diff --git a/dag/health.yml b/dag/health.yml index fdc4bae7c96..3f0f58e2039 100644 --- a/dag/health.yml +++ b/dag/health.yml @@ -969,3 +969,9 @@ steps: - data://meadow/antibiotics/2024-12-03/glass_enrolment data://grapher/antibiotics/2024-12-03/glass_enrolment: - data://garden/antibiotics/2024-12-03/glass_enrolment + data-private://meadow/antibiotics/2024-12-04/microbe_total_pathogens: + - snapshot-private://antibiotics/2024-12-04/microbe_total_pathogens.csv + data-private://garden/antibiotics/2024-12-04/microbe_total_pathogens: + - data-private://meadow/antibiotics/2024-12-04/microbe_total_pathogens + data-private://grapher/antibiotics/2024-12-04/microbe_total_pathogens: + - data-private://garden/antibiotics/2024-12-04/microbe_total_pathogens diff --git a/etl/steps/data/garden/antibiotics/2024-12-02/total_pathogen_bloodstream.meta.yml b/etl/steps/data/garden/antibiotics/2024-12-02/total_pathogen_bloodstream.meta.yml index 60ee224f93b..04044bb693f 100644 --- a/etl/steps/data/garden/antibiotics/2024-12-02/total_pathogen_bloodstream.meta.yml +++ b/etl/steps/data/garden/antibiotics/2024-12-02/total_pathogen_bloodstream.meta.yml @@ -15,31 +15,31 @@ tables: total_pathogen_bloodstream: variables: value: - title: Total deaths from << pathogen >> infections + title: Total deaths from << pathogen >> bloodstream infections unit: deaths - description_short: Estimated number of deaths << pathogen >> infections. << pathogen >> is a {definitions.pathogen_type}. + description_short: Estimated number of deaths << pathogen >> bloodstream infections. << pathogen >> is a {definitions.pathogen_type}. presentation: - title_public: Total deaths from << pathogen >> infections + title_public: Total deaths from << pathogen >> bloodstream infections display: roundingMode: significantFigures numSignificantFigures: 3 name: << pathogen >> upper: - title: Upper bound of total deaths from << pathogen >> infections + title: Upper bound of total deaths from << pathogen >> bloodstream infections unit: deaths - description_short: Estimated number of deaths << pathogen >> infections. << pathogen >> is a {definitions.pathogen_type}. + description_short: Estimated number of deaths << pathogen >> bloodstream infections. << pathogen >> is a {definitions.pathogen_type}. presentation: - title_public: Upper bound of total deaths from << pathogen >> infections + title_public: Upper bound of total deaths from << pathogen >> bloodstream infections display: roundingMode: significantFigures numSignificantFigures: 3 name: << pathogen >> lower: - title: Lower bound of total deaths from << pathogen >> infections + title: Lower bound of total deaths from << pathogen >> bloodstream infections unit: deaths - description_short: Estimated number of deaths << pathogen >> infections. << pathogen >> is a {definitions.pathogen_type}. + description_short: Estimated number of deaths << pathogen >> bloodstream infections. << pathogen >> is a {definitions.pathogen_type}. presentation: - title_public: Lower bound of total deaths from << pathogen >> infections + title_public: Lower bound of total deaths from << pathogen >> bloodstream infections display: roundingMode: significantFigures numSignificantFigures: 3 diff --git a/etl/steps/data/garden/antibiotics/2024-12-04/microbe_total_pathogens.countries.json b/etl/steps/data/garden/antibiotics/2024-12-04/microbe_total_pathogens.countries.json new file mode 100644 index 00000000000..a7f8eced782 --- /dev/null +++ b/etl/steps/data/garden/antibiotics/2024-12-04/microbe_total_pathogens.countries.json @@ -0,0 +1,3 @@ +{ + "Global": "World" +} \ No newline at end of file diff --git a/etl/steps/data/garden/antibiotics/2024-12-04/microbe_total_pathogens.meta.yml b/etl/steps/data/garden/antibiotics/2024-12-04/microbe_total_pathogens.meta.yml new file mode 100644 index 00000000000..e29b06ed86b --- /dev/null +++ b/etl/steps/data/garden/antibiotics/2024-12-04/microbe_total_pathogens.meta.yml @@ -0,0 +1,46 @@ +# NOTE: To learn more about the fields, hover over their names. +definitions: + common: + presentation: + topic_tags: + - Antibiotics + pathogen_type: <% if pathogen_type == "Fungi" %>fungus<% elif pathogen_type == "Viruses" %>virus<% else %><< pathogen_type.lower() >><% endif %> + +# Learn more about the available fields: +# http://docs.owid.io/projects/etl/architecture/metadata/reference/ +dataset: + update_period_days: 365 + +tables: + microbe_total_pathogens: + variables: + value: + title: Total deaths from << pathogen >> infections + unit: deaths + description_short: Estimated number of deaths << pathogen >> infections. << pathogen >> is a {definitions.pathogen_type}. + presentation: + title_public: Total deaths from << pathogen >> infections + display: + roundingMode: significantFigures + numSignificantFigures: 3 + name: << pathogen >> + upper: + title: Upper bound of total deaths from << pathogen >> infections + unit: deaths + description_short: Estimated number of deaths << pathogen >> infections. << pathogen >> is a {definitions.pathogen_type}. + presentation: + title_public: Upper bound of total deaths from << pathogen >> infections + display: + roundingMode: significantFigures + numSignificantFigures: 3 + name: << pathogen >> + lower: + title: Lower bound of total deaths from << pathogen >> infections + unit: deaths + description_short: Estimated number of deaths << pathogen >> infections. << pathogen >> is a {definitions.pathogen_type}. + presentation: + title_public: Lower bound of total deaths from << pathogen >> infections + display: + roundingMode: significantFigures + numSignificantFigures: 3 + name: << pathogen >> diff --git a/etl/steps/data/garden/antibiotics/2024-12-04/microbe_total_pathogens.py b/etl/steps/data/garden/antibiotics/2024-12-04/microbe_total_pathogens.py new file mode 100644 index 00000000000..b6883c23419 --- /dev/null +++ b/etl/steps/data/garden/antibiotics/2024-12-04/microbe_total_pathogens.py @@ -0,0 +1,35 @@ +"""Load a meadow dataset and create a garden dataset.""" + +from etl.data_helpers import geo +from etl.helpers import PathFinder, create_dataset + +# Get paths and naming conventions for current step. +paths = PathFinder(__file__) + + +def run(dest_dir: str) -> None: + # + # Load inputs. + # + # Load meadow dataset. + ds_meadow = paths.load_dataset("microbe_total_pathogens") + + # Read table from meadow dataset. + tb = ds_meadow.read("microbe_total_pathogens") + + # + # Process data. + # + tb = geo.harmonize_countries(df=tb, countries_file=paths.country_mapping_path) + tb = tb.format(["country", "year", "pathogen", "pathogen_type"]) + + # + # Save outputs. + # + # Create a new garden dataset with the same metadata as the meadow dataset. + ds_garden = create_dataset( + dest_dir, tables=[tb], check_variables_metadata=True, default_metadata=ds_meadow.metadata + ) + + # Save changes in the new garden dataset. + ds_garden.save() diff --git a/etl/steps/data/grapher/antibiotics/2024-12-04/microbe_total_pathogens.py b/etl/steps/data/grapher/antibiotics/2024-12-04/microbe_total_pathogens.py new file mode 100644 index 00000000000..898f3506d2b --- /dev/null +++ b/etl/steps/data/grapher/antibiotics/2024-12-04/microbe_total_pathogens.py @@ -0,0 +1,28 @@ +"""Load a garden dataset and create a grapher dataset.""" + +from etl.helpers import PathFinder, create_dataset + +# Get paths and naming conventions for current step. +paths = PathFinder(__file__) + + +def run(dest_dir: str) -> None: + # + # Load inputs. + # + # Load garden dataset. + ds_garden = paths.load_dataset("microbe_total_pathogens") + + # Read table from garden dataset. + tb = ds_garden.read("microbe_total_pathogens", reset_index=False) + + # + # Save outputs. + # + # Create a new grapher dataset with the same metadata as the garden dataset. + ds_grapher = create_dataset( + dest_dir, tables=[tb], check_variables_metadata=True, default_metadata=ds_garden.metadata + ) + + # Save changes in the new grapher dataset. + ds_grapher.save() diff --git a/etl/steps/data/meadow/antibiotics/2024-12-04/microbe_total_pathogens.py b/etl/steps/data/meadow/antibiotics/2024-12-04/microbe_total_pathogens.py new file mode 100644 index 00000000000..f03016ef003 --- /dev/null +++ b/etl/steps/data/meadow/antibiotics/2024-12-04/microbe_total_pathogens.py @@ -0,0 +1,39 @@ +"""Load a snapshot and create a meadow dataset.""" + +from etl.helpers import PathFinder, create_dataset + +# Get paths and naming conventions for current step. +paths = PathFinder(__file__) + + +def run(dest_dir: str) -> None: + # + # Load inputs. + # + # Retrieve snapshot. + snap = paths.load_snapshot("microbe_total_pathogens.csv") + + # Load data from snapshot. + tb = snap.read() + assert all(tb["Age"] == "All Ages") + assert all(tb["Sex"] == "Both sexes") + assert all(tb["Measure"] == "Deaths") + assert all(tb["Metric"] == "Number") + assert all(tb["Counterfactual"] == "Total") + assert all(tb["Infectious syndrome"] == "All infectious syndromes") + + # + # Process data. + tb = tb.drop(columns=["Age", "Sex", "Measure", "Metric", "Infectious syndrome", "Counterfactual"]) + tb = tb.rename(columns={"Location": "country", "Year": "year", "Pathogen": "pathogen"}) + # Ensure all columns are snake-case, set an appropriate index, and sort conveniently. + tb = tb.format(["country", "year", "pathogen"]) + + # + # Save outputs. + # + # Create a new meadow dataset with the same metadata as the snapshot. + ds_meadow = create_dataset(dest_dir, tables=[tb], check_variables_metadata=True, default_metadata=snap.metadata) + + # Save changes in the new meadow dataset. + ds_meadow.save() diff --git a/snapshots/antibiotics/2024-12-04/microbe_total_pathogens.csv.dvc b/snapshots/antibiotics/2024-12-04/microbe_total_pathogens.csv.dvc new file mode 100644 index 00000000000..e904e5d6873 --- /dev/null +++ b/snapshots/antibiotics/2024-12-04/microbe_total_pathogens.csv.dvc @@ -0,0 +1,27 @@ +# Learn more at: +# http://docs.owid.io/projects/etl/architecture/metadata/reference/ +meta: + origin: + # Data product / Snapshot + title: Total deaths by pathogen + description: |- + The MICROBE (Measuring Infectious Causes and Resistance Outcomes for Burden Estimation) tool visualizes the fatal and nonfatal health outcomes of infections, pathogens, and antimicrobial resistance across different countries and regions. The tool shows a novel estimation method, [published in The Lancet](https://www.thelancet.com/journals/lancet/article/PIIS0140-6736(24)01867-1/fulltext), including the burden of infections and their underlying pathogens, as well as, the burden of pathogens that are both susceptible and resistant to antibiotics. This tool is useful for understanding the burden of these outcomes, as well as illustrating how they nest together. The tabs explore different health outcomes by geography, age and sex. All tabs include a bar visualization for comparison, as well as a map view for a global perspective. + date_published: "2024-09-28" + # Citation + producer: Institute for Health Metrics and Evaluation (IHME); University of Oxford + citation_full: |- + Institute for Health Metrics and Evaluation (IHME), University of Oxford. MICROBE. Seattle, WA: IHME, University of Washington, 2024. Available from [https://vizhub.healthdata.org/microbe](https://vizhub.healthdata.org/microbe) + attribution_short: MICROBE + # Files + url_main: https://vizhub.healthdata.org/microbe/ + date_accessed: 2024-12-04 + + # License + license: + name: IHME's Free-of-Charge Non-commercial User Agreement + url: https://www.healthdata.org/Data-tools-practices/data-practices/ihme-free-charge-non-commercial-user-agreement + is_public: false +outs: + - md5: bff21259d44b1ab5a61ecf675285d13b + size: 10960 + path: microbe_total_pathogens.csv diff --git a/snapshots/antibiotics/2024-12-04/microbe_total_pathogens.py b/snapshots/antibiotics/2024-12-04/microbe_total_pathogens.py new file mode 100644 index 00000000000..754aaafe897 --- /dev/null +++ b/snapshots/antibiotics/2024-12-04/microbe_total_pathogens.py @@ -0,0 +1,37 @@ +"""Script to create a snapshot of dataset. + +To download the data visit: https://vizhub.healthdata.org/microbe/ + +- Select the 'Pathogens' tab. +- Infectious syndrome: 'All infectious syndromes' +- Location: 'Global' +- Age: 'All ages' +- Sex: 'Both' +- Measure: 'Deaths' +- Metric: 'Number' + +""" + +from pathlib import Path + +import click + +from etl.snapshot import Snapshot + +# Version for current snapshot dataset. +SNAPSHOT_VERSION = Path(__file__).parent.name + + +@click.command() +@click.option("--upload/--skip-upload", default=True, type=bool, help="Upload dataset to Snapshot") +@click.option("--path-to-file", "-f", prompt=True, type=str, help="Path to local data file.") +def main(path_to_file: str, upload: bool) -> None: + # Create a new snapshot. + snap = Snapshot(f"antibiotics/{SNAPSHOT_VERSION}/microbe_total_pathogens.csv") + + # Download data from source, add file to DVC and upload to S3. + snap.create_snapshot(filename=path_to_file, upload=upload) + + +if __name__ == "__main__": + main()