1.1 研报词袋模型基础表 (rr_bow_base)
FULL_NAME_EN Research Report Bag of Words Info
描述 : 记录了词袋模型分词、词性、情感词,研报标签。
DESCRIPTION_EN : Record words set, words sentiment, words label and tags of research reports.
唯一键 : REPORT_ID
数据起始时间 : 2009-07-08
更新频率 :
数据更新时间 : 05:30,09:30,13:30,16:30,22:30
数据调用方式 : Hermes,API
API文档 : getRrBowBase--研报词袋模型基础表
数据来源 : 通联数据
DATA_SOURCE_EN : Datayes
字段信息 :
序号 字段名 中文名称 FULL_NAME_EN 数据类型 可空 字段描述 DESCRIPTION_EN 参数值 备注
1 ID 自增ID Self-incrementing ID bigint
2 REPORT_ID 研报ID Research Report ID bigint 对应rr_main中的ID Correspond to rr_main.ID
3 REPORT_SUB_TYPE 研报类型(二级) Research Report Subtype varchar(20) 对应rr_main中的REPORT_SUB_TYPE Correspond to rr_main.REPORT_SUB_TYPE
4 TICKER_SYMBOL 个股 Ticker Symbol varchar(20) 对应rr_main中的SEC_CODE Correspond to rr_main.SEC_CODE
5 PUBLISH_DATE 发布日 Publish Date Accessed By Third Party date 对应rr_main中的PUBLISH_DATE Correspond to rr_main.PUBLISH_DATE
6 WRITE_DATE 撰写日 Write Date Recorded In Report Content date 对应rr_main中的WRITE_DATE Correspond to rr_main.WRITE_DATE
7 ORG_NAME 机构名 Orgnization Name varchar(800) 对应rr_main中的ORG_NAME Correspond to rr_main.ORG_NAME
8 WORD_SET_TITLE 词集(标题) Words Set of Report Title varchar(500)
9 WORD_FREQ_TITLE 词频(标题) Words Frequency of Report Title varchar(300)
10 WORD_EMOTION_TITLE 词汇情感(标题) Words Sentiment of Report Title varchar(300) 枚举, 1:负面, 2:正面, 3:其他 1: Negative, 2: Postive, 3: Others
11 WORD_LABEL_TITLE 词性(标题) Words Label of Report Title varchar(300) 枚举, 1:名词, 2:其他名词, 3:人名, 4:动词,5:副动词, 6:名动词, 7:形容词, 8:名形词, 9:副形词, 10:副词, 11:时间词 1: noun, 2: noun proper, 3: noun people, 4: verb, 5: verb adverb, 6: verb noun, 7: adjective, 8: adjective noun, 9: adjective adverb, 10: adverb, 11:time
12 WORD_SET_ABSTRACT 词集(摘要) Words Set of Report Abstract varchar(6000)
13 WORD_FREQ_ABSTRACT 词频(摘要) Words Frequency of Report Abstract varchar(4000)
14 WORD_EMOTION_ABSTRACT 词汇情感(摘要) Words Sentiment of Report Abstract varchar(4000) 枚举, 1:负面, 2:正面, 3:其他 1: Negative, 2: Postive, 3: Others
15 WORD_LABEL_ABSTRACT 词性(摘要) Words Label of Report Abstract varchar(4000) 枚举, 1:名词, 2:其他名词, 3:人名, 4:动词,5:副动词, 6:名动词, 7:形容词, 8:名形词, 9:副形词, 10:副词, 11:时间词 1: noun, 2: noun proper, 3: noun people, 4: verb, 5: verb adverb, 6: verb noun, 7: adjective, 8: adjective noun, 9: adjective adverb, 10: adverb, 11:time
16 IS_PROFIT_ADJ 浮点型,调整盈利预测幅度 Profit Adjusted Ratio Compared with Same Orgnization decimal(20,8)
17 IS_SCORE_ADJ 字符串,调整评级 Rate Score Changed Recored In Report Content varchar(100) 对应rr_main中的RATING_CHANGE Correspond to rr_main.RATING_CHANGE
18 IS_TARGET_PRICE_ADJ 浮点型,调整目标价 Target Price Changed Compared with Same Orgnization decimal(20,8)
19 IS_REVIEW_FISCAL 布尔类型,评价财务报告 Whehter Reviewed Within Five Days After Fiscal Estimation/Brief Report tinyint
20 UPDATE_TIME 更新时间 Update Time datetime
1.2 研报词袋模型打分表 (rr_bow_score)
FULL_NAME_EN Research Report Score of Bag of Words Model
描述 : 记录了研报使用词袋模型,要预测的目标,打分。
DESCRIPTION_EN : Record market impact, profit adjusted ratio and predicted score of research reports.
唯一键 : REPORT_ID
数据起始时间 : 2009-07-08
更新频率 :
数据更新时间 : 05:30,09:30,13:30,16:30,22:30
数据调用方式 : Hermes,API
API文档 : getRrBowScore--研报词袋模型打分表
数据来源 : 通联数据
DATA_SOURCE_EN : Datayes
字段信息 :
序号 字段名 中文名称 FULL_NAME_EN 数据类型 可空 字段描述 DESCRIPTION_EN 参数值 备注
1 ID 自增ID Self-incrementing ID bigint
2 REPORT_ID 研报ID Research Report ID bigint 对应rr_main中的ID Correspond to rr_main.ID
3 REPORT_SUB_TYPE 研报类型(二级) Research Report Subtype varchar(20) 对应rr_main中的REPORT_SUB_TYPE Correspond to rr_main.REPORT_SUB_TYPE
4 TICKER_SYMBOL 个股 Ticker Symbol varchar(20) 对应rr_main中的SEC_CODE Correspond to rr_main.SEC_CODE
5 PUBLISH_DATE 发布日 Publish Date Accessed By Third Party date 对应rr_main中的PUBLISH_DATE Correspond to rr_main.PUBLISH_DATE
6 WRITE_DATE 撰写日 Write Date Recorded In Report Content date 对应rr_main中的WRITE_DATE Correspond to rr_main.WRITE_DATE
7 ORG_NAME 机构名 Orgnization Name varchar(800) 对应rr_main中的ORG_NAME Correspond to rr_main.ORG_NAME
8 NEXT_TRADE_DATE 发布日期后T+1 Next Trade Date After Publish Date date 使用A股交易日历推算发布日下一个交易日 Next Trade Date After Report Publish Date
9 EXCESS_RET_R3D_ZZ500 发布日前后3天超额中证500收益率 Excess Return Compared With ZZ500 Within Recent 3 Days decimal(20,8)
10 EXCESS_RET_R3D_ZZ800 发布日前后3天超额中证800收益率 Excess Return Compared With ZZ800 Within Recent 3 Days decimal(20,8)
11 EXCESS_RET_R3D_ZZ1000 发布日前后3天超额中证1000收益率 Excess Return Compared With ZZ1000 Within Recent 3 Days decimal(20,8)
12 PROFIT_ADJ 较同机构盈利预测调整幅度 Profit Adjusted Ratio Compared with Same Orgnization decimal(20,8)
13 IPA_AR_ZZ500_LOGODDS 打分:数据集1,盈利预测调整;三分类问题,近3天超额分位数 Logodds Score to Predict Excess Return In Profit Adjusted Ratio Not Zero Dataset decimal(20,8)
14 IPA_PA_LOGODDS 打分:数据集1,盈利预测调整;三分类问题,盈利预测调整幅度 Logodds Score to Predict Adjusted Ratio In Profit Adjusted Ratio Not Zero Dataset decimal(20,8)
15 ISA_AR_ZZ500_LOGODDS 打分:数据集2,评级调整;三分类问题,近3天超额分位数 Logodds Score to Predict Excess Return In Rating Score Adjusted Dataset decimal(20,8)
16 ITPA_AR_ZZ500_LOGODDS 打分:数据集3,目标价调整;三分类问题,近3天超额分位数 Logodds Score to Predict Excess Return In Target Price Adjusted Dataset decimal(20,8)
17 IRF_AR_ZZ500_LOGODDS 打分:数据集4,评价财报、预告、快报;三分类问题,近3天超额分位数 Logodds Score to Predict Excess Return In Fiscal Review Dataset decimal(20,8)
18 AR_ZZ500_LOGODDS 打分:数据集1/2/3/4;三分类问题,近3天超额分位数 Logodds Score to Predict Excess Return In All Reports decimal(20,8)
19 UPDATE_TIME 更新时间 Update Time datetime