def merge(): ''' This function merges aidPERSONIDPAPERS with aidRESULTS. Use it after tortoise. ''' last_names = frozenset(name[0].split('.')[0] for name in get_existing_result_clusters()) def get_free_pids(): while True: yield get_new_personid() free_pids = get_free_pids() def try_move_signature(sig, target_pid): """ """ paps = get_signature_info(sig) claimed = filter(lambda p: p[1] <= -2, paps) assigned = filter(lambda p:-2 < p[1] and p[1] < 2, paps) rejected = filter(lambda p: 2 <= p[1] and p[0] == target_pid, paps) if claimed or not assigned or assigned[0] == target_pid: return assert len(assigned) == 1 if rejected: move_signature(sig, free_pids.next()) else: conflicts = find_conflicts(sig, target_pid) if not conflicts: move_signature(sig, target_pid) else: assert len(conflicts) == 1 if conflicts[0][3] == 2: move_signature(sig, free_pids.next()) else: move_signature(conflicts[0][:3], free_pids.next()) move_signature(sig, target_pid) for idx, last in enumerate(last_names): update_status(float(idx) / len(last_names), "%d/%d current: %s" % (idx, len(last_names), last)) results = ((int(row[0].split(".")[1]), row[1:4]) for row in get_lastname_results(last)) # [(last name number, [bibrefrecs])] results = [(k, map(itemgetter(1), d)) for k, d in groupby(sorted(results, key=itemgetter(0)), key=itemgetter(0))] # List of dictionaries. # [{new_pid -> N}] matr = [] # Set of all old pids. old_pids = set() for k, ds in results: pids = [] claim = [] for d in ds: pid_flag = personid_from_signature(d) if pid_flag: pid, flag = pid_flag[0] pids.append(pid) old_pids.add(pid) if flag > 1: claim.append((d, pid)) matr.append(dict((k, len(list(d))) for k, d in groupby(sorted(pids)))) # We cast it to list in order to ensure the order persistence. old_pids = list(old_pids) best_match = maximized_mapping([[row.get(old, 0) for old in old_pids] for row in matr]) matched_clusters = [(results[new_idx][1], old_pids[old_idx]) for new_idx, old_idx, unused in best_match] not_matched_clusters = frozenset(xrange(len(results))) - frozenset(imap(itemgetter(0), best_match)) not_matched_clusters = izip((results[i][1] for i in not_matched_clusters), free_pids) for sigs, pid in chain(matched_clusters, not_matched_clusters): for sig in sigs: try_move_signature(sig, pid) update_status_final() delete_empty_persons() update_personID_canonical_names()
def rabbit(bibrecs, check_invalid_papers=False): ''' @param bibrecs: an iterable full of bibrecs @type bibrecs: an iterable of ints @return: none ''' compare_names = cached_sym(lambda x: x)(comp_names) # fast assign threshold threshold = 0.80 if not bibrecs or check_invalid_papers: all_bibrecs = get_all_valid_bibrecs() if not bibrecs: bibrecs = all_bibrecs if check_invalid_papers: filter_bibrecs_outside(all_bibrecs) updated_pids = set() deleted = frozenset(p[0] for p in get_deleted_papers()) for idx, rec in enumerate(bibrecs): task_sleep_now_if_required(True) update_status(float(idx) / len(bibrecs), "%d/%d current: %d" % (idx, len(bibrecs), rec)) if rec in deleted: delete_paper_from_personid(rec) continue markrefs = frozenset(chain(izip(cycle([100]), imap(itemgetter(0), get_authors_from_paper(rec))), izip(cycle([700]), imap(itemgetter(0), get_coauthors_from_paper(rec))))) personid_rows = [map(int, row[:3]) + [row[4]] for row in get_signatures_from_rec(rec)] personidrefs_names = dict(((row[1], row[2]), row[3]) for row in personid_rows) personidrefs = frozenset(personidrefs_names.keys()) new_signatures = list(markrefs - personidrefs) old_signatures = list(personidrefs - markrefs) new_signatures_names = dict((new, create_normalized_name(split_name_parts(get_name_by_bibrecref(new)))) for new in new_signatures) # matrix |new_signatures| X |old_signatures| matrix = [[compare_names(new_signatures_names[new], personidrefs_names[old]) for old in old_signatures] for new in new_signatures] # [(new_signatures, old_signatures)] best_match = [(new_signatures[new], old_signatures[old]) for new, old, score in maximized_mapping(matrix) if score > threshold] for new, old in best_match: modify_signature(old, rec, new, new_signatures_names[new]) remove_sigs(tuple(list(old) + [rec]) for old in old_signatures) not_matched = frozenset(new_signatures) - frozenset(map(itemgetter(0), best_match)) if not_matched: used_pids = set(r[0] for r in personid_rows) for sig in not_matched: name = new_signatures_names[sig] matched_pids = find_pids_by_exact_name(name) matched_pids = [p for p in matched_pids if int(p[0]) not in used_pids] if not matched_pids: new_pid = new_person_from_signature(list(sig) + [rec], name) used_pids.add(new_pid) updated_pids.add(new_pid) else: add_signature(list(sig) + [rec], name, matched_pids[0][0]) used_pids.add(matched_pids[0][0]) updated_pids.add(matched_pids[0][0]) update_status_final() if updated_pids: # an empty set will update all canonical_names update_personID_canonical_names(updated_pids)