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

Compare commits

merge into: iut:clustering
Branches Tags
iut:main iut:clustering-strategy iut:stat_prediction iut:stat iut:separation iut:csv-delimiters iut:knn iut:prediction iut:bastien.ollier-patch-1 iut:cluster3d iut:feature/missing-values iut:clustering iut:navigation iut:visualisation
...
pull from: iut:cluster3d
Branches Tags
iut:main iut:clustering-strategy iut:stat_prediction iut:stat iut:separation iut:csv-delimiters iut:knn iut:prediction iut:bastien.ollier-patch-1 iut:cluster3d iut:feature/missing-values iut:clustering iut:navigation iut:visualisation

3 Commits
clustering ... cluster3d

Author SHA1 Message Date
bastien ollier
e48c3bfa50 add 3d plot to bdscan 2024-06-21 13:38:27 +02:00
bastien ollier
52cb140746 add 3d to kmeans 2024-06-19 10:03:48 +02:00
Bastien OLLIER
c1f5e55a0b Merge pull request 'clustering' (#5) from clustering into main 
Reviewed-on: https://codefirst.iut.uca.fr/git/clement.freville2/miner/pulls/5
Reviewed-by: Clément FRÉVILLE <clement.freville2@etu.uca.fr>
 2024-06-19 09:38:28 +02:00
2 changed files with 25 additions and 11 deletions
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 data = st.session_state.data
with st.form("my_form"): 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) 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) min_samples = st.number_input("min_samples", step=1, min_value=1, value=5)
st.form_submit_button("launch") 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() x = data[data_name].to_numpy()
dbscan = DBSCAN(eps=eps, min_samples=min_samples) dbscan = DBSCAN(eps=eps, min_samples=min_samples)
y_dbscan = dbscan.fit_predict(x) y_dbscan = dbscan.fit_predict(x)
fig = plt.figure()
fig, ax = plt.subplots(figsize=(12,8)) if len(data_name) == 2:
plt.scatter(x[:, 0], x[:, 1], c=y_dbscan, s=50, cmap="viridis") 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) st.pyplot(fig)
else: else:
st.error("file not loaded") 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"): with st.form("my_form"):
row1 = st.columns([1,1,1]) row1 = st.columns([1,1,1])
n_clusters = row1[0].selectbox("Number of clusters", range(1,data.shape[0])) 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) n_init = row1[2].number_input("n_init",step=1,min_value=1)
row2 = st.columns([1,1]) row2 = st.columns([1,1])
@@ -20,16 +20,24 @@ if "data" in st.session_state:
st.form_submit_button("launch") 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() 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) 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) y_kmeans = kmeans.fit_predict(x)
fig, ax = plt.subplots(figsize=(12,8)) fig = plt.figure()
plt.scatter(x[:, 0], x[:, 1], c=y_kmeans, s=50, cmap="viridis") if len(data_name) == 2:
centers = kmeans.cluster_centers_ ax = fig.add_subplot(projection='rectilinear')
plt.scatter(centers[:, 0], centers[:, 1], c="black", s=200, marker="X") 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) st.pyplot(fig)
else: else: