mindspore 2.0.0a0__cp39-cp39-win_amd64.whl → 2.0.0rc1__cp39-cp39-win_amd64.whl

mindspore/dataset/engine/datasets_text.py

@@ -30,14 +30,15 @@ from .validators import check_imdb_dataset, check_iwslt2016_dataset, check_iwslt
     check_penn_treebank_dataset, check_ag_news_dataset, check_amazon_review_dataset, check_udpos_dataset, \
     check_wiki_text_dataset, check_conll2000_dataset, check_cluedataset, \
     check_sogou_news_dataset, check_textfiledataset, check_dbpedia_dataset, check_yelp_review_dataset, \
-    check_en_wik9_dataset, check_yahoo_answers_dataset, check_multi30k_dataset, check_squad_dataset
+    check_en_wik9_dataset, check_yahoo_answers_dataset, check_multi30k_dataset, check_squad_dataset, \
+    check_sst2_dataset
 
 from ..core.validator_helpers import replace_none
 
 
 class AGNewsDataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses AG News datasets.
+    AG News dataset.
 
     The generated dataset has three columns: :py:obj:`[index, title, description]` ,
     and the data type of three columns is string type.
@@ -46,8 +47,9 @@ class AGNewsDataset(SourceDataset, TextBaseDataset):
         dataset_dir (str): Path to the root directory that contains the dataset.
         usage (str, optional): Acceptable usages include 'train', 'test' and 'all'. Default: None, all samples.
         num_samples (int, optional): Number of samples (rows) to read. Default: None, reads the full dataset.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the mindspore.dataset.config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
             Bool type and Shuffle enum are both supported to pass in. Default: `Shuffle.GLOBAL` .
             If `shuffle` is False, no shuffling will be performed.
@@ -63,7 +65,7 @@ class AGNewsDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . This
             argument can only be specified when `num_shards` is also specified. Default: None.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -129,7 +131,7 @@ class AGNewsDataset(SourceDataset, TextBaseDataset):
 
 class AmazonReviewDataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses Amazon Review Polarity and Amazon Review Full datasets.
+    Amazon Review Polarity and Amazon Review Full datasets.
 
     The generated dataset has three columns: :py:obj:`[label, title, content]` ,
     and the data type of three columns is string.
@@ -145,8 +147,9 @@ class AmazonReviewDataset(SourceDataset, TextBaseDataset):
             'test' will read from 650,000 test samples,
             'all' will read from all 3,650,000 samples. Default: None, all samples.
         num_samples (int, optional): Number of samples (rows) to be read. Default: None, reads the full dataset.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the mindspore.dataset.config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
             Bool type and Shuffle enum are both supported to pass in. Default: `Shuffle.GLOBAL` .
             If `shuffle` is False, no shuffling will be performed.
@@ -162,7 +165,7 @@ class AmazonReviewDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -224,7 +227,7 @@ class AmazonReviewDataset(SourceDataset, TextBaseDataset):
 
 class CLUEDataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses CLUE datasets.
+    CLUE(Chinese Language Understanding Evaluation) dataset.
     Supported CLUE classification tasks: 'AFQMC', 'TNEWS', 'IFLYTEK', 'CMNLI', 'WSC' and 'CSL'.
 
     Args:
@@ -235,8 +238,9 @@ class CLUEDataset(SourceDataset, TextBaseDataset):
         usage (str, optional): Specify the 'train', 'test' or 'eval' part of dataset. Default: 'train'.
         num_samples (int, optional): The number of samples to be included in the dataset.
             Default: None, will include all images.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
             Default: Shuffle.GLOBAL. Bool type and Shuffle enum are both supported to pass in.
             If shuffle is False, no shuffling will be performed.
@@ -252,7 +256,7 @@ class CLUEDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     The generated dataset with different task setting has different output columns:
@@ -402,7 +406,7 @@ class CLUEDataset(SourceDataset, TextBaseDataset):
         ValueError: task is not in 'AFQMC', 'TNEWS', 'IFLYTEK', 'CMNLI', 'WSC' or 'CSL'.
         ValueError: usage is not in 'train', 'test' or 'eval'.
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
 
@@ -459,7 +463,7 @@ class CLUEDataset(SourceDataset, TextBaseDataset):
 
 class CoNLL2000Dataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses CoNLL2000 chunking dataset.
+    CoNLL-2000(Conference on Computational Natural Language Learning) chunking dataset.
 
     The generated dataset has three columns: :py:obj:`[word, pos_tag, chunk_tag]` .
     The tensors of column :py:obj:`word` , column :py:obj:`pos_tag` ,
@@ -485,10 +489,11 @@ class CoNLL2000Dataset(SourceDataset, TextBaseDataset):
             When this argument is specified, `num_samples` reflects the max sample number of per shard. Default: None.
         shard_id (int, optional): The shard ID within `num_shards` . This
             argument can only be specified when `num_shards` is also specified. Default: None.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -549,7 +554,7 @@ class CoNLL2000Dataset(SourceDataset, TextBaseDataset):
 
 class DBpediaDataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses the DBpedia dataset.
+    DBpedia dataset.
 
     The generated dataset has three columns :py:obj:`[class, title, content]` ,
     and the data type of three columns is string.
@@ -562,8 +567,9 @@ class DBpediaDataset(SourceDataset, TextBaseDataset):
             'all' will read from all 630,000 samples. Default: None, all samples.
         num_samples (int, optional): The number of samples to be included in the dataset.
             Default: None, will include all text.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the mindspore.dataset.config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
             Bool type and Shuffle enum are both supported to pass in. Default: `Shuffle.GLOBAL` .
             If shuffle is False, no shuffling will be performed.
@@ -579,7 +585,7 @@ class DBpediaDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -587,7 +593,7 @@ class DBpediaDataset(SourceDataset, TextBaseDataset):
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
 
     Examples:
         >>> dbpedia_dataset_dir = "/path/to/dbpedia_dataset_directory"
@@ -646,19 +652,17 @@ class DBpediaDataset(SourceDataset, TextBaseDataset):
 
 class EnWik9Dataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses EnWik9 Polarity and EnWik9 Full datasets.
+    EnWik9 dataset.
 
     The generated dataset has one column :py:obj:`[text]` with type string.
 
     Args:
         dataset_dir (str): Path to the root directory that contains the dataset.
         num_samples (int, optional): The number of samples to be included in the dataset.
-            For Polarity dataset, 'train' will read from 3,600,000 train samples, 'test' will read from 400,000 test
-            samples, 'all' will read from all 4,000,000 samples.
-            For Full dataset, 'train' will read from 3,000,000 train samples, 'test' will read from 650,000 test
-            samples, 'all' will read from all 3,650,000 samples. Default: None, will include all samples.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the mindspore.dataset.config.
+            Default: None, will include all samples.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
             Bool type and Shuffle enum are both supported to pass in. Default: True.
             If shuffle is False, no shuffling will be performed.
@@ -674,7 +678,7 @@ class EnWik9Dataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -732,7 +736,7 @@ class EnWik9Dataset(SourceDataset, TextBaseDataset):
 
 class IMDBDataset(MappableDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses Internet Movie Database (IMDb).
+    IMDb(Internet Movie Database) dataset.
 
     The generated dataset has two columns: :py:obj:`[text, label]` .
     The tensor of column :py:obj:`text` is of the string type.
@@ -743,12 +747,10 @@ class IMDBDataset(MappableDataset, TextBaseDataset):
         usage (str, optional): Usage of this dataset, can be 'train', 'test' or 'all'.
             Default: None, will read all samples.
         num_samples (int, optional): The number of images to be included in the dataset.
-            For Polarity dataset, 'train' will read from 3,600,000 train samples, 'test' will read from 400,000 test
-            samples, 'all' will read from all 4,000,000 samples. For Full dataset, 'train' will read from 3,000,000
-            train samples, 'test' will read from 650,000 test samples, 'all' will read from all 3,650,000 samples.
             Default: None, will include all samples.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the mindspore.dataset.config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (bool, optional): Whether or not to perform shuffle on the dataset.
             Default: None, expected order behavior shown in the table below.
         sampler (Sampler, optional): Object used to choose samples from the dataset.
@@ -759,7 +761,7 @@ class IMDBDataset(MappableDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -769,7 +771,7 @@ class IMDBDataset(MappableDataset, TextBaseDataset):
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
 
     Note:
         - The shape of the test column.
@@ -877,7 +879,7 @@ class IMDBDataset(MappableDataset, TextBaseDataset):
 
 class IWSLT2016Dataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses IWSLT2016 datasets.
+    IWSLT2016(International Workshop on Spoken Language Translation) dataset.
 
     The generated dataset has two columns: :py:obj:`[text, translation]` .
     The tensor of column :py:obj: `text` is of the string type.
@@ -910,10 +912,11 @@ class IWSLT2016Dataset(SourceDataset, TextBaseDataset):
             When this argument is specified, `num_samples` reflects the max sample number of per shard.
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the mindspore.dataset.config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -1005,7 +1008,7 @@ class IWSLT2016Dataset(SourceDataset, TextBaseDataset):
 
 class IWSLT2017Dataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses IWSLT2017 datasets.
+    IWSLT2017(International Workshop on Spoken Language Translation) dataset.
 
     The generated dataset has two columns: :py:obj:`[text, translation]` .
     The tensor of column :py:obj:`text` and :py:obj:`translation` are of the string type.
@@ -1032,10 +1035,11 @@ class IWSLT2017Dataset(SourceDataset, TextBaseDataset):
             When this argument is specified, `num_samples` reflects the max sample number of per shard.
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the mindspore.dataset.config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -1102,29 +1106,29 @@ class IWSLT2017Dataset(SourceDataset, TextBaseDataset):
 
 class Multi30kDataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses Multi30k dataset.
+    Multi30k dataset.
 
     The generated dataset has two columns :py:obj:`[text, translation]` .
-    The tensor of column :py:obj:'text' is of the string type.
-    The tensor of column :py:obj:'translation' is of the string type.
+    The tensor of column :py:obj:`text` is of the string type.
+    The tensor of column :py:obj:`translation` is of the string type.
 
-      Args:
+    Args:
         dataset_dir (str): Path to the root directory that contains the dataset.
-        usage (str, optional): Acceptable usages include 'train', 'test, 'valid' or 'all'. Default: 'all'.
-        language_pair (str, optional): Acceptable language_pair include ['en', 'de'], ['de', 'en'].
-            Default: ['en', 'de'].
+        usage (str, optional): Acceptable usages include 'train', 'test, 'valid' or 'all'.
+            Default: None, will read all samples.
+        language_pair (Sequence[str, str], optional): Acceptable language_pair include ['en', 'de'], ['de', 'en'].
+            Default: None, means ['en', 'de'].
         num_samples (int, optional): The number of images to be included in the dataset.
-            Default: None, all samples.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
-        shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
-            Bool type and Shuffle enum are both supported to pass in. Default: `Shuffle.GLOBAL` .
-            If shuffle is False, no shuffling will be performed.
-            If shuffle is True, it is equivalent to setting `shuffle` to mindspore.dataset.Shuffle.GLOBAL.
-            Set the mode of data shuffling by passing in enumeration variables:
+            Default: None, will read all samples.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
+        shuffle (Union[bool, Shuffle], optional): Whether to shuffle the dataset. Default: None, means Shuffle.GLOBAL.
+            If False is provided, no shuffling will be performed.
+            If True is provided, it is the same as setting to mindspore.dataset.Shuffle.GLOBAL.
+            If Shuffle is provided, the effect is as follows:
 
             - Shuffle.GLOBAL: Shuffle both the files and samples.
-
             - Shuffle.FILES: Shuffle files only.
 
         num_shards (int, optional): Number of shards that the dataset will be divided
@@ -1133,17 +1137,18 @@ class Multi30kDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
         RuntimeError: If `dataset_dir` does not contain data files.
-        RuntimeError: If `usage` is not 'train', 'test', 'valid' or 'all'.
-        RuntimeError: If the length of language_pair is not equal to 2.
-        ValueError: If `num_parallel_workers` exceeds the max thread numbers.
+        ValueError: If `usage` is not 'train', 'test', 'valid' or 'all'.
+        TypeError: If `language_pair` is not of type Sequence[str, str].
+        RuntimeError: If num_samples is less than 0.
+        RuntimeError: If `num_parallel_workers` exceeds the max thread numbers.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
-        RuntimeError: If num_samples is less than 0.
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
 
     Examples:
         >>> multi30k_dataset_dir = "/path/to/multi30k_dataset_directory"
@@ -1151,11 +1156,11 @@ class Multi30kDataset(SourceDataset, TextBaseDataset):
 
     About Multi30k dataset:
 
-    Multi30K is a dataset to stimulate multilingual multimodal research for English-German.
-    It is based on the Flickr30k dataset, which contains images sourced from online
-    photo-sharing websites. Each image is paired with five English descriptions, which were
-    collected from Amazon Mechanical Turk. The Multi30K dataset extends the Flickr30K
-    dataset with translated and independent German sentences.
+    Multi30K is a multilingual dataset that features approximately 31,000 standardized images
+    described in multiple languages. The images are sourced from Flickr and each image comes
+    with sentence descripitions in both English and German, as well as descriptions in other
+    languages. Multi30k is used primarily for training and testing in tasks such as image
+    captioning, machine translation, and visual question answering.
 
     You can unzip the dataset files into the following directory structure and read by MindSpore's API.
 
@@ -1203,7 +1208,7 @@ class Multi30kDataset(SourceDataset, TextBaseDataset):
 
 class PennTreebankDataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses PennTreebank datasets.
+    PennTreebank dataset.
 
     The generated dataset has one column :py:obj:`[text]` .
     The tensor of column :py:obj:`text` is of the string type.
@@ -1216,8 +1221,9 @@ class PennTreebankDataset(SourceDataset, TextBaseDataset):
             'valid' will read from 3,761 test samples of string type,
             'all' will read from all 49,199 samples of string type. Default: None, all samples.
         num_samples (int, optional): Number of samples (rows) to read. Default: None, reads the full dataset.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the mindspore.dataset.config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
             Bool type and Shuffle enum are both supported to pass in. Default: `Shuffle.GLOBAL` .
             If shuffle is False, no shuffling will be performed.
@@ -1229,11 +1235,11 @@ class PennTreebankDataset(SourceDataset, TextBaseDataset):
             - Shuffle.FILES: Shuffle files only.
 
         num_shards (int, optional): Number of shards that the dataset will be divided into. Default: None.
-            When this argument is specified, 'num_samples' reflects the max sample number of per shard.
+            When this argument is specified, `num_samples` reflects the max sample number of per shard.
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -1300,7 +1306,7 @@ class PennTreebankDataset(SourceDataset, TextBaseDataset):
 
 class SogouNewsDataset(SourceDataset, TextBaseDataset):
     r"""
-    A source dataset that reads and parses Sogou News dataset.
+    Sogou News dataset.
 
     The generated dataset has three columns: :py:obj:`[index, title, content]` ,
     and the data type of three columns is string.
@@ -1324,10 +1330,11 @@ class SogouNewsDataset(SourceDataset, TextBaseDataset):
             When this argument is specified, `num_samples` reflects the max sample number of per shard.
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -1386,31 +1393,30 @@ class SogouNewsDataset(SourceDataset, TextBaseDataset):
 
 class SQuADDataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses SQuAD 1.1 and SQuAD 2.0 datasets.
+    SQuAD 1.1 and SQuAD 2.0 datasets.
 
     The generated dataset with different versions and usages has the same output columns:
-        :py:obj:`[context, question, text, answer_start]` .
+    :py:obj:`[context, question, text, answer_start]` .
     The tensor of column :py:obj:`context` is of the string type.
     The tensor of column :py:obj:`question` is of the string type.
     The tensor of column :py:obj:`text` is the answer in the context of the string type.
     The tensor of column :py:obj:`answer_start` is the start index of answer in context,
-        which is of the uint32 type.
+    which is of the uint32 type.
 
