Update app.py

app.py

@@ -5,10 +5,14 @@ import os
 import requests
 from sklearn.ensemble import RandomForestClassifier
 from sklearn.preprocessing import LabelEncoder
-from nltk.sentiment import SentimentIntensityAnalyzer
 import nltk
+from nltk.sentiment import SentimentIntensityAnalyzer
 
-nltk.download("vader_lexicon")
+# =========================
+# FIX NLTK (VERY IMPORTANT)
+# =========================
+nltk.download('vader_lexicon')
+sia = SentimentIntensityAnalyzer()
 
 # =========================
 # LOAD DATA
@@ -18,7 +22,7 @@ bookings = pd.read_csv("bookings_small.csv")
 X = bookings.drop(columns=["is_canceled"])
 y = bookings["is_canceled"]
 
-# Encode categoricals
+# Encode categorical variables
 encoders = {}
 for col in X.select_dtypes(include="object").columns:
     le = LabelEncoder()
@@ -29,79 +33,96 @@ for col in X.select_dtypes(include="object").columns:
 model = RandomForestClassifier(n_estimators=100, max_depth=10)
 model.fit(X, y)
 
-# Sentiment model
-sia = SentimentIntensityAnalyzer()
-
-# Secret webhook
+# =========================
+# SECRET WEBHOOK
+# =========================
 WEBHOOK_URL = os.getenv("N8N_WEBHOOK_URL")
 
 # =========================
-# BOOKING PREDICTION
+# BOOKING FUNCTION
 # =========================
 def predict_booking(hotel, lead_time, adr, total_nights, total_guests):
+    try:
+        lead_time = int(lead_time)
+        total_nights = int(total_nights)
+        total_guests = int(total_guests)
+        adr = float(adr)
+
+        input_dict = {
+            "hotel": hotel,
+            "lead_time": lead_time,
+            "adr": adr,
+            "total_nights": total_nights,
+            "total_guests": total_guests,
+
+            "market_segment": "Online",
+            "deposit_type": "No Deposit",
+            "is_repeated_guest": 0,
+            "previous_cancellations": 0,
+            "total_of_special_requests": 1,
+
+            "seasonality_index": 1.0,
+            "competitor_price_index": 1.0,
+            "service_quality_proxy": 50,
+            "booking_value_score": adr * total_nights * max(total_guests,1)
+        }
+
+        df_input = pd.DataFrame([input_dict])
+
+        for col, le in encoders.items():
+            if col in df_input:
+                df_input[col] = le.transform(df_input[col].astype(str))
+
+        for col in X.columns:
+            if col not in df_input:
+                df_input[col] = 0
+
+        df_input = df_input[X.columns]
+
+        prob = model.predict_proba(df_input)[0][1]
+
+        if prob > 0.6:
+            risk = "🔴 HIGH RISK"
+            rec = "Reduce pricing and investigate risk"
+        elif prob > 0.3:
+            risk = "🟠 MEDIUM RISK"
+            rec = "Monitor demand"
+        else:
+            risk = "🟢 LOW RISK"
+            rec = "Safe to increase pricing"
 
-    input_dict = {
-        "hotel": hotel,
-        "lead_time": lead_time,
-        "adr": adr,
-        "total_nights": total_nights,
-        "total_guests": total_guests,
-
-        # Auto-fill features
-        "market_segment": "Online",
-        "deposit_type": "No Deposit",
-        "is_repeated_guest": 0,
-        "previous_cancellations": 0,
-        "total_of_special_requests": 1,
-
-        "seasonality_index": 1.0,
-        "competitor_price_index": 1.0,
-        "service_quality_proxy": 50,
-        "booking_value_score": adr * total_nights * max(total_guests,1)
-    }
-
-    df_input = pd.DataFrame([input_dict])
-
-    for col, le in encoders.items():
-        if col in df_input:
-            df_input[col] = le.transform(df_input[col].astype(str))
-
-    for col in X.columns:
-        if col not in df_input:
-            df_input[col] = 0
-
-    df_input = df_input[X.columns]
+        return prob, risk, rec, input_dict
 
