def test_nmf_many_padding(eng):
data, series, truth = make_gaussian(n=5, noise=0.5, seed=42, engine=eng, withparams=True)
algorithm = NMF()
model = algorithm.fit(data, chunk_size=(50, 100), padding=(25, 25))
distances = cdist(model.regions.center, truth.regions.center)
assert model.regions.count == 10
assert allclose(sum(distances < 10), [2, 1, 2, 4, 1])
def test_merging(eng):
data, series, truth = make_gaussian(n=20, seed=42, noise=0.5, withparams=True)
algorithm = NMF(k=5, percentile=95, max_iter=50, overlap=0.1)
model = algorithm.fit(data, chunk_size=(50,100), padding=(15,15))
assert model.regions.count > 20
assert model.merge(overlap=0.5).regions.count <= 20
assert model.merge(overlap=0.1).regions.count < 18
def test_nmf_one(eng):
data, series, truth = make_gaussian(n=1,
noise=0.5,
seed=42,
engine=eng,
withparams=True)
algorithm = NMF()
model = algorithm.fit(data, chunk_size=(100, 200))
assert model.regions.count == 1
assert allclose(model.regions.center, truth.regions.center, 0.1)
def test_nmf_many_padding(eng):
data, series, truth = make_gaussian(n=5,
noise=0.5,
seed=42,
engine=eng,
withparams=True)
algorithm = NMF()
model = algorithm.fit(data, chunk_size=(50, 100), padding=(25, 25))
distances = cdist(model.regions.center, truth.regions.center)
assert model.regions.count == 10
assert allclose(sum(distances < 10), [2, 1, 2, 4, 1])
def test_nmf_many_chunked(eng):
data, series, truth = make_gaussian(n=5,
noise=0.5,
seed=42,
engine=eng,
withparams=True)
algorithm = NMF()
model = algorithm.fit(data, chunk_size=(50, 100))
assert model.regions.count == 5
assert allclose(
sum(cdist(model.regions.center, truth.regions.center) < 10),
[1, 1, 1, 1, 1])
# generate data
from extraction.utils import make_gaussian
data = make_gaussian(noise=0.5)
# fit a model
from extraction import NMF
model = NMF().fit(data, chunk_size=(100, 200))
# show estimated sources
import matplotlib.pyplot as plt
from showit import image
image(
model.regions.mask((100, 200),
fill=None,
stroke='deeppink',
base=data.mean().toarray() / 2))
plt.show()
def test_nmf_one(eng): data, series, truth = make_gaussian(n=1, noise=0.5, seed=42, engine=eng, withparams=True) algorithm = NMF() model = algorithm.fit(data, block_size=(100,200)) assert model.regions.count == 1 assert allclose(model.regions.center, truth.regions.center, 0.1)
def test_nmf_many(eng): data, series, truth = make_gaussian(n=5, noise=0.5, seed=42, engine=eng, withparams=True) algorithm = NMF() model = algorithm.fit(data, block_size=(100,200)) assert model.regions.count == 5 assert allclose(sum(cdist(model.regions.center, truth.regions.center) < 10), [1, 1, 1, 1,1])
# generate data from pyspark import SparkContext sc = SparkContext() from extraction.utils import make_gaussian data = make_gaussian(engine=sc) # fit a model from extraction import NMF model = NMF().fit(data) # extract sources by transforming data sources = model.transform(data) print model.regions.count