     Args:
         dataset_dir (str): Path to the root directory that contains the dataset.
         usage (str, optional): Specify the 'train', 'dev' or 'all' part of dataset. Default: None, all samples.
         num_samples (int, optional): The number of samples to be included in the dataset.
             Default: None, will include all samples.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
-        shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
-            Bool type and Shuffle enum are both supported to pass in. Default: `Shuffle.GLOBAL` .
-            If shuffle is False, no shuffling will be performed.
-            If shuffle is True, it is equivalent to setting `shuffle` to mindspore.dataset.Shuffle.GLOBAL.
-            Set the mode of data shuffling by passing in enumeration variables:
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
+        shuffle (Union[bool, Shuffle], optional): Whether to shuffle the dataset. Default: Shuffle.GLOBAL.
+            If False is provided, no shuffling will be performed.
+            If True is provided, it is the same as setting to mindspore.dataset.Shuffle.GLOBAL.
+            If Shuffle is provided, the effect is as follows:
 
             - Shuffle.GLOBAL: Shuffle both the files and samples.
-
             - Shuffle.FILES: Shuffle files only.
 
         num_shards (int, optional): Number of shards that the dataset will be divided into. Default: None.
@@ -1418,7 +1424,7 @@ class SQuADDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -1426,6 +1432,7 @@ class SQuADDataset(SourceDataset, TextBaseDataset):
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
 
     Examples:
         >>> squad_dataset_dir = "/path/to/squad_dataset_file"
@@ -1433,7 +1440,7 @@ class SQuADDataset(SourceDataset, TextBaseDataset):
 
     About SQuAD dataset:
 
-    Stanford Question Answering Dataset (SQuAD) is a reading comprehension dataset, consisting of questions posed by
+    SQuAD (Stanford Question Answering Dataset) is a reading comprehension dataset, consisting of questions posed by
     crowdworkers on a set of Wikipedia articles, where the answer to every question is a segment of text, or span,
     from the corresponding reading passage, or the question might be unanswerable.
 
@@ -1447,6 +1454,7 @@ class SQuADDataset(SourceDataset, TextBaseDataset):
     For SQuAD 1.1:
 
     .. code-block::
+
         .
         └── SQuAD1
              ├── train-v1.1.json
@@ -1455,6 +1463,7 @@ class SQuADDataset(SourceDataset, TextBaseDataset):
     For SQuAD 2.0:
 
     .. code-block::
+
         .
         └── SQuAD2
              ├── train-v2.0.json
@@ -1496,6 +1505,106 @@ class SQuADDataset(SourceDataset, TextBaseDataset):
                              self.num_shards, self.shard_id)
 
