Update app.py

app.py

@@ -7,87 +7,99 @@ from groq import Groq
 from typing import List
 
 # ---- Setup Groq Client ---- #
-client = Groq(api_key=("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"))
+client = Groq(api_key=os.getenv("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"))
 
-# ---- File Upload ---- #
-st.title("🚦 Real-Time Traffic Optimization using RAG + Groq")
-st.subheader("Upload Traffic Data (CSV)")
-
-# Upload CSV file
-uploaded_file = st.file_uploader("Choose a CSV file", type="csv")
-
-if uploaded_file is not None:
-    # Read the CSV file into a DataFrame
-    df = pd.read_csv(uploaded_file)
-    
-    # ---- Utility: Summarize traffic data to context ---- #
-    def summarize_traffic_data(df: pd.DataFrame) -> List[str]:
-        summaries = []
-        for index, row in df.iterrows():
-            summary = (
-                f"On {row['Date']} ({row['Day of the week']}) at {row['Time']}, "
-                f"there were {row['CarCount']} cars, {row['BikeCount']} bikes, "
-                f"{row['BusCount']} buses, and {row['TruckCount']} trucks. "
-                f"Total traffic: {row['Total']}. Situation: {row['Traffic Situation']}."
-            )
-            summaries.append(summary)
-        return summaries
-
-    # ---- Prompt Constructor ---- #
-    def generate_traffic_prompt(user_query: str, context: List[str]) -> str:
-        context_text = "\n".join(context)
-        prompt = f"""
-    Context:
-    {context_text}
-
-    User Query:
-    {user_query}
-
-    Based on the context above, generate a traffic optimization strategy.
-    """
-        return prompt
-
-    # ---- Groq Query ---- #
-    def get_optimization_recommendation(prompt: str) -> str:
-        response = client.chat.completions.create(
-            messages=[{"role": "user", "content": prompt}],
-            model="llama-3-70b-versatile",
-            stream=False
+# ---- Load and Hardcode CSV Data ---- #
+@st.cache_data
+def load_data():
+    return pd.read_csv("traffic_data.csv")  # Replace with your file path if needed
+
+df = load_data()
+
+# ---- Utility: Summarize traffic data to context ---- #
+def summarize_traffic_data(df: pd.DataFrame) -> List[str]:
+    summaries = []
+    for index, row in df.iterrows():
+        summary = (
+            f"On {row['Date']} ({row['Day of the week']}) at {row['Time']}, "
+            f"there were {row['CarCount']} cars, {row['BikeCount']} bikes, "
+            f"{row['BusCount']} buses, and {row['TruckCount']} trucks. "
+            f"Total traffic: {row['Total']}. Situation: {row['Traffic Situation']}."
         )
-        return response.choices[0].message.content
-
-    # ---- Data Visualization ---- #
-    st.subheader("📊 Traffic Data Visualization")
-    st.dataframe(df.head(10))
-
-    st.write("### Traffic Volume Over Time")
-    fig, ax = plt.subplots(figsize=(10, 4))
-    df['Timestamp'] = pd.to_datetime(df['Date'] + ' ' + df['Time'])
-    df_sorted = df.sort_values("Timestamp")
-    ax.plot(df_sorted['Timestamp'], df_sorted['Total'], marker='o')
-    ax.set_xlabel("Time")
-    ax.set_ylabel("Total Traffic Volume")
-    ax.set_title("Traffic Volume Over Time")
-    st.pyplot(fig)
-
-    st.write("### Vehicle Count Distribution")
-    fig2, ax2 = plt.subplots(figsize=(10, 4))
-    df[['CarCount', 'BikeCount', 'BusCount', 'TruckCount']].plot(kind='box', ax=ax2)
-    ax2.set_title("Distribution of Vehicle Counts")
-    st.pyplot(fig2)
-
-    # ---- User Query and RAG Output ---- #
-    user_query = st.text_area("Enter your traffic-related query")
-    if user_query:
-        with st.spinner("Processing traffic data and generating strategy..."):
-            traffic_context = summarize_traffic_data(df)
-            prompt = generate_traffic_prompt(user_query, traffic_context[:10])  # Limit to first 10 rows
-            result = get_optimization_recommendation(prompt)
-            st.success("Strategy Generated:")
-            st.write(result)
-
-else:
-    st.warning("Please upload a CSV file to proceed.")
+        summaries.append(summary)
+    return summaries
+
+# ---- Prompt Constructor ---- #
+def generate_traffic_prompt(user_query: str, context: List[str]) -> str:
+    context_text = "\n".join(context)
+    prompt = f"""
+Context:
+{context_text}
+
+User Query:
+{user_query}
+
+Based on the context above, generate a traffic optimization strategy.
+"""
+    return prompt
+
+# ---- Groq Query ---- #
+def get_optimization_recommendation(prompt: str) -> str:
+    response = client.chat.completions.create(
+        messages=[{"role": "user", "content": prompt}],
+        model="llama-3-70b-versatile",
+        stream=False
+    )
+    return response.choices[0].message.content
+
+# ---- Streamlit App ---- #
+st.set_page_config(page_title="🚦 Traffic Optimization RAG App")
+st.title("🚦 Real-Time Traffic Optimization using RAG + Groq")
+
+# ---- Data Visualization ---- #
+st.subheader("📊 Traffic Data Visualization")
+st.dataframe(df.head(10))
+
+# Handle 'Date' and 'Time' columns
+df['Date'] = df['Date'].astype(str)
+df['Time'] = df['Time'].astype(str)
+
+# Handle missing values if any
+df['Date'] = df['Date'].fillna('')
+df['Time'] = df['Time'].fillna('')
+
+# Combine 'Date' and 'Time' to create a timestamp
+df['Timestamp'] = pd.to_datetime(df['Date'] + ' ' + df['Time'], errors='coerce')  # `errors='coerce'` will turn invalid dates into NaT
+
+# Check if 'Timestamp' is created successfully
+st.write(f"Timestamp column created successfully: {df['Timestamp'].head()}")
+
+# ---- Traffic Volume Over Time ---- #
+st.write("### Traffic Volume Over Time")
+fig, ax = plt.subplots(figsize=(10, 4))
+df_sorted = df.sort_values("Timestamp")
+ax.plot(df_sorted['Timestamp'], df_sorted['Total'], marker='o')
+ax.set_xlabel("Time")
+ax.set_ylabel("Total Traffic Volume")
+ax.set_title("Traffic Volume Over Time")
+st.pyplot(fig)
+
+# ---- Vehicle Count Distribution ---- #
+st.write("### Vehicle Count Distribution")
+fig2, ax2 = plt.subplots(figsize=(10, 4))
+df[['CarCount', 'BikeCount', 'BusCount', 'TruckCount']].plot(kind='box', ax=ax2)
+ax2.set_title("Distribution of Vehicle Counts")
+st.pyplot(fig2)
+
+# ---- User Query and RAG Output ---- #
+user_query = st.text_area("Enter your traffic-related query")
+if user_query:
+    with st.spinner("Processing traffic data and generating strategy..."):
+        traffic_context = summarize_traffic_data(df)
+        prompt = generate_traffic_prompt(user_query, traffic_context[:10])  # Limit to first 10 rows
+        result = get_optimization_recommendation(prompt)
+        st.success("Strategy Generated:")
+        st.write(result)
 
 st.markdown("---")
 st.caption("🔁 This app analyzes traffic data using RAG + Groq and visualizes traffic patterns.")