# build model to extract the manifold and learn a mapping / encoder to be able
# to reproduce this on test data
embedder = SDAEmbedder((n_features, 10, 2),
noise=0.1,
reconstruction_penalty=1.0,
embedding_penalty=0.1,
sparsity_penalty=0.0,
learning_rate=0.1, seed=0)
# use the randomly initialized encoder to measure the baseline
code = embedder.encode(data)
score_code_data = local_match(data, code, query_size=50, ratio=1, seed=0)
print "kNN score match after pre-training code/data:", score_code_data
fig = pl.figure(1)
_, _, corr = pairwise_distances(data, code, ax=fig.add_subplot(3, 1, 1),
title="random")
print "Pairwise distances correlation:", corr
print "Training encoder to unroll the embedded data..."
start = time.time()
embedder.pre_train(data, slice_=slice(None, None), epochs=1000, batch_size=100)
print "done in %ds" % (time.time() - start)
# evaluation of the quality of the embedding by comparing kNN queries from the
# original (high dim) data and the low dim code on the one hand, and from the
# ground truth low dim manifold and the low dim code on the other hand
code = embedder.encode(data)
score_code_data = local_match(data, code, query_size=50, ratio=1, seed=0)
print "kNN score match after pre-training code/data:", score_code_data
_, _, corr = pairwise_distances(data, code, ax=fig.add_subplot(3, 1, 2),
learning_rate=0.1, seed=0)
print "Training encoder to extract a semantic preserving 2D mapping"
start = time.time()
embedder.pre_train(data, slice_=slice(None, None), epochs=1000, batch_size=100)
print "done in %ds" % (time.time() - start)
# evaluation of the quality of the embedding by comparing kNN queries from the
# original (high dim) data and the low dim code on the one hand, and from the
# ground truth low dim manifold and the low dim code on the other hand
fig = pl.figure(1)
code = embedder.encode(data)
score_code_data = local_match(data, code, query_size=50, ratio=1, seed=0)
print "kNN score match after pre-training code/data:", score_code_data
_, _, corr = pairwise_distances(data, code, ax=fig.add_subplot(1, 1, 1),
title="pre-training")
print "Pairwise distances correlation:", corr
## fine tuning
#print "Fine tuning encoder to unroll the embedded data..."
#start = time.time()
#embedder.fine_tune(data, epochs=100, batch_size=5)
#print "done in %ds" % (time.time() - start)
#code = embedder.encode(data)
#score_code_data = local_match(data, code, query_size=50, ratio=1, seed=0)
#print "kNN score match after fine-tuning code/data:", score_code_data
#_, _, corr = pairwise_distances(data, code, ax=fig.add_subplot(3, 1, 3),
# title="fine tuning")
#print "Pairwise distances correlation:", corr
