Update src/streamlit_app.py

src/streamlit_app.py

@@ -60,9 +60,29 @@ if uploaded_file is not None:
     # Load dataset from uploaded file
     @st.cache_data
     def load_data(uploaded_file):
-        return pd.read_csv(uploaded_file)
+        try:
+            return pd.read_csv(uploaded_file)
+        except Exception as e:
+            st.error(f"Error reading CSV file: {str(e)}")
+            return None
 
     df = load_data(uploaded_file)
+    if df is None:
+        st.stop()
+
+    # Display data preview
+    st.write("**Uploaded Data Preview**")
+    st.dataframe(df.head())
+
+    # Check for required columns
+    required_columns = ['product_category', 'grade', 'ratings', 'supplier_name', 'bidding_amount']
+    missing_columns = [col for col in required_columns if col not in df.columns]
+    if missing_columns:
+        st.error(f"Missing required columns in CSV: {', '.join(missing_columns)}")
+        st.stop()
+
+    # Convert ratings to string for consistency
+    df['ratings'] = df['ratings'].astype(str)
 
     # Filter section
     st.subheader("Filters", anchor="filters")
@@ -79,7 +99,7 @@ if uploaded_file is not None:
             selected_grades = st.multiselect("Grade", grades, default=grades)
 
         with col3:
-            ratings = sorted(df['ratings'].dropna().astype(str).unique())
+            ratings = sorted(df['ratings'].dropna().unique())
             selected_ratings = st.multiselect("Ratings", ratings, default=ratings)
 
         st.markdown('</div>', unsafe_allow_html=True)
@@ -88,9 +108,13 @@ if uploaded_file is not None:
     filtered_df = df[
         (df['product_category'].isin(selected_categories)) &
         (df['grade'].isin(selected_grades)) &
-        (df['ratings'].astype(str).isin(selected_ratings))
+        (df['ratings'].isin(selected_ratings))
     ]
 
+    if filtered_df.empty:
+        st.warning("No data matches the selected filters. Please adjust your filter selections.")
+        st.stop()
+
     # Aggregate by supplier
     seller_data = filtered_df.groupby("supplier_name").agg({
         "bidding_amount": "sum"
@@ -101,26 +125,29 @@ if uploaded_file is not None:
 
     # Overview section
     st.subheader("Overview", anchor="overview")
-    st.write("**Top 5 Suppliers by Total Bidding Amount**")
-    fig_bar = px.bar(
-        top_sellers,
-        x="supplier_name",
-        y="bidding_amount",
-        labels={"supplier_name": "Supplier", "bidding_amount": "Bidding Amount"},
-        title="Top 5 Suppliers",
-        color="supplier_name"
-    )
-    fig_bar.update_layout(showlegend=False)
-    st.plotly_chart(fig_bar, use_container_width=True)
-
-    st.write("**Bidding Distribution (Top 5)**")
-    fig_pie = px.pie(
-        top_sellers,
-        names="supplier_name",
-        values="bidding_amount",
-        title="Bidding Amount by Supplier"
-    )
-    st.plotly_chart(fig_pie, use_container_width=True)
+    if not top_sellers.empty:
+        st.write("**Top 5 Suppliers by Total Bidding Amount**")
+        fig_bar = px.bar(
+            top_sellers,
+            x="supplier_name",
+            y="bidding_amount",
+            labels={"supplier_name": "Supplier", "bidding_amount": "Bidding Amount"},
+            title="Top 5 Suppliers",
+            color="supplier_name"
+        )
+        fig_bar.update_layout(showlegend=False)
+        st.plotly_chart(fig_bar, use_container_width=True)
+
+        st.write("**Bidding Distribution (Top 5)**")
+        fig_pie = px.pie(
+            top_sellers,
+            names="supplier_name",
+            values="bidding_amount",
+            title="Bidding Amount by Supplier"
+        )
+        st.plotly_chart(fig_pie, use_container_width=True)
+    else:
+        st.warning("No supplier data available after filtering.")
 
     total_bidding = seller_data["bidding_amount"].sum()
     st.write(f"**Total Bidding Amount (All Suppliers):** ${total_bidding:,.2f}")
@@ -148,15 +175,22 @@ if uploaded_file is not None:
     # Load Mistral model from Hugging Face
     @st.cache_resource
     def load_mistral_pipeline():
-        model_id = "mistralai/Mistral-7B-Instruct-v0.1"
-        tokenizer = AutoTokenizer.from_pretrained(model_id)
-        model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype="auto")
-        pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512)
-        return pipe
+        try:
+            model_id = "mistralai/Mistral-7B-Instruct-v0.1"
+            tokenizer = AutoTokenizer.from_pretrained(model_id)
+            model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype="auto")
+            pipe = pipeline("text-generation", model=model, tokenizer=tokenizer, max_new_tokens=512)
+            return pipe
+        except Exception as e:
+            st.error(f"Error loading Mistral model: {str(e)}")
+            return None
 
     if user_query:
         with st.spinner("Generating response..."):
             pipe = load_mistral_pipeline()
+            if pipe is None:
+                st.error("Cannot generate response due to model loading failure.")
+                st.stop()
 
             # Prepare prompt
             top_sellers_json = json.dumps(convert_to_serializable(top_sellers), indent=2)
@@ -177,9 +211,10 @@ Question:
 {user_query}
 """
             response = pipe(prompt)[0]['generated_text']
-            # Display only the assistant's answer (trim prompt if echoed)
+            # Extract the answer
+            answer = response[len(prompt):].strip() if response.startswith(prompt) else response.strip()
             st.markdown("**Mistral LLM Response:**")
-            st.write(response.split("Question:")[-1].strip())
+            st.write(answer)
     else:
         st.info("Enter a question to ask Mistral about the bidding data.")
 else: