def __init__(self, maxlen, num_tags, word_index, embeddings, model_type,
texts_to_eval_dir, dumpPath):
self.num_tags = num_tags
self.word_index = word_index
self.texts_to_eval_dir = texts_to_eval_dir
self.dumpPath = dumpPath
self.model_maker = nm.NeuralModel(maxlen, num_tags, word_index,
embeddings)
num_measures = 1 + 3 * (num_tags - 2)
self.evaluator = ev.Evaluator(num_tags, num_measures,
self.model_maker.tags)
self.postprocessing = pp.PostProcessing(num_tags,
self.model_maker.tags)
import ast
import copy
import statistics
import Evaluator as ev
import PostProcessing as pp
import text_to_model_output as ttmo
import statistics
tags = ['(I)', '(O)', '(P)', '(C)']
num_tags = 4
num_measures = 1 + 3*(num_tags - 2)
evaluator = ev.Evaluator(num_tags, num_measures, tags)
postprocessing = pp.PostProcessing(num_tags, tags)
def cluster_counter(unencodedY, y_test_dist, y_pred_dist):
(true_spans, pred_spans) = postprocessing.replace_argument_tag(unencodedY)
true_spans_dict_list = evaluator.spanCreator(true_spans)
true_spans_closure = evaluator.edge_closure(true_spans, true_spans_dict_list, y_test_dist)
true_edges = evaluator.remove_redundant_edges(true_spans_closure, true_spans, 'true')
cluster_counter = []
cluster_sizes = []
for text in range(0, len(true_edges)):
cluster_sets = []
cluster_size = []
for node, links in true_edges[text].items():
new_cluster = set(links)
