Update app.py

app.py

@@ -25,9 +25,25 @@ def apply_kmeans(data, k):
     labels = kmeans.labels_
     return centroids, labels
 
+def generate_data():
+    traffic_data = [np.random.normal(center, 10, (num_samples, 2)) for center in traffic_centers]
+    nature_data = [np.random.normal(center, 10, (num_samples, 2)) for center in nature_centers]
+    population_data = [np.random.normal(center, 10, (num_samples, 2)) for center in population_centers]
+
+    traffic_df = pd.DataFrame(np.vstack(traffic_data), columns=["x", "y"])
+    nature_df = pd.DataFrame(np.vstack(nature_data), columns=["x", "y"])
+    population_df = pd.DataFrame(np.vstack(population_data), columns=["x", "y"])
+    
+    return traffic_df, nature_df, population_df
+
+traffic_df, nature_df, population_df = generate_data()
+
 def main():
     st.title("K-means Clustering Simulator")
     
+    if st.button("Initialize Datasets"):
+        traffic_df, nature_df, population_df = generate_data()
+    
     datasets = st.multiselect("Choose datasets:", ["교통접근성", "자연환경", "인구밀집도"])
     k_value = st.slider("Select k value:", 1, 10)
     
@@ -37,7 +53,7 @@ def main():
         "인구밀집도": population_df
     }
     
-   # Check if any dataset is selected
+    # Check if any dataset is selected
     if datasets:
         combined_data = pd.concat([dataset_mapping[dataset_name] for dataset_name in datasets])
         
@@ -55,4 +71,3 @@ def main():
 if __name__ == "__main__":
     main()
 
-