fasttrack: fasttrack/latest/_2__2023_in_donor_individual_countries__s…

…heet1.csv

dag/fasttrack.yml

@@ -230,3 +230,5 @@ steps:
     - snapshot://fasttrack/latest/try_fast_track_in_donor_costs.csv
   data://grapher/fasttrack/latest/_1__2018_2023_in_donor_costs_dac_countries__sheet1:
     - snapshot://fasttrack/latest/_1__2018_2023_in_donor_costs_dac_countries__sheet1.csv
+  data://grapher/fasttrack/latest/_2__2023_in_donor_individual_countries__sheet1:
+    - snapshot://fasttrack/latest/_2__2023_in_donor_individual_countries__sheet1.csv

etl/steps/data/grapher/fasttrack/latest/_2__2023_in_donor_individual_countries__sheet1.meta.yml

@@ -0,0 +1,27 @@
+dataset:
+  title: DRAFT 2 – 2023 In-donor individual countries - Sheet1
+  description: ''
+tables:
+  _2__2023_in_donor_individual_countries__sheet1:
+    variables:
+      debt_relief:
+        title: Debt_Relief
+        unit: ''
+      in_donor_student_costs:
+        title: In_Donor_Student_Costs
+        unit: ''
+      in_donor_refugee_costs:
+        title: In_Donor_Refugee_Costs
+        unit: ''
+      development_awareness:
+        title: Development_Awareness
+        unit: ''
+      administrative_costs:
+        title: Administrative_Costs
+        unit: ''
+      in_donor_research:
+        title: In_Donor_Research
+        unit: ''
+      total:
+        title: Total
+        unit: ''

etl/steps/data/grapher/fasttrack/latest/_2__2023_in_donor_individual_countries__sheet1.py

@@ -0,0 +1,40 @@
+import pandas as pd
+
+from etl.helpers import PathFinder, create_dataset, get_metadata_path
+from etl.snapshot import Snapshot
+
+paths = PathFinder(__file__)
+
+
+def run(dest_dir: str) -> None:
+    # load snapshot
+    snap = Snapshot("fasttrack/latest/_2__2023_in_donor_individual_countries__sheet1.csv")
+
+    # load data
+    tb = snap.read_csv()
+
+    # add dimensions with dim_ prefix
+    dims = [c for c in tb.columns if c.startswith("dim_")]
+    dims_without_prefix = [c[4:] for c in dims]
+
+    if dims:
+        tb = tb.rename(columns={d: dw for d, dw in zip(dims, dims_without_prefix)})
+
+    if uses_dates(tb["year"]):
+        tb = tb.rename(columns={"year": "date"}).format(["country", "date"] + dims_without_prefix)
+    else:
+        tb = tb.format(["country", "year"] + dims_without_prefix)
+
+    # add table, update metadata from *.meta.yml and save
+    ds = create_dataset(dest_dir, tables=[tb], default_metadata=snap.metadata)
+
+    # override metadata if necessary
+    meta_path = get_metadata_path(dest_dir).with_suffix(".override.yml")
+    if meta_path.exists():
+        ds.update_metadata(meta_path)
+
+    ds.save()
+
+
+def uses_dates(s: pd.Series) -> bool:
+    return pd.to_datetime(s, errors="coerce", format="%Y-%m-%d").notnull().all()

snapshots/fasttrack/latest/_2__2023_in_donor_individual_countries__sheet1.csv.dvc

@@ -0,0 +1,16 @@
+meta:
+  origin:
+    producer: Unknown
+    title: Unknown
+    citation_full: Unknown
+    version_producer: Local CSV
+    url_main: https://unknown.com
+    url_download: 2 – 2023 In-donor individual countries - Sheet1.csv
+    date_accessed: '2025-01-30'
+    date_published: '2025-01-30'
+  name: DRAFT 2 – 2023 In-donor individual countries - Sheet1
+  description: ''
+outs:
+  - md5: 0594ff5700e3df26d0420767f1d08a70
+    size: 1115
+    path: _2__2023_in_donor_individual_countries__sheet1.csv