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.
87 lines
3.7 KiB
87 lines
3.7 KiB
import streamlit as st
|
|
import matplotlib.pyplot as plt
|
|
from clusters import DBSCANCluster, KMeansCluster, CLUSTERING_STRATEGIES
|
|
from sklearn.decomposition import PCA
|
|
from sklearn.metrics import silhouette_score
|
|
import numpy as np
|
|
|
|
st.header("Clustering")
|
|
|
|
if "data" in st.session_state:
|
|
data = st.session_state.data
|
|
|
|
general_row = st.columns([1, 1, 1])
|
|
clustering = general_row[0].selectbox("Clustering method", CLUSTERING_STRATEGIES)
|
|
data_name = general_row[1].multiselect("Columns", data.select_dtypes(include="number").columns)
|
|
n_components = general_row[2].number_input("Reduce dimensions to (PCA)", min_value=1, max_value=3, value=2)
|
|
|
|
with st.form("cluster_form"):
|
|
if isinstance(clustering, KMeansCluster):
|
|
row1 = st.columns([1, 1, 1])
|
|
clustering.n_clusters = row1[0].number_input("Number of clusters", min_value=1, max_value=data.shape[0], value=clustering.n_clusters)
|
|
clustering.n_init = row1[1].number_input("n_init", min_value=1, value=clustering.n_init)
|
|
clustering.max_iter = row1[2].number_input("max_iter", min_value=1, value=clustering.max_iter)
|
|
elif isinstance(clustering, DBSCANCluster):
|
|
row1 = st.columns([1, 1])
|
|
clustering.eps = row1[0].slider("eps", min_value=0.0001, max_value=1.0, step=0.05, value=clustering.eps)
|
|
clustering.min_samples = row1[1].number_input("min_samples", min_value=1, value=clustering.min_samples)
|
|
|
|
st.form_submit_button("Launch")
|
|
|
|
if len(data_name) > 0:
|
|
x = data[data_name].to_numpy()
|
|
n_components = min(n_components, len(data_name))
|
|
if len(data_name) > n_components:
|
|
pca = PCA(n_components)
|
|
x = pca.fit_transform(x)
|
|
if n_components == 2:
|
|
(fig, ax) = plt.subplots(figsize=(8, 8))
|
|
for i in range(0, pca.components_.shape[1]):
|
|
ax.arrow(
|
|
0,
|
|
0,
|
|
pca.components_[0, i],
|
|
pca.components_[1, i],
|
|
head_width=0.1,
|
|
head_length=0.1
|
|
)
|
|
|
|
plt.text(
|
|
pca.components_[0, i] + 0.05,
|
|
pca.components_[1, i] + 0.05,
|
|
data_name[i]
|
|
)
|
|
circle = plt.Circle((0, 0), radius=1, edgecolor='b', facecolor='None')
|
|
ax.add_patch(circle)
|
|
plt.axis("equal")
|
|
ax.set_title("PCA result - Correlation circle")
|
|
st.pyplot(fig)
|
|
|
|
result = clustering.run(x)
|
|
st.write("## Cluster stats")
|
|
st.table(result.statistics)
|
|
|
|
st.write("## Graphical representation")
|
|
fig = plt.figure()
|
|
if n_components == 1:
|
|
plt.scatter(x, np.zeros_like(x))
|
|
elif n_components == 2:
|
|
ax = fig.add_subplot(projection='rectilinear')
|
|
plt.scatter(x[:, 0], x[:, 1], c=result.labels, s=50, cmap="viridis")
|
|
if result.centers is not None:
|
|
plt.scatter(result.centers[:, 0], result.centers[:, 1], c="black", s=200, marker="X")
|
|
else:
|
|
ax = fig.add_subplot(projection='3d')
|
|
|
|
ax.scatter(x[:, 0], x[:, 1],x[:, 2], c=result.labels, s=50, cmap="viridis")
|
|
if result.centers is not None:
|
|
ax.scatter(result.centers[:, 0], result.centers[:, 1], result.centers[:, 2], c="black", s=200, marker="X")
|
|
st.pyplot(fig)
|
|
if not (result.labels == 0).all():
|
|
st.write("Silhouette score:", silhouette_score(x, result.labels))
|
|
else:
|
|
st.error("Select at least one column")
|
|
|
|
else:
|
|
st.error("file not loaded")
|