amazonasdatahub 0.2.4__py3-none-any.whl

amazonasdatahub/__init__.py

@@ -0,0 +1,3 @@
+# read version from installed package
+from importlib.metadata import version
+__version__ = version("amazonasdatahub")

amazonasdatahub/datasets.py

@@ -0,0 +1,36 @@
+import pandas as pd
+import requests
+from pathlib import Path
+
+CACHE_DIR = Path.home() / ".cache" / "amazonasdatahub"
+CACHE_DIR.mkdir(parents = True, exist_ok=True)
+
+def get_dataset(dataset_name, force=False):
+    """
+    Gather an specific dataset.
+    :param dataset_name: Dataset name (example: agriculture_amazonas)
+    :param force: If True, ignores the cache and downloads the dataset again
+    """
+
+    file_name = f"{dataset_name}.parquet"
+    local_path = CACHE_DIR / file_name 
+    url = f"https://github.com/onelsoncarvalho/amazonasdatahubpy/raw/refs/heads/main/raw_data/{file_name}"
+
+    if force or not local_path.exists():
+        print(f"Gathering updated data from {url}...")
+        try:
+            response = requests.get(url)
+            response.raise_for_status()
+
+            with open(local_path, "wb") as f:
+                f.write(response.content)
+            print(f"Saved in: {local_path}")
+
+        except Exception as e:
+            if not local_path.exists():
+                raise Exception(f"Error while downloading and there is no cache available: {e}")
+            print(f"Warning: Download error, using old cache version. Error: {e}")
+
+    return pd.read_parquet(local_path)
+
+

amazonasdatahub/docs.py

@@ -0,0 +1,33 @@
+import frontmatter
+from importlib import resources
+
+
+def get_doc(dataset_name):
+    """
+    Shows the documentation of a dataset
+    """
+
+    try:
+        md_path = resources.files("amazonasdatahub.documentations").joinpath(f"{dataset_name}.md")
+        if not md_path.exists():
+            print(f"Docs for {dataset_name} not found")
+            return
+
+        md_content = md_path.read_text(encoding = "utf-8")
+
+        loaded_md = frontmatter.loads(md_content)
+
+        title = loaded_md.get('title', dataset_name.upper())
+        body = loaded_md.content
+
+        print(f"\n{'='*60}")
+        print(f"Documentation from: {title}")
+        print(f"{'='*60}")
+
+        try :
+            from IPython.display import display, Markdown
+            display(Markdown(body))
+        except ImportError:
+            print(body)
+    except Exception as e:
+        print(f"Error while processing docs: {e}")

amazonasdatahub/documentations/agriculture_amazonas.md

@@ -0,0 +1,109 @@
+---
+title: "agriculture_amazonas"
+---
+
+# 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
+
+```python
+agriculture_amazonas = get_dataset("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
+
+https://www.idam.am.gov.br/biblioteca/relatorio-de-atividades-rat-23-2/
+
+
+### Example
+
+```python
+import matplotlib.pyplot as plt
+from amazonasdatahub.datasets import get_dataset
+
+# Loading data
+agriculture_amazonas = get_dataset("agriculture_amazonas")
+
+# Filtering data
+mandioca_prod = agriculture_amazonas[
+  agriculture_amazonas["cultivation"] == "Mandioca"
+]
+
+# Scatterplot
+plt.figure(figsize=(8,6))
+plt.scatter(
+  mandioca_prod["planted"],
+  mandioca_prod["harvested"],
+  alpha=0.7,
+  edgecolors="none"
+)
+plt.xlabel("Planted area (hectare)")
+plt.ylabel("Harvested area (hectare)")
+plt.title("Cassava production in Amazonas")
+plt.grid(True, linestyle="--", alpha=0.5)
+plt.tight_layout()
+plt.show()
+```

