| Title: | The denguedasets package provide a curated collection of open-access dengue fever surveillance and climate datasets for epidemiological research, data science and machine learning |
|---|---|
| Description: | The denguedasets package provide a curated collection of open-access dengue fever surveillance and climate datasets for epidemiological research and machine learning. Includes surveillance records, climatic co-variates, and mortality indicators from Bangladesh, the Philippines, Taiwan, Sri Lanka, Brazil, Colombia, Pakistan, India, Peru, Indonesia, and Sierra Leone, spanning case counts, deaths, case-fatality rates, and associated meteorological variables (temperature, humidity, precipitation) suitable for spatiotemporal analysis, outbreak prediction, machine learning, and time-series modeling from Kaggle. |
| Authors: | Felipe Antonio Dzul Manzanilla [aut, cre] (ORCID: <https://orcid.org/0000-0002-2085-9141>), Emmanuel Morales García [ctb] (ORCID: <https://orcid.org/0000-0002-6837-9227>), Cecilia Cruz López [ctb] (ORCID: <https://orcid.org/0000-0002-9156-5669>), Fabian Correa Morales [ctb] (ORCID: <https://orcid.org/0000-0002-6193-1242>) |
| Maintainer: | Felipe Antonio Dzul Manzanilla <[email protected]> |
| License: | MIT + file LICENSE |
| Version: | 0.1.0 |
| Built: | 2026-10-19 20:57:50 UTC |
| Source: | https://github.com/fdzul/denguedatasets |
This dataset presents real-world data collected through surveys conducted in the Dhaka region of Bangladesh. It focuses on understanding the prevalence and characteristics of the Dengue fever phenomenon, a significant public health concern in the area. The dataset is updated monthly to reflect the evolving nature of the Dengue outbreak.
dengue_bangladeshdengue_bangladesh
A dataframe object with 1000 rows and 19 variables:
Gender of the survey respondent
Age of the survey respondent
Non-Structural Protein 1 test's data positive as 1 negative as 0
IgG data positive as 1 negative as 0
IgM data positive as 1 negative as 0
The area within the Dhaka region where the respondent resides.
Classification of the area as "Developed" or "Undeveloped
The type of housing in the area, e.g., "Building," "Tin-Shed," or "Others."
The specific district within Dhaka
Acute Dengue febrile phase typically lasts 2–7 days
Biphasic, high fever is the primary clinical entry criterion
Thrombocytopenia (platelets < 150,000) is a critical indicator.
Leukopenia (low WBC count) is highly characteristic of acute Dengue
Arthralgia is so severe it gave Dengue the name "breakbone fever"
Frontal headache is common in acute viral syndromes.
Extremely specific indicator for Dengue vs. other febrile illnesses
Generalized muscle pain is characteristic.
Transient maculopapular rash occurs during convalescence.
Outcome variable indicating the presence (1) or absence (0) of Dengue cases reported
...
The dengue_bangladesh dataset has also been published in the denguedataset package in Python. You can find the Zenodo page https://zenodo.org/records/21499199, GitHub repository https://github.com/fdzul/denguedatasets-py, GitHub Pages https://fdzul.github.io/denguedatasets-py/, and PyPI index at the following links https://pypi.org/project/denguedatasets/.
This dataset explores the spatio-temporal interaction between climate variability and dengue outbreaks across six divisions of Bangladesh from 2000 to 2024. It connects meteorological parameters with epidemiological indicators (cases, deaths, and case-fatality rate) to uncover how changing weather patterns influence dengue mortality
dengue_bangladesh_mortalitydengue_bangladesh_mortality
A dataframe object with 150 rows and 15 variables:
Divisions: Chittagong, Rajshahi, Khulna, Sylhet, Barishal, Rangpur
year covered: 2000-2024
Highest daily temperature influencing mosquito activity and virus transmission
Lowest daily temperature affecting mosquito survival and breeding.
Measures airflow strength, which impacts mosquito movement and dispersion
Measures airflow strength, which impacts mosquito movement and dispersion
Total rainfall contributing to water accumulation for mosquito breeding sites
Moisture level in the soil reflecting wet conditions favorable for breeding habitats.
