def test4(data, features):
n_topics = 3
featureNames = features + ["%s%s" % x for x in zip(["topic"] * n_topics, range(n_topics))]
f = numpy.array(featureNames)
lda = LatentDirichletAllocation(n_topics=n_topics, max_iter=5,
learning_method='online',
learning_offset=50.,
random_state=0)
numpy.random.seed(17)
trainIdx = numpy.random.choice([True, False], size=(data.shape[0],), p=[2. / 3, 1. / 3])
testIdx = numpy.logical_not(trainIdx)
train = data[trainIdx, :]
test = data[testIdx, :]
lda.fit(train)
topicstrain = lda.transform(train)
topicstest = lda.transform(test)
maxtrain = numpy.argmax(topicstrain, axis=1)
topicstrain = numpy.zeros_like(topicstrain)
for i, c in enumerate(maxtrain):
topicstrain[i, c] = 1
maxtest = numpy.argmax(topicstest, axis=1)
topicstest = numpy.zeros_like(topicstest)
for i, c in enumerate(maxtest):
topicstest[i, c] = 1
testMPE = numpy.zeros((test.shape[0], len(featureNames)))
testMPE = testMPE / 0
testMPE[:, numpy.arange(test.shape[1])] = test
print("LEARNING SPN")
traintopics = numpy.hstack((train, topicstrain))
# print(testMPE[:,[99, 100,101,102]])
# print(traintopics[:,[99, 100,101,102]])
print(featureNames)
featureTypes = ["discrete"] * train.shape[1] + ["continuous"] * topicstrain.shape[1]
domains = []
for i, ft in enumerate(featureTypes):
if ft == "continuous":
r = (0.0, 1.0)
fd = estimate_continuous_domain(traintopics, i, range=r, binning_method=20)
domain = numpy.array(sorted(fd.keys()))
else:
domain = numpy.unique(data[:, i])
# print(i, ft, domain)
domains.append(domain)
memory = Memory(cachedir="/tmp/test4", verbose=0, compress=9)
@memory.cache
def learn():
spn = SPN.LearnStructure(traintopics, featureTypes=featureTypes, row_split_method=Splitting.Gower(), col_split_method=Splitting.RDCTest(threshold=0.1, linear=True),
featureNames=featureNames,
domains=domains,
# spn = SPN.LearnStructure(data, featureNames=["X1"], domains =
# domains, families=families, row_split_method=Splitting.KmeansRows(),
# col_split_method=Splitting.RDCTest(),
min_instances_slice=100)
return spn
spn = learn()
spn.root.validate()
prodNodes = spn.get_nodes_by_type(ProductNode)
for pn in prodNodes:
leaves = pn.get_leaves()
words = set()
for leaf in leaves:
# assuming pwl node:
_x = numpy.argmax(leaf.y_range)
max_x = leaf.x_range[_x]
if max_x < 1.0:
continue
words.add(featureNames[leaf.featureIdx])
# ll = pn.eval()
if len(words) < 4:
continue
print(words)
logs, topicsmpe = spn.root.mpe_eval(testMPE)
print(spn.get_leaves())
print(topicsmpe.shape)
print(topicsmpe[:, [100, 101, 102]])
maxmpe = numpy.argmax(topicsmpe[:, [100, 101, 102]], axis=1)
topicsmpe = numpy.zeros_like(topicsmpe[:, [100, 101, 102]])
for i, c in enumerate(maxmpe):
topicsmpe[i, c] = 1
print(topicstest)
print(topicsmpe)
print(topicstest - topicsmpe)
correct = numpy.sum(numpy.abs(topicstest - topicsmpe), axis=1) == 0
print("correct", numpy.sum(correct))
print("incorrect", topicsmpe.shape[0] - numpy.sum(correct))
print_top_words(lda, features, 10)
def test6(data):
print(data.shape)
_, mixt = getArchetypes(data, 3)
def normalize(data):
mixtd = data
mixtd[mixtd == 1] = mixtd[mixtd == 1] - 0.0000001
mixtd[mixtd == 0] = mixtd[mixtd == 0] + 0.0000001
mixtnorm = numpy.sum(mixtd, axis=1)
mixtd = numpy.divide(mixtd, mixtnorm[:, None])
return mixtd
mixt = normalize(mixt)
dirichlet_alphas = dirichlet.mle(mixt, method='meanprecision', maxiter=100000)