 
+class SST2Dataset(SourceDataset, TextBaseDataset):
+    """
+    SST2(Stanford Sentiment Treebank v2) dataset.
+
+    The generated dataset's train.tsv and dev.tsv have two columns :py:obj:`[sentence, label]` .
+    The generated dataset's test.tsv has one column :py:obj:`[sentence]` .
+    The tensor of column :py:obj:`sentence` and :py:obj:`label` are of the string type.
+
+    Args:
+        dataset_dir (str): Path to the root directory that contains the dataset.
+        usage (str, optional): Usage of this dataset, can be `train`, `test` or `dev`. `train` will read
+            from 67,349 train samples, `test` will read from 1,821 test samples, `dev` will read from
+            all 872 samples. Default: None, will read train samples.
+        num_samples (int, optional): The number of samples to be included in the dataset.
+            Default: None, will include all text.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
+        shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
+            Bool type and Shuffle enum are both supported to pass in. Default: `Shuffle.GLOBAL` .
+            If shuffle is False, no shuffling will be performed;
+            If shuffle is True, the behavior is the same as setting shuffle to be Shuffle.GLOBAL
+            Set the mode of data shuffling by passing in enumeration variables:
+
+            - Shuffle.GLOBAL: Shuffle the samples.
+
+        num_shards (int, optional): Number of shards that the dataset will be divided into. Default: None.
+            When this argument is specified, `num_samples` reflects the maximum sample number of per shard.
+        shard_id (int, optional): The shard ID within num_shards. This argument can only be specified when
+            num_shards is also specified. Default: None.
+        cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
+            Default: None, which means no cache is used.
+
+    Raises:
+        RuntimeError: If `dataset_dir` does not contain data files.
+        ValueError: If `num_parallel_workers` exceeds the max thread numbers.
+        RuntimeError: If `num_shards` is specified but shard_id is None.
+        RuntimeError: If `shard_id` is specified but num_shards is None.
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
+
+    Examples:
+        >>> sst2_dataset_dir = "/path/to/sst2_dataset_directory"
+        >>>
+        >>> # 1) Read 3 samples from SST2 dataset
+        >>> dataset = ds.SST2Dataset(dataset_dir=sst2_dataset_dir, num_samples=3)
+        >>>
+        >>> # 2) Read train samples from SST2 dataset
+        >>> dataset = ds.SST2Dataset(dataset_dir=sst2_dataset_dir, usage="train")
+
+    About SST2 dataset:
+    The Stanford Sentiment Treebank is a corpus with fully labeled parse trees that allows for a complete
+    analysis of the compositional effects of sentiment in language. The corpus is based on the dataset introduced
+    by Pang and Lee (2005) and consists of 11,855 single sentences extracted from movie reviews. It was parsed
+    with the Stanford parser and includes a total of 215,154 unique phrases from those parse trees, each
+    annotated by 3 human judges.
+
+    Here is the original SST2 dataset structure.
+    You can unzip the dataset files into this directory structure and read by Mindspore's API.
+
+    .. code-block::
+
+        .
+        └── sst2_dataset_dir
+            ├── train.tsv
+            ├── test.tsv
+            ├── dev.tsv
+            └── original
+
+    Citation:
+
+    .. code-block::
+
+        @inproceedings{socher-etal-2013-recursive,
+            title     = {Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank},
+            author    = {Socher, Richard and Perelygin, Alex and Wu, Jean and Chuang, Jason and Manning,
+                          Christopher D. and Ng, Andrew and Potts, Christopher},
+            booktitle = {Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing},
+            month     = oct,
+            year      = {2013},
+            address   = {Seattle, Washington, USA},
+            publisher = {Association for Computational Linguistics},
+            url       = {https://www.aclweb.org/anthology/D13-1170},
+            pages     = {1631--1642},
+        }
+    """
+
+    @check_sst2_dataset
+    def __init__(self, dataset_dir, usage=None, num_samples=None, num_parallel_workers=None, shuffle=Shuffle.GLOBAL,
+                 num_shards=None, shard_id=None, cache=None):
+        super().__init__(num_parallel_workers=num_parallel_workers, num_samples=num_samples, shuffle=shuffle,
+                         num_shards=num_shards, shard_id=shard_id, cache=cache)
+        self.dataset_dir = dataset_dir
+        self.usage = replace_none(usage, "train")
+
+    def parse(self, children=None):
+        return cde.SST2Node(self.dataset_dir, self.usage, self.num_samples, self.shuffle_flag,
+                            self.num_shards, self.shard_id)
+
+
 class TextFileDataset(SourceDataset, TextBaseDataset):
     """
     A source dataset that reads and parses datasets stored on disk in text format.
@@ -1506,8 +1615,9 @@ class TextFileDataset(SourceDataset, TextBaseDataset):
             pattern of files. The list will be sorted in a lexicographical order.
         num_samples (int, optional): The number of samples to be included in the dataset.
             Default: None, will include all images.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
             Default: `Shuffle.GLOBAL` . Bool type and Shuffle enum are both supported to pass in.
             If shuffle is False, no shuffling will be performed.
@@ -1523,7 +1633,7 @@ class TextFileDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -1531,7 +1641,7 @@ class TextFileDataset(SourceDataset, TextBaseDataset):
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
 
     Examples:
         >>> text_file_dataset_dir = ["/path/to/text_file_dataset_file"] # contains 1 or multiple text files
@@ -1553,7 +1663,7 @@ class TextFileDataset(SourceDataset, TextBaseDataset):
 
 class UDPOSDataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses UDPOS dataset.
+    UDPOS(Universal Dependencies dataset for Part of Speech) dataset.
 
     The generated dataset has three columns: :py:obj:`[word, universal, stanford]` ,
     and the data type of three columns is string.
@@ -1578,10 +1688,11 @@ class UDPOSDataset(SourceDataset, TextBaseDataset):
             When this argument is specified, `num_samples` reflects the max sample number of per shard.
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
@@ -1629,7 +1740,7 @@ class UDPOSDataset(SourceDataset, TextBaseDataset):
 
 class WikiTextDataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses WikiText2 and WikiText103 datasets.
+    WikiText2 and WikiText103 datasets.
 
     The generated dataset has one column :py:obj:`[text]` , and
     the tensor of column `text` is of the string type.
@@ -1638,8 +1749,9 @@ class WikiTextDataset(SourceDataset, TextBaseDataset):
         dataset_dir (str): Path to the root directory that contains the dataset.
         usage (str, optional): Acceptable usages include 'train', 'test', 'valid' and 'all'. Default: None, all samples.
         num_samples (int, optional): Number of samples (rows) to read. Default: None, reads the full dataset.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
             Bool type and Shuffle enum are both supported to pass in. Default: `Shuffle.GLOBAL` .
             If shuffle is False, no shuffling will be performed.
@@ -1651,18 +1763,18 @@ class WikiTextDataset(SourceDataset, TextBaseDataset):
             - Shuffle.FILES: Shuffle files only.
 
         num_shards (int, optional): Number of shards that the dataset will be divided into. Default: None.
-            When this argument is specified, 'num_samples' reflects the max sample number of per shard.
+            When this argument is specified, `num_samples` reflects the max sample number of per shard.
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
         RuntimeError: If `dataset_dir` does not contain data files or invalid.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
         ValueError: If `num_samples` is invalid (< 0).
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
 
@@ -1716,7 +1828,7 @@ class WikiTextDataset(SourceDataset, TextBaseDataset):
 
 class YahooAnswersDataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses the YahooAnswers dataset.
+    YahooAnswers dataset.
 
     The generated dataset has four columns :py:obj:`[class, title, content, answer]` , whose data type is string.
 
@@ -1727,8 +1839,9 @@ class YahooAnswersDataset(SourceDataset, TextBaseDataset):
             all 1,460,000 samples. Default: None, all samples.
         num_samples (int, optional): The number of samples to be included in the dataset.
             Default: None, will include all text.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         shuffle (Union[bool, Shuffle], optional): Perform reshuffling of the data every epoch.
             Bool type and Shuffle enum are both supported to pass in. Default: `Shuffle.GLOBAL` .
             If shuffle is False, no shuffling will be performed.
@@ -1744,14 +1857,14 @@ class YahooAnswersDataset(SourceDataset, TextBaseDataset):
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises:
         RuntimeError: If `dataset_dir` does not contain data files.
         RuntimeError: If `num_shards` is specified but `shard_id` is None.
         RuntimeError: If `shard_id` is specified but `num_shards` is None.
-        ValueError: If `shard_id` is invalid (< 0 or >= `num_shards`).
+        ValueError: If `shard_id` is not in range of [0, `num_shards` ).
         ValueError: If `num_parallel_workers` exceeds the max thread numbers.
 
     Examples:
@@ -1810,7 +1923,7 @@ class YahooAnswersDataset(SourceDataset, TextBaseDataset):
 
 class YelpReviewDataset(SourceDataset, TextBaseDataset):
     """
-    A source dataset that reads and parses Yelp Review Polarity and Yelp Review Full dataset.
+    Yelp Review Polarity and Yelp Review Full datasets.
 
     The generated dataset has two columns: :py:obj:`[label, text]` , and the data type of two columns is string.
 
@@ -1835,10 +1948,11 @@ class YelpReviewDataset(SourceDataset, TextBaseDataset):
             When this argument is specified, `num_samples` reflects the max sample number of per shard.
         shard_id (int, optional): The shard ID within `num_shards` . Default: None. This
             argument can only be specified when `num_shards` is also specified.
-        num_parallel_workers (int, optional): Number of workers to read the data.
-            Default: None, number set in the config.
+        num_parallel_workers (int, optional): Number of worker threads to read the data.
+            Default: None, will use global default workers(8), it can be set
+            by `mindspore.dataset.config.set_num_parallel_workers` .
         cache (DatasetCache, optional): Use tensor caching service to speed up dataset processing. More details:
-            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0.0-alpha/dataset/cache.html>`_ .
+            `Single-Node Data Cache <https://www.mindspore.cn/tutorials/experts/en/r2.0/dataset/cache.html>`_ .
             Default: None, which means no cache is used.
 
     Raises: