From 41be037372c04c8d20c5515141b176675f23ff7d Mon Sep 17 00:00:00 2001
From: DIANE <abderrahim.diane@cefe.cnrs.fr>
Date: Mon, 15 Apr 2024 12:24:03 +0200
Subject: [PATCH] samples selection
---
Class_Mod/UMAP_.py | 2 +-
pages/1-samples_selection.py | 40 +++++++++++++++++-------------------
2 files changed, 20 insertions(+), 22 deletions(-)
diff --git a/Class_Mod/UMAP_.py b/Class_Mod/UMAP_.py
index 21d2f82..90d0566 100644
--- a/Class_Mod/UMAP_.py
+++ b/Class_Mod/UMAP_.py
@@ -10,7 +10,7 @@ class Umap:
self.model = UMAP(n_neighbors=20, n_components=4, min_dist=0.0,) # random_state=42,)
self.model.fit(self.x)
self.scores = self.model.transform(self.x)
- self.scores = pd.DataFrame(self.scores, index = self.numerical_data.index)
+ self.scores = pd.DataFrame(self.scores)
@property
def scores_(self):
diff --git a/pages/1-samples_selection.py b/pages/1-samples_selection.py
index 314bf96..eb05693 100644
--- a/pages/1-samples_selection.py
+++ b/pages/1-samples_selection.py
@@ -101,17 +101,18 @@ if not spectra.empty:
# clustering
if not t.empty:
+ tcr = standardize(t)
# Clustering
- if clus_method == cluster_methods[1]:
- ncluster = scores.number_input(min_value=2, max_value=30, value=3, label = 'Select the desired number of clusters')
- cl_model = Sk_Kmeans(t, max_clusters = 30)
- fig2 = px.scatter(cl_model.inertia_.T, y = 'inertia')
- scores.plotly_chart(fig2)
- data, labels = cl_model.fit_optimal(nclusters = ncluster)
-
- elif clus_method == cluster_methods[2]:
- from hdbscan import HDBSCAN_function
- labels, hdbscan_score = HDBSCAN_function(t, min_cluster_size=10)
+ if clus_method == cluster_methods[1]:
+ ncluster = scores.number_input(min_value=2, max_value=30, value=3, label = 'Select the desired number of clusters')
+ cl_model = Sk_Kmeans(tcr, max_clusters = 30)
+ fig2 = px.scatter(cl_model.inertia_.T, y = 'inertia')
+ scores.plotly_chart(fig2)
+ data, labels = cl_model.fit_optimal(nclusters = ncluster)
+
+ elif clus_method == cluster_methods[2]:
+ from hdbscan import HDBSCAN_function
+ labels, hdbscan_score = HDBSCAN_function(tcr, min_cluster_size=10)
##### Plots
@@ -122,16 +123,16 @@ if not t.empty:
st.write('Scores plot')
# scores plot with clustering
if list(labels) and meta_data.empty:
- fig = px.scatter_3d(t, x=axis1, y=axis2, z = axis3, color = labels)
+ fig = px.scatter_3d(tcr, x=axis1, y=axis2, z = axis3, color = labels)
# scores plot with metadata
elif len(list(labels)) == 0 and not meta_data.empty:
filter = meta_data.columns[1:]
col = st.selectbox('Group by:', options= filter)
if col == 0:
- fig = px.scatter_3d(t, x=axis1, y=axis2, z = axis3)
+ fig = px.scatter_3d(tcr, x=axis1, y=axis2, z = axis3)
else:
- fig = px.scatter_3d(t, x=axis1, y=axis2, z = axis3, color = list(map(str.lower,meta_data[col])) )
+ fig = px.scatter_3d(tcr, x=axis1, y=axis2, z = axis3, color = list(map(str.lower,meta_data[col])) )
# color with scores and metadata
elif len(list(labels)) > 0 and not meta_data.empty:
@@ -143,14 +144,14 @@ if not t.empty:
col = st.selectbox('Group by:', options= filter)
if col == "None":
- fig = px.scatter_3d(t, x=axis1, y=axis2, z = axis3)
+ fig = px.scatter_3d(tcr, x=axis1, y=axis2, z = axis3)
elif col == clus_method:
- fig = px.scatter_3d(t, x=axis1, y=axis2, z = axis3, color = labels)
+ fig = px.scatter_3d(tcr, x=axis1, y=axis2, z = axis3, color = labels)
else:
- fig = px.scatter_3d(t, x=axis1, y=axis2, z = axis3, color = list(map(str.lower,meta_data[col])))
+ fig = px.scatter_3d(tcr, x=axis1, y=axis2, z = axis3, color = list(map(str.lower,meta_data[col])))
else:
- fig = px.scatter_3d(t, x=axis1, y=axis2, z = axis3)
+ fig = px.scatter_3d(tcr, x=axis1, y=axis2, z = axis3)
fig.update_traces(marker=dict(size=4))
st.plotly_chart(fig)
@@ -183,7 +184,4 @@ if not spectra.empty:
hotelling = dr_model.hotelling_
fig = px.scatter(t, x=hotelling[ax2], y=residuals[ax2]).update_layout(xaxis_title="T²",yaxis_title="Residuals")
- st.plotly_chart(fig)
-
-
-
+ st.plotly_chart(fig)
\ No newline at end of file
--
GitLab