Atmospheric moisture level that increases mosquito lifespan and biting frequency
Land surface temperature indicating environmental heat that accelerates mosquito development
Number of reported dengue infections in a given period.
Total number of dengue-related fatalities
Case Fatality Rate showing the percentage of infected individuals who died
...
The dengue_bangladesh dataset has also been published in the denguedataset package in Python. You can find the Zenodo page https://zenodo.org/records/21499199, GitHub repository https://github.com/fdzul/denguedatasets-py, GitHub Pages https://fdzul.github.io/denguedatasets-py/, and PyPI index at the following links https://pypi.org/project/denguedatasets/.
The dataset supplied comprises a comprehensive collection of information pertaining to numerous geographical and environmental characteristics across microregions in Brazil from 2000 to 2019. Microregion codes and names, mesoregion codes and names, state codes and names, region codes and names, biome codes and names, ecozone codes and names, climate regimes, months, years, times, dengue cases, population estimates, population density, maximum and minimum temperatures, Palmer's drought severity index, urban population percentages, access to water network percentages, and reported water shortage frequency are all included in the dataset. This information is linked to individual microregions and provides insights into population dynamics, climatic patterns, urbanization trends, water resources, and disease occurrences.
dengue_brazildengue_brazil
A dataframe object with 26 rows and 4 variables:
Unique ID number given by IBGE to each microregion (5 digits)
Name of each microregion
Name of each microregion from IBGE sources
Unique ID number given by IBGE to each mesoregion: 4 digits
Name of each mesoregion
Unique ID number given by IBGE to each state
Name of state
Region code
Region name
Biome code
Biome name
Ecozone code: same as biome apart from Atlantic Rainforest, biome code 6, which has been separated
Ecozone name: same as biome apart from Atlantic Rainforest, which has been separated into NE..
Most prevalent climate regime in the microregion. Based on Koppen Geiger climate regimes
Calendar month index, 1 = January, to, 12 = December
Year: 2000-2019
Time index starting at 1 for January 2000
Number of notified dengue cases registered in the notifiable diseases system in Brazil by SINAN
Estimated population, based on projections calculated using the 2000 and 2010 censuses, and counts
Population density: number of people per km2
Monthly average daily maximum temperature; gridded values at a 0.5° resolution averaged across eac
Monthly average daily minimum temperature; gridded values at a 0.5° resolution averaged across eac
Self-calibrated Palmer drought severity index for each microregion
Percentage of inhabitants living in urban areas according to the 2010 census
Percentage of inhabitants with access to the piped water network according to the 2010 census
Frequency of reported water shortages per microregion between 2000 - 2016
...
The dengue_brazil dataset has also been published in the denguedataset package in Python
Data dictionary/variable-label reference table accompanying the Brazil Dengue Dataset 2000-2019, documenting field names, codes, and descriptions used across microregion, mesoregion, state, region, biome, and ecozone identifiers, as well as climatic and demographic variables in the main dataset.
dengue_brazil_labelsdengue_brazil_labels
A dataframe object with 26 rows and 4 variables:
variable name
long variable name
variable description
source
...
The dengue_brazil_labels dataset has also been published in the denguedataset package in Python
Dataset with sociodemographic, socioeconomic data, dengue cases, temperature and precipitation for all municipalities
dengue_colombiadengue_colombia
A dataframe object with 1121 rows and 1017 variables:
Unique identifier of the municipality
name of the municipality
population:2007-2019
dengue cases: 2007-2019
Age0-4 percent
Age5-14 percent
Age 15 to 29 percent
Age >30 percent
Percentage of Afro-Colombian population
Percentage of Indian population
Percentage of people with disabilities
Percentage of people who cannot read or write
Percentage of people who have a secondary/higher education level
Percentage of employed population
Percentage of unemployed population
Percentage of people who do domestic work
Percentage of retired people
Gender or population percentage of men
Gender or population percentage of women
Households without access to water
Households without internet access
Housing stratification between 1
Housing stratification between 2
Housing stratification between 3
Housing stratification between 4
Housing stratification between 5
Housing stratification between 6
Number of hospitals per km2
Number of houses per km2
temperature: ene-dec 2007-2018
precipitation: ene-dec 2007-2018
Year/epiweek: year 2007-2019, week 1 to 52
...
