach', 1),
 ('paradies', 1),
 ('groba', 1),
 ('dohnany', 1),
 ('batten', 1),
 ('prudent', 1),
 ('archangelsky', 1),
 ('leon', 1),
 ('oslander', 1),
 ('midi.txt\n', 1),
 ('friderici', 1),
 ('ljadov', 1),
 ('le', 1),
 ('inglot', 1),
 ('trayter', 1),
 ('longueval', 1),
 ('nobunaga', 1),
 ('gascongne', 1),
 ('erlebach', 1),
 ('veit', 1),
 ('weber', 1),
 ('schnabel', 1),
 ('mascagni', 1),
 ('couppey', 1),
 ('nicolai', 1),
 ('caldara', 1),
 ('lassen', 1),
 ('ghizeghem', 1),
 ('lappi', 1),
 ('nardini', 1),
 ('manchicourt', 1),
 ('fornsete', 1),
 ('boeddecker', 1),
 ('torote', 1),
 ('blazquez', 1),
 ('torres', 1),
 ('battiferri', 1),
 ('spendiarov', 1),
 ('grandi', 1),
 ('schnizer', 1),
 ('cantallos', 1),
 ('desmarets', 1),
 ('quantz', 1),
 ('millan', 1),
 ('magnificat', 1),
 ('cristo', 1),
 ('oguri', 1),
 ('bulgaras', 1),
 ('molinaro', 1),
 ('herz', 1),
 ('szimanowsky', 1),
 ('du', 1),
 ('graun', 1),
 ('miaskovski', 1),
 ('herbaut', 1),
 ('colebaut', 1),
 ('lalo', 1),
 ('cornet', 1),
 ('resinarius', 1),
 ('lucchesi', 1),
 ('scharwenka', 1),
 ('bonelli', 1),
 ('zach', 1),
 ('ocon', 1),
 ('pierpont', 1),
 ('dangicourt', 1),
 ('geoffroy', 1),
 ('moszkowsky', 1),
 ('vaugham', 1),
 ('eckardt', 1),
 ('elsbeth', 1),
 ('gutierrez', 1),
 ('weyse', 1),
 ('marchand', 1),
 ('coprario', 1),
 ('boieldieu', 1),
 ('binchois', 1),
 ('kiel', 1),
 ('geneeherzl', 1),
 ('gossec', 1),
 ('ramirez', 1),
 ('josly', 1),
 ('broeer', 1),
 ('leontovich', 1),
 ('jones', 1),
 ('pollarolo', 1),
 ('kuhnau', 1),
 ('swabian', 1),
 ('east', 1),
 ('walsh', 1),
 ('vittoria', 1),
 ('paisiello', 1),
 ('gaengsbacher', 1),
 ('cibulka', 1),
 ('japart', 1),
 ('ahle', 1),
 ('barvinsky', 1),
 ('gabrielli', 1),
 ('matteis', 1),
 ('shepherd', 1),
 ('ruffo', 1),
 ('cherkassky', 1),
 ('araujo', 1),
 ('mayr', 1),
 ('johnston', 1),
 ('bruch', 1),
 ('vila', 1),
 ('kanno', 1),
 ('hawley', 1),
 ('stoianov', 1),
 ('nagiller', 1),
 ('loehlein', 1),
 ('maschera', 1),
 ('knipper', 1),
 ('luthiers', 1),
 ('rimskij', 1),
 ('allegri', 1),
 ('planquette', 1),
 ('kedrov', 1),
 ('kellner', 1),
 ('grillo', 1),
 ('besozzi', 1),
 ('perera', 1),
 ('talexy', 1),
 ('rice', 1),
 ('gorgas', 1),
 ('agostini', 1),
 ('buono', 1),
 ('luscinius', 1),
 ('granados', 1),
 ('molinet', 1),
 ('guastavino', 1),
 ('gevaert', 1),
 ('micieces', 1),
 ('riccio', 1),
 ('kerll', 1),
 ('trabaci', 1),
 ('zimmer', 1),
 ('baron', 1),
 ('klingenberg', 1),
 ('giardini', 1),
 ('marzi', 1),
 ('nielsen', 1),
 ('scandello', 1),
 ('babou', 1),
 ('popular', 1),
 ('vidal', 1),
 ('enescu', 1),
 ('capello', 1),
 ('barnard', 1),
 ('perti', 1),
 ('hofhaimer', 1),
 ('arenskij', 1),
 ('pellegrini', 1),
 ('lavignac', 1),
 ('busnoys', 1),
 ('giordani', 1),
 ('stoehr', 1),
 ('stolle', 1),
 ('bellini', 1),
 ('marbeck', 1),
 ('hauptmann', 1),
 ('medina', 1),
 ('farnaby', 1),
 ('reinhold', 1),
 ('schulhoff', 1),
 ('schonberg', 1),
 ('strata', 1),
 ('walter', 1),
 ('tarrega', 1),
 ('massenet', 1),
 ('eustache', 1),
 ('bartolucci', 1),
 ('bassani', 1),
 ('pesenti', 1),
 ('hofmeister', 1),
 ('balfe', 1),
 ('frei', 1),
 ('duparc', 1),
 ('conseil', 1),
 ('paderewski', 1),
 ('lemire', 1),
 ('allison', 1),
 ('taeggio', 1),
 ('leonin', 1),
 ('baglioni', 1),
 ('ketelbey', 1),
 ('bertali', 1),
 ('antiquis', 1),
 ('szymanovsky', 1),
 ('kreutzer', 1),
 ('dulot', 1),
 ('kalman', 1),
 ('gostena', 1),
 ('witzka', 1),
 ('balduin', 1),
 ('ferriri', 1),
 ('vivanco', 1),
 ('schmid', 1),
 ('esposito', 1),
 ('pitoni', 1),
 ('dretzel', 1),
 ('gabrilowitsch', 1),
 ('pergolesi', 1),
 ('striggio', 1),
 ('bendinelli', 1),
 ('wolff', 1),
 ('fuenllana', 1),
 ('addinsell', 1),
 ('hiller', 1),
 ('urunuela', 1),
 ('esperanca', 1),
 ('serocky', 1),
 ('miskinis', 1),
 ('nanino', 1),
 ('harrison', 1),
 ('casals', 1),
 ('triana', 1),
 ('hartung', 1),
 ('luetzel', 1),
 ('fueher', 1),
 ('noordt', 1),
 ('purday', 1),
 ('cabanillas', 1),
 ('alonso', 1),
 ('brouwer', 1),
 ('ivanovici', 1),
 ('horowitz', 1),
 ('storace', 1),
 ('czech', 1),
 ('jaspers', 1),
 ('lutoslawsky', 1),
 ('luython', 1),
 ('lancaster', 1),
 ('decker', 1),
 ('odojewski', 1),
 ('leschetizky', 1),
 ('gurlitt', 1),
 ('denisov', 1),
 ('benedetti', 1),
 ('zachow', 1),
 ('champion', 1),
 ('richard', 1),
 ('czerny', 1),
 ('glogauer', 1),
 ('stanley', 1),
 ('setrakian', 1),
 ('kraft', 1),
 ('jeep', 1),
 ('durufle', 1),
 ('certon', 1),
 ('schlinck', 1),
 ('dressler', 1),
 ('webern', 1),
 ('rouget', 1),
 ('ceballos', 1),
 ('planson', 1),
 ('pinell', 1),
 ('aranes', 1),
 ('boellman', 1),
 ('drahlovsky', 1),
 ('wanhal', 1),
 ('pereira', 1),
 ('l', 1),
 ('brito', 1),
 ('senleches', 1),
 ('arresti', 1),
 ('iribarren', 1),
 ('stamitz', 1),
 ('cavalli', 1),
 ('erars', 1),
 ('des', 1),
 ('moscheles', 1),
 ('viraldini', 1),
 ('greitter', 1),
 ('seeboeck', 1),
 ('scheidemann', 1),
 ('raison', 1),
 ('lobo', 1),
 ('fairfax', 1),
 ('keler', 1),
 ('azzaiolo', 1),
 ('herbert', 1),
 ('kotter', 1),
 ('bellando', 1),
 ('monk', 1),
 ('quidant', 1),
 ('lefebvre', 1),
 ('moxica', 1),
 ('martucci', 1),
 ('mendellsohn', 1),
 ('titsek', 1),
 ('wolf', 1),
 ('hollander', 1),
 ('castillo', 1),
 ('alberti', 1),
 ('casulleras', 1),
 ('greene', 1),
 ('hernandez', 1),
 ('naujalis', 1),
 ('biebl', 1),
 ('ynera', 1),
 ('moral', 1),
 ('lacombe', 1),
 ('moulinie', 1),
 ('arnold', 1),
 ('seyfried', 1),
 ('liapunov', 1),
 ('carissimi', 1),
 ('perotin', 1),
 ('couillart', 1),
 ('kalkbrenner', 1),
 ('passerau', 1),
 ('erbach', 1),
 ('elgar', 1),
 ('capocci', 1),
 ('ferranti', 1),
 ('schmelzer', 1),
 ('gassmann', 1),
 ('grueber', 1),
 ('thomas', 1),
 ('meacham', 1),
 ('ponchielli', 1),
 ('jaeger', 1),
 ('soutullo', 1),
 ('waelrant', 1),
 ('bertoni', 1),
 ('field', 1),
 ('chueca', 1),
 ('lorca', 1),
 ('arregui', 1),
 ('gussago', 1),
 ('farmer', 1),
 ('davis', 1),
 ('seeger', 1),
 ('farreny', 1),
 ('vitry', 1),
 ('casielles', 1),
 ('furchheim', 1),
 ('erythraeus', 1),
 ('monferrato', 1),
 ('boito', 1),
 ('stanford', 1),
 ('savino', 1),
 ('keiser', 1),
 ('adriaenssen', 1),
 ('moskowski', 1),
 ('gamberini', 1),
 ('palestina', 1)]

In [ ]:


In [54]:
# Below is just poking around the data

In [88]:
plot = ggplot(aes(x='length', color='composer'), data=df) + geom_density() + ylab('density')
plot.save('density.png', width=8, height=6, dpi=180)

In [87]:
plot = ggplot(aes(x='length', fill='composer', color='composer'), data=df) + geom_histogram(binwidth=100, alpha=0.5) + \
ylab('# pieces')
plot.save('histogram.png', width=6, height=6, dpi=180)

In [82]:
ggplot(df, aes(x='length')) + \
    geom_histogram(binwidth=100, alpha=0.6) + \
    facet_wrap("composer", scales="free")


Out[82]:
<ggplot: (-9223372036542203041)>

In [ ]: