Handle multiselect case differently in read_arc_schema()

globaldothealth · Nov 18, 2024 · b885de0 · b885de0
1 parent 390e4ad
commit b885de0
Show file tree

Hide file tree

Showing 3 changed files with 6 additions and 4 deletions.
diff --git a/src/arcmapper/arc.py b/src/arcmapper/arc.py
@@ -15,12 +15,12 @@ def read_arc_schema(
     arc_version_or_file: str, preset: str | None = None
 ) -> pd.DataFrame:
     types_mapping: dict[str, DataType] = {
-        "radio": "categorical",
+        "radio": "enum",
         "number": "number",
         "text": "string",
         "date_dmy": "date",
-        "checkbox": "categorical",
-        "dropdown": "categorical",
+        "checkbox": "multiselect",
+        "dropdown": "enum",
         "datetime_dmy": "date",
     }
     arc_location = (

diff --git a/src/arcmapper/strategies.py b/src/arcmapper/strategies.py
@@ -58,6 +58,7 @@ def get_match_dataframe_from_similarity_matrix(
             "arc_variable",
             "arc_description",
             "arc_response",
+            "arc_type",
             "rank",
         ],
         data=sum(
@@ -71,6 +72,7 @@ def get_match_dataframe_from_similarity_matrix(
                         arc.iloc[k].variable,
                         arc.iloc[k].description,
                         arc.iloc[k].responses,
+                        arc.iloc[k].type,
                         j,
                     ]
                     for j, k in enumerate(S[i])

diff --git a/src/arcmapper/types.py b/src/arcmapper/types.py
@@ -10,7 +10,7 @@
 # example: gender = [(1, "male"), (2, "female")]
 Responses = list[str] | list[tuple[str | int, str]]
 
-DataType = Literal["categorical", "number", "string", "date"]
+DataType = Literal["enum", "number", "string", "date", "multiselect"]
 
 
 class PossibleMatch(NamedTuple):