diff --git a/Home.py b/Home.py
index 016b81f..6c07bfa 100644
--- a/Home.py
+++ b/Home.py
@@ -1,4 +1,7 @@
 import streamlit as st
+import pandas as pd
+import time
+import plotly.express as px
 
 # Configure the page with a modern theme and a custom icon
 st.set_page_config(
@@ -7,10 +10,26 @@
     layout="wide",
     initial_sidebar_state="expanded",
 )
-    # Adding selectboxes for user customization
+
 
 # Sidebar content with advanced layout
 
+st.markdown(
+    """
+    <style>
+    .stApp {
+        background-color: #0F0F0F;
+        color: #FFFFFF;
+    }
+    .sidebar .sidebar-content {
+        background: linear-gradient(45deg, #141E30, #243B55);
+        color: white;
+    }
+    </style>
+    """,
+    unsafe_allow_html=True
+)
+# Sidebar content with user customization options
 with st.sidebar:
     mining_importance = st.selectbox(
         "🔧 **Select Mining Site Importance Level**",
@@ -20,9 +39,14 @@
         "🌐 **Filter Sites by Distance**",
         options=["< 100 light years", "100-500 light years", "500-1000 light years", "> 1000 light years"]
     )
-    outlier_sensitivity = st.selectbox(
+    outlier_sensitivity = st.slider(
         "🔍 **Adjust Sensitivity for Outlier Detection**",
-        options=["Low", "Medium", "High"]
+        min_value=0, max_value=100, value=50
+    )
+    mining_site_types = st.multiselect(
+        "🏔️ **Select Mining Site Types**",
+        options=["Asteroid", "Moon", "Planet", "Comet"],
+        default=["Asteroid", "Planet"]
     )
     st.title("🪐 **Galactic Mining Hub**")
     st.subheader("Deep dive into the infinite cosmic sea!")
@@ -73,6 +97,74 @@
     unsafe_allow_html=True
 )
 
+tab1, tab2, tab3 = st.tabs(["Overview", "Prediction Model", "Visualizations"])
+
+with tab1:
+    st.markdown(
+        """
+        <div style="text-align: center; margin-top: 50px;">
+            <h1>🛰️ <strong>Galactic Mining Hub</strong></h1>
+            <h2><em>Explore, Analyze, and Discover Cosmic Mining Sites with Advanced AI</em></h2>
+        </div>
+        """,
+        unsafe_allow_html=True
+    )
+    st.divider()
+    st.markdown(
+        """
+        **Welcome to the Galactic Mining Hub**, where Machine Learning meets space exploration!
+        """
+    )
+
+with tab2:
+    st.header("🚀 Prediction Model")
+    st.markdown("Engage with predictive analysis to identify the best mining sites.")
+    if st.button("Run Prediction Model"):
+        with st.spinner("Running the model, please wait..."):
+            time.sleep(2)  # Simulate a long-running task
+            st.success("Model prediction completed!")
+
+    # Sample results for demonstration purposes
+    results_df = pd.DataFrame({
+        'Mining Site': ['Site A', 'Site B', 'Site C'],
+        'Predicted Value': [0.85, 0.78, 0.92]
+    })
+    st.write(results_df)
+
+    # Button to download the DataFrame as CSV
+    csv = results_df.to_csv(index=False).encode('utf-8')
+    st.download_button(
+        label="📥 Download Results as CSV",
+        data=csv,
+        file_name='mining_site_predictions.csv',
+        mime='text/csv'
+    )
+
+with tab3:
+    st.header("📈 Cutting-Edge Visualizations")
+    st.markdown("Explore the data through a range of interactive visualizations.")
+
+    # Sample data for visualization
+    data = pd.DataFrame({
+        'Distance (light years)': [50, 150, 300, 750, 1200],
+        'Mining Importance': ['Low', 'Medium', 'High', 'Critical', 'Medium'],
+        'Feasibility Score': [0.2, 0.6, 0.8, 0.95, 0.5]
+    })
+
+    # Interactive scatter plot using Plotly
+    fig = px.scatter(
+        data,
+        x='Distance (light years)',
+        y='Feasibility Score',
+        color='Mining Importance',
+        title="Mining Site Feasibility Analysis",
+        labels={"Feasibility Score": "Feasibility", "Distance (light years)": "Distance"}
+    )
+    st.plotly_chart(fig)
+
+# Footer
+st.markdown("---")
+st.markdown("**Ready to embark on your cosmic journey?** Use the sidebar to navigate through the hub’s capabilities and start your exploration!")
 st.divider()
 
 # Information and interactive section
diff --git a/visualize.py b/visualize.py
index d727505..467fd11 100644
--- a/visualize.py
+++ b/visualize.py
@@ -3,22 +3,35 @@
 import matplotlib.pyplot as plt
 import seaborn as sns
 
+# Set the title and icon of the Streamlit page
 st.set_page_config(page_title="Mining Site Visualization", page_icon="🔍")
 
 def load_data():
-    # Load the dataset
-    data = pd.read_csv("space_mining_dataset.csv")
-    return data
-
+    #Load the dataset from CSV and handle errors if the file is not found.
+    try:
+       data = pd.read_csv("space_mining_dataset.csv")
+       return data
+    except FileNotFoundError:
+        st.error("Dataset file not found. Please upload the correct file.")
+        return pd.DataFrame() 
+    
 def show_visualize_page():
+    #Main function to show the visualization page.
     st.title("Mining Site Visualization")
     st.write("Explore different visualizations to understand the dataset and the impact of user preferences.")
 
     data = load_data()
+    if data.empty:
+        return  
 
     # Check available columns in the dataset
     st.write("Available Columns:", data.columns)
 
+    required_columns = ['iron', 'nickel', 'water_ice', 'other_minerals', 'sustainability_index', 'distance_from_earth']
+    if not all(col in data.columns for col in required_columns):
+        st.error(f"Dataset must contain the following columns: {', '.join(required_columns)}")
+        return
+
     # If 'final_score' does not exist, calculate it based on other features
     if 'final_score' not in data.columns:
         st.write("The 'final_score' column does not exist, calculating it based on weights.")
@@ -52,16 +65,20 @@ def show_visualize_page():
     # Use a more colorful palette for the histogram
     sns.histplot(data[feature], bins=20, kde=True, ax=ax, color='teal')
     ax.set_xlabel(feature)
+    ax.set_title(f"Distribution of {feature}")
     st.pyplot(fig)
 
     # Visualization 2: Pairplot of Selected Features
     st.subheader("Pairplot of Selected Features")
     features = st.multiselect("Select Features for Pairplot", data.columns[1:])  # Exclude non-numeric columns if necessary
     if len(features) > 1:
-        fig, ax = plt.subplots()
+        if len(features) > 4:
+            st.warning("Select up to 4 features for pairplot for better performance.")   
+        else:
+            fig, ax = plt.subplots()
         
         # Customizing pairplot with a color palette
-        pairplot_fig = sns.pairplot(data[features + ['final_score']], diag_kind='kde', hue='final_score', palette="coolwarm")
+        spairplot_fig = sns.pairplot(data[features + ['final_score']], diag_kind='kde', hue='final_score', palette="coolwarm")
         st.pyplot(pairplot_fig.fig)
     else:
         st.write("Please select more than one feature.")
@@ -73,9 +90,9 @@ def show_visualize_page():
     corr_matrix = numeric_data.corr()
     
     # Displaying the heatmap
-    fig, ax = plt.subplots()
+    fig, ax = plt.subplots(figsize=(10, 8))
     sns.heatmap(corr_matrix, annot=True, fmt=".2f", cmap="coolwarm", linewidths=0.5, ax=ax)
-    ax.set_title("Correlation Heatmap")
+    ax.set_title("Correlation Heatmap", fontsize=16)
     st.pyplot(fig)
 
     # Visualization 4: Boxplot of Feature Distribution by Category