chore(repo): Rename data loading module

src/load_data.py

@@ -0,0 +1,49 @@
+import io
+from pathlib import Path
+import sys
+try:
+    import src.yaml as yaml # for quarto document scripts
+except ModuleNotFoundError:
+    import yaml as yaml # for directly running the package
+from pandas import DataFrame, read_csv
+
+DEFAULT_YAML_PATH = Path("02-data/processed")
+
+
+def to_tsv(studies: list[dict]) -> str:
+    if not studies:
+        return ""
+    tsv = ""
+    tab = "\t"
+    tsv += (
+        f"{tab.join(studies[0].keys())}{tab}"
+        f"{tab.join(studies[0]['observation'][0].keys())}\n"
+    )
+    for study in studies:
+        study_list = [str(val).replace("\n", "") for val in study.values()]
+        for obs in study["observation"]:
+            obs_list = [str(val).replace("\n", "") for val in obs.values()]
+            tsv += f"{tab.join(study_list)}{tab}{tab.join(obs_list)}\n"
+    return tsv
+
+
+def from_yml(yml_path: Path | str = DEFAULT_YAML_PATH) -> DataFrame:
+    yml_path = Path(yml_path).resolve()
+    studies = yaml.load(yml_path)
+    if not studies:
+        raise ValueError(f"No studies found in directory {yml_path.resolve()}")
+    tsv = to_tsv(studies)
+    return read_csv(io.StringIO(tsv), sep="\t")
+
+
+if __name__ == "__main__":
+    if len(sys.argv) == 2:
+        res = from_yml(Path(sys.argv[1]))
+    else:
+        res = from_yml()
+
+    from io import StringIO
+    output = StringIO()
+    res.to_csv(output)
+    output.seek(0)
+    print(output.read())