def _predict(self, strings, add_neutral=False): results = self._classify(strings) if add_neutral: result = neutral(results) label = self._label + ['neutral'] else: label = self._label return [label[result] for result in np.argmax(results, axis=1)]
def _predict_proba(self, strings, add_neutral=False): results = self._classify(strings) if add_neutral: results = neutral(results) label = self._label + ['neutral'] else: label = self._label outputs = [] for result in results: outputs.append({label[i]: result[i] for i in range(len(result))}) return outputs
def _predict(self, strings, add_neutral=False): if self._multilabels: probs = self._classify(strings) results = [] probs = np.around(probs) for prob in probs: list_result = [] for no, label in enumerate(self._label): if prob[no]: list_result.append(label) results.append(list_result) return results else: results = self._classify(strings) if add_neutral: result = neutral(results) label = self._label + ['neutral'] else: label = self._label return [label[result] for result in np.argmax(results, axis=1)]
def _predict_words(self, string, method, visualization, add_neutral=False): method = method.lower() if method not in ['last', 'first', 'mean']: raise ValueError( "method not supported, only support 'last', 'first' and 'mean'" ) if add_neutral: label = self._label + ['neutral'] else: label = self._label input_ids, input_masks, segment_ids, s_tokens = xlnet_tokenization( self._tokenizer, [string]) r = self._execute( inputs=[input_ids, segment_ids, input_masks], input_labels=['Placeholder', 'Placeholder_1', 'Placeholder_2'], output_labels=['logits', 'attention', 'logits_seq'], ) result = softmax(r['logits'], axis=-1) words = softmax(r['logits_seq'], axis=-1) attentions = r['attention'] if method == 'first': cls_attn = attentions[0][:, :, 0, :] if method == 'last': cls_attn = attentions[-1][:, :, 0, :] if method == 'mean': cls_attn = np.mean(attentions, axis=0).mean(axis=2) cls_attn = np.mean(cls_attn, axis=1) total_weights = np.sum(cls_attn, axis=-1, keepdims=True) attn = cls_attn / total_weights words = words[0] if add_neutral: result = neutral(result) words = neutral(words) result = result[0] weights = [] merged = merge_sentencepiece_tokens(list(zip(s_tokens[0], attn[0])), model='xlnet') for i in range(words.shape[1]): m = merge_sentencepiece_tokens( list(zip(s_tokens[0], words[:, i])), weighted=False, model='xlnet', ) _, weight = zip(*m) weights.append(weight) w, a = zip(*merged) words = np.array(weights).T distribution_words = words[:, np.argmax(words.sum(axis=0))] y_histogram, x_histogram = np.histogram(distribution_words, bins=np.arange(0, 1, 0.05)) y_histogram = y_histogram / y_histogram.sum() x_attention = np.arange(len(w)) left, right = np.unique(np.argmax(words, axis=1), return_counts=True) left = left.tolist() y_barplot = [] for i in range(len(label)): if i not in left: y_barplot.append(i) else: y_barplot.append(right[left.index(i)]) dict_result = {label[i]: result[i] for i in range(len(result))} dict_result['alphas'] = {w: a[no] for no, w in enumerate(w)} dict_result['word'] = {w: words[no] for no, w in enumerate(w)} dict_result['histogram'] = {'x': x_histogram, 'y': y_histogram} dict_result['attention'] = {'x': x_attention, 'y': np.array(a)} dict_result['barplot'] = {'x': label, 'y': y_barplot} dict_result['module'] = self._module if visualization: render_dict[self._module](dict_result) else: return dict_result