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

Merge pull request 'Visualize clusters in 3d' (#6) from cluster3d into main

Browse Source 
Reviewed-on: https://codefirst.iut.uca.fr/git/clement.freville2/miner/pulls/6
Reviewed-by: Clément FRÉVILLE <clement.freville2@etu.uca.fr>
This commit is contained in:
Bastien OLLIER
2024-06-21 13:49:12 +02:00
parent e255c67972 e48c3bfa50
commit 694ecd0eef
2 changed files with 25 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
frontend/pages/clustering:_dbscan.py
View File

@@ -9,21 +9,27 @@ 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)
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:
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, ax = plt.subplots(figsize=(12,8))
plt.scatter(x[:, 0], x[:, 1], c=y_dbscan, s=50, cmap="viridis")
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")

20
frontend/pages/clustering:_kmeans.py
View File

@@ -11,7 +11,7 @@ if "data" in st.session_state:
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=2)
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])
@@ -20,16 +20,24 @@ if "data" in st.session_state:
st.form_submit_button("launch")
if len(data_name) == 2:
if len(data_name) >= 2 and len(data_name) <=3:
x = data[data_name].to_numpy()
kmeans = KMeans(n_clusters=n_clusters, init="random", n_init=n_init, max_iter=max_iter, random_state=111)
y_kmeans = kmeans.fit_predict(x)
fig, ax = plt.subplots(figsize=(12,8))
plt.scatter(x[:, 0], x[:, 1], c=y_kmeans, s=50, cmap="viridis")
centers = kmeans.cluster_centers_
plt.scatter(centers[:, 0], centers[:, 1], c="black", s=200, marker="X")
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")
centers = kmeans.cluster_centers_
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")
centers = kmeans.cluster_centers_
ax.scatter(centers[:, 0], centers[:, 1],centers[:, 2], c="black", s=200, marker="X")
st.pyplot(fig)
else: