class WeightedAdditiveModel(AdditiveModel):
weighted_additive = None
new_space = None
def __init__(self, space, alpha=None, beta=None, no_diff=False):
AdditiveModel.__init__(self, space, no_diff=no_diff)
self.weighted_additive = WeightedAdditive(alpha=alpha, beta=beta)
def fit(self, train_pairs, verbose=False):
AdditiveModel.fit(self, train_pairs, verbose=verbose)
if verbose:
print 'fit: Fitting a weighted additive model on %d pairs' % (len(train_pairs))
# First, we embed the derived vector into the original space (by simply adding a row)
vec_space = Space(self.diff_vector, ['pattern_vector'], [])
self.new_space = Space.vstack(self.space, vec_space)
# class is designed to be run on a dataset with different function words (==patterns).
# We use a dummy function word here.
train_pairs_ext = [(base, 'pattern_vector', derived) for (base, derived) in train_pairs]
self.weighted_additive.train(train_pairs_ext, self.new_space, self.new_space)
def predict(self, base, verbose=False):
if self.weighted_additive is None:
raise NameError('Error: Model has not yet been trained')
composed_space = self.weighted_additive.compose([(base, 'pattern_vector', 'derived')], self.new_space)
return composed_space.get_row('derived')
def test_train(self):
test_cases = [(self.m11, self.m21, self.ph1, 2, 3),
(self.m12, self.m22, self.ph2, 2, 3),
(self.m11, self.m21, DenseMatrix(np.mat([[0],[0]])), 0, 0),
(SparseMatrix(self.m12), SparseMatrix(self.m22),
SparseMatrix(self.ph2), 2, 3),
(self.m11, DenseMatrix(np.mat([[0],[0]])), self.ph1, 3, 0),
(DenseMatrix(np.mat([[0],[0]])), self.m11, self.ph1, 0, 3),
(DenseMatrix(np.mat([[1,2,3]])),
DenseMatrix(np.mat([[2,4,6]])),
DenseMatrix(np.mat([[3,6,9]])), 0.6, 1.2),
(DenseMatrix(np.mat([[0],[0]])),
DenseMatrix(np.mat([[0],[0]])),
DenseMatrix(np.mat([[0],[0]])), 0.0, 0.0)
]
id2row_dict = {1:["a"],2:["a", "b"]}
train_dict = {1:[("a", "a", "a")],2:[("a", "a", "a"), ("b", "b", "b")]}
for m1, m2, ph, expected_alpha, expected_beta in test_cases:
model = WeightedAdditive()
arg_space1 = Space(m1, id2row_dict[m1.shape[0]],[])
arg_space2 = Space(m2, id2row_dict[m1.shape[0]],[])
ph_space = Space(ph, id2row_dict[m1.shape[0]],[])
train_data = train_dict[m1.shape[0]]
#model._train(m1, m2, ph)
model.train(train_data, (arg_space1, arg_space2), ph_space)
self.assertAlmostEqual(model.alpha, expected_alpha, 8)
self.assertAlmostEqual(model.beta, expected_beta, 8)
def test_space_train(self):
test_cases = [ ([("a", "b", "a_b"), ("a", "a", "a_a")],
self.space1,
Space(DenseMatrix(np.mat([[12,3],[6,2]])),
["a_b", "a_a"],["f1", "f2"]),
1, 1
),
([("a", "b", "a_b"), ("a", "a", "a_a")],
self.space1,
Space(DenseMatrix(np.mat([[0,0],[0,0]])),
["a_b", "a_a"],["f1", "f2"]),
0, 0
),
([("a", "b", "a_b"), ("a", "a", "a_a")],
self.space1,
Space(DenseMatrix(np.mat([[0,0],[0,0]])),
["a_b", "a_a"],[]),
0, 0
),
([("a", "b", "a_b")],
self.space1,
Space(DenseMatrix(np.mat([[21,5]])),
["a_b"],[]),
1, 2
),
([("a", "b", "a_b"), ("bla", "b", "a_b"), ("a", "bla", "a_b")],
self.space1,
Space(DenseMatrix(np.mat([[21,5]])),
["a_b"],[]),
1, 2
)
]
for in_data, arg_space, phrase_space, alpha, beta in test_cases:
model = WeightedAdditive()
model.train(in_data, arg_space, phrase_space)
self.assertAlmostEqual(model.alpha, alpha, 7)
self.assertAlmostEqual(model.beta, beta, 7)
comp_space = model.compose(in_data, arg_space)
self.assertListEqual(comp_space.id2row, phrase_space.id2row)
self.assertListEqual(comp_space.id2column, phrase_space.id2column)
self.assertDictEqual(comp_space.row2id, phrase_space.row2id)
self.assertDictEqual(comp_space.column2id, phrase_space.column2id)
np.testing.assert_array_almost_equal(comp_space.cooccurrence_matrix.mat,
phrase_space.cooccurrence_matrix.mat,
8)
def test_weighted_additive(self):
self.m12 = DenseMatrix(np.mat([[3, 1], [9, 2]]))
self.m22 = DenseMatrix(np.mat([[4, 3], [2, 1]]))
self.ph2 = DenseMatrix(np.mat([[18, 11], [24, 7]]))
self.row = ["a", "b"]
self.ft = ["f1", "f2"]
self.space1 = Space(DenseMatrix(self.m12), self.row, self.ft)
self.space2 = Space(DenseMatrix(self.ph2), ["a_a", "a_b"], self.ft)
m = WeightedAdditive()
m.export(self.prefix + ".add1")
m.train([("a", "a", "a_a")], self.space1, self.space2)
m.export(self.prefix + ".add2")
def test_weighted_additive(self):
self.m12 = DenseMatrix(np.mat([[3,1],[9,2]]))
self.m22 = DenseMatrix(np.mat([[4,3],[2,1]]))
self.ph2 = DenseMatrix(np.mat([[18,11],[24,7]]))
self.row = ["a", "b"]
self.ft = ["f1","f2"]
self.space1 = Space(DenseMatrix(self.m12), self.row, self.ft)
self.space2 = Space(DenseMatrix(self.ph2), ["a_a","a_b"], self.ft)
m = WeightedAdditive()
m.export(self.prefix + ".add1")
m.train([("a","a","a_a")], self.space1, self.space2)
m.export(self.prefix + ".add2")
def create_model(model, alpha, beta, lambda_):
#TODO: IMPORTANT here: if alpha, beta of lambda are none
model_dict = {
"weighted_add": WeightedAdditive,
"dilation": Dilation,
"mult": Multiplicative
}
if not model in model_dict:
raise ValueError("Invalid model:%s" % model)
if model == "weighted_add":
model_obj = WeightedAdditive(alpha, beta)
elif model == "dilation":
model_obj = Dilation(lambda_)
else:
model_obj = Multiplicative()
return model_obj
def test_compose(self):
model = WeightedAdditive(2,3)
np.testing.assert_array_equal(model._compose(self.m11, self.m21).mat,
self.ph1.mat)
model = WeightedAdditive()
np.testing.assert_array_equal(model._compose(self.m11, self.m21).mat,
np.mat([[7/2.],[11/2.]]))
model = WeightedAdditive(0.5)
np.testing.assert_array_equal(model._compose(self.m11, self.m21).mat,
np.mat([[7/2.],[11/2.]]))
