Spaces:
Running
Running
Create app.py
Browse files
app.py
ADDED
@@ -0,0 +1,125 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import pandas as pd
|
2 |
+
import folium
|
3 |
+
from sklearn.cluster import KMeans
|
4 |
+
from folium.plugins import MarkerCluster
|
5 |
+
import requests
|
6 |
+
from io import BytesIO
|
7 |
+
import streamlit as st
|
8 |
+
import folium
|
9 |
+
from streamlit.components.v1 import html
|
10 |
+
import math
|
11 |
+
|
12 |
+
# Load data from Excel (directly from the URL)
|
13 |
+
def load_data(url):
|
14 |
+
# Request the file content
|
15 |
+
response = requests.get(url)
|
16 |
+
|
17 |
+
# Check if the content is an Excel file by inspecting the MIME type
|
18 |
+
if 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet' not in response.headers['Content-Type']:
|
19 |
+
raise ValueError("The file is not a valid Excel file.")
|
20 |
+
|
21 |
+
# Read the file content into a pandas dataframe with the engine specified
|
22 |
+
lat_long_data = pd.read_excel(BytesIO(response.content), sheet_name="lat long", engine='openpyxl')
|
23 |
+
measurement_data = pd.read_excel(BytesIO(response.content), sheet_name="measurement data", engine='openpyxl')
|
24 |
+
|
25 |
+
# Merge data on school_id_giga
|
26 |
+
merged_data = pd.merge(
|
27 |
+
lat_long_data,
|
28 |
+
measurement_data,
|
29 |
+
left_on="school_id_giga",
|
30 |
+
right_on="school_id_giga",
|
31 |
+
how="inner"
|
32 |
+
)
|
33 |
+
|
34 |
+
# Strip whitespace from all column names
|
35 |
+
merged_data.columns = merged_data.columns.str.strip()
|
36 |
+
|
37 |
+
return merged_data
|
38 |
+
|
39 |
+
# Haversine formula to calculate distance between two lat/long points
|
40 |
+
def haversine(lat1, lon1, lat2, lon2):
|
41 |
+
# Convert latitude and longitude from degrees to radians
|
42 |
+
lat1, lon1, lat2, lon2 = map(math.radians, [lat1, lon1, lat2, lon2])
|
43 |
+
|
44 |
+
# Haversine formula
|
45 |
+
dlat = lat2 - lat1
|
46 |
+
dlon = lon2 - lon1
|
47 |
+
a = math.sin(dlat / 2) ** 2 + math.cos(lat1) * math.cos(lat2) * math.sin(dlon / 2) ** 2
|
48 |
+
c = 2 * math.asin(math.sqrt(a))
|
49 |
+
|
50 |
+
# Radius of Earth in kilometers
|
51 |
+
R = 6371
|
52 |
+
return R * c
|
53 |
+
|
54 |
+
# Perform clustering to find data center location
|
55 |
+
def find_data_center(df, n_clusters=1):
|
56 |
+
kmeans = KMeans(n_clusters=n_clusters, random_state=0).fit(df[["latitude", "longitude"]])
|
57 |
+
return kmeans.cluster_centers_
|
58 |
+
|
59 |
+
# Estimate latency and bandwidth based on distance from the data center (inverse relationship)
|
60 |
+
def estimate_latency_bandwidth(df, data_center_lat, data_center_lon):
|
61 |
+
df["distance_to_data_center"] = df.apply(
|
62 |
+
lambda row: haversine(row["latitude"], row["longitude"], data_center_lat, data_center_lon),
|
63 |
+
axis=1
|
64 |
+
)
|
65 |
+
|
66 |
+
# Latency estimation: Assuming latency decreases inversely with distance (this is just an example scale)
|
67 |
+
df["estimated_latency"] = df["distance_to_data_center"].apply(lambda x: max(10, 100 / (x + 1))) # Max latency 100ms
|
68 |
+
|
69 |
+
# Bandwidth estimation: Assuming bandwidth increases inversely with distance (again, an example scale)
|
70 |
+
df["estimated_bandwidth"] = df["distance_to_data_center"].apply(lambda x: max(10, 100 / (x + 1))) # Max bandwidth 100 Mbps
|
71 |
+
|
72 |
+
return df
|
73 |
+
|
74 |
+
# Create a map and plot the points
|
75 |
+
def plot_map(df, center):
|
76 |
+
# Create map centered on the data center location
|
77 |
+
map = folium.Map(location=[center[0][0], center[0][1]], zoom_start=10)
|
78 |
+
marker_cluster = MarkerCluster().add_to(map)
|
79 |
+
|
80 |
+
# Add school locations to the map
|
81 |
+
for idx, row in df.iterrows():
|
82 |
+
school_name = row.get("school_name", "No Name Provided") # Ensure correct column access
|
83 |
+
|
84 |
+
# Popup text showing original latency, estimated latency, bandwidth before and after
|
85 |
+
popup_text = (
|
86 |
+
f"School Name: {school_name}<br>"
|
87 |
+
f"Original Latency: {row['latency']} ms<br>"
|
88 |
+
f"Original Bandwidth: {row['download_speed']} Mbps<br>"
|
89 |
+
f"Estimated Latency After Data Center: {row['estimated_latency']} ms<br>"
|
90 |
+
f"Estimated Bandwidth After Data Center: {row['estimated_bandwidth']} Mbps"
|
91 |
+
)
|
92 |
+
|
93 |
+
folium.Marker(
|
94 |
+
location=[row["latitude"], row["longitude"]],
|
95 |
+
popup=popup_text,
|
96 |
+
icon=folium.Icon(color="blue", icon="info-sign")
|
97 |
+
).add_to(marker_cluster)
|
98 |
+
|
99 |
+
# Add data center location to the map
|
100 |
+
folium.Marker(
|
101 |
+
location=[center[0][0], center[0][1]],
|
102 |
+
popup="Proposed Data Center",
|
103 |
+
icon=folium.Icon(color="red", icon="cloud")
|
104 |
+
).add_to(map)
|
105 |
+
|
106 |
+
return map
|
107 |
+
|
108 |
+
# Main function to run the application
|
109 |
+
def main():
|
110 |
+
url = "https://huggingface.co/spaces/engralimalik/lace/resolve/main/data%20barbados.xlsx" # Correct raw file URL
|
111 |
+
df = load_data(url)
|
112 |
+
center = find_data_center(df)
|
113 |
+
df = estimate_latency_bandwidth(df, center[0][0], center[0][1]) # Estimate latency and bandwidth based on distance
|
114 |
+
|
115 |
+
map = plot_map(df, center)
|
116 |
+
|
117 |
+
# Embed the map directly in the Streamlit app
|
118 |
+
map_html = map._repr_html_() # Render the folium map as HTML
|
119 |
+
html(map_html, width=700, height=500) # Adjust the size of the embedded map
|
120 |
+
|
121 |
+
st.title("Impact of Data Center on Latency and Bandwidth")
|
122 |
+
st.write("This map shows school locations and proposed data center locations based on clustering. The latency and bandwidth values represent the potential improvements for schools closer to the data center.")
|
123 |
+
|
124 |
+
if __name__ == "__main__":
|
125 |
+
main()
|