Standardized Hudup dataset based on Film Trust data

Standardized Hudup dataset receives information from raw data, which is composed of ten units such as “hdp_config”, “hdp_account”, “hdp_attribute_map”, “hdp_nominal”, “hdp_user”, “hdp_item”, “hdp_rating”, “hdp_context_template”, “hdp_context”, and “hdp_sample”. Each unit has particular functions, which is described in the section of data description. Hudup dataset is meta-data which models any raw data with abstract level. The raw data which is source of Hudup dataset here is Film Trust data. It is possible to consider that Hudup dataset is secondary data whereas Film Trust is primary data. The raw rating data Film Trust has 35,497 ratings from 1,508 users on 2,071 films (items), which is available at https://guoguibing.github.io/librec/datasets/filmtrust.zip.

标准化后的 Hudup 数据集，源于原始数据，该数据集由十个单元组成，包括‘hdp_config’、‘hdp_account’、‘hdp_attribute_map’、‘hdp_nominal’、‘hdp_user’、‘hdp_item’、‘hdp_rating’、‘hdp_context_template’、‘hdp_context’以及‘hdp_sample’。每个单元各司其职，其具体功能在数据描述章节中有所阐述。Hudup 数据集作为一种元数据，能够以抽象层次模拟任何原始数据。在此，Hudup 数据集可视为次级数据，而 Film Trust 数据则为一级数据。原始的 Film Trust 评分数据包含来自 1,508 位用户对 2,071 部电影（项目）的 35,497 条评分记录，详细信息可访问 https://guoguibing.github.io/librec/datasets/filmtrust.zip。