def setUp(self): self.id = False self.uv = False self.ub = False self.threshold = 0.8 self.assoc_threshold = 0.3 seed = 10 dim = 512 prop = 0.1 input_dir, output_dir = tools.read_config() relation_symbols = symbol_definitions.uni_relation_symbols() vector_factory = VectorFactory(seed) isA_symbols = symbol_definitions.isA_symbols() sentence_symbols = symbol_definitions.sentence_role_symbols() self.corpus_dict, self.id_vectors, self.semantic_pointers = \ tools.setup_corpus( input_dir, relation_symbols, dim, vector_factory, seed, self.id, self.uv, prop) self.createAssociator(self.id_vectors, self.semantic_pointers) self.tester = WordnetAssociativeMemoryTester( self.corpus_dict, self.id_vectors, self.semantic_pointers, relation_symbols, self.associator, seed, output_dir, isA_symbols, sentence_symbols, VectorFactory(), self.uv, True)
def __init__(self, dimension=512, input_dir="wordnet_data", unitary_relations=False, proportion=1.0, num_synsets=-1, id_vecs=True, relation_symbols=None, create_namedict=False, dry_run=False, sp_noise=0, normalize=True): self.dimension = dimension self.input_dir = input_dir self.unitary_relations = unitary_relations self.create_namedict = create_namedict self.normalize = normalize if sp_noise < 0: sp_noise = 0 self.sp_noise = sp_noise if relation_symbols is None: self.relation_symbols = symbol_definitions.uni_relation_symbols() else: self.relation_symbols = relation_symbols self.parse_wordnet() self.proportion = (float(num_synsets) / len(self.corpus_dict) if num_synsets > 0 else proportion) if self.proportion < 1.0: self.create_corpus_subset(self.proportion) print "Wordnet data parsed." if dry_run: print "Dry run. Skipping vectorization." else: self.form_knowledge_base(id_vecs, unitary_relations) print "Vectorization of WordNet complete"
def __init__(self, dimension=512, input_dir="wordnet_data", unitary_relations=False, proportion=1.0, num_synsets=-1, id_vecs=True, relation_symbols=None, create_namedict=False, dry_run=False, sp_noise=0, normalize=True): self.dimension = dimension self.input_dir = input_dir self.unitary_relations = unitary_relations self.create_namedict = create_namedict self.normalize = normalize if sp_noise < 0: sp_noise = 0 self.sp_noise = sp_noise if relation_symbols is None: self.relation_symbols = symbol_definitions.uni_relation_symbols() else: self.relation_symbols = relation_symbols self.parse_wordnet() self.proportion = (float(num_synsets)/len(self.corpus_dict) if num_synsets > 0 else proportion) if self.proportion < 1.0: self.create_corpus_subset(self.proportion) print "Wordnet data parsed." if dry_run: print "Dry run. Skipping vectorization." else: self.form_knowledge_base(id_vecs, unitary_relations) print "Vectorization of WordNet complete"