Dengue Challenge 2 - Make Health LATAM 2022. This challenge will provide a dataset for each municipality in Colombia, composed of weekly dengue cases between 2007 and 2019, along with other social and climatological variables. You will also find a special dataset we have prepared for the municipality of Medellín, with preprocessed climatological variables and a compressed version of satellite images for inclusion in the models. The dengue_colombia dataset has also been published in the denguedataset package in Python
Dataset with weekly Dengue cases, temperature and precipitation in Medellin using the epidemiological week.
dengue_colombia_medellindengue_colombia_medellin
A dataframe object with 624 rows and 10 variables:
dengue cases
year-week
year
yearweek:
Last day week
month
precipitation
precipitation rural
precipitation urban
temperature
...
Dengue Challenge 2 - Make Health LATAM 2022. This challenge will provide a dataset for each municipality in Colombia, composed of weekly dengue cases between 2007 and 2019, along with other social and climatological variables. You will also find a special dataset we have prepared for the municipality of Medellín, with preprocessed climatological variables and a compressed version of satellite images for inclusion in the models. The dengue_colombia_medellin dataset has also been published in the denguedataset package in Python
This data contains dengue cases and deaths happening in each state of India over the years
dengue_indiadengue_india
A dataframe object with 36 rows and 10 variables:
numeric id
state of India
dengue cases of 2019
deaths cases of 2019
dengue cases of 2020
deaths cases of 2020
dengue cases of 2021
deaths cases of 2021
dengue cases of 2022
deaths cases of 2022
...
This data is scrapped from the National Center for Vector Borne Diseases Control. It's a website managed by the Ministry of Health & Family Welfare, Government of India. This data contains dengue cases and deaths happening in each state of India over the years. The dengue_india dataset has also been published in the denguedataset package in Python
This data contains dengue cases hospitalized of Jakarta
dengue_jakartadengue_jakarta
A dataframe object with 2922 rows and 14 variables:
numeric id
Region of Regency or City
Date of observation
Minimum temperature in Celsius
Maximum temperature in Celsius
mean temperature in Celsius
Average relative humidity in percent
Rainfall in mm
Sunshine duration in hours
Maximum wind speed in meters by seconds)
Wind direction at maximum wind speed
Average wind speed in meters by second)
Most frequent wind direction
Number of hospitalized patients
...
The dengue_jakarta dataset has also been published in the denguedataset package in Python. jupyter notebook related https://www.kaggle.com/code/yutakatarokusumah/jakarta-dengue-risk-prediction
This dataset contains monthly dengue fever surveillance data from Pakistan covering the period from 2016 to 2020.
dengue_pakistandengue_pakistan
A dataframe object with 420 rows and 5 variables:
Month name: January through December
Year of observation from 2016 to 2020
Province or territory name
Total number of confirmed dengue fever cases reported
Total number of deaths attributed to dengue fever
...
This dataset contains monthly dengue fever surveillance data from Pakistan covering the period 2016-2020. It provides comprehensive information on dengue cases and deaths across all provinces and territories, making it valuable for epidemiological research, public health policy development, and disease outbreak analysis. Time Period: January 2016 to December 2020 (5 years). Geographic Coverage: All provinces and territories of Pakistan. Frequency: Monthly aggregated data. Total Records: 420 monthly observations. Geographic Regions Included Punjab: Most populous province, Sindh: Second largest province including Karachi, KPK (Khyber Pakhtunkhwa): Northwestern province, Balochistan: Largest province by area, ICT (Islamabad Capital Territory): Federal capital territory, AJK (Azad Jammu & Kashmir): Administered territory, GB (Gilgit-Baltistan): Northern territory.The dengue_pakistan dataset has also been published in the denguedataset package in Python. jupyter notebook related https://www.kaggle.com/code/yutakatarokusumah/jakarta-dengue-risk-prediction
This dataset contains yearly dengue cases from 2019 to 2022.
dengue_perudengue_peru
A dataframe object with 171281 rows and 8 variables:
name state
name of province
name of distric
dengue type
year of cases
week of year
age of case
gender
...
The dengue_peru dataset has also been published in the denguedataset package in Python. You can find the Zenodo page https://zenodo.org/records/21499199, GitHub repository https://github.com/fdzul/denguedatasets-py, GitHub Pages https://fdzul.github.io/denguedatasets-py/, and PyPI index at the following links https://pypi.org/project/denguedatasets/.
This dataset contains monthly and regional cases of dengue from 2016 to 2020
dengue_philippinesdengue_philippines
A dataframe object with 1020 rows and 5 variables:
Month of the year in text format
Ranges from 2016 to 2020 in numerical format
Region in the Philippines
Number of Monthly Cases per region
Number of Monthly Deaths per region due to dengue
...
Data set contains the recorded number of dengue cases per region of the Philippines from year 2016 to 2020. It can be used to find trends about the disease as well as spatiotemporal analysis that can result into data-driven solution about the trends of the desease for the past 5 years. The dengue_philippines dataset has also been published in the denguedataset package in Python. You can find the Zenodo page https://zenodo.org/records/21499199, GitHub repository https://github.com/fdzul/denguedatasets-py, GitHub Pages https://fdzul.github.io/denguedatasets-py/, and PyPI index at the following links https://pypi.org/project/denguedatasets/.
The dataset captures monthly variations in temperature, humidity, and precipitation, as well as confirmed dengue cases in Freetown, Sierra Leone.
dengue_sierra_leonedengue_sierra_leone
A dataframe object with 120 rows and 5 variables:
date
Temperature in celsius
Humidity
Precipitation
dengue cases
...
The Sierra Leone Freetown DengueAI Dataset from 2015 to 2024 offers an integrated collection of epidemiological and climatic variables, specifically designed for AI-based dengue outbreak prediction and time-series modeling. The dataset captures monthly variations in temperature, humidity, and precipitation, as well as confirmed dengue cases in Freetown, Sierra Leone. Data sources include OpenDengue and NOAA GSOD.The dengue_sierra_leone dataset has also been published in the denguedataset package in Python. You can find the [Zenodo page](https://zenodo.org/records/21499199), [GitHub repository](https://github.com/fdzul/denguedatasets-py), [GitHub Pages](https://fdzul.github.io/denguedatasets-py/), and PyPI index at the following links https://pypi.org/project/denguedatasets/.
Michael Marko Sesay. 2025. Sierra Leone Freetown DengueAI Dataset (2015–2024) [Data set]. Kaggle. https://doi.org/10.34740/KAGGLE/DSV/13257213
District & Provincial Trends: Monthly Dengue Insights from 2019
dengue_sri_lanka_2019dengue_sri_lanka_2019
A dataframe object with 26 rows and 14 variables:
The province in Sri Lanka where data was recorded.
Specific district within the province
dengue cases of january
dengue cases of febrary
dengue cases of march
dengue cases of april
dengue cases of may
dengue cases of june
dengue cases of july
dengue cases of august
dengue cases of september
dengue cases of octuber
dengue cases of november
dengue cases of december
...
A comprehensive record of dengue cases across all districts and provinces in Sri Lanka, detailing monthly occurrences from January to December for the years 2019-2021. Data serves as a critical resource for understanding the epidemiological trends of dengue, facilitating public health responses and preventive strategies. Though compact, this dataset offers rich opportunities for data science applications including trend analysis, hotspot detection, and predictive modeling for future outbreaks. Data was meticulously compiled and made available by the National Dengue Control Unit (NDCU) of Sri Lanka. For more details, visit the NDCU Dengue Information Portal. The dengue_sri_lanka_2019 dataset has also been published in the denguedataset package in Python. You can find the [Zenodo page](https://zenodo.org/records/21499199), [GitHub repository](https://github.com/fdzul/denguedatasets-py), [GitHub Pages](https://fdzul.github.io/denguedatasets-py/), and PyPI index at the following links https://pypi.org/project/denguedatasets/.
District & Provincial Trends: Monthly Dengue Insights from 2020
dengue_sri_lanka_2020dengue_sri_lanka_2020
A dataframe object with 26 rows and 14 variables:
The province in Sri Lanka where data was recorded.
Specific district within the province
dengue cases of january
dengue cases of febrary
dengue cases of march
dengue cases of april
dengue cases of may
dengue cases of june
dengue cases of july
dengue cases of august
dengue cases of september
dengue cases of octuber
dengue cases of november
dengue cases of december
...
A comprehensive record of dengue cases across all districts and provinces in Sri Lanka, detailing monthly occurrences from January to December for the years 2019-2021. Data serves as a critical resource for understanding the epidemiological trends of dengue, facilitating public health responses and preventive strategies. Though compact, this dataset offers rich opportunities for data science applications including trend analysis, hotspot detection, and predictive modeling for future outbreaks. Data was meticulously compiled and made available by the National Dengue Control Unit (NDCU) of Sri Lanka. For more details, visit the NDCU Dengue Information Portal. The dengue_sri_lanka_2020 dataset has also been published in the denguedataset package in Python. You can find the [Zenodo page](https://zenodo.org/records/21499199), [GitHub repository](https://github.com/fdzul/denguedatasets-py), [GitHub Pages](https://fdzul.github.io/denguedatasets-py/), and PyPI index at the following links https://pypi.org/project/denguedatasets/.
District & Provincial Trends: Monthly Dengue Insights from 2021
dengue_sri_lanka_2021dengue_sri_lanka_2021
A dataframe object with 26 rows and 14 variables:
The province in Sri Lanka where data was recorded.
Specific district within the province
dengue cases of january
dengue cases of febrary
dengue cases of march
dengue cases of april
dengue cases of may
dengue cases of june
dengue cases of july
dengue cases of august
dengue cases of september
dengue cases of octuber
dengue cases of november
dengue cases of december
...
A comprehensive record of dengue cases across all districts and provinces in Sri Lanka, detailing monthly occurrences from January to December for the years 2019-2021. Data serves as a critical resource for understanding the epidemiological trends of dengue, facilitating public health responses and preventive strategies. Though compact, this dataset offers rich opportunities for data science applications including trend analysis, hotspot detection, and predictive modeling for future outbreaks. Data was meticulously compiled and made available by the National Dengue Control Unit (NDCU) of Sri Lanka. For more details, visit the NDCU Dengue Information Portal. The dengue_sri_lanka_2021 dataset has also been published in the denguedataset package in Python. You can find the [Zenodo page](https://zenodo.org/records/21499199), [GitHub repository](https://github.com/fdzul/denguedatasets-py), [GitHub Pages](https://fdzul.github.io/denguedatasets-py/), and PyPI index at the following links https://pypi.org/project/denguedatasets/.
Daily and Regional Confirmed Cases of Dengue from 1998 to 2024
dengue_taiwandengue_taiwan
A dataframe object with 26 rows and 14 variables:
Date when symptoms first appeared
Date when the case was confirmed
Date when the case was reported
Gender of the affected individual
Age category of the affected individual
County where the individual resides
Township where the individual resides
Village where the individual resides
Code for the village of residence
Statistical unit for enumeration
Longitude of the enumeration unit
Latitude of the enumeration unit
Highest administrative unit for dissemination
Secondary administrative unit for dissemination
County where the individual was infected
Township where the individual was infected
where the individual was infected
Code for the infected village
Indicates if the case was imported from another country
Country where the infection was acquired.
Number of confirmed dengue cases
Serotype of the dengue virus
Code for the township of residence from the Ministry of Interior
County code of Ministry of Interior
Township code (Ministry of Interior
Code for the infected county of Ministry of Interior
Code for the infected township of Ministry of Interior
Infected county code of Ministry of Interior
Infected township code of Ministry of Interio)
...
The dataset contains detailed information on dengue fever cases since 1998, encompassing various aspects such as dates, geographical locations, and serotype details. This data can be leveraged to analyze temporal trends, spatial distribution, and the serotype of dengue cases. It is valuable for understanding the disease's progression, its impact across different regions, and the effectiveness of intervention measures over time. The dengue_taiwan dataset has also been published in the denguedataset package in Python. You can find the [Zenodo page](https://zenodo.org/records/21499199), [GitHub repository](https://github.com/fdzul/denguedatasets-py), [GitHub Pages](https://fdzul.github.io/denguedatasets-py/), and PyPI index at the following links https://pypi.org/project/denguedatasets/.