test handle_edge_case_percentages

As part of this handle descriptions without match top 5

interactive_templates/templates/v2/analysis/top_5.py

@@ -88,11 +88,20 @@ def calculate_proportion(event_counts):
 
 
 def add_description(event_counts, code_df, code_column, term_column):
+    if code_df.empty:
+        event_counts["Description"] = "-"
+        return event_counts
+
     code_df = code_df.set_index(code_column).rename(
         columns={term_column: "Description"}
     )
+
     event_counts = event_counts.set_index(code_column).join(code_df).reset_index()
     event_counts.loc[event_counts[code_column] == "Other", "Description"] = "-"
+
+    # For codes that did not find a match in code_df set a default value
+    event_counts["Description"].fillna("-", inplace=True)
+
     return event_counts
 
 

interactive_templates/templates/v2/tests/test_top_5.py

@@ -139,3 +139,20 @@ def test_add_description(event_counts, code_df):
 
     # Ensure that no rows were lost
     assert len(result) == len(event_counts)
+
+
+@given(df=df_strategy)
+def test_handle_edge_case_percentages(df):
+    df_with_proportions = calculate_proportion(df.copy())
+    result_df = handle_edge_case_percentages(df_with_proportions.copy())
+
+    for _, row in result_df.iterrows():
+        if (row["Proportion of codes (%)"] == 0) and (row["num"] > 0):
+            assert (
+                row["Proportion of codes (%)"] == "<0.001"
+            ), f"Expected '<0.001' but got {row['Proportion of codes (%)']} for num {row['num']}"
+
+        if (row["Proportion of codes (%)"] == 100) and (row["num"] < df["num"].sum()):
+            assert (
+                row["Proportion of codes (%)"] == ">99.99"
+            ), f"Expected '>99.99' but got {row['Proportion of codes (%)']} for num {row['num']}"