import streamlit as st
import matplotlib.pyplot as plt
from sklearn.cluster import DBSCAN

st.header("Clustering: dbscan")


if "data" in st.session_state:
    data = st.session_state.data

    with st.form("my_form"):
        data_name = st.multiselect("Data Name", data.select_dtypes(include="number").columns, max_selections=3)
        eps = st.slider("eps", min_value=0.0, max_value=1.0, value=0.5, step=0.01)
        min_samples = st.number_input("min_samples", step=1, min_value=1, value=5)
        st.form_submit_button("launch")

    if len(data_name) >= 2 and len(data_name) <=3:
        x = data[data_name].to_numpy()

        dbscan = DBSCAN(eps=eps, min_samples=min_samples)
        y_dbscan = dbscan.fit_predict(x)

        fig = plt.figure()
        if len(data_name) == 2:
            ax = fig.add_subplot(projection='rectilinear')
            plt.scatter(x[:, 0], x[:, 1], c=y_dbscan, s=50, cmap="viridis")
        else:
            ax = fig.add_subplot(projection='3d')
            ax.scatter(x[:, 0], x[:, 1],x[:, 2], c=y_dbscan, s=50, cmap="viridis")
        st.pyplot(fig)

    

else:
    st.error("file not loaded")