Create app.py

app.py

@@ -0,0 +1,93 @@
+import streamlit as st
+import pandas as pd
+from collections import Counter
+import numpy as np
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+
+class SmartBubble:
+    def __init__(self):
+        self.keywords = Counter()
+        self.liked_content = []
+        self.vectorizer = TfidfVectorizer(stop_words='english')
+    
+    def absorb_content(self, content, is_liked=True):
+        """Absorb content and extract its key features"""
+        # Extract words and update keyword counter
+        words = content.lower().split()
+        if is_liked:
+            self.keywords.update(words)
+            self.liked_content.append(content)
+    
+    def get_similarity_score(self, new_content):
+        """Calculate similarity between new content and liked content"""
+        if not self.liked_content:
+            return 0
+        
+        # Combine liked content into one document
+        all_content = self.liked_content + [new_content]
+        
+        # Calculate TF-IDF vectors
+        tfidf_matrix = self.vectorizer.fit_transform(all_content)
+        
+        # Calculate average similarity with all liked content
+        similarities = cosine_similarity(
+            tfidf_matrix[-1:],  # New content vector
+            tfidf_matrix[:-1]   # Liked content vectors
+        )
+        return float(similarities.mean())
+
+# Streamlit app
+st.title("Smart Bubble Protocol")
+
+# Initialize session state
+if 'smart_bubble' not in st.session_state:
+    st.session_state.smart_bubble = SmartBubble()
+if 'content_list' not in st.session_state:
+    st.session_state.content_list = []
+
+# Input section
+st.header("Add New Content")
+new_content = st.text_area("Enter content to analyze:")
+if st.button("Add to Content List"):
+    if new_content:
+        st.session_state.content_list.append(new_content)
+        st.success("Content added!")
+
+# Like/Training section
+st.header("Train Your Bubble")
+for i, content in enumerate(st.session_state.content_list):
+    col1, col2 = st.columns([4, 1])
+    with col1:
+        st.text_area(f"Content {i+1}", content, height=100, key=f"content_{i}")
+    with col2:
+        if st.button("Like", key=f"like_{i}"):
+            st.session_state.smart_bubble.absorb_content(content)
+            st.success("Content absorbed into bubble!")
+
+# Analysis section
+st.header("Smart Bubble Analysis")
+if st.session_state.content_list:
+    analysis_data = []
+    for content in st.session_state.content_list:
+        score = st.session_state.smart_bubble.get_similarity_score(content)
+        keywords = " ".join(word for word, _ in 
+            Counter(content.lower().split()).most_common(5))
+        analysis_data.append({
+            'Content Preview': content[:100] + "...",
+            'Similarity Score': f"{score:.2%}",
+            'Top Keywords': keywords
+        })
+    
+    # Create and display analysis DataFrame
+    df = pd.DataFrame(analysis_data)
+    df = df.sort_values('Similarity Score', ascending=False)
+    st.dataframe(df)
+
+# Bubble insights
+st.header("Bubble Insights")
+if st.session_state.smart_bubble.keywords:
+    top_keywords = st.session_state.smart_bubble.keywords.most_common(10)
+    st.write("Top keywords in your bubble:")
+    for word, count in top_keywords:
+        st.write(f"- {word}: {count}")