def test_shortest_path():
nn, ngram = get_models()
syms = nn.data.syms
# trans = nn.Ys['1'].value
trans = ngram.ngram
fixed = {0: 'I', 2: 'V', 4: 'I'}
shortest_path(trans, syms, fixed)
def run_chord2vec():
"""
To run the model. To finishing the training early, set configs['max_iter'] to less.
"""
configs = get_configs()
configs['retrieve_model'] = False
configs['max_iter'] = 1
data = get_data(configs)
nn, bigram = get_models(data, configs)
print nn.plot_w1()
def test_continue_to_end():
nn, ngram = get_models()
# fixed = {0: 'I', 2: 'V', 7: 'I'}
# original_seq = ['I', 'IV', 'V']
fixed = {0: 'C', 2: 'G', 7: 'C'}
original_seq = ['C', 'F', 'G']
new_seq, sym_inds = shortest_path(nn, fixed, 2, original_seq)
print new_seq
print sym_inds
def retrieve_skipgram_and_ngram():
"""
By default, loads cached model. To train new model, set configs['retrieve_model']
as in the run_chord2vec function
:return: neural-net skipgram, bigram model
"""
configs = get_configs()
data = get_data(configs)
nn, bigram = get_models(data, configs)
# saves a plot of the 2D PCA of the chord vectors
nn.plot_w1()
def get_trans():
configs = get_configs()
data = get_data()
nn, ngram = get_models()
# if bigram nn, it's from t to t-1, then need to transpose?
nn_trans_dict = nn.predict_identity()
nn_trans = nn_trans_dict.values()[0]
print '...nn_trans type', type(nn_trans), nn_trans.shape
nn_trans = nn_trans_dict['1']
print nn_trans_dict.keys()
print '...nn_trans type', type(nn_trans), nn_trans.shape
nn_trans = np.exp(nn_trans)
ngram_trans = ngram.ngram
return ngram_trans, nn_trans, ngram, nn, configs, data
def predict_probs_seq():
# want for each sym a prediction list of prob for all syms
ON_LOG = True
# seq = ['I', 'IV', 'I6', 'V']
# seq = [u'I', u'vi', u'V7', u'I', u'V2', u'I6', u'V', u'V7', u'I', u'V6/vi', u'V6/5/vi', u'IV6', u'vii/o7', u'I',
# u'IV7', u'V2', u'I', u'V', u'V7', u'I', u'V', u'V', u'viio6', u'i', u'vii/o7/V', u'V', u'V7', u'i', u'i',
# u'V4/3', u'i6', u'V6/5/iv', u'iv', u'V6/5/V', u'V', u'V7', u'i', u'V', u'I6', u'I', u'IV6', u'viio', u'I',
# u'vi', u'V6/5/V', u'V7/V', u'V', u'I6', u'IV', u'V7', u'IV6/5', u'viio', u'I', u'ii6/5', u'V']
seq = [u'IV6', u'vii/o7', u'I', u'IV7']
model, ngram_model = get_models()
processed_seq = PreprocessedSeq(seq, model.data.syms, model.data.window)
probs, mean_score_total, probs_all = model.predict_reverse([processed_seq],
return_probs=True,
return_all=True)
ngram_probs, ngram_probs_all = ngram_model.predict(seq, log=False,
return_all=True)
assert len(seq) == len(ngram_probs_all)
print 'len(probs)', len(probs)
print 'len()', len(probs[0])
print len(probs_all[0][0])
print len(probs_all[0][0])
print len(model.data.syms)
syms = model.data.syms
topn = 8
# b/c assumes multiple sequences
probs_all = probs_all[0]
for i, sym in enumerate(seq):
probs = probs_all[i]
inds = np.argsort(probs)[::-1]
ngram_probs = ngram_probs_all[i]
ngram_inds = np.argsort(ngram_probs)[::-1]
print '--- %s ---' % sym
for j in range(topn):
# ind for nn
ind = inds[j]
ngram_ind = ngram_inds[j]
if not ON_LOG:
nn_prob = np.exp(probs[ind])
ngram_prob = ngram_probs[ngram_ind]
else:
nn_prob = probs[ind]
ngram_prob = np.log(ngram_probs[ngram_ind])
print '%s: \t%.2f, \t%s: \5%.4f' % (syms[ind],
nn_prob,
syms[ngram_ind],
ngram_prob)
topn = 10
similars = nn.most_similar(sym, topn=topn)
for i, sim in enumerate(similars):
print sim
if i > topn/2:
top_syms.append(sim[0])
else:
next_top_syms.append(sim[0])
nn.plot_w1(query_syms + top_syms)
nn.plot_w1(query_syms + next_top_syms)
# syms = data.syms
# print 'ngram counts'
# print ngram.n_gram_counts[syms.index(query_syms[0]), :]
query_syms_on_matrices(query_syms + top_syms, trans, trans_names,
data.syms, configs)
query_syms_on_mat(query_syms+top_syms, nn_trans, data.syms, configs)
query_syms_on_matrices(query_syms + next_top_syms, trans, trans_names,
data.syms, configs)
query_syms_on_mat(query_syms+next_top_syms, nn_trans, data.syms, configs)
if __name__ == '__main__':
# predict_probs_seq()
# compare_transition_matrices()
# query_syms_on_trans()
get_models()