featureTypes = ["continuous"] * mixt.shape[1]
domains = []
for i, ft in enumerate(featureTypes):
if ft == "continuous":
r = (0.0, 1.0)
fd = estimate_continuous_domain(mixt, i, range=r, binning_method=400)
domain = numpy.array(sorted(fd.keys()))
else:
domain = numpy.unique(data[:, i])
domains.append(domain)
print(domains)
@memory.cache
def learn(data):
spn = SPN.LearnStructure(data, featureTypes=featureTypes, row_split_method=Splitting.Gower(), col_split_method=Splitting.RDCTest(threshold=0.3),
domains=domains,
alpha=1,
# spn = SPN.LearnStructure(data, featureNames=["X1"], domains =
# domains, families=families, row_split_method=Splitting.KmeansRows(),
# col_split_method=Splitting.RDCTest(),
min_instances_slice=50)
return spn
spn = learn(mixt)
print(spn)
spn_samples = numpy.zeros((data.shape[0], 3))/0
a,spn_samples = spn.root.sample(spn_samples)
spn_samples = normalize(spn_samples)
#dtrain_fit = scipy.stats.dirichlet.logpdf(numpy.transpose(mixt_train), alpha=dirichlet_alphas)
def plotDirichlet(data):
data = data.reshape(-1, mixt.shape[1])
result = scipy.stats.dirichlet.logpdf(numpy.transpose(normalize(data)), alpha=dirichlet_alphas)
return result
def spnpdf(data):
data = data.reshape(-1, mixt.shape[1])
res = spn.root.eval(normalize(data))[0]
return res
xy_all = cartesian(mixt)
filename = 'plots/dirichlet_mle.pdf'
try:
import os
os.remove(filename)
except OSError:
pass
pp = PdfPages(filename)
# all
fig = plt.figure()
draw_pdf_contours_func(plotDirichlet)
plt.title("dirichlet trained on all, original points")
plt.plot(xy_all[:, 0], xy_all[:, 1], 'ro', markersize=markersize)
plt.colorbar()
pp.savefig(fig)
numpy.random.seed(17)
mixt_samples = numpy.random.dirichlet(dirichlet_alphas, data.shape[0])
print(dirichlet_alphas)
xy_samples = cartesian(mixt_samples)
fig = plt.figure()
draw_pdf_contours_func(plotDirichlet)
plt.title("dirichlet trained on all, sampled points")
plt.plot(xy_samples[:, 0], xy_samples[:, 1], 'ro', markersize=markersize)
plt.colorbar()
pp.savefig(fig)
xy_spn_samples = cartesian(spn_samples)
fig = plt.figure()
draw_pdf_contours_func(spnpdf)
plt.title("spn trained on all, original points")
plt.plot(xy_all[:, 0], xy_all[:, 1], 'ro', markersize=markersize)
plt.colorbar()
pp.savefig(fig)
xy_spn_samples = cartesian(spn_samples)
fig = plt.figure()
draw_pdf_contours_func(spnpdf)
plt.title("spn trained on all, sampled points")
plt.plot(xy_spn_samples[:, 0], xy_spn_samples[:, 1], 'ro', markersize=markersize)
plt.colorbar()
pp.savefig(fig)
pp.close()
def computeSimplexExperiment(dsname, data, dimensions, mixttype, min_instances_slice=700):
if mixttype == "Archetype":
_, mixt = getArchetypes(data, dimensions)
if mixt is None:
return ()
elif mixttype == "LDA":
lda = LatentDirichletAllocation(n_topics=dimensions, max_iter=50,
learning_method='online',
learning_offset=50.,
random_state=0)
lda.fit(data)
mixt = lda.transform(data)
elif mixttype == "RandomSample":
mixt = numpy.random.dirichlet((1,1,1), 20).transpose()
print(mixt)
0/0
print(mixt.shape)
def normalize(data):
mixtd = data
mixtd[mixtd == 1] = mixtd[mixtd == 1] - 0.0000001
mixtd[mixtd == 0] = mixtd[mixtd == 0] + 0.0000001
mixtnorm = numpy.sum(mixtd, axis=1)
mixtd = numpy.divide(mixtd, mixtnorm[:, None])
return mixtd+0.0
mixt = normalize(mixt)
mixt_train, mixt_test = train_test_split(mixt, test_size=0.30, random_state=42)
numpy.savetxt("mixt_train.csv", mixt_train)
