iut/miner
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Merge files using strategies

Browse Source
This commit is contained in:
Clément Fréville
2024-06-26 12:00:21 +02:00
parent 9da6e2d594
commit 01ef19a2f8
4 changed files with 97 additions and 105 deletions
Download Patch File Download Diff File Expand all files Collapse all files

48
frontend/pages/clustering.py Normal file
View File

@@ -0,0 +1,48 @@
import streamlit as st
import matplotlib.pyplot as plt
from clusters import DBSCANCluster, KMeansCluster, CLUSTERING_STRATEGIES
st.header("Clustering")
if "data" in st.session_state:
data = st.session_state.data
general_row = st.columns([1, 1])
clustering = general_row[0].selectbox("Clustering method", CLUSTERING_STRATEGIES)
data_name = general_row[1].multiselect("Data Name",data.select_dtypes(include="number").columns, max_selections=3)
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):
clustering.eps = st.slider("eps", min_value=0.0001, max_value=1.0, step=0.1, value=clustering.eps)
clustering.min_samples = st.number_input("min_samples", min_value=1, value=clustering.min_samples)
st.form_submit_button("Launch")
if len(data_name) >= 2 and len(data_name) <=3:
x = data[data_name].to_numpy()
result = clustering.run(x)
st.table(result.statistics)
fig = plt.figure()
if len(data_name) == 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)
else:
st.error("file not loaded")

32
frontend/pages/clustering_dbscan.py
View File

@@ -1,32 +0,0 @@
import streamlit as st
import matplotlib.pyplot as plt
from clusters import DBSCAN_cluster
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_cluster(eps,min_samples,x)
y_dbscan = dbscan.run()
st.table(dbscan.get_stats())
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")

44
frontend/pages/clustering_kmeans.py
View File

@@ -1,44 +0,0 @@
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")