Spaces:
Running
Running
| import streamlit as st | |
| import requests | |
| import pandas as pd | |
| import tempfile | |
| import os | |
| import plotly.express as px | |
| from datetime import datetime | |
| import uuid | |
| # Simulated in-memory storage for churn log | |
| if "churn_log" not in st.session_state: | |
| st.session_state.churn_log = [] | |
| st.set_page_config(page_title="ChurnSight AI", page_icon="🧠", layout="wide") | |
| if os.path.exists("logo.png"): | |
| st.image("logo.png", width=180) | |
| # Session state setup | |
| defaults = { | |
| "review": "", | |
| "dark_mode": False, | |
| "intelligence_mode": True, | |
| "trigger_example_analysis": False, | |
| "last_response": None, | |
| "followup_answer": None, | |
| "use_aspects": False, | |
| "use_explain_bulk": False | |
| } | |
| for k, v in defaults.items(): | |
| if k not in st.session_state: | |
| st.session_state[k] = v | |
| # Dark mode styling | |
| if st.session_state.dark_mode: | |
| st.markdown(""" | |
| <style> | |
| html, body, [class*="st-"] { | |
| background-color: #121212; | |
| color: #f5f5f5; | |
| } | |
| </style> | |
| """, unsafe_allow_html=True) | |
| # Sidebar config | |
| with st.sidebar: | |
| st.header("⚙️ PM Config") | |
| st.session_state.dark_mode = st.toggle("🌙 Dark Mode", value=st.session_state.dark_mode) | |
| st.session_state.intelligence_mode = st.toggle("🧠 Intelligence Mode", value=st.session_state.intelligence_mode) | |
| api_token = st.text_input("🔐 API Token", value="my-secret-key", type="password") | |
| if api_token.strip() == "my-secret-key": | |
| st.warning("🧪 Demo Mode — Not all features are active. Add your API token to unlock full features.") | |
| backend_url = st.text_input("🌐 Backend URL", value="http://localhost:8000") | |
| sentiment_model = st.selectbox("📊 Sentiment Model", ["Auto-detect", "distilbert-base-uncased-finetuned-sst-2-english"]) | |
| industry = st.selectbox("🏭 Industry", ["Auto-detect", "Generic", "E-commerce", "Healthcare", "Education"]) | |
| product_category = st.selectbox("🧩 Product Category", ["Auto-detect", "General", "Mobile Devices", "Laptops"]) | |
| st.session_state.use_aspects = st.checkbox("🔍 Detect Pain Points", value=st.session_state.get("use_aspects", False)) | |
| st.session_state.use_explain_bulk = st.checkbox("🧠 Generate PM Insight (Bulk)", value=st.session_state.get("use_explain_bulk", False)) | |
| verbosity = st.radio("🗣️ Response Style", ["Brief", "Detailed"]) | |
| tab1, tab2 = st.tabs(["🧠 Analyze Review", "📚 Bulk Reviews"]) | |
| # === SINGLE REVIEW ANALYSIS === | |
| with tab1: | |
| st.title("📊 ChurnSight AI — Product Feedback Assistant") | |
| st.markdown("Analyze feedback to detect churn risk, extract pain points, and support product decisions.") | |
| review = st.text_area("📝 Enter Customer Feedback", value=st.session_state.review, height=180) | |
| st.session_state.review = review | |
| analyze = False | |
| col1, col2, col3 = st.columns(3) | |
| with col1: | |
| analyze = st.button("🔍 Analyze") | |
| with col2: | |
| if st.button("🎲 Example"): | |
| st.session_state.review = ( | |
| "The app crashes every time I try to checkout. It's so slow and unresponsive. " | |
| "Customer support never replied. I'm switching to another brand." | |
| ) | |
| st.session_state.trigger_example_analysis = True | |
| st.rerun() | |
| with col3: | |
| if st.button("🧹 Clear"): | |
| for key in ["review", "last_response", "followup_answer"]: | |
| st.session_state[key] = "" | |
| st.rerun() | |
| if st.session_state.review and (analyze or st.session_state.get("trigger_example_analysis")): | |
| with st.spinner("Analyzing feedback..."): | |
| try: | |
