def evaluate_file(self, das_file, ttree_file): """Evaluate the reranking classifier on a given pair of DA/tree files (show the total Hamming distance and total number of DAIs) @param das_file: DA file path @param ttree_file: trees/sentences file path @return: a tuple (total DAIs, distance) """ das = read_das(das_file) ttree_doc = read_ttrees(ttree_file) if self.mode == 'tokens': tokens = tokens_from_doc(ttree_doc, self.language, self.selector) trees = self._tokens_to_flat_trees(tokens) elif self.mode == 'tagged_lemmas': tls = tagged_lemmas_from_doc(ttree_doc, self.language, self.selector) trees = self._tokens_to_flat_trees(tls) else: trees = trees_from_doc(ttree_doc, self.language, self.selector) da_len = 0 dist = 0 for da, tree in zip(das, trees): da_len += len(da) dist += self.dist_to_da(da, [tree])[0] return da_len, dist
def _load_trees(self, ttree_file, selector=None): """Load input trees/sentences from a .yaml.gz/.pickle.gz (trees) or .txt (sentences) file.""" log_info('Reading t-trees/sentences from ' + ttree_file + '...') if ttree_file.endswith('.txt'): if self.mode == 'trees': raise ValueError("Cannot read trees from a .txt file (%s)!" % ttree_file) return read_tokens(ttree_file) else: ttree_doc = read_ttrees(ttree_file) if selector is None: selector = self.selector if self.mode == 'tokens': return tokens_from_doc(ttree_doc, self.language, selector) elif self.mode == 'tagged_lemmas': return tagged_lemmas_from_doc(ttree_doc, self.language, selector) else: return trees_from_doc(ttree_doc, self.language, selector)
def _init_training(self, das, trees, data_portion): """Initialize training. Store input data, initialize 1-hot feature representations for input and output and transform training data accordingly, initialize the classification neural network. @param das: name of source file with training DAs, or list of DAs @param trees: name of source file with corresponding trees/sentences, or list of trees @param data_portion: portion of the training data to be used (0.0-1.0) """ # read input from files or take it directly from parameters if not isinstance(das, list): log_info('Reading DAs from ' + das + '...') das = read_das(das) if not isinstance(trees, list): log_info('Reading t-trees from ' + trees + '...') ttree_doc = read_ttrees(trees) if self.mode == 'tokens': tokens = tokens_from_doc(ttree_doc, self.language, self.selector) trees = self._tokens_to_flat_trees(tokens) elif self.mode == 'tagged_lemmas': tls = tagged_lemmas_from_doc(ttree_doc, self.language, self.selector) trees = self._tokens_to_flat_trees(tls, use_tags=True) else: trees = trees_from_doc(ttree_doc, self.language, self.selector) elif self.mode in ['tokens', 'tagged_lemmas']: trees = self._tokens_to_flat_trees( trees, use_tags=self.mode == 'tagged_lemmas') # make training data smaller if necessary train_size = int(round(data_portion * len(trees))) self.train_trees = trees[:train_size] self.train_das = das[:train_size] # ignore contexts, if they are contained in the DAs if isinstance(self.train_das[0], tuple): self.train_das = [da for (context, da) in self.train_das] # delexicalize if DAs are lexicalized and we don't want that if self.delex_slots: self.train_das = [ da.get_delexicalized(self.delex_slots) for da in self.train_das ] # add empty tree + empty DA to training data # (i.e. forbid the network to keep any of its outputs "always-on") train_size += 1 self.train_trees.append(TreeData()) empty_da = DA.parse('inform()') self.train_das.append(empty_da) self.train_order = range(len(self.train_trees)) log_info('Using %d training instances.' % train_size) # initialize input features/embeddings if self.tree_embs: self.dict_size = self.tree_embs.init_dict(self.train_trees) self.X = np.array([ self.tree_embs.get_embeddings(tree) for tree in self.train_trees ]) else: self.tree_feats = Features(['node: presence t_lemma formeme']) self.tree_vect = DictVectorizer(sparse=False, binarize_numeric=True) self.X = [ self.tree_feats.get_features(tree, {}) for tree in self.train_trees ] self.X = self.tree_vect.fit_transform(self.X) # initialize output features self.da_feats = Features(['dat: dat_presence', 'svp: svp_presence']) self.da_vect = DictVectorizer(sparse=False, binarize_numeric=True) self.y = [ self.da_feats.get_features(None, {'da': da}) for da in self.train_das ] self.y = self.da_vect.fit_transform(self.y) log_info('Number of binary classes: %d.' % len(self.da_vect.get_feature_names())) # initialize I/O shapes if not self.tree_embs: self.input_shape = list(self.X[0].shape) else: self.input_shape = self.tree_embs.get_embeddings_shape() self.num_outputs = len(self.da_vect.get_feature_names()) # initialize NN classifier self._init_neural_network() # initialize the NN variables self.session.run(tf.global_variables_initializer())
def _init_training(self, das, trees, data_portion): """Initialize training. Store input data, initialize 1-hot feature representations for input and output and transform training data accordingly, initialize the classification neural network. @param das: name of source file with training DAs, or list of DAs @param trees: name of source file with corresponding trees/sentences, or list of trees @param data_portion: portion of the training data to be used (0.0-1.0) """ # read input from files or take it directly from parameters if not isinstance(das, list): log_info('Reading DAs from ' + das + '...') das = read_das(das) if not isinstance(trees, list): log_info('Reading t-trees from ' + trees + '...') ttree_doc = read_ttrees(trees) if self.mode == 'tokens': tokens = tokens_from_doc(ttree_doc, self.language, self.selector) trees = self._tokens_to_flat_trees(tokens) elif self.mode == 'tagged_lemmas': tls = tagged_lemmas_from_doc(ttree_doc, self.language, self.selector) trees = self._tokens_to_flat_trees(tls, use_tags=True) else: trees = trees_from_doc(ttree_doc, self.language, self.selector) elif self.mode in ['tokens', 'tagged_lemmas']: trees = self._tokens_to_flat_trees(trees, use_tags=self.mode == 'tagged_lemmas') # make training data smaller if necessary train_size = int(round(data_portion * len(trees))) self.train_trees = trees[:train_size] self.train_das = das[:train_size] # ignore contexts, if they are contained in the DAs if isinstance(self.train_das[0], tuple): self.train_das = [da for (context, da) in self.train_das] # delexicalize if DAs are lexicalized and we don't want that if self.delex_slots: self.train_das = [da.get_delexicalized(self.delex_slots) for da in self.train_das] # add empty tree + empty DA to training data # (i.e. forbid the network to keep any of its outputs "always-on") train_size += 1 self.train_trees.append(TreeData()) empty_da = DA.parse('inform()') self.train_das.append(empty_da) self.train_order = range(len(self.train_trees)) log_info('Using %d training instances.' % train_size) # initialize input features/embeddings if self.tree_embs: self.dict_size = self.tree_embs.init_dict(self.train_trees) self.X = np.array([self.tree_embs.get_embeddings(tree) for tree in self.train_trees]) else: self.tree_feats = Features(['node: presence t_lemma formeme']) self.tree_vect = DictVectorizer(sparse=False, binarize_numeric=True) self.X = [self.tree_feats.get_features(tree, {}) for tree in self.train_trees] self.X = self.tree_vect.fit_transform(self.X) # initialize output features self.da_feats = Features(['dat: dat_presence', 'svp: svp_presence']) self.da_vect = DictVectorizer(sparse=False, binarize_numeric=True) self.y = [self.da_feats.get_features(None, {'da': da}) for da in self.train_das] self.y = self.da_vect.fit_transform(self.y) log_info('Number of binary classes: %d.' % len(self.da_vect.get_feature_names())) # initialize I/O shapes if not self.tree_embs: self.input_shape = list(self.X[0].shape) else: self.input_shape = self.tree_embs.get_embeddings_shape() self.num_outputs = len(self.da_vect.get_feature_names()) # initialize NN classifier self._init_neural_network() # initialize the NN variables self.session.run(tf.global_variables_initializer())