SinaTools 0.1.41__py2.py3-none-any.whl → 1.0.1__py2.py3-none-any.whl

sinatools/ner/trainers/BertTrainer.py

@@ -1,163 +1,163 @@
-import os
-import logging
-import torch
-import numpy as np
-from sinatools.ner.trainers import BaseTrainer
-from sinatools.ner.metrics import compute_single_label_metrics
-    
-logger = logging.getLogger(__name__)
-
-
-class BertTrainer(BaseTrainer):
-    def __init__(self, **kwargs):
-        super().__init__(**kwargs)
-
-    def train(self):
-        best_val_loss, test_loss = np.inf, np.inf
-        num_train_batch = len(self.train_dataloader)
-        patience = self.patience
-
-        for epoch_index in range(self.max_epochs):
-            self.current_epoch = epoch_index
-            train_loss = 0
-
-            for batch_index, (_, gold_tags, _, _, logits) in enumerate(self.tag(
-                self.train_dataloader, is_train=True
-            ), 1):
-                self.current_timestep += 1
-                batch_loss = self.loss(logits.view(-1, logits.shape[-1]), gold_tags.view(-1))
-                batch_loss.backward()
-
-                # Avoid exploding gradient by doing gradient clipping
-                torch.nn.utils.clip_grad_norm_(self.model.parameters(), self.clip)
-
-                self.optimizer.step()
-                self.scheduler.step()
-                train_loss += batch_loss.item()
-
-                if self.current_timestep % self.log_interval == 0:
-                    logger.info(
-                        "Epoch %d | Batch %d/%d | Timestep %d | LR %.10f | Loss %f",
-                        epoch_index,
-                        batch_index,
-                        num_train_batch,
-                        self.current_timestep,
-                        self.optimizer.param_groups[0]['lr'],
-                        batch_loss.item()
-                    )
-
-            train_loss /= num_train_batch
-
-            logger.info("** Evaluating on validation dataset **")
-            val_preds, segments, valid_len, val_loss = self.eval(self.val_dataloader)
-            val_metrics = compute_single_label_metrics(segments)
-
-            epoch_summary_loss = {
-                "train_loss": train_loss,
-                "val_loss": val_loss
-            }
-            epoch_summary_metrics = {
-                "val_micro_f1": val_metrics.micro_f1,
-                "val_precision": val_metrics.precision,
-                "val_recall": val_metrics.recall
-            }
-
-            logger.info(
-                "Epoch %d | Timestep %d | Train Loss %f | Val Loss %f | F1 %f",
-                epoch_index,
-                self.current_timestep,
-                train_loss,
-                val_loss,
-                val_metrics.micro_f1
-            )
-
-            if val_loss < best_val_loss:
-                patience = self.patience
-                best_val_loss = val_loss
-                logger.info("** Validation improved, evaluating test data **")
-                test_preds, segments, valid_len, test_loss = self.eval(self.test_dataloader)
-                self.segments_to_file(segments, os.path.join(self.output_path, "predictions.txt"))
-                test_metrics = compute_single_label_metrics(segments)
-
-                epoch_summary_loss["test_loss"] = test_loss
