feat(api): add average thread length per emotion

server/analysis/interactional.py

@@ -124,3 +124,85 @@ class InteractionAnalysis:
             interactions[a][b] = interactions[a].get(b, 0) + 1
 
         return interactions
+    
+    def average_thread_depth(self):
+        depths = []
+        id_to_reply = self.df.set_index("id")["reply_to"].to_dict()
+        for _, row in self.df.iterrows():
+            depth = 0
+            current_id = row["id"]
+
+            while True:
+                reply_to = id_to_reply.get(current_id)
+                if pd.isna(reply_to) or reply_to == "":
+                    break
+
+                depth += 1
+                current_id = reply_to
+
+            depths.append(depth)
+
+        if not depths:
+            return 0
+        
+        return round(sum(depths) / len(depths), 2)
+    
+    def average_thread_length_by_emotion(self):
+        emotion_exclusions = {"emotion_neutral", "emotion_surprise"}
+
+        emotion_cols = [
+            c for c in self.df.columns
+            if c.startswith("emotion_") and c not in emotion_exclusions
+        ]
+
+        id_to_reply = self.df.set_index("id")["reply_to"].to_dict()
+        length_cache = {}
+
+        def thread_length_from(start_id):
+            if start_id in length_cache:
+                return length_cache[start_id]
+
+            seen = set()
+            length = 1
+            current = start_id
+
+            while True:
+                if current in seen:
+                    # infinite loop shouldn't happen, but just in case
+                    break
+                seen.add(current)
+
+                reply_to = id_to_reply.get(current)
+
+                if reply_to is None or (isinstance(reply_to, float) and pd.isna(reply_to)) or reply_to == "":
+                    break
+
+                length += 1
+                current = reply_to
+
+                if current in length_cache:
+                    length += (length_cache[current] - 1)
+                    break
+
+            length_cache[start_id] = length
+            return length
+
+        emotion_to_lengths = {}
+
+        # Fill NaNs in emotion cols to avoid max() issues
+        emo_df = self.df[["id"] + emotion_cols].copy()
+        emo_df[emotion_cols] = emo_df[emotion_cols].fillna(0)
+
+        for _, row in emo_df.iterrows():
+            msg_id = row["id"]
+            length = thread_length_from(msg_id)
+
+            emotions = {c: row[c] for c in emotion_cols}
+            dominant = max(emotions, key=emotions.get)
+
+            emotion_to_lengths.setdefault(dominant, []).append(length)
+
+        return {
+            emotion: round(sum(lengths) / len(lengths), 2)
+            for emotion, lengths in emotion_to_lengths.items()
+        }

server/app.py

@@ -55,7 +55,7 @@ def word_frequencies():
         return jsonify({"error": "No data uploaded"}), 400
     
     try:
-        return jsonify(stat_obj.content_analysis()), 200
+        return jsonify(stat_obj.get_content_analysis()), 200
     except ValueError as e:
         return jsonify({"error": f"Malformed or missing data: {str(e)}"}), 400
     except Exception as e:
@@ -80,7 +80,7 @@ def get_time_analysis():
         return jsonify({"error": "No data uploaded"}), 400
     
     try:
-        return jsonify(stat_obj.time_analysis()), 200
+        return jsonify(stat_obj.get_time_analysis()), 200
     except ValueError as e:
         return jsonify({"error": f"Malformed or missing data: {str(e)}"}), 400
     except Exception as e:
@@ -93,7 +93,7 @@ def get_user_analysis():
         return jsonify({"error": "No data uploaded"}), 400
     
     try:
-        return jsonify(stat_obj.user_analysis()), 200
+        return jsonify(stat_obj.get_user_analysis()), 200
     except ValueError as e:
         return jsonify({"error": f"Malformed or missing data: {str(e)}"}), 400
     except Exception as e:
@@ -106,7 +106,20 @@ def get_cultural_analysis():
         return jsonify({"error": "No data uploaded"}), 400
     
     try:
-        return jsonify(stat_obj.cultural_analysis()), 200
+        return jsonify(stat_obj.get_cultural_analysis()), 200
+    except ValueError as e:
+        return jsonify({"error": f"Malformed or missing data: {str(e)}"}), 400
+    except Exception as e:
+        print(traceback.format_exc())
+        return jsonify({"error": f"An unexpected error occurred: {str(e)}"}), 500
+
+@app.route("/stats/interaction", methods=["GET"])
+def get_interaction_analysis():
+    if stat_obj is None:
+        return jsonify({"error": "No data uploaded"}), 400
+    
+    try:
+        return jsonify(stat_obj.get_interactional_analysis()), 200
     except ValueError as e:
         return jsonify({"error": f"Malformed or missing data: {str(e)}"}), 400
     except Exception as e:

server/stat_gen.py

@@ -66,14 +66,14 @@ class StatGen:
 
     # topics over time
     # emotions over time
-    def time_analysis(self) -> pd.DataFrame:
+    def get_time_analysis(self) -> pd.DataFrame:
         return {
             "events_per_day": self.temporal_analysis.posts_per_day(),
             "weekday_hour_heatmap": self.temporal_analysis.heatmap()
         }
 
     # average topic duration
-    def content_analysis(self) -> dict:
+    def get_content_analysis(self) -> dict:
         return {
             "word_frequencies": self.linguistic_analysis.word_frequencies(),
             "common_two_phrases": self.linguistic_analysis.ngrams(),
@@ -84,7 +84,7 @@ class StatGen:
     
     # average emotion per user
     # average chain length
-    def user_analysis(self) -> dict:
+    def get_user_analysis(self) -> dict:
         return {
             "top_users": self.interaction_analysis.top_users(),
             "users": self.interaction_analysis.per_user_analysis(),
@@ -94,14 +94,15 @@ class StatGen:
     # average / max thread depth
     # high engagment threads based on volume
 
-    def conversational_analysis(self) -> dict:
+    def get_interactional_analysis(self) -> dict:
         return {
-
+            "average_thread_depth": self.interaction_analysis.average_thread_depth(),
+            "average_thread_length_by_emotion": self.interaction_analysis.average_thread_length_by_emotion()
         }
     
     # detect community jargon
     # in-group and out-group linguistic markers
-    def cultural_analysis(self) -> dict:
+    def get_cultural_analysis(self) -> dict:
         return {
             "identity_markers": self.linguistic_analysis.identity_markers()
         }