Update app.py

app.py

@@ -41,23 +41,28 @@ def main():
         nature_df = pd.DataFrame(nature_data, columns=["x", "y"])
         population_df = pd.DataFrame(population_data, columns=["x", "y"])
     
-    datasets = st.multiselect("Choose datasets:", ["교통접근성", "자연환경", "인구밀집도"])
+    datasets = st.multiselect("Choose datasets:", ["Traffic Accessibility", "Natural Environment", "Population Density"])
     k_value = st.slider("Select k value:", 1, 10)
     
     dataset_mapping = {
-        "교통접근성": (traffic_df, 'o'),
-        "자연환경": (nature_df, 'x'),
-        "인구밀집도": (population_df, '^')
+        "Traffic Accessibility": (traffic_df, 'o'),
+        "Natural Environment": (nature_df, 'x'),
+        "Population Density": (population_df, '^')
     }
     
+    combined_data = pd.concat([dataset_mapping[dataset_name][0] for dataset_name in datasets])
+
+    centroids, labels = apply_kmeans(combined_data.values, k_value)
+    
     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)
+        subset_labels = labels[:len(data)]
+        ax.scatter(data['x'], data['y'], c=subset_labels, cmap='viridis', marker=marker, label=dataset_name)
+        labels = labels[len(data):]
         
-        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.scatter(centroids[:, 0], centroids[:, 1], s=200, c='red', marker='X')
     
     ax.set_xlim(0, 100)
     ax.set_ylim(0, 100)