Last active
August 1, 2021 14:15
-
-
Save Christopher-Thornton/77d157158f643c75e2033779c1370de6 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import itertools | |
def prepro(pairs, filterout=None, hard_lmt=100000): | |
pairs['relation'] = 1 | |
G = nx.from_pandas_edgelist(pairs, 'subject', 'object', | |
create_using=nx.DiGraph()) | |
if filterout: | |
nodes = \ | |
list(set(pairs[~pairs.subject_type.isin(filterout)]['subject'].tolist() | |
+ pairs[~pairs.object_type.isin(filterout)]['object'].tolist())) | |
else: | |
nodes = G.nodes() | |
permutation = \ | |
pd.DataFrame(list(set(itertools.islice(itertools.permutations(nodes, | |
2), hard_lmt)) - set(zip(pairs.subject, | |
pairs.object))), columns=['subject', 'object']) | |
permutation.insert(1, 'relation', 0) | |
pairs.drop(['subject_type', 'object_type'], axis=1, inplace=True) | |
pairs = pairs.append(permutation) | |
pairs['subject_vector_norm'] = pairs.apply(lambda row: \ | |
nlp(row.subject).vector_norm, axis=1) | |
pairs['object_vector_norm'] = pairs.apply(lambda row: \ | |
nlp(row.object).vector_norm, axis=1) | |
pairs['cosine_similarity'] = pairs.apply(lambda row: \ | |
nlp(row.subject).similarity(nlp(row.object)), axis=1) | |
out_deg = nx.out_degree_centrality(G) | |
in_deg = nx.in_degree_centrality(G) | |
pairs['subject_out_centrality'] = pairs.apply(lambda row: \ | |
out_deg[row.subject], axis=1) | |
pairs['object_in_centrality'] = pairs.apply(lambda row: \ | |
in_deg[row.object], axis=1) | |
pagerank = nx.pagerank_scipy(G) | |
pairs['object_pagerank'] = pairs.apply(lambda row: \ | |
pagerank[row.object], axis=1) | |
hits = nx.hits(G) | |
pairs['subject_hub'] = pairs.apply(lambda row: \ | |
hits[0][row.subject], axis=1) | |
pairs['object_authority'] = pairs.apply(lambda row: \ | |
hits[1][row.object], axis=1) | |
cols = pairs.columns.tolist() | |
cols.insert(len(cols), cols.pop(cols.index('relation'))) | |
pairs = pairs.reindex(columns=cols) | |
return pairs |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment