Package 'amazonasdatahub' reference manual

Title:	Integrating Data, Research, and Education
Description:	Various datasets from the state of Amazonas (AM), Brazil, to apply Deep Learning and statistical methods.
Authors:	Nelson Carvalho [aut, cre], Leonardo Nascimento [aut]
Maintainer:	Nelson Carvalho <[email protected]>
License:	MIT + file LICENSE
Version:	1.2.1
Built:	2026-11-10 18:11:10 UTC
Source:	https://github.com/cran/amazonasdatahub

agriculture_amazonas - Plant production data from the Institute of Sustainable Agricultural and Forestry Development of Amazonas - IDAM (2023).

Description

This database, which is the consolidation of data from IDAM's activity reports, provides crop production data for crops that this institute considers a priority.

Usage

agriculture_amazonas
agriculture_amazonas

Format

‘agriculture_amazonas’ A data frame with 1072 rows and 13 columns:

municipality: Municipality
local_unit: Local Unit of the Institute
n_beneficiary: Number of assisted beneficiaries
planted: Planted area in hectares (ha)
harvested: Harvested area in hectares (ha)
production: Production (in the unit of measurement - measure)
estimated_n_beneficiary: Estimate of the number of beneficiaries
estimated_planted: Estimate of the planted area (ha)
estimated_harvested: Estimate of the harvested area (ha)
estimated_production: Estimate of production (in the unit of measurement - measure)
measure: Unit of Measurement of production
cultivation: Cultivation
year: Year of cultivation

Source

INSTITUTO DE DESENVOLVIMENTO AGROPECUÁRIO E FLORESTAL SUSTENTÁVEL DO ESTADO DO AMAZONAS (IDAM). Relatório de Atividades (RAT 23-2). Manaus: IDAM, 2023. Disponível em: https://www.idam.am.gov.br/biblioteca/relatorio-de-atividades-rat-23-2/.

Examples


# Cassava production plot (Gráfico de Produção de Mandioca)
mandioca_prod <- agriculture_amazonas[agriculture_amazonas$cultivation == "Mandioca", ]
plot(
  mandioca_prod$planted,
  mandioca_prod$harvested,
  xlab = "Planted area (hectare)",
  ylab = "Harvested area (hectare)",
  main = "Cassava production in Amazonas",
  sub = "Planted area x Harvested Area"
)


# Cassava production plot (Gráfico de Produção de Mandioca)
mandioca_prod <- agriculture_amazonas[agriculture_amazonas$cultivation == "Mandioca", ]
plot(
  mandioca_prod$planted,
  mandioca_prod$harvested,
  xlab = "Planted area (hectare)",
  ylab = "Harvested area (hectare)",
  main = "Cassava production in Amazonas",
  sub = "Planted area x Harvested Area"
)

aids_amazonas - A dataset of AIDS occurrences from 2011 to 2023 in Amazonas

Description

This dataset contains data of the AIDS occurrences in each municipality from Amazonas.

Usage

aids_amazonas
aids_amazonas

Format

‘aids_amazonas’ A data frame with 1612 rows and 5 columns:

code_muni: Municipality code
name_muni: Municipality name
cases: Case count
gender: Gender of the infected individual - M for Male and F for female
year: Year of observation

Source

BRASIL. Ministério da Saúde. Departamento de HIV, Aids, Tuberculose, Hepatites Virais e Infecções Sexualmente Transmissíveis. Indicadores HIV, Aids. Available in: https://indicadores.aids.gov.br/.

Examples


# Aids - case count in Manaus
# Loading dplyr and ggplot to structure the data
require(dplyr)
require(ggplot2)

# Filtering by municipality and plotting case count by gender
aids_amazonas %>%
  filter(name_muni == "Manaus") %>%
  group_by(gender) %>%
  ggplot(aes(x = year, y = cases, group = gender, color = gender)) +
  geom_line() +
  scale_color_manual(values = c("blue", "red")) +
  theme_minimal() +
  labs(
    title = "AIDS ocurrences in Manaus (2011-2023)",
    x = "Year",
    y = "Case count",
    color = "Gender"
  )


# Aids - case count in Manaus
# Loading dplyr and ggplot to structure the data
require(dplyr)
require(ggplot2)

# Filtering by municipality and plotting case count by gender
aids_amazonas %>%
  filter(name_muni == "Manaus") %>%
  group_by(gender) %>%
  ggplot(aes(x = year, y = cases, group = gender, color = gender)) +
  geom_line() +
  scale_color_manual(values = c("blue", "red")) +
  theme_minimal() +
  labs(
    title = "AIDS ocurrences in Manaus (2011-2023)",
    x = "Year",
    y = "Case count",
    color = "Gender"
  )

gdp_amazonas - Gross Domestic Product - GDP of Amazonas

Description

This database contains information about the Gross Domestic Product (GDP) of the state of Amazonas over the years (from 2010 to 2021). It includes values in R$ 1,000,000.

Usage

gdp_amazonas
gdp_amazonas

Format

‘gdp_amazonas’ A data frame with 48 rows and 21 columns:

year: Indicates the year in which the GDP info was collected
quarter: Specifies the quarter of the year
agriculture: Refers to the economic output from agricultural activities, including cultivation, harvesting, and logistical support after harvest
livestock: Represents the economic contribution from livestock farming, covering meat, dairy production, and related support services
forest_fishing_prod: Outputs from forestry (timber and non-timber products), fishing activities and aquaculture (fish farming)
extractive_ind: Extractive industries of natural resources as minearls and oil
manufacturing_ind: Refers to the transformation of raw materials into finished goods industries
basic_infrastructure: Encompasses services related to electricity and gas generation, water supply, sewage treatment, and waste management.
construction: Represents economic activities related to building construction.
vehicle_retail_repair: Includes all commercial activities related to selling goods and services as well as vehicle repair services.
transport_storage_post: Covers services related to transporting people and goods, storage facilities, and postal services.
accomodation_food: Refers to economic activities in tourism-related sectors such as hotels and restaurants.
information_communication: Encompasses sectors dealing with information technology and telecommunications.
financial_activities: Includes banks, financial institutions, insurance companies, and various financial services.
real_state_activities: Refers to transactions involving buying, selling, or renting properties.
professional_activities: Covers a wide range of specialized professional services including consulting and administrative support.
public_admin_defense_health_edu: Represents public sector spending on government administration, national defense, public education, health care services, and social security programs.
private_edu_health: Refers to educational institutions and health care providers operating in the private sector.
art_culture_sport: Encompasses activities related to entertainment, cultural events, sports facilities, and other service-oriented sectors.
domestic_services: Includes personal services provided within households such as cleaning or caregiving.
taxes: Represents taxes levied on goods and services included in GDP calculations.

Source

Scientific Journal of Applied Social and Clinical Science - TIME SERIES ANALYSIS FOR THE QUARTERLY GROSS DOMESTIC PRODUCT OF AMAZONAS

Examples


# Time series - Gross Domestic Product of Amazonas
# Loading dplyr and ggplot2
require(dplyr)
require(ggplot2)

# Selecting only year and taxes and ploting
gdp_amazonas %>%
  select(year, taxes) %>%
  ggplot(., aes(x = year, y = taxes)) +
  geom_line(linewidth = 1L, colour = "#cb181d") +
  geom_hline(
    yintercept = mean(gdp_amazonas$taxes),
    linetype = "dashed",
    size = 1
  ) +
  theme_light() +
  theme(
    plot.title = element_text(face = "bold", size = 16)
  ) +
  labs(
    x = "Year",
    y = "Taxes",
    title = "Quarterly GDP of Amazonas",
    subtitle = "2010 - 2021"
  )


# Time series - Gross Domestic Product of Amazonas
# Loading dplyr and ggplot2
require(dplyr)
require(ggplot2)

# Selecting only year and taxes and ploting
gdp_amazonas %>%
  select(year, taxes) %>%
  ggplot(., aes(x = year, y = taxes)) +
  geom_line(linewidth = 1L, colour = "#cb181d") +
  geom_hline(
    yintercept = mean(gdp_amazonas$taxes),
    linetype = "dashed",
    size = 1
  ) +
  theme_light() +
  theme(
    plot.title = element_text(face = "bold", size = 16)
  ) +
  labs(
    x = "Year",
    y = "Taxes",
    title = "Quarterly GDP of Amazonas",
    subtitle = "2010 - 2021"
  )

humidity_manaus - Time series with Extreme Values of Limited Range

Description

A time series dataset consisting of the minimum relative humidity observed in the city of Manaus from January 2009 to December 2020. This dataset is a sample of size n = 144 monthly blocks.

Usage

humidity_manaus
humidity_manaus

Format

‘humidity_manaus’ A tibble with 144 rows and 5 columns

year: The year in which this data was observed
rh: Relative Humidity
dbt: Dry Bulb Temperature
wbt: Wet Bulb Temperature
month: The month in which this data was observed

Source

NASCIMENTO, Leonardo Brandão Freitas; LIMA, Max Sousa; DUCZMAL, Luiz H. P-min-stable regression models for time series with extreme values of limited range. Environmetrics, Issue 2, v. 36, 2025.

Examples

# Relative humidity time series of Amazonas
# Loading dplyr and ggplot to structure the data
require(dplyr)
require(ggplot2)

# Creating date column and plotting the time series
humidity_manaus %>%
  mutate(date = as.Date(paste0(year, "-", month, "-","01"))) %>%
  ggplot(aes(x = date, y = rh)) +
  geom_line() +
  theme_minimal() +
  labs(
    title = "Relative Humidity of Amazonas (2010 - 2020)",
    x = "Date",
    y = "Relative Humidity"
  )

# Relative humidity time series of Amazonas
# Loading dplyr and ggplot to structure the data
require(dplyr)
require(ggplot2)

# Creating date column and plotting the time series
humidity_manaus %>%
  mutate(date = as.Date(paste0(year, "-", month, "-","01"))) %>%
  ggplot(aes(x = date, y = rh)) +
  geom_line() +
  theme_minimal() +
  labs(
    title = "Relative Humidity of Amazonas (2010 - 2020)",
    x = "Date",
    y = "Relative Humidity"
  )

malaria_amazonas - An integrated dataset of malaria notifications in the state of Amazonas

Description

This dataset contains medical records of patients who underwent malaria screening tests in the Legal Amazon. The data in this dataset were filtered to include only the cases reported in the state of Amazonas and for patients who reside specifically in the state of Amazonas between 2014 and 2019.

Usage

malaria_amazonas
malaria_amazonas

Format

‘malaria_amazonas’ A data frame with 551633 rows and 35 columns:

notification_hr: Health region of notification
notification_county: County of notification
infection_state: Probable state where the patient was infected
infection_hr: Probable health region where the patient was infected
infection_county: Probable county where the patient was infected
home_hr: Health region of residence of the patient
home_county: County of residence of the patient
exam_interval: Time interval between notification and examination
treatment_interval: Time interval between examination and beginning of treatment
notification_interval: Time interval between symptom and notification
notification_month: Month in which the notification was recorded
notification_year: Year in which the notification was recorded
symptom_month: Month in which the patient felt the first symptoms of malaria
symptom_year: Year in which the patient felt the first symptoms of malaria
exam_month: Month in which the examination was performed
exam_year: Year in which the examination was performed
treatment_month: Month in which the treatment started
treatment_year: Year in which the treatment started
migration: Health region of residence different than that of notification
exam_result: Result of examination
detection_type: Type of detection
exam_type: Type of examination
symptom: Indicates if the patient felt a symptom
hemiparasite: The result of the examination for other hemiparasites
previous_treatment: Previous treatment for P. vivax or P.falciparum
occupation: Main activity in the last 15 days
education_level: Level of education of the patient
age: Interval of the age of the patient
race: Race/color of the patient
gender: Gender of the patient
pregnancy: Indicates pregnancy and the gestational age
crosses: Indicates the amount of parasitemia in crosses
cvl_case: Indicates the existence of cases of canine visceral leishmaniasis
scheme: Indicates the treatment scheme employed
qty_parasites: Indicates the number of parasites per mm^3

Source

Lais Baroni, M. P. (2020). An Integrated Dataset of Malaria Notifications in the Legal Amazon (Dataset). Synapse. https://doi.org/10.7303/SYN21552203

Examples


# Bar plot of malaria tests results (2019)
library(dplyr)
library(ggplot2)

malaria_amazonas %>%
  filter(exam_year == 2019) %>%
  count(exam_result) %>%
  ggplot(aes(x = reorder(exam_result, -n), y = n)) +
  geom_bar(stat = "identity") +
  geom_text(
    aes(label = n),
    vjust = -0.5
  ) +
  theme_minimal() +
  labs(
    title = "Results of malaria tests conducted in 2019",
    subtitle = "Documented cases in Amazonas and of patients residing in the state",
    x = "Result",
    y = "Count"
  )




# Bar plot of malaria tests results (2019)
library(dplyr)
library(ggplot2)

malaria_amazonas %>%
  filter(exam_year == 2019) %>%
  count(exam_result) %>%
  ggplot(aes(x = reorder(exam_result, -n), y = n)) +
  geom_bar(stat = "identity") +
  geom_text(
    aes(label = n),
    vjust = -0.5
  ) +
  theme_minimal() +
  labs(
    title = "Results of malaria tests conducted in 2019",
    subtitle = "Documented cases in Amazonas and of patients residing in the state",
    x = "Result",
    y = "Count"
  )

prf_amazonas - Traffic accident data from Amazonas recorded by Federal Highway Police (2012-2025)

Description

Traffic accident data from Amazonas (2012-2025)

Usage

prf_amazonas
prf_amazonas

Format

‘prf_amazonas’ A data frame with 116 rows and 30 columns:

id: Record ID
date: Date of the record - yyyy-mm-dd
days_of_week: Day of the week
time: Hour of the record
federative_unit: Federative unit (UF)
br: Federal Highway
km: Kilometer of BR
municipality: Municipality
accident_cause: Accident cause
accident_type: Accident type
accident_classification: Accident classification: victims, no victims, unharmed victims, fatal victims
road_direction: Road direction
weather: Weather conditions at the time of the accident
track_type: Track type: Simples, Múltipla ou Dupla
track_layout: Track layout
land_use: Land use
people: People involved in the accident
deceased: Death toll
minor_injuries: Number of victims with minor injuries
serious_injuries: Number of victims with serious injuries
unharmed: Number of unharmed victims
ignored: Ignored
harmed: Number of harmed victims
latitude: Latitude
longitude: Longitude
regional: Superintendency of the Federal Highway Police of Brazil
police_station: Police station where the report was filed
operating_unit: Operating unit and police station

Source

Brasil. Polícia Rodoviária Federal (PRF). Dados Abertos da PRF: Acidentes de Trânsito. https://www.gov.br/prf/pt-br/acesso-a-informacao/dados-abertos/dados-abertos-da-prf.

Examples


# Accident count by weather condition
# Loading dplyr and ggplot
require(dplyr)
require(ggplot2)
require(forcats)

# Counting accidents by weather condition and ploting
prf_amazonas %>%
  count(weather) %>%
  mutate(
    weather = fct_reorder(weather, -n)
  ) %>%
  ggplot(aes(x = weather, y = n)) +
  geom_bar(stat = "identity", fill = "steelblue") +
  geom_text(aes(label = n), vjust = -0.5) +
  theme_minimal() +
  labs(
    title = "Accident count by weather condition",
    x = "Weather",
    y = "Count"
  )


# Accident count by weather condition
# Loading dplyr and ggplot
require(dplyr)
require(ggplot2)
require(forcats)

# Counting accidents by weather condition and ploting
prf_amazonas %>%
  count(weather) %>%
  mutate(
    weather = fct_reorder(weather, -n)
  ) %>%
  ggplot(aes(x = weather, y = n)) +
  geom_bar(stat = "identity", fill = "steelblue") +
  geom_text(aes(label = n), vjust = -0.5) +
  theme_minimal() +
  labs(
    title = "Accident count by weather condition",
    x = "Weather",
    y = "Count"
  )

rionegro_amazonas - A dataset of the Rio Negro River (Amazonas) level from 2003 to 2023

Description

This dataset contains data of the Rio Negro River level in the state of Amazonas (Brazil), compiling information on years, semesters and days, along with the river's level in meters and whether it filled or dropped (in centimeters).

Usage

rionegro_amazonas
rionegro_amazonas

Format

‘rionegro_amazonas’ A data frame with 8003 rows and 7 columns:

level_m: River level in meters
increase_decrease_cm: Wheter the river level filled or dropped (in centimeters)
day: Measurement day
month: Measurement month
year: Measurement year
semester: Measurement semester

Source

Porto de Manaus. Nível do Rio Negro. https://portodemanaus.com.br/nivel-do-rio-negro/.