-    prob = model.predict_proba(df_input)[0][1]
+    except Exception as e:
+        return 0, "ERROR", str(e), {}
 
-    if prob > 0.6:
-        risk = "🔴 HIGH RISK"
-        rec = "Reduce pricing and investigate booking risk"
-    elif prob > 0.3:
-        risk = "🟠 MEDIUM RISK"
-        rec = "Monitor demand and pricing"
-    else:
-        risk = "🟢 LOW RISK"
-        rec = "Safe to increase pricing"
+# =========================
+# SENTIMENT FUNCTION (FIXED)
+# =========================
+def run_sentiment(text):
+    try:
+        score = sia.polarity_scores(text)["compound"]
 
-    return prob, risk, rec, input_dict
+        if score > 0.2:
+            label = "🟢 Positive"
+        elif score < -0.2:
+            label = "🔴 Negative"
+        else:
+            label = "🟡 Neutral"
 
+        return f"""
+### 💬 Sentiment Analysis
 
-# =========================
-# SENTIMENT ANALYSIS
-# =========================
-def analyze_review(text):
-    score = sia.polarity_scores(text)["compound"]
+**Score:** {score:.2f}
 
-    if score > 0.2:
-        label = "🟢 Positive"
-    elif score < -0.2:
-        label = "🔴 Negative"
-    else:
-        label = "🟡 Neutral"
+**Label:** {label}
 
-    return score, label
+**Insight:**  
+{"🚨 Negative feedback → improve service" if "Negative" in label else "✅ Customer perception supports pricing"}
+""", {"sentiment": score, "label": label}
 
+    except Exception as e:
+        return f"❌ ERROR: {str(e)}", {}
 
 # =========================
 # SEND TO N8N
@@ -140,7 +161,6 @@ def send_to_n8n(source_tab, payload):
     except Exception as e:
         return f"❌ Request failed: {str(e)}"
 
-
 # =========================
 # UI
 # =========================
@@ -168,7 +188,7 @@ with gr.Blocks() as demo:
                 hotel, lead_time, adr, total_nights, total_guests
             )
 
-            text = f"""
+            return f"""
 ### 📊 Booking Analysis
 
 **Cancellation Probability:** {prob:.2%}
@@ -177,13 +197,14 @@ with gr.Blocks() as demo:
 
 **Recommendation:**  
 {rec}
-"""
-            return text, payload
+""", payload
 
-        gr.Button("🔍 Analyze Booking").click(
-            run_booking,
-            [hotel, lead_time, adr, total_nights, total_guests],
-            [output, state_payload]
+        analyze_btn = gr.Button("🔍 Analyze Booking")
+
+        analyze_btn.click(
+            fn=run_booking,
+            inputs=[hotel, lead_time, adr, total_nights, total_guests],
+            outputs=[output, state_payload],
         )
 
         send_output = gr.Markdown()
@@ -204,24 +225,12 @@ with gr.Blocks() as demo:
         sentiment_output = gr.Markdown()
         state_review = gr.State()
 
-        def run_sentiment(text):
-            score, label = analyze_review(text)
-
-            return f"""
-### 💬 Sentiment Analysis
-
-**Score:** {score:.2f}
-
-**Label:** {label}
-
-**Insight:**  
-{"Improve service before increasing prices" if "Negative" in label else "Customer perception supports pricing"}
-""", {"sentiment": score, "label": label}
+        analyze_btn2 = gr.Button("🔍 Analyze Sentiment")
 
-        gr.Button("🔍 Analyze Sentiment").click(
-            run_sentiment,
-            review,
-            [sentiment_output, state_review]
+        analyze_btn2.click(
+            fn=run_sentiment,
+            inputs=review,
+            outputs=[sentiment_output, state_review]
         )
 
         send_output2 = gr.Markdown()