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.
miner/frontend/pages/clustering_kmeans.py

45 lines
1.5 KiB

import streamlit as st
import matplotlib.pyplot as plt
from clusters import KMeans_cluster
st.header("Clustering: kmeans")
if "data" in st.session_state:
data = st.session_state.data
with st.form("my_form"):
row1 = st.columns([1,1,1])
n_clusters = row1[0].selectbox("Number of clusters", range(1,data.shape[0]))
data_name = row1[1].multiselect("Data Name",data.select_dtypes(include="number").columns, max_selections=3)
n_init = row1[2].number_input("n_init",step=1,min_value=1)
row2 = st.columns([1,1])
max_iter = row1[0].number_input("max_iter",step=1,min_value=1)
st.form_submit_button("launch")
if len(data_name) >= 2 and len(data_name) <=3:
x = data[data_name].to_numpy()
kmeans = KMeans_cluster(n_clusters, n_init, max_iter, x)
y_kmeans = kmeans.run()
st.table(kmeans.get_stats())
centers = kmeans.centers
fig = plt.figure()
if len(data_name) == 2:
ax = fig.add_subplot(projection='rectilinear')
plt.scatter(x[:, 0], x[:, 1], c=y_kmeans, s=50, cmap="viridis")
plt.scatter(centers[:, 0], centers[:, 1], c="black", s=200, marker="X")
else:
ax = fig.add_subplot(projection='3d')
ax.scatter(x[:, 0], x[:, 1],x[:, 2], c=y_kmeans, s=50, cmap="viridis")
ax.scatter(centers[:, 0], centers[:, 1], centers[:, 2], c="black", s=200, marker="X")
st.pyplot(fig)
else:
st.error("file not loaded")