Create app.py

app.py

@@ -0,0 +1,128 @@
+# app.py
+import pandas as pd
+import gradio as gr
+import re
+from sentence_transformers import SentenceTransformer
+from sklearn.neighbors import NearestNeighbors
+
+# -------------------------------
+# Load dataset
+# -------------------------------
+df = pd.read_csv("food_order_cleaned.csv")
+df['rating'] = pd.to_numeric(df['rating'], errors='coerce')
+df['search_text'] = df['restaurant_name'].astype(str) + " | " + df['cuisine_type'].astype(str) + " | " + df['rating'].astype(str)
+
+# -------------------------------
+# Rule-based functions
+# -------------------------------
+def find_by_cuisine(cuisine, limit=10):
+    mask = df['cuisine_type'].str.strip().str.lower() == cuisine.strip().lower()
+    cols = ['restaurant_name', 'cuisine_type', 'cost_of_the_order', 'rating']
+    return df.loc[mask, cols].head(limit)
+
+def best_rated_by_cuisine(cuisine, top_n=10):
+    mask = df['cuisine_type'].str.strip().str.lower() == cuisine.strip().lower()
+    subset = df[mask].dropna(subset=['rating']).sort_values('rating', ascending=False)
+    cols = ['restaurant_name', 'cuisine_type', 'cost_of_the_order', 'rating']
+    return subset[cols].head(top_n)
+
+def cheapest_high_rated(max_cost=None, min_rating=4.0, top_n=10):
+    subset = df.dropna(subset=['rating'])
+    subset = subset[subset['rating'] >= min_rating]
+    if max_cost is not None:
+        subset = subset[subset['cost_of_the_order'] <= max_cost]
+    subset = subset.sort_values('cost_of_the_order')
+    cols = ['restaurant_name', 'cuisine_type', 'cost_of_the_order', 'rating']
+    return subset[cols].head(top_n)
+
+def personalized_recall(customer_id, day):
+    mask = (df['customer_id'].astype(str) == str(customer_id)) & \
+           (df['day_of_the_week'].str.strip().str.lower() == day.strip().lower())
+    cols = ['order_id', 'restaurant_name', 'cuisine_type', 'cost_of_the_order', 'rating', 'day_of_the_week']
+    return df.loc[mask, cols]
+
+# -------------------------------
+# Semantic Search
+# -------------------------------
+model = SentenceTransformer('all-MiniLM-L6-v2')
+corpus = df['search_text'].tolist()
+corpus_embeddings = model.encode(corpus, show_progress_bar=True)
+nn = NearestNeighbors(n_neighbors=10, metric='cosine').fit(corpus_embeddings)
+
+def semantic_search(query, k=5):
+    q_emb = model.encode([query])
+    dists, idxs = nn.kneighbors(q_emb, n_neighbors=k)
+    results = df.iloc[idxs[0]].copy()
+    results['score'] = 1 - dists[0]
+    cols = ['restaurant_name', 'cuisine_type', 'cost_of_the_order', 'rating', 'score']
+    return results[cols]
+
+# -------------------------------
+# Combined Chat Handler
+# -------------------------------
+def handle_query(message, customer_id="", history=[]):
+    text = message.strip().lower()
+    
+    # Rule-Based: Specific Recommendation
+    if 'find' in text and 'restaurant' in text:
+        known = set(df['cuisine_type'].str.strip().str.lower().unique())
+        words = text.split()
+        found = [w for w in words if w in known]
+        if found:
+            res = find_by_cuisine(found[0])
+            return res.to_html(index=False)
+        else:
+            return semantic_search(message).to_html(index=False)
+    
+    # Rule-Based: Best Rated
+    if 'best' in text and ('place' in text or 'best-rated' in text):
+        known = set(df['cuisine_type'].str.strip().str.lower().unique())
+        words = text.split()
+        found = [w for w in words if w in known]
+        if found:
+            res = best_rated_by_cuisine(found[0])
+            return res.to_html(index=False)
+        else:
+            return semantic_search(message).to_html(index=False)
+    
+    # Rule-Based: Cheapest / Value Search
+    if 'cheapest' in text or 'cheap' in text or 'value' in text:
+        res = cheapest_high_rated(min_rating=4.0, top_n=10)
+        return res.to_html(index=False)
+    
+    # Rule-Based: Personalized Recall
+    if 'what did i order' in text:
+        day_match = re.search(r'on (\w+)', text)
+        day = day_match.group(1) if day_match else ''
+        if customer_id == '':
+            return "Please enter your customer_id in the input box."
+        if day == '':
+            return "Please specify the day, e.g. 'on Weekend'."
+        res = personalized_recall(customer_id, day)
+        if res.empty:
+            return "No orders found for that customer/day."
+        return res.to_html(index=False)
+    
+    # Fallback: Semantic Search
+    return semantic_search(message).to_html(index=False)
+
+# -------------------------------
+# Gradio Chatbot Interface
+# -------------------------------
+def chat_reply(history, message, customer_id):
+    reply = handle_query(message, customer_id)
+    history.append((message, reply))
+    return history, ""
+
+with gr.Blocks(title="Restaurant Guide Chatbot") as demo:
+    gr.Markdown("## Restaurant Guide Chatbot\nAsk queries like:\n- Find me a Thai restaurant\n- What are the best Italian places?\n- Show me the cheapest highly-rated places\n- What did I order on Weekend? (enter customer_id)")
+    
+    chatbot = gr.Chatbot()
+    with gr.Row():
+        user_msg = gr.Textbox(placeholder="Type your message here...")
+        cust_id = gr.Textbox(label="Customer ID (optional)")
+        send = gr.Button("Send")
+    
+    send.click(chat_reply, inputs=[chatbot, user_msg, cust_id], outputs=[chatbot, user_msg])
+
+demo.launch()