def by_mrmr(X, y, n_features_to_select=None, only_get_index=True):
from sklmrmr import MRMR
mrmr = MRMR(n_features_to_select=n_features_to_select)
mrmr.fit(X, y)
index = ret.get_support(indices=True)
if only_get_index == True:
return index
else:
return mrmr.transform(X, y)
def test_mrmr(self):
X = np.zeros((10, 10))
X[5:, 0] = 1
y = np.zeros(10)
y[5:] = 1
model = MRMR(k=1)
model.fit(X, y)
assert model.selected_[0] == 0
assert model.n_features_ == 1
def test_discrete(ARGS):
# set these to this so we don't exclude anything (just testing file generation and parsing)
ARGS.NUM_FEATURES = 15 # should be enough, the number is known to be 13
ARGS.MRMR_METHOD = 'MID'
ARGS.MAX_CONSERVATION = 1.0
ARGS.MAX_GAP_RATIO = 1.0
ARGS.MIN_CONSERVATION = 1.0
ARGS.CUTOFF = 20.
# if we don't do this, DOOMBUNNIES
set_util_params(ARGS.REFSEQ_IDS)
fd, sto_filename = mkstemp(); close(fd)
try:
fh = open(sto_filename, 'w')
print(TEST_AMINO_STO, file=fh)
fh.close()
alignment = AlignIO.read(sto_filename, 'stockholm')
for ARGS.ENCODER in (AminoEncoder, StanfelEncoder):
if ARGS.ENCODER == StanfelEncoder:
TEST_NAMES = TEST_STANFEL_NAMES
TEST_X = TEST_STANFEL_X
else:
TEST_NAMES = TEST_AMINO_NAMES
TEST_X = TEST_AMINO_X
# test mRMR and LSVM file generation
ylabeler = Labeler(
seqrecord_get_values,
lambda row: is_refseq(row) or False, # TODO: again filtration function
lambda x: x > ARGS.CUTOFF,
False
)
alignment, y, ic50 = ylabeler(alignment)
refidx = reference_index(alignment, is_refseq)
alignment = LabeledMSA.from_msa_with_ref(alignment, refidx)
extractor = SiteVectorizer(ARGS.ENCODER)
x = extractor.fit_transform(alignment)
colnames = extractor.get_feature_names()
# test the feature names portion
try:
assert(len(colnames) == len(TEST_NAMES))
except AssertionError:
raise AssertionError('gen: %s\ntruth: %s' % (colnames, TEST_NAMES))
for name in TEST_NAMES:
try:
assert(name in colnames)
except AssertionError:
raise AssertionError('ERROR: \'%s\' not found in %s' % (name, ', '.join(colnames)))
assert(np.all(TEST_X == x))
assert(np.all(TEST_Y == y))
# generate and test the mRMR portion
mrmr = MRMR(
estimator=SVC(kernel='linear'),
n_features_to_select=ARGS.NUM_FEATURES,
method=ARGS.MRMR_METHOD,
normalize=ARGS.MRMR_NORMALIZE,
similar=ARGS.SIMILAR
)
mrmr.fit(x, y)
finally:
remove(sto_filename)
print('ALL TESTS PASS', file=sys.stderr)
' maximum relevance feature selection')
parser.add_argument('--method', type=str, default="mid")
parser.add_argument('--normalize', action='store_true')
parser.add_argument('--n_features', type=int, default=10)
parser.add_argument('--file', type=FileType('r'),
default=open(DEFAULT_FILE))
parser.add_argument('--digits', action='store_true')
ns = parser.parse_args(args)
if ns.digits:
X, y = get_digits()
data_name = 'digits'
else:
X, y = read_csv(ns.file)
data_name = ns.file.name
model = MRMR(k=ns.n_features, method=ns.method, normalize=ns.normalize)
names = list("feature_{}".format(i) for i in range(X.shape[1]))
print('running on {}'.format(data_name))
print('model: {}'.format(model))
t = time()
model.fit(X, y)
t = time() - t
print("time: {:.3f} seconds".format(t))
selected_names = list(names[i]
for i in np.argsort(model.ranking_)[:model.k])
print("selected features:\n{}".format(", ".join(selected_names)))
def test_discrete(ARGS):
# set these to this so we don't exclude anything (just testing file generation and parsing)
ARGS.NUM_FEATURES = 15 # should be enough, the number is known to be 13
ARGS.MRMR_METHOD = 'MID'
ARGS.MAX_CONSERVATION = 1.0
ARGS.MAX_GAP_RATIO = 1.0
ARGS.MIN_CONSERVATION = 1.0
ARGS.CUTOFF = 20.
# if we don't do this, DOOMBUNNIES
set_util_params(ARGS.REFSEQ_IDS)
fd, sto_filename = mkstemp(); close(fd)
try:
fh = open(sto_filename, 'w')
print(TEST_AMINO_STO, file=fh)
fh.close()
alignment = AlignIO.read(sto_filename, 'stockholm')
for ARGS.ENCODER in (AminoEncoder, StanfelEncoder):
if ARGS.ENCODER == StanfelEncoder:
TEST_NAMES = TEST_STANFEL_NAMES
TEST_X = TEST_STANFEL_X
else:
TEST_NAMES = TEST_AMINO_NAMES
TEST_X = TEST_AMINO_X
# test mRMR and LSVM file generation
ylabeler = Labeler(
seqrecord_get_values,
lambda row: is_refseq(row) or False, # TODO: again filtration function
lambda x: x > ARGS.CUTOFF,
False
)
alignment, y, ic50 = ylabeler(alignment)
refidx = reference_index(alignment, is_refseq)
alignment = LabeledMSA.from_msa_with_ref(alignment, refidx)
extractor = MSAVectorizer(ARGS.ENCODER)
x = extractor.fit_transform(alignment)
colnames = extractor.get_feature_names()
# test the feature names portion
try:
assert(len(colnames) == len(TEST_NAMES))
except AssertionError:
raise AssertionError('gen: %s\ntruth: %s' % (colnames, TEST_NAMES))
for name in TEST_NAMES:
try:
assert(name in colnames)
except AssertionError:
raise AssertionError('ERROR: \'%s\' not found in %s' % (name, ', '.join(colnames)))
assert(np.all(TEST_X == x))
assert(np.all(TEST_Y == y))
# generate and test the mRMR portion
mrmr = MRMR(
estimator=SVC(kernel='linear'),
n_features_to_select=ARGS.NUM_FEATURES,
method=ARGS.MRMR_METHOD,
normalize=ARGS.MRMR_NORMALIZE,
similar=ARGS.SIMILAR
)
mrmr.fit(x, y)
finally:
remove(sto_filename)
print('ALL TESTS PASS', file=sys.stderr)
