added all files

README.md

@@ -1,6 +1,6 @@
 ---
-title: Iris Flower Clustering Using DBSCAN
-emoji: 🌍
+title: Earthquake Location Clustering Using DBSCAN
+emoji: 🌐
 colorFrom: purple
 colorTo: green
 sdk: streamlit

app.py

@@ -0,0 +1,65 @@
+import streamlit as st
+import pandas as pd
+import matplotlib.pyplot as plt
+from sklearn.preprocessing import StandardScaler
+from sklearn.cluster import DBSCAN
+
+# Title
+st.title("🌍 Earthquake Location Clustering")
+st.markdown("#### Explore how earthquakes are grouped based on their geographic locations using DBSCAN")
+
+# Load dataset
+df = pd.read_csv("database.csv")
+
+# Clean and filter necessary columns
+df = df[['Latitude', 'Longitude']].dropna()
+
+# Standardize data
+scaler = StandardScaler()
+X_scaled = scaler.fit_transform(df[['Latitude', 'Longitude']])
+
+# Apply DBSCAN
+db = DBSCAN(eps=0.3, min_samples=5)
+df['Cluster'] = db.fit_predict(X_scaled)
+
+# Tabs
+tab1, tab2, tab3 = st.tabs(["🌐 Raw Earthquake Data", "🗺️ Cluster Visualization", "📍 Guess Cluster"])
+
+with tab1:
+    st.header("🌐 Earthquake Data")
+    st.dataframe(df[['Latitude', 'Longitude', 'Cluster']].head(10))
+
+with tab2:
+    st.header("🗺️ Earthquake Clusters Plot")
+    st.write("Scatter plot showing how earthquakes are grouped based on their locations.")
+    
+    fig, ax = plt.subplots(figsize=(10, 6))
+    scatter = ax.scatter(df['Longitude'], df['Latitude'], c=df['Cluster'], cmap='rainbow', s=10)
+    ax.set_xlabel('Longitude')
+    ax.set_ylabel('Latitude')
+    ax.set_title('Earthquake Location Clusters')
+    st.pyplot(fig)
+
+with tab3:
+    st.header("📍 Which Cluster Is An Earthquake In?")
+    st.write("Pick a location to see what cluster it would belong to.")
+
+    lat = st.slider("Latitude", float(df['Latitude'].min()), float(df['Latitude'].max()), 0.0)
+    lon = st.slider("Longitude", float(df['Longitude'].min()), float(df['Longitude'].max()), 0.0)
+
+    # Scaling the new input data point
+    new_point = scaler.transform([[lat, lon]])
+
+    # Apply DBSCAN to the whole dataset including the new point
+    updated_data = pd.DataFrame(df[['Latitude', 'Longitude']].values.tolist() + [[lat, lon]], columns=['Latitude', 'Longitude'])
+    updated_scaled = scaler.transform(updated_data)
+
+    db_updated = DBSCAN(eps=0.5, min_samples=5)
+    clusters = db_updated.fit_predict(updated_scaled)
+
+    new_cluster = clusters[-1]
+
+    if new_cluster == -1:
+        st.warning("This point does not belong to any cluster (outlier).")
+    else:
+        st.success(f"This point likely belongs to **Cluster {new_cluster}**.")

requirements.txt

@@ -0,0 +1,5 @@
+streamlit 
+pandas 
+matplotlib 
+scikit-learn 
+numpy