Update app.py

app.py

@@ -4,7 +4,7 @@ import numpy as np
 import matplotlib.pyplot as plt
 from sklearn.cluster import KMeans
 
-# Data Generation
+# 데이터 생성
 np.random.seed(42)
 num_samples = 30
 traffic_centers = [(20, 20), (80, 80)]
@@ -27,7 +27,7 @@ def apply_kmeans(data, k):
 
 
 def main():
-    st.title("K-means Clustering Simulator")
+    st.title("K-means Clustering simulator \n k-means Clustering 시뮬레이션을 제공합니다.")
     
     # Global variables declaration
     global traffic_df, nature_df, population_df
@@ -45,24 +45,25 @@ def main():
     k_value = st.slider("Select k value:", 1, 10)
     
     dataset_mapping = {
-        "교통접근성": traffic_df,
-        "자연환경": nature_df,
-        "인구밀집도": population_df
+        "교통접근성": (traffic_df, 'o')
+        "자연환경": (nature_df, 'x')
+        "인구밀집도": (population_df, '▲')
     }
-   
-    if datasets:
-        combined_data = pd.concat([dataset_mapping[dataset_name] for dataset_name in datasets])
-        
-        fig, ax = plt.subplots(figsize=(8, 8))
+
+    fig, ax = plt.subplots(figsize=(8, 8))
+
+   for dataset_name in datasets:
+        data, marker = dataset_mapping[dataset_name]
+        centroids, labels = apply_kmeans(data.values, k_value)
         
-        centroids, labels = apply_kmeans(combined_data.values, k_value)
-        ax.scatter(combined_data['x'], combined_data['y'], c=labels, cmap='viridis')
+        ax.scatter(data['x'], data['y'], c=labels, cmap='viridis', marker=marker, label=dataset_name)
         ax.scatter(centroids[:, 0], centroids[:, 1], s=200, c='red', marker='X')
-        
-        ax.set_xlim(0, 100)
-        ax.set_ylim(0, 100)
-        ax.set_title(f"K-means clustering result (k={k_value})")
-        st.pyplot(fig)
+    
+    ax.set_xlim(0, 100)
+    ax.set_ylim(0, 100)
+    ax.set_title(f"K-means clustering result (k={k_value})")
+    ax.legend()
+    st.pyplot(fig)
 
 if __name__ == "__main__":
-    main()
+    main()