-                epoch_summary_metrics["test_micro_f1"] = test_metrics.micro_f1
-                epoch_summary_metrics["test_precision"] = test_metrics.precision
-                epoch_summary_metrics["test_recall"] = test_metrics.recall
-
-                logger.info(
-                    f"Epoch %d | Timestep %d | Test Loss %f | F1 %f",
-                    epoch_index,
-                    self.current_timestep,
-                    test_loss,
-                    test_metrics.micro_f1
-                )
-
-                self.save()
-            else:
-                patience -= 1
-
-            # No improvements, terminating early
-            if patience == 0:
-                logger.info("Early termination triggered")
-                break
-
-            self.summary_writer.add_scalars("Loss", epoch_summary_loss, global_step=self.current_timestep)
-            self.summary_writer.add_scalars("Metrics", epoch_summary_metrics, global_step=self.current_timestep)
-
-    def eval(self, dataloader):
-        golds, preds, segments, valid_lens = list(), list(), list(), list()
-        loss = 0
-
-        for _, gold_tags, tokens, valid_len, logits in self.tag(
-            dataloader, is_train=False
-        ):
-            loss += self.loss(logits.view(-1, logits.shape[-1]), gold_tags.view(-1))
-            preds += torch.argmax(logits, dim=2).detach().cpu().numpy().tolist()
-            segments += tokens
-            valid_lens += list(valid_len)
-
-        loss /= len(dataloader)
-
-        # Update segments, attach predicted tags to each token
-        segments = self.to_segments(segments, preds, valid_lens, dataloader.dataset.vocab)
-
-        return preds, segments, valid_lens, loss.item()
-
-    def infer(self, dataloader):
-        golds, preds, segments, valid_lens = list(), list(), list(), list()
-
-        for _, gold_tags, tokens, valid_len, logits in self.tag(
-            dataloader, is_train=False
-        ):
-            preds += torch.argmax(logits, dim=2).detach().cpu().numpy().tolist()
-            segments += tokens
-            valid_lens += list(valid_len)
-
-        segments = self.to_segments(segments, preds, valid_lens, dataloader.dataset.vocab)
-        return segments
-
-    def to_segments(self, segments, preds, valid_lens, vocab):
-        if vocab is None:
-            vocab = self.vocab
-
-        tagged_segments = list()
-        tokens_stoi = vocab.tokens.get_stoi()
-        tags_itos = vocab.tags[0].get_itos()
-        unk_id = tokens_stoi["UNK"]
-
-        for segment, pred, valid_len in zip(segments, preds, valid_lens):
-            # First, the token at 0th index [CLS] and token at nth index [SEP]
-            # Combine the tokens with their corresponding predictions
-            segment_pred = zip(segment[1:valid_len-1], pred[1:valid_len-1])
-
-            # Ignore the sub-tokens/subwords, which are identified with text being UNK
-            segment_pred = list(filter(lambda t: tokens_stoi[t[0].text] != unk_id, segment_pred))
-
-            # Attach the predicted tags to each token
-            list(map(lambda t: setattr(t[0], 'pred_tag', [{"tag": tags_itos[t[1]]}]), segment_pred))
-
-            # We are only interested in the tagged tokens, we do no longer need raw model predictions
-            tagged_segment = [t for t, _ in segment_pred]
-            tagged_segments.append(tagged_segment)
-
-        return tagged_segments
+import os
+import logging
+import torch
+import numpy as np
+from sinatools.ner.trainers import BaseTrainer
+from sinatools.ner.metrics import compute_single_label_metrics
+    
+logger = logging.getLogger(__name__)
+
+
+class BertTrainer(BaseTrainer):
+    def __init__(self, **kwargs):
+        super().__init__(**kwargs)
+
+    def train(self):
+        best_val_loss, test_loss = np.inf, np.inf
+        num_train_batch = len(self.train_dataloader)
+        patience = self.patience
+
+        for epoch_index in range(self.max_epochs):
+            self.current_epoch = epoch_index
+            train_loss = 0
+
+            for batch_index, (_, gold_tags, _, _, logits) in enumerate(self.tag(
+                self.train_dataloader, is_train=True
+            ), 1):
+                self.current_timestep += 1
+                batch_loss = self.loss(logits.view(-1, logits.shape[-1]), gold_tags.view(-1))
+                batch_loss.backward()
+
+                # Avoid exploding gradient by doing gradient clipping
+                torch.nn.utils.clip_grad_norm_(self.model.parameters(), self.clip)
+
+                self.optimizer.step()
+                self.scheduler.step()
+                train_loss += batch_loss.item()
+
+                if self.current_timestep % self.log_interval == 0:
+                    logger.info(
+                        "Epoch %d | Batch %d/%d | Timestep %d | LR %.10f | Loss %f",
+                        epoch_index,
+                        batch_index,
+                        num_train_batch,
+                        self.current_timestep,
+                        self.optimizer.param_groups[0]['lr'],
+                        batch_loss.item()
+                    )
+
+            train_loss /= num_train_batch
+
+            logger.info("** Evaluating on validation dataset **")
+            val_preds, segments, valid_len, val_loss = self.eval(self.val_dataloader)
+            val_metrics = compute_single_label_metrics(segments)
+
+            epoch_summary_loss = {
+                "train_loss": train_loss,
+                "val_loss": val_loss
+            }
+            epoch_summary_metrics = {
+                "val_micro_f1": val_metrics.micro_f1,
+                "val_precision": val_metrics.precision,
+                "val_recall": val_metrics.recall
+            }
+
+            logger.info(
+                "Epoch %d | Timestep %d | Train Loss %f | Val Loss %f | F1 %f",
+                epoch_index,
+                self.current_timestep,
+                train_loss,
+                val_loss,
+                val_metrics.micro_f1
+            )
+
+            if val_loss < best_val_loss:
+                patience = self.patience
+                best_val_loss = val_loss
+                logger.info("** Validation improved, evaluating test data **")
+                test_preds, segments, valid_len, test_loss = self.eval(self.test_dataloader)
+                self.segments_to_file(segments, os.path.join(self.output_path, "predictions.txt"))
+                test_metrics = compute_single_label_metrics(segments)
+
+                epoch_summary_loss["test_loss"] = test_loss
+                epoch_summary_metrics["test_micro_f1"] = test_metrics.micro_f1
+                epoch_summary_metrics["test_precision"] = test_metrics.precision
+                epoch_summary_metrics["test_recall"] = test_metrics.recall
+
+                logger.info(
+                    f"Epoch %d | Timestep %d | Test Loss %f | F1 %f",
+                    epoch_index,
+                    self.current_timestep,
+                    test_loss,
+                    test_metrics.micro_f1
+                )
+
+                self.save()
+            else:
+                patience -= 1
+
+            # No improvements, terminating early
+            if patience == 0:
+                logger.info("Early termination triggered")
+                break
+
+            self.summary_writer.add_scalars("Loss", epoch_summary_loss, global_step=self.current_timestep)
+            self.summary_writer.add_scalars("Metrics", epoch_summary_metrics, global_step=self.current_timestep)
+
+    def eval(self, dataloader):
+        golds, preds, segments, valid_lens = list(), list(), list(), list()
+        loss = 0
+
+        for _, gold_tags, tokens, valid_len, logits in self.tag(
+            dataloader, is_train=False
+        ):
+            loss += self.loss(logits.view(-1, logits.shape[-1]), gold_tags.view(-1))
+            preds += torch.argmax(logits, dim=2).detach().cpu().numpy().tolist()
+            segments += tokens
+            valid_lens += list(valid_len)
+
+        loss /= len(dataloader)
+
+        # Update segments, attach predicted tags to each token
+        segments = self.to_segments(segments, preds, valid_lens, dataloader.dataset.vocab)
+
+        return preds, segments, valid_lens, loss.item()
+
+    def infer(self, dataloader):
+        golds, preds, segments, valid_lens = list(), list(), list(), list()
+
+        for _, gold_tags, tokens, valid_len, logits in self.tag(
+            dataloader, is_train=False
+        ):
+            preds += torch.argmax(logits, dim=2).detach().cpu().numpy().tolist()
+            segments += tokens
+            valid_lens += list(valid_len)
+
+        segments = self.to_segments(segments, preds, valid_lens, dataloader.dataset.vocab)
+        return segments
+
+    def to_segments(self, segments, preds, valid_lens, vocab):
+        if vocab is None:
+            vocab = self.vocab
+
+        tagged_segments = list()
+        tokens_stoi = vocab.tokens.get_stoi()
+        tags_itos = vocab.tags[0].get_itos()
+        unk_id = tokens_stoi["UNK"]
+
+        for segment, pred, valid_len in zip(segments, preds, valid_lens):
+            # First, the token at 0th index [CLS] and token at nth index [SEP]
+            # Combine the tokens with their corresponding predictions
+            segment_pred = zip(segment[1:valid_len-1], pred[1:valid_len-1])
+
+            # Ignore the sub-tokens/subwords, which are identified with text being UNK
+            segment_pred = list(filter(lambda t: tokens_stoi[t[0].text] != unk_id, segment_pred))
+
+            # Attach the predicted tags to each token
+            list(map(lambda t: setattr(t[0], 'pred_tag', [{"tag": tags_itos[t[1]]}]), segment_pred))
+
+            # We are only interested in the tagged tokens, we do no longer need raw model predictions
+            tagged_segment = [t for t, _ in segment_pred]
+            tagged_segments.append(tagged_segment)
+
+        return tagged_segments

sinatools/ner/trainers/__init__.py

@@ -1,3 +1,3 @@
-from sinatools.ner.trainers.BaseTrainer import BaseTrainer
-from sinatools.ner.trainers.BertTrainer import BertTrainer
+from sinatools.ner.trainers.BaseTrainer import BaseTrainer
+from sinatools.ner.trainers.BertTrainer import BertTrainer
 from sinatools.ner.trainers.BertNestedTrainer import BertNestedTrainer

SinaTools-0.1.41.dist-info/RECORD

@@ -1,123 +0,0 @@
-SinaTools-0.1.41.data/data/sinatools/environment.yml,sha256=i0UFZc-vwU9ZwnI8hBdz7vi-x22vG-HR8ojWBUAOkno,5422
-sinatools/VERSION,sha256=MoDOfoT2nFdWJzX_rU2mpf_gRhWTZlYybGVGv8AKRLk,6
-sinatools/__init__.py,sha256=bEosTU1o-FSpyytS6iVP_82BXHF2yHnzpJxPLYRbeII,135
-sinatools/environment.yml,sha256=i0UFZc-vwU9ZwnI8hBdz7vi-x22vG-HR8ojWBUAOkno,5422
-sinatools/install_env.py,sha256=EODeeE0ZzfM_rz33_JSIruX03Nc4ghyVOM5BHVhsZaQ,404
-sinatools/sinatools.py,sha256=vR5AaF0iel21LvsdcqwheoBz0SIj9K9I_Ub8M8oA98Y,20
-sinatools/CLI/DataDownload/download_files.py,sha256=EezvbukR3pZ8s6mGZnzTcjsbo3CBDlC0g6KhJWlYp1w,2686
-sinatools/CLI/morphology/ALMA_multi_word.py,sha256=rmpa72twwIJHme_kpQ1lu3_7y_Jorj70QTvOnQMJRuI,1274
-sinatools/CLI/morphology/morph_analyzer.py,sha256=HPamEKos_JRYCJv_2q6c12N--da58_JXTno9haww5Ao,3497
-sinatools/CLI/ner/corpus_entity_extractor.py,sha256=DdvigsDQzko5nJBjzUXlIDqoBMBTVzktjSo7JfEXTIA,4778
-sinatools/CLI/ner/entity_extractor.py,sha256=G9j-t0WKm2CRORhqARJM-pI-KArQ2IXIvnBK_NHxlHs,2885
-sinatools/CLI/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sinatools/CLI/utils/arStrip.py,sha256=NLyp8vOu2xv80tL9jiKRvyptmbkRZVg-wcAr-9YyvNY,3264
-sinatools/CLI/utils/corpus_tokenizer.py,sha256=nH0T4h6urr_0Qy6-wN3PquOtnwybj0REde5Ts_OE4U8,1650
-sinatools/CLI/utils/implication.py,sha256=AojpkCwUQJiQjxhyEUWKRHmBnIt1tVqr485cAF7Thq0,2857
-sinatools/CLI/utils/jaccard.py,sha256=w56N_cNEFJ0A7WtunmY_xtms4srFagKBzrW_0YhH2DE,4216
-sinatools/CLI/utils/remove_latin.py,sha256=NOaTm2RHxt5IQrV98ySTmD8rTXTmcqSmfbPAwTyaXqU,848
-sinatools/CLI/utils/remove_punctuation.py,sha256=vJAZlEn7WGftZAFVFYnddkRrxdJ_rMmKB9vFZkY-jN4,1097
-sinatools/CLI/utils/sentence_tokenizer.py,sha256=Wli8eiDbWSd_Z8UKpu_JkaS8jImowa1vnRL0oYCSfqw,2823
-sinatools/CLI/utils/text_dublication_detector.py,sha256=dW70O5O20GxeUDDF6zVYn52wWLmJF-HBZgvqIeVL2rQ,1661
-sinatools/CLI/utils/text_transliteration.py,sha256=vz-3kxWf8pNYVCqNAtBAiA6u_efrS5NtWT-ofN1NX6I,2014
-sinatools/DataDownload/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sinatools/DataDownload/downloader.py,sha256=VdUNgSqMKz1J-DuQD_eS1U2KWqEpy94WlSJ0pPODLig,7833
-sinatools/arabert/__init__.py,sha256=ely2PttjgSv7vKdzskuD1rtK_l_UOpmxJSz8isrveD0,16
-sinatools/arabert/preprocess.py,sha256=qI0FsuMTOzdRlYGCtLrjpXgikNElUZPv9bnjaKDZKJ4,33024
-sinatools/arabert/arabert/__init__.py,sha256=KbSAH-XqbRygn0y59m5-ZYOLXgpT1gSgE3F-qd4rKEc,627
-sinatools/arabert/arabert/create_classification_data.py,sha256=BhemGNRbYz_Pun0Q5WerN2-9n-ILmU3tm4J-OlHw5-A,7678
-sinatools/arabert/arabert/create_pretraining_data.py,sha256=2M-cF3CLHbQ0cdWrzFT6Frg1vVP4Y-CFoq8iEPyxgsE,18924
-sinatools/arabert/arabert/extract_features.py,sha256=C1IzASrlX7u4_M2xdr_PjzWfTRZgklhUXA2WHKgQt-I,15585
-sinatools/arabert/arabert/lamb_optimizer.py,sha256=uN3Dcx-6n2_OwepyymRrGrB4EcSkR8b2ZczZrOr7bpY,6263
-sinatools/arabert/arabert/modeling.py,sha256=KliecCmA1pP3owg0mYge6On3IRHunMF5kMLuEwc0VLw,40896
-sinatools/arabert/arabert/optimization.py,sha256=Wx0Js6Zsfc3iVw-_7Q1SCnxfP_qqbdTAyFD-vZSpOyk,8153
-sinatools/arabert/arabert/run_classifier.py,sha256=AdVGyvidlmbEp12b-PauiBo6EmFLEO7tqeJKuLhK2DA,38777
-sinatools/arabert/arabert/run_pretraining.py,sha256=yO16nKkHDfcYA2Zx7vv8KN4te6_1qFOzyVeDzFT-DQw,21894
-sinatools/arabert/arabert/run_squad.py,sha256=PORxgiByP8L6vZqAFkqgHPJ_ZjAlqlg64gtkdLmDNns,53456
-sinatools/arabert/arabert/tokenization.py,sha256=R6xkyCb8_vgeksXiLeqDvV5vOnLb1cPNsvfDij6YVFk,14132
-sinatools/arabert/araelectra/__init__.py,sha256=ely2PttjgSv7vKdzskuD1rtK_l_UOpmxJSz8isrveD0,16
-sinatools/arabert/araelectra/build_openwebtext_pretraining_dataset.py,sha256=pIo6VFT3XXOYroZaab3msZAP6XjCKu0KcrIZQA0Pj8U,3881
-sinatools/arabert/araelectra/build_pretraining_dataset.py,sha256=Z8ZmKznaE_2SPDRoPYR1SDhjTN_NTpNCFFuhUkykwl8,9041
-sinatools/arabert/araelectra/build_pretraining_dataset_single_file.py,sha256=W7HFr1XoO6bCDR7X7w-bOuwULFtTSjeKbJ2LHzzHf9k,3224
-sinatools/arabert/araelectra/configure_finetuning.py,sha256=YfGLMdgN6Qqm357Mzy5UMjkuLPPWtBs7f4dA-DKE6JM,7768
-sinatools/arabert/araelectra/configure_pretraining.py,sha256=oafQgu4WmVdxBcU5mSfXhPlvCk43CJwAWXC10Q58BlI,5801
-sinatools/arabert/araelectra/flops_computation.py,sha256=krHTeuPH9xQu5ldprBOPJNlJRvC7fmmvXXqUjfWrzPE,9499
-sinatools/arabert/araelectra/run_finetuning.py,sha256=JecbrSmGikBNyid4JKRZ49Rm5xFpt02WfgIIcs3TpcU,12976
-sinatools/arabert/araelectra/run_pretraining.py,sha256=1K2aAFTY0p3iaLY0xkhTlm6v0B-Zun8SwEzz-K6RXM4,20665
-sinatools/arabert/araelectra/finetune/__init__.py,sha256=d55FZ9ZE-_t_WWMnIiRGozkTw50vBZ-s9BMy7l_I-ao,619
-sinatools/arabert/araelectra/finetune/feature_spec.py,sha256=cqNlBa2KK_G1-vkKm1EJUv6BoS3gesCUAHwVagZB6wM,1888
-sinatools/arabert/araelectra/finetune/preprocessing.py,sha256=1mf7-IxknCRsobQZ-VV1zs4Cwt-mfOtoVxysDJa9LZ0,6657
-sinatools/arabert/araelectra/finetune/scorer.py,sha256=PjRg0P5ANCtul2ute7ccq3mRCCoIAoCb-lVLlwd4rVY,1571
-sinatools/arabert/araelectra/finetune/task.py,sha256=zM8M4PGSIrY2u6ytpmkQEXxG-jjoeN9wouEyVR23qeQ,1991
-sinatools/arabert/araelectra/finetune/task_builder.py,sha256=Zsoiuw5M3Ca8QhaZVLVLZyWw09K5R75UeMuPmazMlHI,2768
-sinatools/arabert/araelectra/model/__init__.py,sha256=d55FZ9ZE-_t_WWMnIiRGozkTw50vBZ-s9BMy7l_I-ao,619
-sinatools/arabert/araelectra/model/modeling.py,sha256=5XLIutnmr-SFQOV_XntJ-U5evSCY-J2e9NjvlwVXKkk,40877
-sinatools/arabert/araelectra/model/optimization.py,sha256=BCMb_C5hgBw7wC9ZR8AQ4lwoPopqLIcSiqcCrIjx9XU,7254
-sinatools/arabert/araelectra/model/tokenization.py,sha256=9CkyPzs3L6OEPzN-7EWQDNQmW2mIJoZD4o1rn6xLdL4,11082
-sinatools/arabert/araelectra/pretrain/__init__.py,sha256=d55FZ9ZE-_t_WWMnIiRGozkTw50vBZ-s9BMy7l_I-ao,619
-sinatools/arabert/araelectra/pretrain/pretrain_data.py,sha256=NLgIcLAq1-MgtBNXYu_isDxnOY5k67SyADYy-8nzBok,5413
-sinatools/arabert/araelectra/pretrain/pretrain_helpers.py,sha256=nFl7LEdxAU5kKwiodqJHzi-ty9jMFsCCNYOF__A69j8,9255
-sinatools/arabert/araelectra/util/__init__.py,sha256=d55FZ9ZE-_t_WWMnIiRGozkTw50vBZ-s9BMy7l_I-ao,619
