Update src/extract_features.py

src/extract_features.py

@@ -1,72 +1,72 @@
-import re
-import random
-from collections import Counter, defaultdict
-
-def parse_chat(file_path):
-    pattern = r"(\d{1,2}/\d{1,2}/\d{2,4}), (\d{1,2}:\d{2}) - ([^:]+): (.*)"
-    messages = []
-
-    with open(file_path, "r", encoding="utf-8") as f:
-        for line in f:
-            match = re.match(pattern, line)
-            if match:
-                date, time, sender, text = match.groups()
-                
-                # Normalize names
-                if sender == "ak":
-                    sender = "Aman"
-                elif sender == "Sarah con H":
-                    sender = "Sarah"
-                
-                messages.append({
-                    "date": date,
-                    "time": time,
-                    "sender": sender,
-                    "text": text.strip()
-                })
-    return messages
-
-
-def extract_inside_jokes(messages):
-    funny_candidates = []
-    cute_candidates = []
-    memory_candidates = []
-    phrase_counter = Counter()
-
-    funny_keywords = ["lol", "😂", "🤣", "lmao", "funny", "haha", "hehe","hahaha"]
-    cute_keywords = ["miss", "thank", "sweet", "cute", "proud", "happy","aww","glad"]
-
-    for msg in messages:
-        text = msg["text"].lower()
-
-        # Funny moments
-        if any(k in text for k in funny_keywords):
-            funny_candidates.append(msg["text"])
-
-        # Cute/emotional moments
-        if any(k in text for k in cute_keywords):
-            cute_candidates.append(msg["text"])
-
-        # Memorable random moments
-        if len(msg["text"].split()) > 4:  # skip too short
-            memory_candidates.append(msg["text"])
-
-        # Count repeated words
-        phrase_counter.update(text.split())
-
-    top_words = [w for w, c in phrase_counter.most_common(40)]
-
-    return {
-        "funny": funny_candidates,
-        "cute": cute_candidates,
-        "memories": memory_candidates,
-        "top_words": top_words
-    }
-
-
-def random_memory(messages):
-    """Returns a random meaningful moment."""
-    long_messages = [m["text"] for m in messages if len(m["text"]) > 10]
-    if not long_messages:
-        return "One of your old conversations ❤️"
-    return random.choice(long_messages)
+import re
+import random
+from collections import Counter, defaultdict
+
+def parse_chat(file_path):
+    pattern = r"(\d{1,2}/\d{1,2}/\d{2,4}), (\d{1,2}:\d{2}) - ([^:]+): (.*)"
+    messages = []
+
+    with open(file_path, "r", encoding="utf-8") as f:
+        for line in f:
+            match = re.match(pattern, line)
+            if match:
+                date, time, sender, text = match.groups()
+                
+                # Normalize names
+                if sender == "ak":
+                    sender = "Aman"
+                elif sender == "Sarah con H":
+                    sender = "Sarah"
+                
+                messages.append({
+                    "date": date,
+                    "time": time,
+                    "sender": sender,
+                    "text": text.strip()
+                })
+    return messages
+
+
+def extract_inside_jokes(messages):
+    funny_candidates = []
+    cute_candidates = []
+    memory_candidates = []
+    phrase_counter = Counter()
+
+    funny_keywords = ["lol", "😂", "🤣", "lmao", "funny", "haha", "hehe","hahaha","😅","😁","hahahaha"]
+    cute_keywords = ["miss", "thank", "sweet", "cute", "proud", "happy","aww","glad","nice","kind","brave"]
+
+    for msg in messages:
+        text = msg["text"].lower()
+
+        # Funny moments
+        if any(k in text for k in funny_keywords):
+            funny_candidates.append(msg["text"])
+
+        # Cute/emotional moments
+        if any(k in text for k in cute_keywords):
+            cute_candidates.append(msg["text"])
+
+        # Memorable random moments
+        if len(msg["text"].split()) > 4:  # skip too short
+            memory_candidates.append(msg["text"])
+
+        # Count repeated words
+        phrase_counter.update(text.split())
+
+    top_words = [w for w, c in phrase_counter.most_common(40)]
+
+    return {
+        "funny": funny_candidates,
+        "cute": cute_candidates,
+        "memories": memory_candidates,
+        "top_words": top_words
+    }
+
+
+def random_memory(messages):
+    """Returns a random meaningful moment."""
+    long_messages = [m["text"] for m in messages if len(m["text"]) > 10]
+    if not long_messages:
+        return "One of your old conversations ❤️"
+    return random.choice(long_messages)