Loading code/absinth_nx.py +3 −5 Changes for code/absinth_nx.py: 3 added lines, 5 removed lines. Original line number Diff line number Diff line Loading @@ -9,7 +9,7 @@ import numpy as np # for calculations nlp = spacy.load('en') # standard english nlp def frequencies(corpus_path, target, stop_words=['utc', 'new', 'other'], allowed_tags=['NN','NNS','JJ','JJS','JJR','NNP'], min_context_size = 4, max_nodes=10000, max_edges=1000000): def frequencies(corpus_path, target, stop_words=['utc', 'new', 'other'], allowed_tags=['NN','NNS','JJ','JJS','JJR','NNP'], min_context_size = 4, max_nodes=100000, max_edges=10000000): node_freq = dict() edge_freq = dict() Loading Loading @@ -201,14 +201,12 @@ def disambiguate(mst, hubs, contexts): try: if max(vector) == 0: result.append((backup_cluster, idx)) backup_cluster += 1 pass else: cluster = np.argmax(vector) result.append((cluster, idx)) except: result.append((backup_cluster, idx)) backup_cluster += 1 result.append((0, idx)) return result Loading Loading
code/absinth_nx.py +3 −5 Changes for code/absinth_nx.py: 3 added lines, 5 removed lines. Original line number Diff line number Diff line Loading @@ -9,7 +9,7 @@ import numpy as np # for calculations nlp = spacy.load('en') # standard english nlp def frequencies(corpus_path, target, stop_words=['utc', 'new', 'other'], allowed_tags=['NN','NNS','JJ','JJS','JJR','NNP'], min_context_size = 4, max_nodes=10000, max_edges=1000000): def frequencies(corpus_path, target, stop_words=['utc', 'new', 'other'], allowed_tags=['NN','NNS','JJ','JJS','JJR','NNP'], min_context_size = 4, max_nodes=100000, max_edges=10000000): node_freq = dict() edge_freq = dict() Loading Loading @@ -201,14 +201,12 @@ def disambiguate(mst, hubs, contexts): try: if max(vector) == 0: result.append((backup_cluster, idx)) backup_cluster += 1 pass else: cluster = np.argmax(vector) result.append((cluster, idx)) except: result.append((backup_cluster, idx)) backup_cluster += 1 result.append((0, idx)) return result Loading