def test_init_svd(self):
test_cases = [(self.space2, self.us, self.us2, self.x, self.row3)]
red1 = Svd(2)
red2 = Svd(1)
for in_s, expected_mat, expected_mat2, data, rows in test_cases:
in_s = in_s.apply(red1)
per_s = PeripheralSpace(in_s, DenseMatrix(data), rows)
np.testing.assert_array_almost_equal(expected_mat,
per_s.cooccurrence_matrix.mat,
2)
self.assertListEqual(per_s.id2row, in_s.id2row)
self.assertListEqual(per_s.id2column, [])
self.assertDictEqual(per_s.row2id, in_s.row2id)
self.assertDictEqual(per_s.column2id, {})
self.assertEqual(1, len(per_s.operations))
in_s = in_s.apply(red2)
per_s = PeripheralSpace(in_s, DenseMatrix(data), rows)
np.testing.assert_array_almost_equal(expected_mat2,
per_s.cooccurrence_matrix.mat,
2)
self.assertListEqual(per_s.id2row, in_s.id2row)
self.assertListEqual(per_s.id2column, [])
self.assertDictEqual(per_s.row2id, in_s.row2id)
self.assertDictEqual(per_s.column2id, {})
self.assertEqual(2, len(per_s.operations))
def transform_raw_per_space(raw_per_space, in_file_prefix, out_dir, out_format, core_space_file):
in_file_descr = "PER_SS." + in_file_prefix.split("/")[-1]
core_space = io_utils.load(core_space_file, Space)
core_descr = ".".join(core_space_file.split("/")[-1].split(".")[0:-1])
space = PeripheralSpace(core_space, raw_per_space.cooccurrence_matrix, raw_per_space.id2row, raw_per_space.row2id)
print "Printing..."
out_file_prefix = "%s/%s.%s" % (out_dir, in_file_descr, core_descr)
io_utils.save(space, out_file_prefix + ".pkl")
if not out_format is None:
space.export(out_file_prefix, format=out_format)
def test_init(self):
test_cases = [(self.space1, self.m2, self.row2, np.array([[2, 0.5,
1]]),
np.array([[0.69314718, 0, 0]]))]
w1 = EpmiWeighting()
w2 = PlogWeighting()
for core_s, per_mat, per_row, per_mat_out1, per_mat_out2 in test_cases:
tmp_mat = per_mat.copy()
tmp_core_mat = core_s.cooccurrence_matrix.mat
per_s1 = PeripheralSpace(core_s, DenseMatrix(per_mat), per_row)
np.testing.assert_array_equal(per_s1.cooccurrence_matrix.mat,
tmp_mat)
self.assert_column_identical(per_s1, core_s)
self.assertListEqual(per_s1.id2row, per_row)
self.assertListEqual(per_s1.operations, core_s.operations)
core_s1 = core_s.apply(w1)
per_s2 = PeripheralSpace(core_s1, DenseMatrix(per_mat), per_row)
np.testing.assert_array_almost_equal(
per_s2.cooccurrence_matrix.mat, per_mat_out1)
self.assert_column_identical(per_s2, core_s1)
self.assertListEqual(per_s2.id2row, per_row)
self.assertListEqual(per_s2.operations, core_s1.operations)
self.assertEqual(len(per_s2.operations), 1)
core_s2 = core_s1.apply(w2)
per_s3 = PeripheralSpace(core_s2, DenseMatrix(per_mat), per_row)
np.testing.assert_array_almost_equal(
per_s3.cooccurrence_matrix.mat, per_mat_out2)
self.assert_column_identical(per_s3, core_s2)
self.assertListEqual(per_s3.id2row, per_row)
self.assertListEqual(per_s3.operations, core_s2.operations)
self.assertEqual(len(per_s3.operations), 2)
np.testing.assert_array_equal(tmp_core_mat,
core_s.cooccurrence_matrix.mat)
core_s3 = core_s2
per_s4 = PeripheralSpace(core_s3, DenseMatrix(per_mat), per_row)
np.testing.assert_array_almost_equal(
per_s4.cooccurrence_matrix.mat, per_mat_out2)
self.assert_column_identical(per_s4, core_s2)
self.assertListEqual(per_s4.id2row, per_row)
self.assertListEqual(per_s4.operations, core_s3.operations)
self.assertEqual(len(per_s4.operations), 2)
np.testing.assert_array_equal(tmp_core_mat,
core_s.cooccurrence_matrix.mat)
def transform_raw_per_space(raw_per_space, in_file_prefix, out_dir, out_format,
core_space_file):
in_file_descr = "PER_SS." + in_file_prefix.split("/")[-1]
core_space = io_utils.load(core_space_file, Space)
core_descr = ".".join(core_space_file.split("/")[-1].split(".")[0:-1])
space = PeripheralSpace(core_space, raw_per_space.cooccurrence_matrix,
raw_per_space.id2row, raw_per_space.row2id)
print("Printing...")
out_file_prefix = "%s/%s.%s" % (out_dir, in_file_descr, core_descr)
io_utils.save(space, out_file_prefix + ".pkl")
if not out_format is None:
space.export(out_file_prefix, format=out_format)
def build_bigram_space():
bigrams_space = PeripheralSpace.build(unigrams_space,
data=args.function[3],
cols=args.function[1],
format="sm")
save_space(bigrams_space, "bigrams_space")
def test_add_rows_svd(self):
test_cases = [(self.space2, np.vstack([self.us2[0], self.us2[0]]),
self.m1, ["e"], ["f"], {"e":0, "f":1})]
red1 = Svd(2)
red2 = Svd(1)
for in_s, expected_mat, data, id2row1, id2row2, row2id in test_cases:
in_s = in_s.apply(red1)
in_s = in_s.apply(red2)
per_s = PeripheralSpace(in_s, DenseMatrix(data), id2row1)
per_s.add_rows(DenseMatrix(data), id2row2)
np.testing.assert_array_almost_equal(expected_mat,
per_s.cooccurrence_matrix.mat,
2)
self.assertListEqual(per_s.id2row, id2row1 + id2row2)
self.assertListEqual(per_s.id2column, [])
self.assertDictEqual(per_s.row2id, row2id)
self.assertDictEqual(per_s.column2id, {})
self.assertEqual(2, len(per_s.operations))
def test_add_rows_svd(self):
test_cases = [(self.space2, np.vstack([self.us2[0], self.us2[0]]),
self.m1, ["e"], ["f"], {
"e": 0,
"f": 1
})]
red1 = Svd(2)
red2 = Svd(1)
for in_s, expected_mat, data, id2row1, id2row2, row2id in test_cases:
in_s = in_s.apply(red1)
in_s = in_s.apply(red2)
per_s = PeripheralSpace(in_s, DenseMatrix(data), id2row1)
per_s.add_rows(DenseMatrix(data), id2row2)
np.testing.assert_array_almost_equal(expected_mat,
per_s.cooccurrence_matrix.mat,
2)
self.assertListEqual(per_s.id2row, id2row1 + id2row2)
self.assertListEqual(per_s.id2column, [])
self.assertDictEqual(per_s.row2id, row2id)
self.assertDictEqual(per_s.column2id, {})
self.assertEqual(2, len(per_s.operations))
def test_add_rows(self):
test_cases = [(self.space1, self.m2, self.row2, np.array([[4, 2,
6]]), ["c"],
np.array([[4, 2, 6], [4, 2, 6]]),
np.array([[0.69314718, 0, 0], [0.69314718, 0, 0]]), {
"b": 0,
"c": 1
}, ["b", "c"])]
for (core_sp, per_mat1, id2row1, per_mat2, id2row2, per_exp_mat1,
per_exp_mat2, per_exp_row2id, per_exp_id2row) in test_cases:
per_sp = PeripheralSpace(core_sp, DenseMatrix(per_mat1), id2row1)
per_sp.add_rows(DenseMatrix(per_mat2), id2row2)
np.testing.assert_array_almost_equal(
per_sp.cooccurrence_matrix.mat, per_exp_mat1, 7)
self.assertDictEqual(per_sp.row2id, per_exp_row2id)
self.assertListEqual(per_sp.id2row, per_exp_id2row)
self.assertDictEqual(per_sp.column2id, core_sp.column2id)
self.assertListEqual(per_sp.id2column, core_sp.id2column)
core_sp2 = core_sp.apply(PpmiWeighting())
per_sp2 = PeripheralSpace(core_sp2, DenseMatrix(per_mat1), id2row1)
per_sp2.add_rows(DenseMatrix(per_mat2), id2row2)
np.testing.assert_array_almost_equal(
per_sp2.cooccurrence_matrix.mat, per_exp_mat2, 7)
self.assertRaises(ValueError, per_sp2.add_rows,
DenseMatrix(per_mat2), id2row1)
self.assertRaises(ValueError, per_sp2.add_rows,
DenseMatrix(per_mat2), id2row2)
self.assertRaises(ValueError, per_sp2.add_rows,
DenseMatrix(per_mat2), ["d", "e"])
def test_add_rows(self):
test_cases = [(self.space1, self.m2, self.row2,
np.array([[4,2,6]]), ["c"],
np.array([[4,2,6],[4,2,6]]),
np.array([[0.69314718,0,0],[0.69314718,0,0]]),
{"b":0,"c":1},
["b", "c"])]
for (core_sp, per_mat1, id2row1, per_mat2, id2row2, per_exp_mat1,
per_exp_mat2, per_exp_row2id, per_exp_id2row) in test_cases:
per_sp = PeripheralSpace(core_sp, DenseMatrix(per_mat1), id2row1)
per_sp.add_rows(DenseMatrix(per_mat2), id2row2)
np.testing.assert_array_almost_equal(per_sp.cooccurrence_matrix.mat,
per_exp_mat1, 7)
self.assertDictEqual(per_sp.row2id, per_exp_row2id)
self.assertListEqual(per_sp.id2row, per_exp_id2row)
self.assertDictEqual(per_sp.column2id, core_sp.column2id)
self.assertListEqual(per_sp.id2column, core_sp.id2column)
core_sp2 = core_sp.apply(PpmiWeighting())
per_sp2 = PeripheralSpace(core_sp2, DenseMatrix(per_mat1), id2row1)
per_sp2.add_rows(DenseMatrix(per_mat2), id2row2)
np.testing.assert_array_almost_equal(per_sp2.cooccurrence_matrix.mat,
per_exp_mat2, 7)
self.assertRaises(ValueError, per_sp2.add_rows,
DenseMatrix(per_mat2), id2row1)
self.assertRaises(ValueError, per_sp2.add_rows,
DenseMatrix(per_mat2), id2row2)
self.assertRaises(ValueError, per_sp2.add_rows,
DenseMatrix(per_mat2), ["d", "e"])
def test_per_space_top_feat_selection(self):
test_cases = [(self.space_d, 1, ["f3"], {
"f3": 0
}, np.mat([[3], [5]])),
(self.space_d, 2, ["f3", "f1"], {
"f3": 0,
"f1": 1
}, np.mat([[3, 1], [5, 4]])),
(self.space_d, 4, ["f3", "f1", "f2"], {
"f3": 0,
"f1": 1,
"f2": 2
}, np.mat([[3, 1, 2], [5, 4, 0]]))]
for space_d, no_dim, id2col, col2id, mat in test_cases:
trans = TopFeatureSelection(no_dim)
new_space = space_d.apply(trans)
#peripheral test simple test
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a),
["c", "d"])
self.assertListEqual(per_sp.id2row, ["c", "d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_equal(per_sp.cooccurrence_matrix.mat, mat)
#peripheral test with add rows
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a[0, :]),
["c"])
per_sp.add_rows(DenseMatrix(self.a[1, :]), ["d"])
self.assertListEqual(per_sp.id2row, ["c", "d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_equal(per_sp.cooccurrence_matrix.mat, mat)
#peripheral test, with plog applied to core BEFORE feat selection
plogmat = mat.copy()
plogmat[plogmat == 0] = 1
plogmat = np.log(plogmat)
new_space = space_d.apply(PlogWeighting())
trans = TopFeatureSelection(no_dim)
new_space = new_space.apply(trans)
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a),
["c", "d"])
self.assertListEqual(per_sp.id2row, ["c", "d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_almost_equal(
per_sp.cooccurrence_matrix.mat, plogmat, 7)
#peripheral test, with plog applied to core AFTER feat selection
trans = TopFeatureSelection(no_dim)
new_space = space_d.apply(trans)
new_space = new_space.apply(PlogWeighting())
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a),
["c", "d"])
self.assertListEqual(per_sp.id2row, ["c", "d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_almost_equal(
per_sp.cooccurrence_matrix.mat, plogmat, 7)
space_file = data_path + "CORE_SS.verbnoun.core.pkl"
space = io_utils.load(space_file)
print "Applying PPMI..."
space = space.apply(PpmiWeighting())
print "Applying feature selection..."
space = space.apply(TopFeatureSelection(2000))
print "Applying SVD..."
space = space.apply(Svd(100))
print "Creating peripheral space.."
per_space = PeripheralSpace.build(space,
data=data_path + "per.raw.SV.sm",
cols=data_path + "per.raw.SV.cols",
format="sm")
#reading in train data
train_data_file = data_path + "ML08_SV_train.txt"
train_data = io_utils.read_tuple_list(train_data_file, fields=[0, 1, 2])
print "Training Lexical Function composition model..."
comp_model = LexicalFunction(learner=RidgeRegressionLearner(param=2))
comp_model.train(train_data, space, per_space)
print "Composing phrases..."
test_phrases_file = data_path + "ML08nvs_test.txt"
test_phrases = io_utils.read_tuple_list(test_phrases_file, fields=[0, 1, 2])
composed_space = comp_model.compose(test_phrases, space)
#ex05.py
#-------
from composes.utils import io_utils
from composes.semantic_space.peripheral_space import PeripheralSpace
from composes.transformation.scaling.ppmi_weighting import PpmiWeighting
#load a space and apply ppmi on it
my_space = io_utils.load("./data/out/ex01.pkl")
my_space = my_space.apply(PpmiWeighting())
print(my_space.cooccurrence_matrix)
print(my_space.id2row)
#create a peripheral space
my_per_space = PeripheralSpace.build(my_space,
data="./data/in/ex05.sm",
cols="./data/in/ex05.cols",
format="sm")
print(my_per_space.cooccurrence_matrix)
print(my_per_space.id2row)
#save the space
io_utils.save(my_per_space, "./data/out/PER_SS.ex05.pkl")
space_file = data_path + "CORE_SS.verbnoun.core.pkl"
space = io_utils.load(space_file)
print "Applying PPMI..."
space = space.apply(PpmiWeighting())
print "Applying feature selection..."
space = space.apply(TopFeatureSelection(2000))
print "Applying SVD..."
space = space.apply(Svd(100))
print "Creating peripheral space.."
per_space = PeripheralSpace.build(space,
data = data_path + "per.raw.SV.sm",
cols = data_path + "per.raw.SV.cols",
format = "sm"
)
#reading in train data
train_data_file = data_path + "ML08_SV_train.txt"
train_data = io_utils.read_tuple_list(train_data_file, fields=[0,1,2])
print "Training Lexical Function composition model..."
comp_model = LexicalFunction(learner = RidgeRegressionLearner(param=2))
comp_model.train(train_data, space, per_space)
print "Composing phrases..."
test_phrases_file = data_path + "ML08nvs_test.txt"
test_phrases = io_utils.read_tuple_list(test_phrases_file, fields=[0,1,2])
composed_space = comp_model.compose(test_phrases, space)
#ex05.py
#-------
from composes.utils import io_utils
from composes.semantic_space.peripheral_space import PeripheralSpace
from composes.transformation.scaling.ppmi_weighting import PpmiWeighting
#load a space and apply ppmi on it
my_space = io_utils.load("./data/out/ex01.pkl")
my_space = my_space.apply(PpmiWeighting())
print my_space.cooccurrence_matrix
print my_space.id2row
#create a peripheral space
my_per_space = PeripheralSpace.build(my_space,
data="./data/in/ex05.sm",
cols="./data/in/ex05.cols",
format="sm")
print my_per_space.cooccurrence_matrix
print my_per_space.id2row
#save the space
io_utils.save(my_per_space, "./data/out/PER_SS.ex05.pkl")
def train_baroni_guevara_composers(all_vectors,
ROOT_DIR,
baroni_output_path, guevara_output_path,
baroni_threshold=10):
"""
:type all_vectors: str; path to vectors file containing both N and observed AN vectors
:type ROOT_DIR: str; where to write temp files
:type baroni_output_path: str; where to write pickled baroni composer
:type guevara_output_path: str
:type baroni_threshold: int
"""
SVD_DIMS = 100
baroni_training_phrase_types = {'AN', 'NN'} # what kind of NPs to train Baroni composer for
# prepare the input files to be fed into Dissect
mkdirs_if_not_exists(ROOT_DIR)
filename = basename(all_vectors)
noun_events_file = join(ROOT_DIR, '%s-onlyN-SVD%d.tmp' % (filename, SVD_DIMS))
NPs_events_file = join(ROOT_DIR, '%s-onlyPhrases-SVD%d.tmp' % (filename, SVD_DIMS))
thes = Vectors.from_tsv(all_vectors, lowercasing=False)
thes.to_tsv(noun_events_file,
entry_filter=lambda x: x.type == '1-GRAM' and x.tokens[0].pos == 'N')
_translate_byblo_to_dissect(noun_events_file)
thes.to_tsv(NPs_events_file,
entry_filter=lambda x: x.type in baroni_training_phrase_types,
row_transform=lambda x: str(x).replace(' ', '_'))
_translate_byblo_to_dissect(NPs_events_file)
my_space = Space.build(data="{}.sm".format(noun_events_file),
rows="{}.rows".format(noun_events_file),
cols="{}.cols".format(noun_events_file),
format="sm")
logging.info('Each unigram vector has dimensionality %r', my_space.element_shape)
# create a peripheral space
my_per_space = PeripheralSpace.build(my_space,
data="{}.sm".format(NPs_events_file),
rows="{}.rows".format(NPs_events_file),
# The columns of the peripheral space have to be identical to those
# in the core space (including their order)!
cols="{}.cols".format(NPs_events_file),
format="sm")
logging.info('Each phrase vector has dimensionality %r', my_per_space.element_shape)
# use the model to compose words in my_space
all_data = []
for phrase in my_per_space._row2id:
# make sure there are only NPs here
if DocumentFeature.from_string(phrase.replace(' ', '_')).type in baroni_training_phrase_types:
adj, noun = phrase.split('_')
all_data.append((adj, noun, '%s_%s' % (adj, noun)))
# train a composition model on the data and save it
baroni = LexicalFunction(min_samples=baroni_threshold, learner=RidgeRegressionLearner())
guevara = FullAdditive(learner=RidgeRegressionLearner())
for composer, out_path in zip([baroni, guevara],
[baroni_output_path, guevara_output_path]):
composer.train(all_data, my_space, my_per_space)
io_utils.save(composer, out_path)
logging.info('Saved trained composer to %s', out_path)
def test_per_space_top_feat_selection(self):
test_cases = [(self.space_d, 1, ["f3"], {"f3":0},
np.mat([[3],[5]])),
(self.space_d, 2, ["f3", "f1"], {"f3":0, "f1":1},
np.mat([[3,1],[5,4]])),
(self.space_d, 4, ["f3", "f1", "f2"],
{"f3":0, "f1":1, "f2":2},
np.mat([[3,1,2],[5,4,0]]))
]
for space_d, no_dim, id2col, col2id, mat in test_cases:
trans = TopFeatureSelection(no_dim)
new_space = space_d.apply(trans)
#peripheral test simple test
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a), ["c","d"])
self.assertListEqual(per_sp.id2row, ["c","d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_equal(per_sp.cooccurrence_matrix.mat,
mat)
#peripheral test with add rows
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a[0,:]), ["c"])
per_sp.add_rows(DenseMatrix(self.a[1,:]), ["d"])
self.assertListEqual(per_sp.id2row, ["c","d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_equal(per_sp.cooccurrence_matrix.mat,
mat)
#peripheral test, with plog applied to core BEFORE feat selection
plogmat = mat.copy()
plogmat[plogmat==0] = 1
plogmat = np.log(plogmat)
new_space = space_d.apply(PlogWeighting())
trans = TopFeatureSelection(no_dim)
new_space = new_space.apply(trans)
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a), ["c","d"])
self.assertListEqual(per_sp.id2row, ["c","d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_almost_equal(per_sp.cooccurrence_matrix.mat,
plogmat, 7)
#peripheral test, with plog applied to core AFTER feat selection
trans = TopFeatureSelection(no_dim)
new_space = space_d.apply(trans)
new_space = new_space.apply(PlogWeighting())
per_sp = PeripheralSpace(new_space, DenseMatrix(self.a), ["c","d"])
self.assertListEqual(per_sp.id2row, ["c","d"])
self.assertListEqual(per_sp.id2column, id2col)
self.assertDictEqual(per_sp.column2id, col2id)
np.testing.assert_array_almost_equal(per_sp.cooccurrence_matrix.mat,
plogmat, 7)
sys.stderr.flush()
gastrovec = Space.build(data = "../corpus_collection/corpus.sm",
rows = "../corpus_collection/corpus.rows",
cols = "../corpus_collection/corpus.cols",
format = "sm")
print("done.", file=sys.stderr)
io_utils.save(gastrovec, "gastrovec.pkl")
print("Applying PPMI... ",end="", file=sys.stderr)
sys.stderr.flush()
gastrovec = gastrovec.apply(PpmiWeighting())
print("Applying SVD (20)... ",end="",file=sys.stderr)
sys.stderr.flush()
gastrovec = gastrovec.apply(Svd(20))
print("done.", file=sys.stderr)
io_utils.save(gastrovec, "gastrovec.ppmi.svd20.pkl")
print("Loading recipe peripheral space...",end="",file=sys.stderr)
sys.stderr.flush()
recipes = PeripheralSpace.build(gastrovec,
data = "../corpus_collection/recipes.sm",
rows = "../corpus_collection/recipes.rows",
cols = "../corpus_collection/recipes.cols",
format = "sm")
print("done.", file=sys.stderr)
io_utils.save(recipes, "recipes.ppmi.svd20.pkl")