samples_selection:

- export samples for wet-chem analysis
- export metadata if it exists
- color selected samples on scores plot

Class_Mod/KMEANS_.py

@@ -21,4 +21,5 @@ class Sk_Kmeans:
         model.fit(self.x)
         yp = model.predict(self.x)+1
         clu = [f'cluster#{i}' for i in yp]
-        return self.x, clu
+
\ No newline at end of file
+        return self.x, clu, model.cluster_centers_
\ No newline at end of file

pages/1-samples_selection.py

@@ -68,6 +68,9 @@ container2 = st.container(border=True)
 container2.header("Exploratory Data Analysis-Multivariable Data Analysis", divider='blue')
 scores, loadings, pc = st.columns([2, 3, 0.5])
 influence, hotelling, qexp = st.columns([2, 2, 1])
+st.header('Selected samples for chemical analysis')
+selected_s, selected_samples_metd = st.columns([3, 3])
+selected_s.write('Samples scores')
 
 dim_red_methods=['', 'PCA','UMAP', 'NMF']  # List of dimensionality reduction algos
 cluster_methods = ['', 'Kmeans','HDBSCAN', 'AP'] # List of clustering algos
@@ -106,7 +109,7 @@ if not t.empty:
         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)
+        data, labels, clu_centers = cl_model.fit_optimal(nclusters = ncluster)
 
     elif clus_method == cluster_methods[2]:
         optimized_hdbscan = Hdbscan(model.scores_raw_)
@@ -114,7 +117,51 @@ if not t.empty:
 
 ##### Plots
 
-## Scores
+
+#####################################################################################################
+selec_strategy = ['center','random']
+samples_df_chem = pd.DataFrame
+selected_samples = []
+selected_samples_idx = []
+
+if labels:
+    selection = scores.radio('Select samples selection strategy:', options = selec_strategy)
+#################### selection strategy to  be corrected
+    if selection == selec_strategy[0]:
+        # list samples at clusters centers - Use sklearn.metrics.pairwise_distances_argmin if you want more than 1 sample per cluster
+        closest, _ = pairwise_distances_argmin_min(clu_centers, tcr)
+        selected_samples_idx = list(closest)
+    elif selection == selec_strategy[1]:
+        selection_number = scores.number_input('How many samples per cluster?', min_value = 1, step=1, value = 3)
+        for i in np.unique(labels):
+            C = np.where(np.array(labels) ==i)[0]
+            if C.shape[0] >= selection_number:
+                #scores.write(list(tcr.index)[labels== i])
+                km2 = KMeans(n_clusters = selection_number)
+                km2.fit(tcr.iloc[C,:])
+                clos, _ = pairwise_distances_argmin_min(km2.cluster_centers_, tcr.iloc[C,:])
+                selected_samples_idx2 = list(clos)
+                selected_samples_idx.extend(tcr.iloc[C,:].index[selected_samples_idx2])                
+            #    selected_samples_idx.extend(tcr.iloc[C,:].sample(n=selection_number).index.to_list())
+            else:
+                selected_samples_idx.extend(tcr.iloc[C,:].index.to_list())
+            # list indexes of selected samples for colored plot    
+
+if labels:
+    if selected_samples_idx:
+        sam = pd.DataFrame({'cluster':np.array(labels)[selected_samples_idx],
+                            'index': spectra.index[selected_samples_idx]})
+        selected_s.write(sam)
+
+        if not meta_data.empty:
+            selected_samples_metd.write('Corresponding meta-data')
+            meta = meta_data.iloc[selected_samples_idx,:]
+            meta['cluster'] = np.array(labels)[selected_samples_idx]
+            meta['index'] = spectra.index[selected_samples_idx]
+            selected_samples_metd.write(meta)
+
+
+    ## Scores
 if not t.empty:
     with scores:
         st.write('Scores plot')
@@ -150,6 +197,12 @@ if not t.empty:
         else:
             fig = px.scatter_3d(tcr, x=axis1, y=axis2, z = axis3)
         fig.update_traces(marker=dict(size=4))
+
+        if selected_samples_idx:
+            tt = tcr.iloc[selected_samples_idx,:]
+            fig.add_scatter3d(x = tt.loc[:,axis1], y = tt.loc[:,axis2],
+                              z = tt.loc[:,axis3], mode ='markers', marker = dict(size = 7, color = 'black'),
+                              name = 'selected samples')
         st.plotly_chart(fig)
 
 
@@ -181,4 +234,12 @@ 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
+
+
+
+
+
+
+
+