from collections import defaultdict
from sklearn.neural_network import BernoulliRBM
import pandas as pd
import numpy as np

# Extract chords into unique ids, e.g. 1, 2, 3, 4, 5
allchords = defaultdict()
with open("oscar2chords_extract.txt", 'rb') as f:
    assert len(allchords) == len(set(allchords)) # ensure no duplicate chords
    for ix, line in enumerate(f):
        allchords[ix] = line.rstrip()
print len(allchords) # oscar uses this number of unique chords

# Read in Oscar's data.
vectors = []
notedata = pd.read_csv(open("oscar2notes.txt", 'rb'), skiprows=2)
allnotes = []
for note, octave in zip(notedata["Note/Rest"], notedata["Octave"]):
    allnotes.append("%s%s" % (note, octave))

print "Number of notes (# of samples for RBM): ", len(notedata)
notedata.head()

# Given a MUSIC21 note, such as C5 or D#7, convert it
# into a note on the keyboard between 0 and 87 inclusive.
# Don't convert it for mingus; try to use music21 note style
# as much as possible for all this stuff.
def quantify(note):
    notevals = {
        'C' : 0,
        'D' : 2,
        'E' : 4,
        'F' : 5,
        'G' : 7,
        'A' : 9,
        'B' : 11
    }
    quantized = 0
    octave = int(note[-1]) - 1
    for i in note[:-1]:
        if i in notevals: quantized += notevals[i]
        if i == '-': quantized -= 1
        if i == '#': quantized += 1
    quantized += 12 * octave
    return quantized

# Create bitwise note vectors for use with Restricted Boltzmann Machine.
vectors = np.zeros((1, 88))
for ix, note in enumerate(allnotes):
    vect = np.zeros((1, 88))
    vect[0, quantify(note)] = 1
    if ix == 0:
        vectors = vect
    else:
        vectors = np.vstack((vectors, vect))
print vectors.shape