You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
30 lines
908 B
30 lines
908 B
import streamlit as st
|
|
import matplotlib.pyplot as plt
|
|
from sklearn.cluster import DBSCAN
|
|
import numpy as np
|
|
|
|
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=2)
|
|
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:
|
|
x = data[data_name].to_numpy()
|
|
|
|
dbscan = DBSCAN(eps=eps, min_samples=min_samples)
|
|
y_dbscan = dbscan.fit_predict(x)
|
|
|
|
|
|
fig, ax = plt.subplots(figsize=(12,8))
|
|
plt.scatter(x[:, 0], x[:, 1], c=y_dbscan, s=50, cmap='viridis')
|
|
st.pyplot(fig)
|
|
|
|
else:
|
|
st.error("file not loaded") |