Structured Dengue Data for São José dos Campos, Ouro Preto, and Resende (2014–2024)

This dataset contains structured dengue epidemiological data for the Brazilian cities of São José dos Campos, Ouro Preto, and Resende, covering the period from 2014 to 2024. The data were collected from Info Dengue and SINAN (Sistema de Informação de Agravos de Notificação – Notifiable Diseases Information System) and processed according to structured data principles and data handling operations. As a result, four relations were generated: R1, R21, R22, and R23. The dataset is part of an ongoing academic investigation, with further details and analyses to be presented in future publications. It is intended to support epidemiological research, data analysis, and the development of predictive models for dengue surveillance and control. It is important to note that the dataset contains missing values in some attributes. Users are encouraged to apply pre-processing techniques, such as missing value imputation, normalization, or filtering, depending on the intended analysis. The attributes of each relation are organized as follows: Relation R1 epi_weeks: Epidemiological week (2014–2024). casos: Number of reported cases. avg_temp: Average temperature (°C). avg_humid: Average relative humidity (%). Relation R21 year: Year of record (2014-2024). cases_autoc: Autochthonous cases. cases_clinical: Clinical cases. cases_laboratory: Laboratory-confirmed cases. Relation R22 year: Year of record (2014-2024). hospitalization: Indicator of hospitalization (1 = Yes, 0 = No). quantity: Number of cases associated with hospitalization status. Relation R23 year: Year of record (2014-2024). status: Indicator of case outcome (1 = Recovered, 0 = Other) quantity: Number of cases associated with the outcome. Observation. An inconsistency was identified in the dataset because integer-valued data were incorrectly stored as floating-point values. Additionally, in Relation R23 for the city of Resende, data issues were also observed. These issues affected the dataset used in the analyses. The original source data remain unchanged. A new repository with the updated dataset will be made available.