Update app.py

app.py

@@ -4,19 +4,20 @@ import numpy as np
 import matplotlib.pyplot as plt
 from sklearn.cluster import KMeans
 
-# Generate the datasets
+# Data Generation
 np.random.seed(42)
 num_samples = 30
+traffic_centers = [(20, 20), (80, 80)]
+nature_centers = [(0, 80), (80, 0)]
+population_centers = [(0, 0), (50, 50), (100, 100)]
 
 traffic_data = np.random.uniform(0, 100, (num_samples * len(traffic_centers), 2))
 nature_data = np.random.uniform(0, 100, (num_samples * len(nature_centers), 2))
 population_data = np.random.uniform(0, 100, (num_samples * len(population_centers), 2))
 
-traffic_df_uniform = pd.DataFrame(traffic_data, columns=["x", "y"])
-nature_df_uniform = pd.DataFrame(nature_data, columns=["x", "y"])
-population_df_uniform = pd.DataFrame(population_data, columns=["x", "y"])
-
-traffic_df_uniform.head(), nature_df_uniform.head(), population_df_uniform.head()
+traffic_df = pd.DataFrame(traffic_data, columns=["x", "y"])
+nature_df = pd.DataFrame(nature_data, columns=["x", "y"])
+population_df = pd.DataFrame(population_data, columns=["x", "y"])
 
 def apply_kmeans(data, k):
     kmeans = KMeans(n_clusters=k, random_state=42).fit(data)
@@ -24,23 +25,18 @@ def apply_kmeans(data, k):
     labels = kmeans.labels_
     return centroids, labels
 
-def generate_data():
-    global traffic_df, nature_df, population_df
-    
-    # 랜덤데이터 생성
-    traffic_data = np.random.uniform(0, 100, (num_samples, 2))
-    nature_data = np.random.uniform(0, 100, (num_samples, 2))
-    population_data = np.random.uniform(0, 100, (num_samples, 2))
-
-    traffic_df = pd.DataFrame(traffic_data, columns=["x", "y"])
-    nature_df = pd.DataFrame(nature_data, columns=["x", "y"])
-    population_df = pd.DataFrame(population_data, columns=["x", "y"])
-
 def main():
     st.title("K-means Clustering Simulator")
     
     if st.button("Initialize Datasets"):
-        generate_data()    
+        traffic_data = np.random.uniform(0, 100, (num_samples * len(traffic_centers), 2))
+        nature_data = np.random.uniform(0, 100, (num_samples * len(nature_centers), 2))
+        population_data = np.random.uniform(0, 100, (num_samples * len(population_centers), 2))
+
+        traffic_df = pd.DataFrame(traffic_data, columns=["x", "y"])
+        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"])
     k_value = st.slider("Select k value:", 1, 10)
     
@@ -50,7 +46,6 @@ def main():
         "인구밀집도": population_df
     }
     
-    # 아무 값도 없을때
     if datasets:
         combined_data = pd.concat([dataset_mapping[dataset_name] for dataset_name in datasets])
         
@@ -67,4 +62,3 @@ def main():
 
 if __name__ == "__main__":
     main()
-