Update app.py

app.py

@@ -4,18 +4,26 @@ from sklearn.cluster import KMeans
 from folium.plugins import MarkerCluster
 import requests
 from io import BytesIO
-import streamlit as st
 
-# Load data from Excel
+# Load data from Excel URL
 def load_data(url):
-    # Fetch the file from the URL
     response = requests.get(url)
     # Read the Excel file from the response content
     lat_long_data = pd.read_excel(BytesIO(response.content), sheet_name="lat long", engine='openpyxl')
     measurement_data = pd.read_excel(BytesIO(response.content), sheet_name="measurement data", engine='openpyxl')
-
+    
     # Merge data on school_id_giga
-    merged_data = pd.merge(lat_long_data, measurement_data, on="school_id_giga", how="inner")
+    merged_data = pd.merge(
+        lat_long_data,
+        measurement_data,
+        left_on="school_id_giga",
+        right_on="school_id_giga",
+        how="inner"
+    )
+    
+    # Strip any extra spaces from column names
+    merged_data.columns = merged_data.columns.str.strip()
+    
     return merged_data
 
 # Perform clustering to find data center location
@@ -23,8 +31,11 @@ def find_data_center(df, n_clusters=1):
     kmeans = KMeans(n_clusters=n_clusters, random_state=0).fit(df[["latitude", "longitude"]])
     return kmeans.cluster_centers_
 
-# Create a map and plot the points
+# Plot the map with markers
 def plot_map(df, center):
+    # Print column names for debugging
+    print(df.columns)
+    
     map = folium.Map(location=[center[0][0], center[0][1]], zoom_start=10)
     marker_cluster = MarkerCluster().add_to(map)
     
@@ -33,7 +44,7 @@ def plot_map(df, center):
         folium.Marker(
             location=[row["latitude"], row["longitude"]],
             popup=(
-                f"School Name: {row['school_name']}<br>"
+                f"School Name: {row.get('school_name', 'N/A')}<br>"
                 f"Download Speed: {row['download_speed']} Mbps<br>"
                 f"Upload Speed: {row['upload_speed']} Mbps<br>"
                 f"Latency: {row['latency']} ms"
@@ -41,62 +52,68 @@ def plot_map(df, center):
             icon=folium.Icon(color="blue", icon="info-sign")
         ).add_to(marker_cluster)
     
-    # Add data center
+    # Add data center location
     folium.Marker(
         location=[center[0][0], center[0][1]],
         popup="Proposed Data Center",
         icon=folium.Icon(color="red", icon="cloud")
     ).add_to(map)
+    
     return map
 
-# Calculate before and after data center metrics
-def calculate_metrics(df, center):
-    # Calculate distances to the data center for each school
-    df['distance_to_center'] = ((df['latitude'] - center[0][0])**2 + (df['longitude'] - center[0][1])**2)**0.5
+# Calculate the impact of data center on latency and bandwidth
+def calculate_impact(df, center):
+    # Calculate average latency and bandwidth before the data center
+    avg_latency_before = df['latency'].mean()
+    avg_download_before = df['download_speed'].mean()
+    avg_upload_before = df['upload_speed'].mean()
     
-    # Assuming that schools closer to the center represent the "after" data center scenario
-    before_data = df[df['distance_to_center'] > df['distance_to_center'].median()]
-    after_data = df[df['distance_to_center'] <= df['distance_to_center'].median()]
+    # Assuming the data center reduces latency and increases bandwidth by 20%
+    latency_reduction = avg_latency_before * 0.8
+    download_increase = avg_download_before * 1.2
+    upload_increase = avg_upload_before * 1.2
     
-    # Calculate average bandwidth and latency
-    before_bandwidth = before_data[['download_speed', 'upload_speed']].mean()
-    before_latency = before_data['latency'].mean()
-    
-    after_bandwidth = after_data[['download_speed', 'upload_speed']].mean()
-    after_latency = after_data['latency'].mean()
+    # Return the new statistics
+    return latency_reduction, download_increase, upload_increase, avg_latency_before, avg_download_before, avg_upload_before
 
-    return before_bandwidth, before_latency, after_bandwidth, after_latency
+# Display the impact of the data center on latency and bandwidth
+def display_impact(latency_reduction, download_increase, upload_increase, avg_latency_before, avg_download_before, avg_upload_before):
+    impact_data = {
+        "Before Data Center": {
+            "Latency": f"{avg_latency_before:.2f} ms",
+            "Download Speed": f"{avg_download_before:.2f} Mbps",
+            "Upload Speed": f"{avg_upload_before:.2f} Mbps"
+        },
+        "After Data Center": {
+            "Latency": f"{latency_reduction:.2f} ms",
+            "Download Speed": f"{download_increase:.2f} Mbps",
+            "Upload Speed": f"{upload_increase:.2f} Mbps"
+        }
+    }
+    
+    return impact_data
 
 # Main function to run the application
 def main():
-    url = "https://huggingface.co/spaces/engralimalik/lace/resolve/main/data%20barbados.xlsx"
+    url = "https://huggingface.co/spaces/engralimalik/lace/resolve/main/data%20barbados.xlsx"  # URL of your Excel file
     df = load_data(url)
     
-    # Find the center for the data center location
+    # Find the data center location using clustering
     center = find_data_center(df)
     
-    # Plot the map
+    # Create the map and save it
     map = plot_map(df, center)
     map.save("index.html")
     
-    # Calculate before and after metrics
-    before_bandwidth, before_latency, after_bandwidth, after_latency = calculate_metrics(df, center)
-    
-    # Display the map in Streamlit
-    st.title("Impact of Data Center Addition")
-    st.markdown("Here’s the map of the schools and the proposed data center location.")
-    st.components.v1.html(open("index.html", "r").read(), height=500)
+    # Calculate the impact of adding the data center
+    latency_reduction, download_increase, upload_increase, avg_latency_before, avg_download_before, avg_upload_before = calculate_impact(df, center)
     
-    # Display before and after metrics
-    st.subheader("Before Data Center Addition")
-    st.write(f"Average Download Speed: {before_bandwidth['download_speed']} Mbps")
-    st.write(f"Average Upload Speed: {before_bandwidth['upload_speed']} Mbps")
-    st.write(f"Average Latency: {before_latency} ms")
-    
-    st.subheader("After Data Center Addition")
-    st.write(f"Average Download Speed: {after_bandwidth['download_speed']} Mbps")
-    st.write(f"Average Upload Speed: {after_bandwidth['upload_speed']} Mbps")
-    st.write(f"Average Latency: {after_latency} ms")
+    # Display the impact
+    impact_data = display_impact(latency_reduction, download_increase, upload_increase, avg_latency_before, avg_download_before, avg_upload_before)
+    print("Impact of Data Center on Latency and Bandwidth:")
+    print(impact_data)
+
+    print("Map has been saved as index.html.")
 
 if __name__ == "__main__":
     main()