terrorism snapshot + meadow

dag/main.yml

@@ -528,6 +528,14 @@ steps:
   data://garden/oecd/2023-06-20/ppp_exchange_rates:
   - data://meadow/oecd/2023-06-20/ppp_exchange_rates
 
+# Terrorism
+  data://meadow/terrorism/2023-07-20/global_terrorism_database:
+  - snapshot://terrorism/2023-07-20/global_terrorism_database.xlsx
+  - snapshot://terrorism/2023-07-20/global_terrorism_database_2021.xlsx
+  data://garden/terrorism/2023-07-20/global_terrorism_database:
+  - data://meadow/terrorism/2023-07-20/global_terrorism_database
+  data://grapher/terrorism/2023-07-20/global_terrorism_database:
+  - data://garden/terrorism/2023-07-20/global_terrorism_database
 
 
 

dag/walkthrough.yml

@@ -7,4 +7,5 @@ steps:
   data://grapher/dummy/2020-01-01/dummy:
   - data://garden/dummy/2020-01-01/dummy
   data://explorers/dummy/2020-01-01/dummy:
-  - data://garden/dummy/2020-01-01/dummy
+  - data://garden/dummy/2020-01-01/dummy
+

etl/steps/data/garden/terrorism/2023-07-20/global_terrorism_database.countries.json

@@ -0,0 +1,206 @@
+{
+  "Afghanistan": "Afghanistan",
+  "Albania": "Albania",
+  "Algeria": "Algeria",
+  "Andorra": "Andorra",
+  "Angola": "Angola",
+  "Antigua and Barbuda": "Antigua and Barbuda",
+  "Argentina": "Argentina",
+  "Armenia": "Armenia",
+  "Australia": "Australia",
+  "Austria": "Austria",
+  "Azerbaijan": "Azerbaijan",
+  "Bahamas": "Bahamas",
+  "Bahrain": "Bahrain",
+  "Bangladesh": "Bangladesh",
+  "Barbados": "Barbados",
+  "Belarus": "Belarus",
+  "Belgium": "Belgium",
+  "Belize": "Belize",
+  "Benin": "Benin",
+  "Bhutan": "Bhutan",
+  "Bolivia": "Bolivia",
+  "Botswana": "Botswana",
+  "Brazil": "Brazil",
+  "Brunei": "Brunei",
+  "Bulgaria": "Bulgaria",
+  "Burkina Faso": "Burkina Faso",
+  "Burundi": "Burundi",
+  "Cambodia": "Cambodia",
+  "Cameroon": "Cameroon",
+  "Canada": "Canada",
+  "Central African Republic": "Central African Republic",
+  "Chad": "Chad",
+  "Chile": "Chile",
+  "China": "China",
+  "Colombia": "Colombia",
+  "Comoros": "Comoros",
+  "Costa Rica": "Costa Rica",
+  "Croatia": "Croatia",
+  "Cuba": "Cuba",
+  "Cyprus": "Cyprus",
+  "Czech Republic": "Czechia",
+  "Czechoslovakia": "Czechoslovakia",
+  "Democratic Republic of the Congo": "Democratic Republic of Congo",
+  "Denmark": "Denmark",
+  "Djibouti": "Djibouti",
+  "Dominica": "Dominica",
+  "Dominican Republic": "Dominican Republic",
+  "East Timor": "East Timor",
+  "Ecuador": "Ecuador",
+  "Egypt": "Egypt",
+  "El Salvador": "El Salvador",
+  "Equatorial Guinea": "Equatorial Guinea",
+  "Eritrea": "Eritrea",
+  "Estonia": "Estonia",
+  "Ethiopia": "Ethiopia",
+  "Falkland Islands": "Falkland Islands",
+  "Fiji": "Fiji",
+  "Finland": "Finland",
+  "France": "France",
+  "French Guiana": "French Guiana",
+  "French Polynesia": "French Polynesia",
+  "Gabon": "Gabon",
+  "Gambia": "Gambia",
+  "Georgia": "Georgia",
+  "Germany": "Germany",
+  "Ghana": "Ghana",
+  "Greece": "Greece",
+  "Grenada": "Grenada",
+  "Guadeloupe": "Guadeloupe",
+  "Guatemala": "Guatemala",
+  "Guinea": "Guinea",
+  "Guinea-Bissau": "Guinea-Bissau",
+  "Guyana": "Guyana",
+  "Haiti": "Haiti",
+  "Honduras": "Honduras",
+  "Hong Kong": "Hong Kong",
+  "Hungary": "Hungary",
+  "Iceland": "Iceland",
+  "India": "India",
+  "Indonesia": "Indonesia",
+  "Iran": "Iran",
+  "Iraq": "Iraq",
+  "Ireland": "Ireland",
+  "Israel": "Israel",
+  "Italy": "Italy",
+  "Ivory Coast": "Cote d'Ivoire",
+  "Jamaica": "Jamaica",
+  "Japan": "Japan",
+  "Jordan": "Jordan",
+  "Kazakhstan": "Kazakhstan",
+  "Kenya": "Kenya",
+  "Kosovo": "Kosovo",
+  "Kuwait": "Kuwait",
+  "Kyrgyzstan": "Kyrgyzstan",
+  "Laos": "Laos",
+  "Latvia": "Latvia",
+  "Lebanon": "Lebanon",
+  "Lesotho": "Lesotho",
+  "Liberia": "Liberia",
+  "Libya": "Libya",
+  "Lithuania": "Lithuania",
+  "Luxembourg": "Luxembourg",
+  "Macau": "Macao",
+  "Macedonia": "North Macedonia",
+  "Madagascar": "Madagascar",
+  "Malawi": "Malawi",
+  "Malaysia": "Malaysia",
+  "Maldives": "Maldives",
+  "Mali": "Mali",
+  "Malta": "Malta",
+  "Martinique": "Martinique",
+  "Mauritania": "Mauritania",
+  "Mauritius": "Mauritius",
+  "Mexico": "Mexico",
+  "Moldova": "Moldova",
+  "Montenegro": "Montenegro",
+  "Morocco": "Morocco",
+  "Mozambique": "Mozambique",
+  "Myanmar": "Myanmar",
+  "Namibia": "Namibia",
+  "Nepal": "Nepal",
+  "Netherlands": "Netherlands",
+  "New Caledonia": "New Caledonia",
+  "New Zealand": "New Zealand",
+  "Nicaragua": "Nicaragua",
+  "Niger": "Niger",
+  "Nigeria": "Nigeria",
+  "North Korea": "North Korea",
+  "Norway": "Norway",
+  "Pakistan": "Pakistan",
+  "Panama": "Panama",
+  "Papua New Guinea": "Papua New Guinea",
+  "Paraguay": "Paraguay",
+  "Peru": "Peru",
+  "Philippines": "Philippines",
+  "Poland": "Poland",
+  "Portugal": "Portugal",
+  "Qatar": "Qatar",
+  "Romania": "Romania",
+  "Russia": "Russia",
+  "Rwanda": "Rwanda",
+  "Saudi Arabia": "Saudi Arabia",
+  "Senegal": "Senegal",
+  "Serbia": "Serbia",
+  "Seychelles": "Seychelles",
+  "Sierra Leone": "Sierra Leone",
+  "Singapore": "Singapore",
+  "Slovak Republic": "Slovakia",
+  "Slovenia": "Slovenia",
+  "Solomon Islands": "Solomon Islands",
+  "Somalia": "Somalia",
+  "South Africa": "South Africa",
+  "South Korea": "South Korea",
+  "South Sudan": "South Sudan",
+  "Soviet Union": "USSR",
+  "Spain": "Spain",
+  "Sri Lanka": "Sri Lanka",
+  "St. Kitts and Nevis": "Saint Kitts and Nevis",
+  "St. Lucia": "Saint Lucia",
+  "Sudan": "Sudan",
+  "Suriname": "Suriname",
+  "Swaziland": "Eswatini",
+  "Sweden": "Sweden",
+  "Switzerland": "Switzerland",
+  "Syria": "Syria",
+  "Taiwan": "Taiwan",
+  "Tajikistan": "Tajikistan",
+  "Tanzania": "Tanzania",
+  "Thailand": "Thailand",
+  "Togo": "Togo",
+  "Trinidad and Tobago": "Trinidad and Tobago",
+  "Tunisia": "Tunisia",
+  "Turkey": "Turkey",
+  "Turkmenistan": "Turkmenistan",
+  "Uganda": "Uganda",
+  "Ukraine": "Ukraine",
+  "United Arab Emirates": "United Arab Emirates",
+  "United Kingdom": "United Kingdom",
+  "United States": "United States",
+  "Uruguay": "Uruguay",
+  "Uzbekistan": "Uzbekistan",
+  "Vanuatu": "Vanuatu",
+  "Venezuela": "Venezuela",
+  "Vietnam": "Vietnam",
+  "Wallis and Futuna": "Wallis and Futuna",
+  "Western Sahara": "Western Sahara",
+  "Yemen": "Yemen",
+  "Yugoslavia": "Yugoslavia",
+  "Zambia": "Zambia",
+  "Zimbabwe": "Zimbabwe",
+  "Bosnia-Herzegovina": "Bosnia and Herzegovina",
+  "East Germany (GDR)": "East Germany",
+  "International": "International",
+  "New Hebrides": "New Hebrides",
+  "North Yemen": "Yemen Arab Republic",
+  "People's Republic of the Congo": "People's Republic of the Congo",
+  "Republic of the Congo": "Republic of the Congo",
+  "Rhodesia": "Rhodesia",
+  "Serbia-Montenegro": "Serbia and Montenegro",
+  "South Yemen": "South Yemen",
+  "Vatican City": "Vatican",
+  "West Bank and Gaza Strip": "West Bank and Gaza Strip",
+  "West Germany (FRG)": "West Germany",
+  "Zaire": "Zaire"
+}

etl/steps/data/garden/terrorism/2023-07-20/global_terrorism_database.excluded_countries.json

@@ -0,0 +1,2 @@
+[
+]

etl/steps/data/garden/terrorism/2023-07-20/global_terrorism_database.meta.yml

@@ -0,0 +1,35 @@
+# (Inherited from meadow, remove if not different.)
+all_sources:
+  - source_testing: &source-testing
+      name: # Example: Testing Short Citation
+      published_by: # (if different to short citation). Example: Testing Full Citation
+      url: # Example: https://url_of_testing_source.com/
+      date_accessed: # Example: 2023-01-01
+      publication_date: # Example: 2023-01-01
+      publication_year: # (if publication_date is not given). Example: 2023
+      # description: Source description.
+
+# (Inherited from meadow, remove if not different.)
+dataset:
+  title: # Example: Testing Dataset Name (Institution, 2023)
+  # description: Dataset description.
+  licenses:
+    - name: # Example: Testing License Name
+      url: # Example: https://url_of_testing_source.com/license
+  sources:
+    - *source-testing
+
+tables:
+  global_terrorism_database:
+    # (Inherited from meadow, remove if not different.)
+    variables:
+      # testing_variable:
+      #   title: Testing variable title
+      #   unit: arbitrary units
+      #   short_unit: au
+      #   description: Full description of testing variable.
+      #   sources:
+      #     - *source-testing
+      #   display:
+      #     entityAnnotationsMap: Test annotation
+      #     numDecimalPlaces: 0

etl/steps/data/garden/terrorism/2023-07-20/global_terrorism_database.py

@@ -0,0 +1,38 @@
+"""Load a meadow dataset and create a garden dataset."""
+
+from typing import cast
+
+from owid.catalog import Dataset, Table
+
+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 = cast(Dataset, paths.load_dependency("global_terrorism_database"))
+
+    # Read table from meadow dataset.
+    tb = ds_meadow["global_terrorism_database"]
+
+    #
+    # Process data.
+    #
+    tb: Table = geo.harmonize_countries(
+        df=tb, countries_file=paths.country_mapping_path, excluded_countries_file=paths.excluded_countries_path
+    )
+
+    #
+    # Save outputs.
+    #
+    # Create a new garden dataset with the same metadata as the meadow dataset.
+    ds_garden = create_dataset(dest_dir, tables=[tb], default_metadata=ds_meadow.metadata)
+
+    # Save changes in the new garden dataset.
+    ds_garden.save()

etl/steps/data/grapher/terrorism/2023-07-20/global_terrorism_database.py

@@ -0,0 +1,39 @@
+"""Load a garden dataset and create a grapher dataset."""
+
+from typing import cast
+
+from owid.catalog import Dataset
+
+from etl.helpers import PathFinder, create_dataset, grapher_checks
+
+# Get paths and naming conventions for current step.
+paths = PathFinder(__file__)
+
+
+def run(dest_dir: str) -> None:
+    #
+    # Load inputs.
+    #
+    # Load garden dataset.
+    ds_garden = cast(Dataset, paths.load_dependency("global_terrorism_database"))
+
+    # Read table from garden dataset.
+    tb = ds_garden["global_terrorism_database"]
+
+    #
+    # Process data.
+    #
+
+    #
+    # Save outputs.
+    #
+    # Create a new grapher dataset with the same metadata as the garden dataset.
+    ds_grapher = create_dataset(dest_dir, tables=[tb], default_metadata=ds_garden.metadata)
+
+    #
+    # Checks.
+    #
+    grapher_checks(ds_grapher)
+
+    # Save changes in the new grapher dataset.
+    ds_grapher.save()