def query():
w = pickle.load(open('weights_from_query.pkl', 'rb')).squeeze()
topk_vals, topk_idxs = torch.topk(w, 30)
bottomk_vals, bottomk_idxs = torch.topk(-w, 30)
docs, lookup = pickle.load(open('parsed_robust_queries.pkl', 'rb'))
tf, df, idf = count_me(docs)
inv_lookup = _.invert(lookup)
print('Top30: ', [inv_lookup[idx] for idx in topk_idxs.tolist()])
print('Bottom30: ', [inv_lookup[idx] for idx in bottomk_idxs.tolist()])
glove = get_glove_lookup()
glove_by_idx = _.map_keys(
glove, lambda vec, token: lookup[token]
if token in lookup else lookup['<unk>'])
norms_by_idx = _.map_values(glove_by_idx, torch.norm)
idxs_in_order = list(norms_by_idx.keys())
idfs_in_order = torch.tensor([idf[idx] for idx in idxs_in_order])
dfs_in_order = torch.tensor([df[idx] for idx in idxs_in_order])
tfs_in_order = torch.tensor([tf[idx] for idx in idxs_in_order])
norms_in_order = torch.tensor([norms_by_idx[idx] for idx in idxs_in_order])
w_subset = w[torch.tensor(idxs_in_order)]
print(np.corrcoef(w_subset, tfs_in_order)[0, 1])
print(np.corrcoef(w_subset, dfs_in_order)[0, 1])
print(np.corrcoef(w_subset, idfs_in_order)[0, 1])
print(np.corrcoef(w_subset, norms_in_order)[0, 1])
print(np.corrcoef(w_subset, np.log(tfs_in_order + 1))[0, 1])
print(np.corrcoef(w_subset, np.log(dfs_in_order))[0, 1])
print(np.corrcoef(w_subset, np.log(idfs_in_order))[0, 1])
print(np.corrcoef(w_subset, np.log(norms_in_order + 1))[0, 1])
def _check(self, batch_num=0):
if self.dont_smooth:
smooth = 0.0
val_results = self.metrics_at_k(self.val_ranking_dataset, smooth)
else:
smooth, val_results = self._find_best_smooth()
train_results = self.metrics_at_k(self.train_ranking_dataset, smooth)
test_results = self.metrics_at_k(self.test_ranking_dataset, smooth)
test_results_no_smooth = self.metrics_at_k(self.test_ranking_dataset,
0.0)
self.experiment.record_metrics(
_.assign({},
_.map_keys(train_results,
lambda val, key: 'train_' + key),
_.map_keys(test_results, lambda val, key: 'test_' + key),
_.map_keys(test_results_no_smooth,
lambda val, key: 'test_no_smooth_' + key),
_.map_keys(val_results, lambda val, key: 'val_' + key)),
batch_num)
def process_raw_candidates(query_name_to_id, queries, document_title_to_id,
query_names, raw_ranking_candidates):
ranking_candidates = _.pick(raw_ranking_candidates, query_names)
lookup_by_title = lambda title: document_title_to_id.get(title) or 0
test_ranking_candidates = _.map_values(
ranking_candidates,
lambda candidate_names: _.map_(candidate_names, lookup_by_title))
return _.map_keys(
test_ranking_candidates, lambda ranking, query_name: str(queries[
query_name_to_id[query_name]])[1:-1])
def _from_bibliography_entry(
bibliography_entry: Union[dict, None] = None) -> dict:
if not bibliography_entry:
bibliography_entry = BibliographyEntryFactory.build()
return pydash.map_keys(bibliography_entry, lambda _, key: "_id"
if key == "id" else key)