示例代码

• 示例一：根据数据类型创建图像数据集

  from modelarts.session import Session
  from modelarts.dataset import Dataset
  
  session = Session()
  
  dataset_name = "dataset-image"  # 数据集名称
  data_type = "IMAGE"             # 数据集类型，图像类型数据集
  data_sources = dict()           # 数据集数据来源
  data_sources["type"] = 0        # 数据来源类型，0表示OBS
  data_sources["path"] = "/obs-gaia-test/data/image/image-classification/" # 数据在OBS中的路径
  work_path = dict()              # 数据集输出位置，用于存放输出的标注信息等文件
  work_path['type'] = 0           # 数据集工作目录的类型，0表示OBS
  work_path['path'] = "/obs-gaia-test/data/output/work_path/"  # 数据集工作目录在OBS中的路径
  create_dataset_resp = Dataset.create_dataset(session, dataset_name=dataset_name, data_type=data_type,
                                               data_sources=data_sources, work_path=work_path)

• 示例二：根据数据类型创建图像数据集（导入标注信息）

  from modelarts.session import Session
  from modelarts.dataset import Dataset
  
  session = Session()
  
  dataset_name = "dataset-image-with-annotations"
  data_type = "IMAGE"
  data_sources = dict()
  data_sources["type"] = 0
  data_sources["path"] = "/obs-gaia-test/data/image/image-classification/"
  annotation_config = dict()      # 源数据的标注格式
  annotation_config['scene'] = "image_classification" # 数据标注场景为图像分类标注
  annotation_config['format_name'] = "ModelArts image classification 1.0" # 标注格式为ModelArts image classification 1.0
  data_sources['annotation_config'] = annotation_config
  work_path = dict()
  work_path['type'] = 0
  work_path['path'] = "/obs-gaia-test/data/output/work_path/"
  create_dataset_resp = Dataset.create_dataset(session, dataset_name=dataset_name, data_type=data_type,
                                               data_sources=data_sources, work_path=work_path)

• 示例三：根据数据类型创建表格数据集

  from modelarts.session import Session
  from modelarts.dataset import Dataset
  
  session = Session()
  
  dataset_name = "dataset-table"
  data_type = "TABLE"
  data_sources = dict()
  data_sources["type"] = 0
  data_sources["path"] = "/obs-gaia-test/data/table/table0/"
  data_sources['with_column_header'] = True
  work_path = dict()
  work_path['type'] = 0
  work_path['path'] = "/obs-gaia-test/data/output/work_path/"
  # 表格类型的数据集需要指定表格数据的schema信息
  schema0 = dict()
  schema0['schema_id'] = 0
  schema0['name'] = "name"
  schema0['type'] = "STRING"
  schema1 = dict()
  schema1['schema_id'] = 1
  schema1['name'] = "age"
  schema1['type'] = "STRING"
  schema2 = dict()
  schema2['schema_id'] = 2
  schema2['name'] = "label"
  schema2['type'] = "STRING"
  schemas = []
  schemas.append(schema0)
  schemas.append(schema1)
  schemas.append(schema2)
  create_dataset_resp = Dataset.create_dataset(session, dataset_name=dataset_name, data_type=data_type,
                                               data_sources=data_sources, work_path=work_path, schema=schemas)

• 示例四：根据标注类型创建图像分类数据集

  from modelarts.session import Session
  from modelarts.dataset import Dataset
  
  session = Session()
  
  dataset_name = "dataset-image-classification"
  dataset_type = 0   # 数据集的标注类型，0表示图像分类标注类型
  data_sources = dict()
  data_sources["path"] = "/obs-gaia-test/data/image/image-classification/"
  data_sources["type"] = "0"
  work_path = dict()
  work_path['type'] = 0
  work_path['path'] = "/obs-gaia-test/data/output/work_path/"
  create_dataset_resp = Dataset.create_dataset(session, dataset_name=dataset_name, dataset_type=dataset_type, data_sources=data_sources, work_path=work_path)

• 示例五：根据标注类型创建文本三元组数据集

  dataset_name = "dataset-text-triplet"
  dataset_type = 102   # 数据集标注类型，102表示文本三元组标注类型
  data_sources = dict()
  data_sources['type'] = 0
  data_sources['path'] = "/obs-gaia-test/data/text/text-classification/"
  work_path = dict()
  work_path['type'] = 0
  work_path['path'] = "/obs-gaia-test/data/output/work_path/"
  
  # 创建文本三元组标注类型的数据集，需要传入标签参数
  label_entity1 = dict()    # 标签对象
  label_entity1['name'] = "疾病"    # 标签名称
  label_entity1['type'] = 101     # 标签类型，101表示实体类型标签
  label_entity2 = dict()
  label_entity2['name'] = "疾病别称"
  label_entity2['type'] = 101
  label_relation1 = dict()
  label_relation1['name'] = "又称为"
  label_relation1['type'] = 102    # 标签类型，102表示关系类型标签
  property = dict()    # 关系类型标签需要在标签属性中指定起始实体标签和终止实体标签
  property['@modelarts:from_type'] = "疾病"    # 起始实体标签
  property['@modelarts:to_type'] = "疾病别称"    # 终止实体标签
  label_relation1['property'] = property
  labels = []
  labels.append(label_entity1)
  labels.append(label_entity2)
  labels.append(label_relation1)
  create_dataset_resp = Dataset.create_dataset(session, dataset_name=dataset_name, dataset_type=dataset_type, data_sources=data_sources, work_path=work_path, labels=labels)

• 示例六：根据标注类型创建表格数据集

  dataset_name = "dataset-table"
  dataset_type = 400    # 数据集标注类型，400表示表格数据集
  data_sources = dict()
  data_sources['type'] = 0
  data_sources['path'] = "/obs-gaia-test/data/table/table0/"
  data_sources['with_column_header'] = True    # 用来指明表格数据中是否包含表头
  work_path = dict()
  work_path['type'] = 0
  work_path['path'] = "/obs-gaia-test/data/output/work_path/"
  
  # 表格数据集需要传入表格数据的表头参数
  schema0 = dict()    # 表格的表头
  schema0['schema_id'] = 0    # 第一列表头
  schema0['name'] = "name"    # 表头名称，该列表头为name
  schema0['type'] = "STRING"    # 表头数据类型，表示字符串
  schema1 = dict()
  schema1['schema_id'] = 1
  schema1['name'] = "age"
  schema1['type'] = "STRING"
  schema2 = dict()
  schema2['schema_id'] = 2
  schema2['name'] = "label"
  schema2['type'] = "STRING"
  schemas = []
  schemas.append(schema0)
  schemas.append(schema1)
  schemas.append(schema2)
  create_dataset_resp = Dataset.create_dataset(session, dataset_name=dataset_name, dataset_type=dataset_type, data_sources=data_sources, work_path=work_path, schema=schemas)