app.py

import streamlit as st
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.cluster import KMeans

# Generate the datasets
np.random.seed(42)
num_samples = 100
traffic_centers = [(20, 20), (80, 20)]
nature_centers = [(20, 80), (80, 80)]
population_centers = [(50, 50), (30, 30), (70, 70)]

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"])

def apply_kmeans(data, k):
    kmeans = KMeans(n_clusters=k, random_state=42).fit(data)
    centroids = kmeans.cluster_centers_
    labels = kmeans.labels_
    return centroids, labels

def main():
    st.title("K-means Clustering Simulator")
    
    datasets = st.multiselect("Choose datasets:", ["교통접근성", "자연환경", "인구밀집도"])
    k_value = st.slider("Select k value:", 1, 10)
    
    dataset_mapping = {
        "교통접근성": traffic_df,
        "자연환경": nature_df,
        "인구밀집도": population_df
    }
    
    fig, ax = plt.subplots(figsize=(8, 8))
    for dataset_name in datasets:
        data = dataset_mapping[dataset_name]
        centroids, labels = apply_kmeans(data.values, k_value)
        
        ax.scatter(data['x'], data['y'], label=dataset_name, cmap='viridis')
        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})")
    ax.legend()
    st.pyplot(fig)

if __name__ == "__main__":
    main()