amazonasdatahub/documentations/aids_amazonas.md

@@ -0,0 +1,75 @@
+---
+title: "aids_amazonas"
+---
+
+
+# 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
+
+```python
+aids_amazonas = get_dataset("aids_amazonas")
+```
+
+### Format
+
+‘aids_amazonas’ A data frame with 48 rows and 21 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
+
+https://indicadores.aids.gov.br
+
+
+### Example
+
+```python
+import matplotlib.pyplot as plt
+from amazonasdatahub.datasets import get_dataset
+
+# Load dataset
+aids_amazonas = get_dataset("aids_amazonas")
+
+# Filter by municipality and pivot data by gender
+manaus_aids = aids_amazonas[aids_amazonas["name_muni"] == "Manaus"]
+pivot_aids = manaus_aids.pivot(
+    index="year", columns="gender", values="cases"
+)
+
+# Plot line chart
+pivot_aids.plot(marker="o", figsize=(9, 5))
+
+# Titles, labels and custom configurations
+plt.title("AIDS occurrences in Manaus (2011-2023)")
+plt.xlabel("Year")
+plt.ylabel("Case count")
+plt.legend(title="Gender")
+plt.grid(True, linestyle="--", alpha=0.5)
+plt.tight_layout()
+plt.show()
+```

amazonasdatahub/documentations/gdp_amazonas.md

@@ -0,0 +1,144 @@
+---
+title: "gdp_amazonas"
+---
+
+# 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
+
+```python
+gdp_amazonas = get_dataset("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.constructionRepresents 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_communicationEncompasses 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
+
+### Example
+
+```python
+import matplotlib.pyplot as plt
+from amazonasdatahub.datasets import get_dataset
+
+# Load dataset
+gdp_amazonas = get_dataset("gdp_amazonas")
+
+# Select only year and taxes
+df_gdp = gdp_amazonas[["year", "taxes"]]
+
+# Plot time series
+plt.figure(figsize=(9, 5))
+plt.plot(
+    df_gdp["year"],
+    df_gdp["taxes"],
+    color="#cb181d",
+    linewidth=2,
+)
+
+# Add horizontal dashed line for the mean of taxes
+mean_taxes = df_gdp["taxes"].mean()
+plt.axhline(
+    y=mean_taxes,
+    color="gray",
+    linestyle="--",
+    linewidth=1.5,
+)
+
+# Information - Title, subtitle and style
+plt.title(
+    "Quarterly GDP of Amazonas (2010-2021)", fontweight="bold", fontsize=14, loc="left"
+)
+plt.xlabel("Year")
+plt.ylabel("Taxes")
+
+plt.grid(True, linestyle=":", alpha=0.6)
+plt.tight_layout()
+plt.show()
+```

amazonasdatahub/documentations/humidity_manaus.md

@@ -0,0 +1,84 @@
+---
+title: "humidity_manaus"
+---
+
+# 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
+
+```python
+humidity_manaus = get_dataset("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.
+
+### Example
+
+```python
+import matplotlib.pyplot as plt
+import pandas as pd
+from amazonasdatahub.datasets import get_dataset
+
+# Load dataset
+humidity_manaus = get_dataset("humidity_manaus")
+
+# Create date column from year and month
+humidity_manaus["date"] = pd.to_datetime(
+    humidity_manaus["year"].astype(str)
+    + "-"
+    + humidity_manaus["month"].astype(str)
+    + "-01"
+)
+
+# Sort by date for proper line plotting
+humidity_manaus = humidity_manaus.sort_values("date")
+
+# Plot time series
+fig, ax = plt.subplots(figsize=(10, 5))
+ax.plot(
+    humidity_manaus["date"], humidity_manaus["rh"], color="tab:blue", lw=1.5
+)
+
+# Titles and labels
+ax.set_title("Relative Humidity of Amazonas (2010 - 2020)")
+ax.set_xlabel("Date")
+ax.set_ylabel("Relative Humidity")
+
+plt.grid(axis="y", linestyle="--", alpha=0.5)
+plt.tight_layout()
+plt.show()
+```

amazonasdatahub/documentations/malaria_amazonas.md

@@ -0,0 +1,225 @@
+---
+title: "malaria_amazonas"
+---
+
+# 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
+
+```python
+malaria_amazonas = get_dataset("malaria_amazonas")
+```
+
+### Format
+
+‘malaria_amazonas’ A data frame with 551633 rows and 35 columns:
+
+#### notification_state
+
+State of notification
+
+#### notification_rh
+
+Health region of notification
+
+#### notification_county
+
+County of notification
+
+#### infection_country
+
+Probable county where the patient was infected
+
+#### 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_country
+
+Country of residence of the patient
+
+#### home_state
+
+State of residence of the patient
+
+#### 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
+
+#### autochthonous_case
+
+Health region of infection identical to that of residence
+
+#### 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
+
+#### month
+
+The month in which this data was observed
+
+### Source
+
+https://www.synapse.org/Synapse:syn21552203/files
+
+### Example
+
+```python
+import matplotlib.pyplot as plt
+from amazonasdatahub.datasets import get_dataset
+
+# Load dataset
+malaria_amazonas = get_dataset("malaria_amazonas")
+
+# Filter by year 2019 and count exam results
+counts = (
+    malaria_amazonas[malaria_amazonas["exam_year"] == 2019]["exam_result"]
+    .value_counts()
+)
+
+# Plot bar chart
+fig, ax = plt.subplots(figsize=(10, 6))
+bars = ax.bar(counts.index, counts.values, color="skyblue", edgecolor="gray")
+
+# Add text labels on top of bars
+ax.bar_label(bars, padding=3)
+
+# Titles and labels
+ax.set_title(
+    "Results of malaria tests conducted in 2019\nDocumented cases in Amazonas and of patients residing in the state",
+    fontsize=10,
+    loc="left"
+)
+ax.set_xlabel("Result")
+ax.set_ylabel("Count")
+
+plt.grid(axis="y", linestyle="--", alpha=0.5)
+plt.tight_layout()
+plt.show()
+```

amazonasdatahub/documentations/prf_amazonas.md

@@ -0,0 +1,167 @@
+---
+title: "prf_amazonas"
+---
+
+# prf_amazonas
+
+Traffic accident data from Amazonas recorded by Federal Highway Police (PRF) in 2025
+
+### Description
+
+Traffic accident data from Amazonas 2025
+
+### Usage
+
+```python
+prf_amazonas = get_dataset("prf_amazonas")
+```
+
+### Format
+
+‘prf_amazonas’ A data frame with 116 rows and 30 variables:
+
+#### 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.
+
+### Example
+
+```python
+import matplotlib.pyplot as plt
+from amazonasdatahub.datasets import get_dataset
+
+# Load dataset
+prf_amazonas = get_dataset("prf_amazonas")
+
+# Count occurrences by weather condition (automatically sorted descending)
+counts = prf_amazonas["weather"].value_counts()
+
+# Plot bar chart
+fig, ax = plt.subplots(figsize=(9, 6))
+bars = ax.bar(counts.index, counts.values, color="steelblue", edgecolor="gray")
+
+# Add text labels on top of bars
+ax.bar_label(bars, padding=3)
+
+# Titles and labels
+ax.set_title("Accident count by weather condition", loc="left")
+ax.set_xlabel("Weather")
+ax.set_ylabel("Count")
+
+plt.xticks(rotation=45, ha="right")
+plt.grid(axis="y", linestyle="--", alpha=0.5)
+plt.tight_layout()
+plt.show()
+```

amazonasdatahub/documentations/rionegro_amazonas.md

@@ -0,0 +1,79 @@
+---
+title: "rionegro_amazonas"
+---
+
+# 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
+
+```python
+rionegro_amazonas = get_dataset("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
+
+https://portodemanaus.com.br/nivel-do-rio-negro/
+
+### Example
+
+```python
+import matplotlib.pyplot as plt
+from amazonasdatahub.datasets import get_dataset
+
+# Load dataset
+rionegro_amazonas = get_dataset("rionegro_amazonas")
+
+# Prepare data for boxplot grouped by year
+years = sorted(rionegro_amazonas["year"].unique())
+data_by_year = [
+    rionegro_amazonas[rionegro_amazonas["year"] == yr]["level_m"].dropna()
+    for yr in years
+]
+
+# Plot boxplot
+fig, ax = plt.subplots(figsize=(10, 5))
+ax.boxplot(data_by_year, tick_labels=years)
+
+# Labels
+ax.set_xlabel("Year")
+ax.set_ylabel("Water level (m)")
+
+plt.xticks(rotation=45, ha="right")
+plt.grid(axis="y", linestyle="--", alpha=0.5)
+plt.tight_layout()
+plt.show()
+```

amazonasdatahub/documentations/srl_muni.md

@@ -0,0 +1,132 @@
+---
+title: "srl_muni"
+---
+
+# srl_muni
+
+Physical literacy and reading performance of children in schools in Amazonas.
+
+### 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
+
+```python
+srl_muni = get_dataset("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
+
+Physical Activity (PA) - Level of physical activity in 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
+
+https://tede.ufam.edu.br/handle/tede/10627
+
+### Example
+
+```python
+import matplotlib.pyplot as plt
+import numpy as np
+from matplotlib.colors import LinearSegmentedColormap
+from amazonasdatahub.datasets import get_dataset
+
+srl_muni = get_dataset("srl_muni")
+
+# Selecting numeric variables and computing the correlation matrix
+corr = srl_muni.select_dtypes("number").corr()
+labels = corr.columns
+
+# Plotting the correlation matrix
+cmap = LinearSegmentedColormap.from_list("corr", ["#2166AC", "white", "#d50e0b"])
+
+fig, ax = plt.subplots(figsize=(8, 8))
+im = ax.imshow(corr.values, cmap=cmap, vmin=-1, vmax=1)
+
+ax.set_xticks(np.arange(len(labels)), labels=labels, rotation=45, ha="right")
+ax.set_yticks(np.arange(len(labels)), labels=labels)
+
+# Cell borders and value labels
+ax.set_xticks(np.arange(-0.5, len(labels), 1), minor=True)
+ax.set_yticks(np.arange(-0.5, len(labels), 1), minor=True)
+ax.grid(which="minor", color="white", linewidth=1)
+ax.tick_params(which="minor", length=0)
+
+for i in range(len(labels)):
+    for j in range(len(labels)):
+        ax.text(j, i, f"{corr.values[i, j]:.2f}", ha="center", va="center", fontsize=8)
+
+fig.colorbar(im, ax=ax, shrink=0.7, label="Correlation")
+ax.set_title("Correlation matrix: Motor Competence\nand Reading Performance")
+plt.tight_layout()
+plt.show()
+```

amazonasdatahub-0.2.4.dist-info/METADATA

@@ -0,0 +1,209 @@
+Metadata-Version: 2.4
+Name: amazonasdatahub
+Version: 0.2.4
+Summary: The goal of amazonasdatahub is to gather various data sets from the state of Amazonas (AM), Brazil, to which Deep Learning can be applied.
+License: MIT
+License-File: LICENSE
+Author: Nelson Geraldo Aquino de Carvalho
+Requires-Python: >=3.12,<4.0
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
+Requires-Dist: pandas (>=3.0.2,<4.0.0)
+Requires-Dist: pyarrow (>=24.0.0,<25.0.0)
+Requires-Dist: python-frontmatter (>=1.1.0,<2.0.0)
+Requires-Dist: requests (>=2.33.1,<3.0.0)
+Description-Content-Type: text/markdown
+
+# amazonasdatahub
+
+![amazonasdatahub logo](assets/figures/logo_amazonasdatahub_small.png)
+<!-- badges: start -->
+
+<!-- badges: end -->
+
+The goal of `amazonasdatahub` is to aggregate databases from the State
+of Amazonas (AM), Brazil, for conducting studies and preparing
+educational materials, as well as to facilitate access to organized and
+processed data, thereby supporting research and teaching and enabling
+the application of statistical methods.
+
+Full documentation of both Python and R versions is available in the
+following languages/Documentação das versões em Python e R estão
+disponíveis nos seguintes idiomas:
+
+- [English
+  documentation](https://onelsoncarvalho.github.io/amazonasdatahubsite/en/)
+- [🇧🇷 Documentação em Português
+  (BR)](https://onelsoncarvalho.github.io/amazonasdatahubsite/)
+
+Python only documentation:
+
+- [English documentation for Python
+  version](https://onelsoncarvalho.github.io/amazonasdatahubpy/en/)
+- [🇧🇷 Documentação em Português (BR) para versão do
+  Python](https://onelsoncarvalho.github.io/amazonasdatahubpy/br/)
+
+## Overview
+
+This `amazonasdatahub` package provides databases from various types and
+sources, all of which concern the State of Amazonas.
+
+List of available datasets:
+
+| Dataset | Area | Source |
+|:---|:--:|:---|
+| agriculture_amazonas | Agriculture and Livestock | Institute of Agricultural and Sustainable Forestry Development of the State of Amazonas - 2024 |
+| aids_amazonas | Health | Department of HIV, AIDS, Tuberculosis, Viral Hepatitis, and Sexually Transmitted Infections, 2024 |
+| gdp_amazonas | Economy | Scientific Journal of Applied Social and Clinical Science - TIME SERIES ANALYSIS FOR THE QUARTERLY GROSS DOMESTIC PRODUCT OF AMAZONAS |
+| humidity_manaus | Climate | 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. |
+| malaria_amazonas | Health | Lais Baroni, M. P. (2020). An Integrated Dataset of Malaria Notifications in the Legal Amazon (Dataset). Synapse. <https://doi.org/10.7303/SYN21552203> |
+| prf_amazonas | Road Safety | Brasil. Polícia Rodoviária Federal (PRF). Dados Abertos da PRF: Acidentes de Trânsito |
+| rionegro_amazonas | Environment | Porto de Manaus. Nível do Rio Negro |
+| srl_muni | Education | 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. |
+
+## Installation
+
+To install `amazonasdatahub`, you need the following tools installed on your computer or development environment:
+
+- Python 3.14.3
+- `pip` (package manager)
+- Git
+
+You can install the development version of `amazonasdatahub` using `git clone` to clone the remote repository into your local environment and `pip` to install it:
+``` 
+# cloning
+git clone https://github.com/onelsoncarvalho/amazonasdatahubpy amazonasdatahub
+cd amazonasdatahub
+
+# installing
+pip install amazonasdatahub
+```
+
+## Usage and Examples
+
+### Loading `amazonasdatahub`
+
+Use `import` and `from` to require the functions from `datasets` module of `amazonasdatahub`:
+
+``` python
+from amazonasdatahub.datasets import get_dataset
+```
+
+The dataset name should be provided as argument of `get_dataset(dataset: str)` function.
+
+```python
+agriculture_amazonas = get_dataset('agriculture_amazonas')
+aids_amazonas = get_dataset('aids_amazonas')
+gdp_amazonas = get_dataset('gdp_amazonas')
+```
+
+### Get dataset documentation
+
+Each dataset has its own documentation to provide the user information about the dataset variables.
+
+Use `import` and `from` to require the functions from `docs` module:
+
+```python
+from amazonasdatahub.docs import get_doc
+```
+
+The dataset name should be provided as argument of `get_docs(dataset: str)` function.
+
+```python
+get_doc('agriculture_amazonas')
+get_doc('aids_amazonas')
+get_doc('gdp_amazonas')
+```
+
+<!-- ### Examples
+
+#### Disease occurrence
+
+The dataset `aids_amazonas` contains data of the AIDS occurrences in
+each municipality from Amazonas.
+
+One of the analysis that can be made is: visualize the time series of
+counts filtered by municipality, where each case is grouped by the
+sex/gender of each observation. To do this, we will use the dplyr
+package to structure the data and the ggplot2 package to create and
+customize the chart.
+
+``` r
+# Loading dplyr and ggplot to structure the data
+require(dplyr)
+require(ggplot2)
+```
+
+``` r
+# 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 occurrences in Manaus (2011-2023)",
+    x = "Year",
+    y = "Case count",
+    color = "Gender"
+  )
+```
+
+<img src="man/figures/README-unnamed-chunk-6-1.png" alt="" width="100%" />
+
+#### Time Series
+
+The `humidity_manaus` consists of the minimum relative humidity observed
+in the city of Manaus from January 2009 to December 2020. We can
+visualize the time series of the relative humidity during this time
+interval.
+
+Using `dplyr`, it is possible to create a date column, which will be
+composed of the month and year. Using`ggplot2`, the time series chart
+can be plotted.
+
+``` r
+# 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 (2009-2020)",
+    x = "Date",
+    y = "Relative Humidity"
+  )
+```
+
+<img src="man/figures/README-unnamed-chunk-7-1.png" alt="" width="100%" /> -->
+
+
+## Contributing
+
+Interested in contributing? Check out the contributing guidelines. Please note that this project is released with a Code of Conduct. By contributing to this project, you agree to abide by its terms.
+
+## License
+
+`amazonasdatahub` was created by Nelson Geraldo Aquino de Carvalho. It is licensed under the terms of the MIT license.
+
+<!-- ## Credits
+
+`amazonasdatahub` was created with [`cookiecutter`](https://cookiecutter.readthedocs.io/en/latest/) and the `py-pkgs-cookiecutter` [template](https://github.com/py-pkgs/py-pkgs-cookiecutter). -->
+
+## Citation
+
+- CARVALHO, Nelson Geraldo Aquino de; NASCIMENTO, Leonardo Brandão
+  Freitas do. **amazonasdatahub**. 2026.
+  <https://onelsoncarvalho.github.io/amazonasdatahubpy>.
+
+

amazonasdatahub-0.2.4.dist-info/RECORD

@@ -0,0 +1,15 @@
+amazonasdatahub/__init__.py,sha256=5JgY-IAZT-r0A1dv8henW4V1sXniUqgCfes0ab42_D4,118
+amazonasdatahub/datasets.py,sha256=h0UJ8-x1mdgInY8yYQnkFacplKWTYrV2_YnyT3VvXE8,1213
+amazonasdatahub/docs.py,sha256=6yJxHuNNZSlD6jdUQyIlKiuPzW8O7OS0qIIsIqpRnxo,901
+amazonasdatahub/documentations/agriculture_amazonas.md,sha256=_7BnQa3DRtfPc25OoHn54D0Wr2_6b6WtxJQI1158ii0,1943
+amazonasdatahub/documentations/aids_amazonas.md,sha256=BbVkTA6fRbwy_5BZLNfXTt9IkAxeGeWN7twmg0sA7ws,1288
+amazonasdatahub/documentations/gdp_amazonas.md,sha256=ojxPPvwDth-gJx0vqLIdKI0b9xOUKk3P8lBakBlN40w,3829
+amazonasdatahub/documentations/humidity_manaus.md,sha256=VsuF6fsnx2c-KuyoMgiCj-d1aWmsF167s1xTj_zluMw,1711
+amazonasdatahub/documentations/malaria_amazonas.md,sha256=Qs1o4z-GAUY5lnN53FYVpUk0uF2V9qcR_UZG8Q7OpNs,4034
+amazonasdatahub/documentations/prf_amazonas.md,sha256=HQWCK_U2xa_itNmA_TG5Wki_ZR25L1cMcUDbkNm5ZJs,2466
+amazonasdatahub/documentations/rionegro_amazonas.md,sha256=MyHApcegRNC6GTs9hnefNaw1QUav53dycgJELGtehas,1510
+amazonasdatahub/documentations/srl_muni.md,sha256=wNA1F2gphJU5qrVW5jcQLZNtNzrfiedBeslN2RydEPI,3633
+amazonasdatahub-0.2.4.dist-info/METADATA,sha256=Pm8RZHipsQEo9Q9ms_LUzeqF7wR3zWLfywdaahUHHlo,7458
+amazonasdatahub-0.2.4.dist-info/WHEEL,sha256=EGEvSphFYqXKs23-kQBeyNoJP1nrT8ZJKQoi5p5DYL8,88
+amazonasdatahub-0.2.4.dist-info/licenses/LICENSE,sha256=Y1y_XO9X6N-aoaPQ91bwmKAtn6Up1pttUd8dyJ7NV44,1092
+amazonasdatahub-0.2.4.dist-info/RECORD,,

amazonasdatahub-0.2.4.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: poetry-core 2.4.0
+Root-Is-Purelib: true
+Tag: py3-none-any

amazonasdatahub-0.2.4.dist-info/licenses/LICENSE

@@ -0,0 +1,22 @@
+MIT License
+
+Copyright (c) 2026, Nelson Geraldo Aquino de Carvalho
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
+