Suppress duplicates in Label Recognition spreadsheet

rhunwicks · rhunwicks · commit a5ce9ab67e27 · 2026-03-26T12:23:48.000-04:00
diff --git a/pipelines/assets/livelihood_activity.py b/pipelines/assets/livelihood_activity.py
@@ -671,6 +671,7 @@ def livelihood_activity_label_recognition_dataframe(
         all_labels_df[
             [
                 "label_lower",
+                "activity_type",
                 "activity_label_regex",
                 "strategy_type_regex",
                 "is_start_regex",
@@ -693,8 +694,8 @@ def livelihood_activity_label_recognition_dataframe(
             ]
         ]
         .drop_duplicates()
-        .set_index("label_lower"),
-        on="label",
+        .set_index(["label_lower", "activity_type"]),
+        on=["label", "activity_type"],
         how="inner",
     )
 

Original file line number	Diff line number	Diff line change
`@@ -671,6 +671,7 @@ def livelihood_activity_label_recognition_dataframe(`
`671`	`671`	`all_labels_df[`
`672`	`672`	`[`
`673`	`673`	`"label_lower",`
	`674`	`+ "activity_type",`
`674`	`675`	`"activity_label_regex",`
`675`	`676`	`"strategy_type_regex",`
`676`	`677`	`"is_start_regex",`
`@@ -693,8 +694,8 @@ def livelihood_activity_label_recognition_dataframe(`
`693`	`694`	`]`
`694`	`695`	`]`
`695`	`696`	`.drop_duplicates()`
`696`		`- .set_index("label_lower"),`
`697`		`- on="label",`
	`697`	`+ .set_index(["label_lower", "activity_type"]),`
	`698`	`+ on=["label", "activity_type"],`
`698`	`699`	`how="inner",`
`699`	`700`	`)`
`700`	`701`