| model_used = None if sentiment_model == "Auto-detect" else sentiment_model | |
| payload = { | |
| "text": st.session_state.review, | |
| "model": model_used or "distilbert-base-uncased-finetuned-sst-2-english", | |
| "industry": industry, | |
| "product_category": product_category, | |
| "verbosity": verbosity, | |
| "aspects": st.session_state.use_aspects, | |
| "intelligence": st.session_state.get("intelligence_mode", False) | |
| } | |
| headers = {"x-api-key": st.session_state.get("api_token", "my-secret-key")} | |
| res = requests.post(f"{backend_url}/analyze/", json=payload, headers=headers) | |
| if res.ok: | |
| st.session_state.last_response = res.json() | |
| else: | |
| try: | |
| err_detail = res.json().get("detail", "No detail provided.") | |
| except Exception: | |
| err_detail = res.text | |
| st.error(f"❌ Backend Error ({res.status_code}): {err_detail}") | |
| except Exception as e: | |
| st.error(f"🚫 Exception: {e}") | |
| data = st.session_state.last_response | |
| if data: | |
| st.subheader("📌 PM Insight Summary") | |
| st.info(data["summary"]) | |
| st.markdown(f"**Industry:** `{data['industry']}` | **Category:** `{data['product_category']}` | **Device:** Web") | |
| st.metric("📊 Sentiment", data["sentiment"]["label"], delta=f"{data['sentiment']['score']:.2%}") | |
| st.progress(data["sentiment"]["score"]) | |
| st.info(f"💢 Emotion: {data['emotion']}") | |
| if "churn_risk" in data: | |
| risk = data["churn_risk"] | |
| color = "🔴" if risk == "High Risk" else "🟢" | |
| st.metric("🚨 Churn Risk", f"{color} {risk}") | |
| if st.session_state.use_aspects: | |
| if data.get("pain_points"): | |
| st.error("🔍 Pain Points: " + ", ".join(data["pain_points"])) | |
| else: | |
| st.info("✅ No specific pain points were detected.") | |
| try: | |
| st.session_state.churn_log.append({ | |
| "timestamp": datetime.now(), | |
| "product": data.get("product_category", "General"), | |
| "churn_risk": data.get("churn_risk", "Unknown"), | |
| "session_id": str(uuid.uuid4()) | |
| }) | |
| if len(st.session_state.churn_log) > 1000: | |
| st.session_state.churn_log = st.session_state.churn_log[-1000:] | |
| except Exception as e: | |
| st.warning(f"🧪 Logging failed: {e}") | |
| st.markdown("### 🔁 Ask a Follow-Up") | |
| sentiment = data["sentiment"]["label"].lower() | |
| churn = data.get("churn_risk", "") | |
| pain = data.get("pain_points", []) | |
| if sentiment == "positive" and churn == "Low Risk": | |
| suggestions = [ | |
| "What features impressed the user?", | |
| "Would they recommend the product?", | |
| "What benefits did they mention?", | |
| "What made their experience smooth?" | |
| ] | |
| elif churn == "High Risk": | |
| suggestions = [ | |
| "What made the user upset?", | |
| "Is this user likely to churn?", | |
| "What were the major complaints?", | |
| "What could improve their experience?" | |
| ] | |
| else: | |
| suggestions = [ | |
| "What are the key takeaways?", | |
| "Is there any concern raised?", | |
| "Did the user express dissatisfaction?", | |
| "Is this feedback actionable?" | |
| ] | |
| selected_q = st.selectbox("💡 Suggested Questions", ["Type your own..."] + suggestions) | |
| q_input = st.text_input("🔍 Your Question") if selected_q == "Type your own..." else selected_q | |
| if q_input: | |
| try: | |
| follow_payload = { | |
| "text": st.session_state.review, | |
| "question": q_input, | |
| "verbosity": verbosity | |
| } | |
| headers = {"x-api-key": api_token} | |
| res = requests.post(f"{backend_url}/followup/", json=follow_payload, headers=headers) | |
| if res.ok: | |
| st.success(res.json().get("answer")) | |
| else: | |
| try: | |
| err_detail = res.json().get("detail", "No detail provided.") | |
| except Exception: | |
| err_detail = res.text | |
| st.error(f"❌ Follow-up API Error ({res.status_code}): {err_detail}") | |
| except Exception as e: | |
| st.error(f"⚠️ Follow-up error: {e}") | |
| if st.checkbox("📊 Show Churn Risk Trends"): | |
| try: | |
| df = pd.DataFrame(st.session_state.churn_log) | |
| df["date"] = pd.to_datetime(df["timestamp"]).dt.date | |
| trend = df.groupby(["date", "churn_risk"]).size().unstack(fill_value=0).reset_index() | |
| y_columns = [col for col in trend.columns if col != "date"] | |
| st.markdown("#### 📅 Daily Churn Trend") | |
| fig = px.bar(trend, x="date", y=y_columns, barmode="group") | |
| st.plotly_chart(fig, use_container_width=True) | |
| st.download_button("⬇️ Export Trend CSV", trend.to_csv(index=False), "churn_trend.csv") | |
| except Exception as e: | |
| st.error(f"Trend error: {e}") | |
| # === BULK REVIEW ANALYSIS === | |
| with tab2: | |
| st.title("📚 Bulk Feedback Analysis") | |
| st.markdown("#### 📥 Upload CSV or Paste Reviews") | |
| uploaded_file = st.file_uploader("Upload a CSV with a 'review' column", type=["csv"]) | |
| bulk_input = st.text_area("Or paste multiple reviews (one per line)", height=180) | |
| reviews = [] | |
| if uploaded_file is not None: | |
| try: | |
| df_csv = pd.read_csv(uploaded_file) | |
| if "review" in df_csv.columns: | |
| reviews = df_csv["review"].dropna().astype(str).tolist() | |
| else: | |
| st.warning("CSV must contain a 'review' column.") | |
| except Exception as e: | |
| st.error(f"CSV error: {e}") | |
| elif bulk_input.strip(): | |
| reviews = [line.strip() for line in bulk_input.split("\\n") if line.strip()] | |
| st.markdown("#### 🧠 Bulk Analysis Configuration") | |
| explain_bulk = st.checkbox("🧠 Generate Explanations", value=st.session_state.get("use_explain_bulk", False)) | |
| enable_followups = st.checkbox("💬 Generate Follow-Up Q&A", value=True) | |
| if st.button("🚀 Analyze Bulk") and reviews: | |
| payload = { | |
| "reviews": reviews, | |
| "model": "distilbert-base-uncased-finetuned-sst-2-english" if sentiment_model == "Auto-detect" else sentiment_model, | |
| "industry": None, | |
| "product_category": None, | |
| "device": None, | |
| "aspects": st.session_state.use_aspects, | |
| "intelligence": st.session_state.intelligence_mode, | |
| "explain_bulk": explain_bulk, | |
| "follow_up": [["What is the issue here?", "What could be improved?"]] * len(reviews) if enable_followups else None | |
| } | |
| try: | |
| res = requests.post(f"{backend_url}/bulk/?token={api_token}", json=payload) | |
| if res.ok: | |
| results = res.json().get("results", []) | |
| df = pd.DataFrame(results) | |
| st.dataframe(df) | |
| if any("follow_up" in r for r in results): | |
| st.markdown("### 💬 Follow-Up Answers") | |
| for r in results: | |
| st.markdown(f"**Review:** {r['review']}") | |
| if isinstance(r.get("follow_up"), list): | |
| for ans in r["follow_up"]: | |
| st.info(ans) | |
| elif "follow_up" in r: | |
| st.info(r["follow_up"]) | |
| if "churn_risk" in df.columns: | |
| st.markdown("### 📈 Churn Risk Chart") | |
| churn_summary = df["churn_risk"].value_counts().reset_index() | |
| churn_summary.columns = ["Churn Risk", "Count"] | |
| fig = px.pie(churn_summary, names="Churn Risk", values="Count", title="Churn Risk Distribution") | |
| st.plotly_chart(fig, use_container_width=True) | |
| st.download_button("⬇️ Export Results CSV", df.to_csv(index=False), "bulk_results.csv") | |
| else: | |
| try: | |
| err_detail = res.json().get("detail", "No detail provided.") | |
| except Exception: | |
| err_detail = res.text | |
| st.error(f"❌ Bulk API Error ({res.status_code}): {err_detail}") | |
| except Exception as e: | |
| st.error(f"Bulk analysis failed: {e}") | |