-sinatools/arabert/araelectra/util/training_utils.py,sha256=7h_J1ljUWM0ynBcofEtjZWL_oAfZtTxEemQLkixgn-0,4142
-sinatools/arabert/araelectra/util/utils.py,sha256=G0UAETUCZMlU9R9ASD9AXrWZeodWI1aZJEE9F-goaH4,2591
-sinatools/arabert/aragpt2/__init__.py,sha256=aQkKhQwWaS61wYEeOdx682upeMWFPUjLxXSs7JM1sOA,18
-sinatools/arabert/aragpt2/create_pretraining_data.py,sha256=fFa2_DAyTwc8L2IqQbshsh_Ia26nj1qtVLzC6DooSac,3105
-sinatools/arabert/aragpt2/train_bpe_tokenizer.py,sha256=b-8zHQ02fLmZV4GfjnrPptwjpX259F41SlnWzBrflMA,1888
-sinatools/arabert/aragpt2/gpt2/__init__.py,sha256=aQkKhQwWaS61wYEeOdx682upeMWFPUjLxXSs7JM1sOA,18
-sinatools/arabert/aragpt2/gpt2/lamb_optimizer.py,sha256=uN3Dcx-6n2_OwepyymRrGrB4EcSkR8b2ZczZrOr7bpY,6263
-sinatools/arabert/aragpt2/gpt2/optimization.py,sha256=iqh23cypRSRUt53wt2G5SbNNpJMwERM7gZAOKVh5l4U,8411
-sinatools/arabert/aragpt2/gpt2/run_pretraining.py,sha256=4jjkUbvTO1DHoKJ89yKtlkkofcND_fyAunQ-mlnJhTM,13298
-sinatools/arabert/aragpt2/grover/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sinatools/arabert/aragpt2/grover/dataloader.py,sha256=-FWPTjtsvweEE1WaWRHBXfOSbsGiUmnXT3qK7KJP8cM,6853
-sinatools/arabert/aragpt2/grover/modeling.py,sha256=XcUvFwqRaxAwWiJstrH2FPBvDJe03pTWIyipdMfWj9g,38280
-sinatools/arabert/aragpt2/grover/modeling_gpt2.py,sha256=WFpCWn1792yATFzt8rZ0rpWvExfbLzV2BqiEs7llFUw,51602
-sinatools/arabert/aragpt2/grover/optimization_adafactor.py,sha256=1geOsCWuv5xxtSnKDz9a8aY5SVwZ1MGq-xVQDBg4Gpg,9765
-sinatools/arabert/aragpt2/grover/train_tpu.py,sha256=qNgLI_j6-KYkTMJfVoFlh4NIKweY1aPz1XPDw6odld0,7102
-sinatools/arabert/aragpt2/grover/utils.py,sha256=V5wMUxK03r5g_pb7R3_uGLOPqQJfbIB0VaJ8ZDM4XAo,8473
-sinatools/morphology/ALMA_multi_word.py,sha256=hj_-8ojrYYHnfCGk8WKtJdUR8mauzQdma4WUm-okDps,1346
-sinatools/morphology/__init__.py,sha256=I4wVBh8BhyNl-CySVdiI_nUSn6gj1j-gmLKP300RpE0,1216
-sinatools/morphology/morph_analyzer.py,sha256=JOH2UWKNQWo5UzpWNzP9R1D3B3qLSogIiMp8n0N_56o,7177
-sinatools/ner/__init__.py,sha256=59kLMX6UQhF6JpE10RhaDYC3a2_jiWOIVPuejsoflFE,1050
-sinatools/ner/data_format.py,sha256=VmFshZbEPOsWxsb4tgSkwvbM1k7yCce4kmtPkCiWgwM,4513
-sinatools/ner/datasets.py,sha256=mG1iwqSm3lXCFHLqE-b4wNi176cpuzNBz8tKaBU6z6M,5059
-sinatools/ner/entity_extractor.py,sha256=O2epRwRFUUcQs3SnFIYHVBI4zVhr8hRcj0XJYeby4ts,3588
-sinatools/ner/helpers.py,sha256=sX6ezVbuVQxk_xJqZwhUzJVFVuVmFGmei_kd6r3sPHE,3652
-sinatools/ner/metrics.py,sha256=Irz6SsIvpOzGIA2lWxrEV86xnTnm0TzKm9SUVT4SXUU,2734
-sinatools/ner/transforms.py,sha256=vti3mDdi-IRP8i0aTQ37QqpPlP9hdMmJ6_bAMa0uL-s,4871
-sinatools/ner/data/__init__.py,sha256=W0C1ge_XxTfmdEGz0hkclz57aLI5VFS5t6BjByCfkFk,57
-sinatools/ner/data/datasets.py,sha256=_uUlvBAhnTtPwKLj0wIbmB04VCBidfwffxKorLGHq_g,5134
-sinatools/ner/data/transforms.py,sha256=URMz1dHzkHjgUGAkDOenCWvQThO1ha8XeQVjoLL9RXM,4874
-sinatools/ner/nn/BaseModel.py,sha256=3GmujQasTZZunOBuFXpY2p1W8W256iI_Uu4hxhOY2Z0,608
-sinatools/ner/nn/BertNestedTagger.py,sha256=_fwAn1kiKmXe6m5y16Ipty3kvXIEFEmiUq74Ad1818U,1219
-sinatools/ner/nn/BertSeqTagger.py,sha256=dFcBBiMw2QCWsyy7aQDe_PS3aRuNn4DOxKIHgTblFvc,504
-sinatools/ner/nn/__init__.py,sha256=UgQD_XLNzQGBNSYc_Bw1aRJZjq4PJsnMT1iZwnJemqE,170
-sinatools/ner/trainers/BaseTrainer.py,sha256=Uar8HxtgBXCVhKa85sEN622d9P7JiFBcWfs46uRG4aA,4068
-sinatools/ner/trainers/BertNestedTrainer.py,sha256=iJOah69tXZsAXBimqP0odEsk8SPX4A355riePzW2BFs,8632
-sinatools/ner/trainers/BertTrainer.py,sha256=BtttsrHPolmK3eRDqrgVUuv6lVMuImIeskxhi02Q-44,6596
-sinatools/ner/trainers/__init__.py,sha256=Xnbi_M4KKJRqV7FJe1vklyT0nEW2Q2obxgcWkbR0ZbA,190
-sinatools/relations/__init__.py,sha256=cYjsP2mlTYvAwVIEFtgA6i9gLUSkGVOuDggMs7TvG5k,272
-sinatools/relations/relation_extractor.py,sha256=UuDlaaR0ch9BFv4sBF1tr7P-P9xq8oRZF41tAze6_ok,9751
-sinatools/semantic_relatedness/__init__.py,sha256=S0xrmqtl72L02N56nbNMudPoebnYQgsaIyyX-587DsU,830
-sinatools/semantic_relatedness/compute_relatedness.py,sha256=_9HFPs3nQBLklHFfkc9o3gEjEI6Bd34Ha4E1Kvv1RIg,2256
-sinatools/synonyms/__init__.py,sha256=yMuphNZrm5XLOR2T0weOHcUysJm-JKHUmVLoLQO8390,548
-sinatools/synonyms/synonyms_generator.py,sha256=jRd0D3_kn-jYBaZzqY-7oOy0SFjSJ-mjM7JhsySzX58,9037
-sinatools/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-sinatools/utils/charsets.py,sha256=rs82oZJqRqosZdTKXfFAJfJ5t4PxjMM_oAPsiWSWuwU,2817
-sinatools/utils/parser.py,sha256=qvHdln5R5CAv_0UOJWe0mcp8JCsGqgazoeIIkoALH88,6259
-sinatools/utils/readfile.py,sha256=xE4LEaCqXJIk9v37QUSSmWb-aY3UnCFUNb7uVdx3cpM,133
-sinatools/utils/similarity.py,sha256=HAK6OmyVnfjPm0GWL3z9s4ZoUwpZHVKxt3CeSMfqLIQ,11990
-sinatools/utils/text_dublication_detector.py,sha256=FeSkbfWGMQluz23H4CBHXION-walZPgjueX6AL8u_Q0,5660
-sinatools/utils/text_transliteration.py,sha256=F3smhr2AEJtySE6wGQsiXXOslTvSDzLivTYu0btgc10,8769
-sinatools/utils/tokenizer.py,sha256=nyk6lh5-p38wrU62hvh4wg7ni9ammkdqqIgcjbbBxxo,6965
-sinatools/utils/tokenizers_words.py,sha256=efNfOil9qDNVJ9yynk_8sqf65PsL-xtsHG7y2SZCkjQ,656
-sinatools/utils/word_compare.py,sha256=rS2Z74sf7R-7MTXyrFj5miRi2TnSG9OdTDp_qQYuo2Y,28200
-sinatools/wsd/__init__.py,sha256=mwmCUurOV42rsNRpIUP3luG0oEzeTfEx3oeDl93Oif8,306
-sinatools/wsd/disambiguator.py,sha256=h-3idc5rPPbMDSE_QVJAsEVkDHwzYY3L2SEPNXIdOcc,20104
-sinatools/wsd/settings.py,sha256=6XflVTFKD8SVySX9Wj7zYQtV26WDTcQ2-uW8-gDNHKE,747
-sinatools/wsd/wsd.py,sha256=gHIBUFXegoY1z3rRnIlK6TduhYq2BTa_dHakOjOlT4k,4434
-SinaTools-0.1.41.dist-info/AUTHORS.rst,sha256=aTWeWlIdfLi56iLJfIUAwIrmqDcgxXKLji75_Fjzjyg,174
-SinaTools-0.1.41.dist-info/LICENSE,sha256=uwsKYG4TayHXNANWdpfMN2lVW4dimxQjA_7vuCVhD70,1088
-SinaTools-0.1.41.dist-info/METADATA,sha256=9zBmOUN3RovUR57RCZeJNWwTxjSqEmLSjka3SL04KZA,3410
-SinaTools-0.1.41.dist-info/WHEEL,sha256=9Hm2OB-j1QcCUq9Jguht7ayGIIZBRTdOXD1qg9cCgPM,109
-SinaTools-0.1.41.dist-info/entry_points.txt,sha256=_CsRKM_tSCWV5hefBNUsWf9_6DrJnzFlxeAo1wm5XqY,1302
-SinaTools-0.1.41.dist-info/top_level.txt,sha256=8tNdPTeJKw3TQCaua8IJIx6N6WpgZZmVekf1OdBNJpE,10
-SinaTools-0.1.41.dist-info/RECORD,,

sinatools/arabert/arabert/__init__.py

@@ -1,14 +0,0 @@
-# coding=utf-8
-# Copyright 2018 The Google AI Language Team Authors.
-#
-# Licensed under the Apache License, Version 2.0 (the "License");
-# you may not use this file except in compliance with the License.
-# You may obtain a copy of the License at
-#
-#     http://www.apache.org/licenses/LICENSE-2.0
-#
-# Unless required by applicable law or agreed to in writing, software
-# distributed under the License is distributed on an "AS IS" BASIS,
-# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
-# See the License for the specific language governing permissions and
-# limitations under the License.