Find `num_neighbors` most similar items. Parameters ---------- vector : numpy.array Vector for word/document. num_neighbors : int Number of most similar items Returns ------- list of (str, float) List of mo
(self, vector, num_neighbors)
| 167 | self.labels = labels |
| 168 | |
| 169 | def most_similar(self, vector, num_neighbors): |
| 170 | """Find `num_neighbors` most similar items. |
| 171 | |
| 172 | Parameters |
| 173 | ---------- |
| 174 | vector : numpy.array |
| 175 | Vector for word/document. |
| 176 | num_neighbors : int |
| 177 | Number of most similar items |
| 178 | |
| 179 | Returns |
| 180 | ------- |
| 181 | list of (str, float) |
| 182 | List of most similar items in format [(`item`, `cosine_distance`), ... ] |
| 183 | |
| 184 | """ |
| 185 | ids, distances = self.index.get_nns_by_vector( |
| 186 | vector, num_neighbors, include_distances=True) |
| 187 | |
| 188 | return [(self.labels[ids[i]], 1 - distances[i] ** 2 / 2) for i in range(len(ids))] |
no outgoing calls