numpy.savetxt("mixt_test.csv", mixt_test)
#0/0
featureTypes = ["continuous"] * mixt.shape[1]
domains = []
for i, ft in enumerate(featureTypes):
if ft == "continuous":
r = (0.0, 1.0)
fd = estimate_continuous_domain(mixt, i, range=r, binning_method=400)
domain = numpy.array(sorted(fd.keys()))
else:
domain = numpy.unique(data[:, i])
domains.append(domain)
dirichlet_alphas = dirichlet.mle(mixt_train, method='meanprecision', maxiter=100000)
#@memory.cache
def learn(data):
spn = SPN.LearnStructure(data, featureTypes=featureTypes, row_split_method=Splitting.Gower(), col_split_method=Splitting.RDCTest(threshold=0.3),
domains=domains,
alpha=0.1,
families = ['histogram'] * data.shape[1],
# spn = SPN.LearnStructure(data, featureNames=["X1"], domains =
# domains, families=families, row_split_method=Splitting.KmeansRows(),
# col_split_method=Splitting.RDCTest(),
min_instances_slice=min_instances_slice)
return spn
#for the good pdf it was 700
spn = learn(mixt_train)
print(spn)
def spnpdf(data):
data = data.reshape(-1, mixt.shape[1])
res = spn.root.eval(normalize(data))[0]
return res
print(dirichlet_alphas)
def plotDirichlet(data):
data = data.reshape(-1, mixt.shape[1])
try:
result = scipy.stats.dirichlet.logpdf(numpy.transpose(normalize(data)), alpha=dirichlet_alphas)
except:
print(normalize(data))
print(normalize(data)*1.0)
print(normalize(data)+1)
print(normalize(data)+0)
0/0
return result
df_train = pandas.DataFrame()
df_test = pandas.DataFrame()
dtrain_fit = scipy.stats.dirichlet.logpdf(numpy.transpose(mixt_train), alpha=dirichlet_alphas)
dtest_fit = scipy.stats.dirichlet.logpdf(numpy.transpose(mixt_test), alpha=dirichlet_alphas)
df_train["dirichlet_train"] = dtrain_fit
df_test["dirichlet_test"] = dtest_fit
spn_train_fit = spn.root.eval(mixt_train)
spn_test_fit = spn.root.eval(mixt_test)
df_train["spn_train"] = spn_train_fit
df_test["spn_test"] = spn_test_fit
if dimensions == 3:
xy_train = cartesian(mixt_train)
xy_test = cartesian(mixt_test)
filename = 'plots/%s_%s.pdf' % (dsname, mixttype)
try:
import os
os.remove(filename)
except OSError:
pass
pp = PdfPages(filename)
markersize = 1.0
# all
# fig = plt.figure()
# plt.title("dirichlet, original points")
# draw_pdf_contours_func2(plotDirichlet, vmin=-2, vmax=12)
# #draw_pdf_contours_func2(xy_all[:, 0], xy_all[:, 1],plotDirichlet)
# plt.plot(xy_all[:, 0], xy_all[:, 1], 'ro', markersize=markersize)
# plt.colorbar()
# pp.savefig(fig)
# train
fig = plt.figure()
plt.title("Dirichlet, train points")
draw_pdf_contours_func2(plotDirichlet, vmin=-2, vmax=12)
#draw_pdf_contours_func2(xy_all[:, 0], xy_all[:, 1],plotDirichlet)
plt.plot(xy_train[:, 0], xy_train[:, 1], 'ro', markersize=markersize)
#plt.colorbar()
fig.tight_layout()
pp.savefig(fig)
# test
fig = plt.figure()
plt.title("Dirichlet, test points")
draw_pdf_contours_func2(plotDirichlet, vmin=-2, vmax=12)
#draw_pdf_contours_func2(xy_all[:, 0], xy_all[:, 1],plotDirichlet)
plt.plot(xy_test[:, 0], xy_test[:, 1], 'ro', markersize=markersize)
#plt.colorbar()
fig.tight_layout()
pp.savefig(fig)
# all
# fig = plt.figure()
# plt.title("spn, original points")
# draw_pdf_contours_func2(spnpdf, vmin=-2, vmax=12)
# #draw_pdf_contours_func2(xy_all[:, 0], xy_all[:, 1],spnpdf)
#
# plt.plot(xy_all[:, 0], xy_all[:, 1], 'ro', markersize=markersize)
# plt.colorbar()
# pp.savefig(fig)
# train
fig = plt.figure()
plt.title("SPN, train points")
draw_pdf_contours_func2(spnpdf, vmin=-2, vmax=12)