Examples

# Rio Negro - Boxplot (water level by year)

# Loading ggplot
require(ggplot2)
require(dplyr)

rionegro_amazonas %>%
  ggplot(aes(x = year, y = level_m, group = year)) +
  stat_boxplot(geom = "errorbar") +
  geom_boxplot() +
  theme_minimal() +
  labs(
    x = "Year",
    y = "Water level (m)"
  )

# Rio Negro - Boxplot (water level by year)

# Loading ggplot
require(ggplot2)
require(dplyr)

rionegro_amazonas %>%
  ggplot(aes(x = year, y = level_m, group = year)) +
  stat_boxplot(geom = "errorbar") +
  geom_boxplot() +
  theme_minimal() +
  labs(
    x = "Year",
    y = "Water level (m)"
  )

srl_muni - School Read Levels - Physical literacy and reading performance of amazonian schoolchildren

Description

This is a dataset from an association, cross-sectional, quantitative study carried out with Amazonian schoolchildren (n=100; aged between 10 and 13 years) from 3 public schools in the municipality of Borba (Amazonas).

Usage

srl_muni
srl_muni

Format

‘srl_muni’ A data frame with 100 rows and 17 columns:

school: School of observation
sex: Sex - 1 for Masculine and 2 for Feminine
age: Age in years
weight_kg: Weight in kilograms (kg)
height_m: Height in meters (m)
bmi: Body Mass Index (BMI)
bmi_status: Body Mass Index Status - A categorical description of the BMI
phv: Peak Height Velocity (PHV) is a continuous variable, measured by age (in years) relative to the peak height in the period where maximum rate of growth occurs and this is an indication of maturity
phv_state: Categorical description for Peak Height Velocity (PHV)
eses: Exercise Self-Efficacy Scale measures how confident the students are with regard to carrying out regular physical activities and exercise, measured by a psychometric scale
pmc: Perceived Motor Competence (PMC) assesses the child's self-perception regarding their ability to perform motor movements. Measured by a psychometric scale
kupa: Knowledge and Understanding of Physical Activity (KUPA) - Evaluates knowledge regarding the benefits, safety, and engagement in physical activity. Measured by scores obtained in objective questions
sb: Sedentary Behavior - Evalutes the exposition time to sedentary behaviors. Measured by psychometric scale
pa: Pyshical Activity (PA) - Level of physical activity ian children, based on the frequency and duration of routine daily activities. Measured by score on the physical activity frequency questions
mc: Motor Competence - Supine To Stand (in seconds) - Measures the time (in seconds) it takes for the child to stand up from the floor, from a supine position to a standing position
tde: Total Score on the TDE test - Measures reading level based on time and accuracy in word reading
tde_categorical: Categorical description of the TDE Score

Source

ALMEIDA, Thiago da Cruz de. Physical Literacy e desempenho em leitura de escolares amazônicos: um estudo de associação. 2024. 104 f. Dissertação (Mestrado em Educação) - Universidade Federal do Amazonas, Manaus, 2024. Disponível em: https://tede.ufam.edu.br/handle/tede/10627.

Package 'amazonasdatahub'

Help Index

agriculture_amazonas - Plant production data from the Institute of Sustainable Agricultural and Forestry Development of Amazonas - IDAM (2023).

Description

Usage

Format

‘agriculture_amazonas’ A data frame with 1072 rows and 13 columns:

Source

Examples

aids_amazonas - A dataset of AIDS occurrences from 2011 to 2023 in Amazonas

Description

Usage

Format

‘aids_amazonas’ A data frame with 1612 rows and 5 columns:

Source

Examples

gdp_amazonas - Gross Domestic Product - GDP of Amazonas

Description

Usage

Format

‘gdp_amazonas’ A data frame with 48 rows and 21 columns:

Source

Examples

humidity_manaus - Time series with Extreme Values of Limited Range

Description

Usage

Format

‘humidity_manaus’ A tibble with 144 rows and 5 columns

Source

Examples

malaria_amazonas - An integrated dataset of malaria notifications in the state of Amazonas

Description

Usage

Format

‘malaria_amazonas’ A data frame with 551633 rows and 35 columns:

Source

Examples

prf_amazonas - Traffic accident data from Amazonas recorded by Federal Highway Police (2012-2025)

Description

Usage

Format

‘prf_amazonas’ A data frame with 116 rows and 30 columns:

Source

Examples

rionegro_amazonas - A dataset of the Rio Negro River (Amazonas) level from 2003 to 2023

Description

Usage

Format

‘rionegro_amazonas’ A data frame with 8003 rows and 7 columns:

Source

Examples

srl_muni - School Read Levels - Physical literacy and reading performance of amazonian schoolchildren

Description

Usage

Format

‘srl_muni’ A data frame with 100 rows and 17 columns:

Source