els_for_comp.append(element)
return els_for_comp
typ_space = create_space(TypDmFile, TypRowsFile)
distr_space = create_space(DistrDmFile, DistrRowsFile)
#load a space from a pickle file
#my_space = io_utils.load("./sharp/lexfunc/lexfunc_Ridge_pract.pkl")
#distributional vectors processing
distr_space = distr_space.apply(PpmiWeighting())
distr_space = distr_space.apply(Svd(300))
#io_utils.save(distr_space, "./spaces/smooth_phrases_ppmi.pkl")
items = items_from_file(itemsFile)
els_for_comp = elements_for_composition(items)
my_comp = WeightedAdditive(alpha=1, beta=1)
distr_space = my_comp.compose(els_for_comp, distr_space)
pairs = pairs(items)
predicted = distr_space.get_sims(pairs, CosSimilarity())
gold = typ_space.get_sims(pairs, CosSimilarity())
#compute correlations
print "Spearman"
print scoring_utils.score(gold, predicted, "spearman")
print "Pearson"
print scoring_utils.score(gold, predicted, "pearson")
#testAnalogy.py
#argv[1]: space pkl file
#argv[2]: analogy test file
#EXAMPLE: python testAnalogy.py ../../spaces/wikipedia.pkl analogy_dataset.txt
#-------
from composes.utils import io_utils
from composes.utils import scoring_utils
from composes.similarity.cos import CosSimilarity
from composes.composition.weighted_additive import WeightedAdditive
import sys
add = WeightedAdditive(alpha = 1, beta = 1.2)
sub = WeightedAdditive(alpha = 1, beta = -1)
#read in a space
space = io_utils.load(sys.argv[1])
def computeAnalogy(w1,w2,w3):
composed_space = sub.compose([(w1,w2, "step1")], space)
composed_space2 = add.compose([("step1", w3, "step2")], (composed_space,space))
guess=composed_space2.get_neighbours("step2", 1, CosSimilarity(),space)
return guess
score=0
#read in test file
fname = sys.argv[2]
f=open(fname,'r')
flines=f.readlines()
# 2) a file with short phrases (2 words, e.g. parliamentary potato) #------- from composes.utils import io_utils from composes.utils import scoring_utils from composes.similarity.cos import CosSimilarity from composes.composition.weighted_additive import WeightedAdditive from composes.composition.multiplicative import Multiplicative from composes.transformation.scaling.row_normalization import RowNormalization import numpy as np import sys #read in a space my_space = io_utils.load(sys.argv[1]) my_space = my_space.apply(RowNormalization()) add = WeightedAdditive(alpha = 1, beta = 1) mult = Multiplicative() #compute multiplication/addition of a list of word pairs fname = sys.argv[2] word_pairs = io_utils.read_tuple_list(fname, fields=[0,1]) lengths=[] found=True for wp in word_pairs: try: v1=my_space.get_row(wp[0]) v2=my_space.get_row(wp[1]) except KeyError: #print wp[0],"or",wp[1],"not found"
from __future__ import print_function
import sys
from random import randint
from itertools import count
from composes.utils import io_utils
from composes.composition.weighted_additive import WeightedAdditive
from composes.semantic_space.space import Space
stacked_space = io_utils.load("gastrovec.ppmi.svd20.pkl")
WA = WeightedAdditive(alpha = 1, beta = 1)
recipes = {}
max_size = 0
with open("../corpus_collection/composition_counts.txt") as f:
for line in f:
words = line.split()
recipes[words[0]] = words[1:]
if len(words)-1 > max_size:
max_size = len(words)-1
WA = WeightedAdditive(alpha = 1, beta = 1)
last_space = None
number = count()
for size in xrange(max_size,1,-1):
relevant = (rec for rec in recipes if len(recipes[rec]) == size)
print(size)
composition = []
for recipe in relevant:
old = recipes[recipe]
#ex10.py
#-------
from composes.utils import io_utils
from composes.composition.weighted_additive import WeightedAdditive
#load a space
my_space = io_utils.load("./data/out/ex10.pkl")
print my_space.id2row
print my_space.cooccurrence_matrix
# instantiate a weighted additive model
my_comp = WeightedAdditive(alpha = 1, beta = 1)
# use the model to compose words in my_space
composed_space = my_comp.compose([("good", "book", "good_book"),
("good", "car", "good_car")],
my_space)
print composed_space.id2row
print composed_space.cooccurrence_matrix
#save the composed space
io_utils.save(composed_space, "data/out/PHRASE_SS.ex10.pkl")
print "Computing similarity with lexical function..." pred = composed_space.get_sims(test_pairs, CosSimilarity()) #use this composed space to assign similarities print "Scoring lexical function..." print scoring_utils.score(gold, pred, "spearman") print "Training Full Additive composition model..." comp_model = FullAdditive(learner=RidgeRegressionLearner(param=2)) comp_model.train(train_data, space, per_space) composed_space = comp_model.compose(test_phrases, space) pred = composed_space.get_sims(test_pairs, CosSimilarity()) print scoring_utils.score(gold, pred, "spearman") print "Training Weighted Additive composition model..." comp_model = WeightedAdditive() comp_model.train(train_data, space, per_space) print "alpha, beta:", comp_model.alpha, comp_model.beta composed_space = comp_model.compose(test_phrases, space) pred = composed_space.get_sims(test_pairs, CosSimilarity()) print scoring_utils.score(gold, pred, "spearman") print "Training Dilation composition model..." comp_model = Dilation() comp_model.train(train_data, space, per_space) print "lambda:", comp_model._lambda composed_space = comp_model.compose(test_phrases, space) pred = composed_space.get_sims(test_pairs, CosSimilarity()) print scoring_utils.score(gold, pred, "spearman") print "Multiplicative composition model..."
##########################################################################
from composes.utils import io_utils
from composes.composition.weighted_additive import WeightedAdditive
from composes.similarity.cos import CosSimilarity
import sys
pkl=sys.argv[1]
base=sys.argv[2]
minus=sys.argv[3]
plus=sys.argv[4]
space = io_utils.load(pkl)
# instantiate an additive and subtractive model
add = WeightedAdditive(alpha = 1, beta = 1)
sub = WeightedAdditive(alpha = 1, beta = -1)
#print space.get_neighbours(base, 10, CosSimilarity())
print "Subtracting",minus,"from",base
composed_space = sub.compose([(base, minus, "step1")], space)
#print composed_space.get_neighbours("step1", 10, CosSimilarity(),space)
print "Adding",plus,"..."
composed_space2 = add.compose([("step1", plus, "step2")], (composed_space,space))
print composed_space2.get_neighbours("step2", 10, CosSimilarity(),space)
def ins(lst, el):
if len(lst) < num:
lst.append(el)
lst.sort(reverse=True)
return
else:
if el[0] > lst[-1][0]:
lst.pop(-1)
lst.append(el)
lst.sort(reverse=True)
stacked = io_utils.load("gastrovec.ppmi.svd20.pkl")
recicomp = io_utils.load(recipe_space)
WA = WeightedAdditive(alpha = 1, beta = 1)
number = count()
ingredients = []
print("Enter ingredients, enter when done")
while True:
ingredient = raw_input("> ").replace(" ","_")
if ingredient == "":
break
if ingredient not in stacked.id2row:
print("(not found, skipping)")
continue
ingredients.append(ingredient)
name = ""
while True:
#ex13.py
#-------
from composes.utils import io_utils
from composes.composition.weighted_additive import WeightedAdditive
#training data
train_data = [("good", "car", "good_car"), ("good", "book", "good_book")]
#load an argument space
arg_space = io_utils.load("./data/out/ex10.pkl")
print arg_space.id2row
print arg_space.cooccurrence_matrix
#load a phrase space
phrase_space = io_utils.load("data/out/PHRASE_SS.ex10.pkl")
print phrase_space.id2row
print phrase_space.cooccurrence_matrix
#train a weighted additive model on the data
my_comp = WeightedAdditive()
my_comp.train(train_data, arg_space, phrase_space)
#print its parameters
print "alpha:", my_comp.alpha
print "beta:", my_comp.beta
#ex11.py
#-------
from composes.utils import io_utils
from composes.composition.weighted_additive import WeightedAdditive
# instantiate a weighted additive model
my_comp = WeightedAdditive(alpha = 1, beta = 1)
#save it to pickle
io_utils.save(my_comp, "./data/out/model01.pkl")
#print its parameters
my_comp.export("./data/out/model01.params")
def __init__(self, space, alpha=None, beta=None, no_diff=False):
AdditiveModel.__init__(self, space, no_diff=no_diff)
self.weighted_additive = WeightedAdditive(alpha=alpha, beta=beta)
# 2) a file with short phrases (2 words, e.g. parliamentary potato)
#-------
from composes.utils import io_utils
from composes.utils import scoring_utils
from composes.similarity.cos import CosSimilarity
from composes.composition.weighted_additive import WeightedAdditive
from composes.composition.multiplicative import Multiplicative
from composes.transformation.scaling.row_normalization import RowNormalization
import numpy as np
import sys
#read in a space
my_space = io_utils.load(sys.argv[1])
my_space = my_space.apply(RowNormalization())
add = WeightedAdditive(alpha=1, beta=1)
mult = Multiplicative()
#compute multiplication/addition of a list of word pairs
fname = sys.argv[2]
word_pairs = io_utils.read_tuple_list(fname, fields=[0, 1])
lengths = []
found = True
for wp in word_pairs:
try:
v1 = my_space.get_row(wp[0])
v2 = my_space.get_row(wp[1])
except KeyError:
#print wp[0],"or",wp[1],"not found"
found = False
# Just exposing the possibility to learn peripheral space if we have a corpus where phrases etc are marked
# as one token. Then we can use the word2vec_bin_to_DISSECT_dm convertor to generate a similar dm
# print "Creating peripheral space.."
# per_space = PeripheralSpace.build(space,
# format = "dm",
# data ="SOME_PATH_FOR_A_WORD_TO_VEC_PERIPHERAL_SPACE_DATA"
# )
# Debug
# print space.cooccurrence_matrix
# print space.id2row
# instantiate a weighted additive model
my_comp = WeightedAdditive(alpha = 1, beta = 1)
# use the model to compose words in my_space
composed_space = my_comp.compose([("good", "book", "good_book"),
("good", "car", "good_car")],
space)
print composed_space.id2row
print composed_space.cooccurrence_matrix
print composed_space.get_sims([("good_car","good_book")], CosSimilarity()) # Similarity metric
#===============================================================================================================
print "="*80
#===============================================================================================================
##Training Models
#ex10.py
#-------
from composes.utils import io_utils
from composes.composition.weighted_additive import WeightedAdditive
#load a space
my_space = io_utils.load("./data/out/ex10.pkl")
print my_space.id2row
print my_space.cooccurrence_matrix
# instantiate a weighted additive model
my_comp = WeightedAdditive(alpha = 1, beta = 1)
# use the model to compose words in my_space
composed_space = my_comp.compose([("good", "book", "good_book"),
("good", "car", "good_car")],
my_space)
print composed_space.id2row
print composed_space.cooccurrence_matrix
#save the composed space
io_utils.save(composed_space, "data/out/PHRASE_SS.ex10.pkl")
#-------
from composes.utils import io_utils
from composes.composition.weighted_additive import WeightedAdditive
#training data
train_data = [("good", "car", "good_car"),
("good", "book", "good_book")
]
#load an argument space
arg_space = io_utils.load("./data/out/ex10.pkl")
print arg_space.id2row
print arg_space.cooccurrence_matrix
#load a phrase space
phrase_space = io_utils.load("data/out/PHRASE_SS.ex10.pkl")
print phrase_space.id2row
print phrase_space.cooccurrence_matrix
#train a weighted additive model on the data
my_comp = WeightedAdditive()
my_comp.train(train_data, arg_space, phrase_space)
#print its parameters
print "alpha:", my_comp.alpha
print "beta:", my_comp.beta