#draw_pdf_contours_func2(xy_all[:, 0], xy_all[:, 1],spnpdf)
plt.plot(xy_train[:, 0], xy_train[:, 1], 'ro', markersize=markersize)
#plt.colorbar()
fig.tight_layout()
pp.savefig(fig)
# test
fig = plt.figure()
plt.title("SPN, test points")
draw_pdf_contours_func2(spnpdf, vmin=-2, vmax=12)
#draw_pdf_contours_func2(xy_all[:, 0], xy_all[:, 1],spnpdf)
plt.plot(xy_test[:, 0], xy_test[:, 1], 'ro', markersize=markersize)
#plt.colorbar()
fig.tight_layout()
pp.savefig(fig)
pp.close()
return ("name", dsname, "size", data.shape, "type", mixttype, "dims", dimensions,
"spn_train_LL", numpy.mean(spn_train_fit), "dir_train_LL", numpy.mean(dtrain_fit),
"spn_test_LL", numpy.mean(spn_test_fit), "dir_test_LL", numpy.mean(dtest_fit) ,
"spn_#_sum_nodes", spn.n_sum_nodes(), "spn_#_prod_nodes", spn.n_prod_nodes(), "spn_#_layers", spn.n_layers()
)
numpy.savetxt(proc_path,
proc_data,
fmt=feature_formats,
delimiter=',')
pfdomains = []
for i, (fn, ft, fd) in enumerate(zip(fnames, ftypes, cfdomains)):
if ft == 'continuous':
r = (fd['min'], fd['max'])
print('range', r)
#
# using astropy
fd = estimate_continuous_domain(train,
i,
range=r,
binning_method=args.bins)
# fd = estimate_continuous_domain_min_max(train, i, min=fd['min'], max=fd['max'])
print(fd)
pfdomains.append(fd)
#
# writing back the domain for the missing values
feature_info_name = '{}.{}'.format(d, FEATURE_INFO_EXT)
proc_feature_info_path = os.path.join(proc_dir, feature_info_name)
save_feature_info_dict(fnames,
ftypes,
pfdomains,
proc_feature_info_path,
domain_keys=False,
range=False)
feature_info_name = 'autism.{}'.format(FEATURE_INFO_EXT)
feature_info_path = os.path.join(args.datadir, feature_info_name)
fnames, ftypes, fdomains = load_feature_info_preprocess(feature_info_path)
logging.info('Loaded feature info file {}'.format(feature_info_path))
cfdomains = []
for i, (fn, ft, fd) in enumerate(zip(fnames, ftypes, fdomains)):
if ft == 'categorical':
if fd is None:
fd = estimate_categorical_domain(data, i)
elif ft == 'continuous':
if fd is None:
fd = estimate_continuous_domain(data, i,
range=(data[:, i].min() - 0.01,
data[:, i].max() + 0.01),
binning_method=bin_method)
elif ft == 'discrete':
if fd is None:
fd = estimate_categorical_domain(data, i)
# try:
# _ = [float(k) for k, v in fd.items()]
# except:
# logging.info('Cannot convert discrete domain to float {}'.format(fd))
# fd = {str(v): v for _k, v in fd.items()}
cfdomains.append(fd)
#
# feature info
print('Reading domains by feature info file stub {}'.format(
args.stub_feature_info_file))
_fnames, _ftypes, _domains = load_feature_info_preprocess(
args.stub_feature_info_file)
domains_x = _domains[:n_x]
print(domains_x)
print(_domains)
else:
print('Estimating domains by embeddings')
# domains_x = estimate_domains_range(full_x, feature_types_x)
bin_method = args.bins
bin_range_width = 0.001
domains_x = [
estimate_continuous_domain(
full_x,
i,
range=(full_x[:, i].min() - bin_range_width,
full_x[:, i].max() + bin_range_width),
binning_method=bin_method) for i in range(n_x)
]
domains_y = [estimate_categorical_domain(full_y, i) for i in range(n_y)]
domains = domains_x + domains_y
print('domains', domains)
out_feature_info_path = os.path.join(out_path, 'aug.raelk.features')
save_feature_info_dict(feature_names,
feature_types,
domains,
out_feature_info_path,
range=False)
print('Saved feature info file to ', out_feature_info_path)
