Merge branch 'master' of https://src.koda.cnrs.fr/cefe/pace/nirs_workflow

.gitignore

 .idea/
 GUI_Pinard.iml
 __pycache__/
-src/data/models/*
-src/data/predictions/*
-src/data/sample_selections/*
-src/data/params/*
 src/Report/*.pdf
 src/Report/*.tex
-src/Report/figures/
-src/temp/*
 config/config.json
\ No newline at end of file

src/Class_Mod/LWPLSR_Call.py

@@ -5,7 +5,7 @@ from LWPLSR_ import LWPLSR
 
 # loading the lwplsr_inputs.json
 temp_path = Path("temp/")
-for i in ['x_train_np', 'y_train_np', 'x_test_np', 'y_test_np']:#,'x_train_np_cv1', 'y_train_np_cv1', 'x_test_np_cv1', 'y_test_np_cv1', 'x_train_np_cv2', 'y_train_np_cv2', 'x_test_np_cv2', 'y_test_np_cv2', 'x_train_np_cv3', 'y_train_np_cv3', 'x_test_np_cv3', 'y_test_np_cv3',]:
+for i in ['x_train_np', 'y_train_np', 'x_test_np', 'y_test_np','x_train_np_cv1', 'y_train_np_cv1', 'x_test_np_cv1', 'y_test_np_cv1', 'x_train_np_cv2', 'y_train_np_cv2', 'x_test_np_cv2', 'y_test_np_cv2', 'x_train_np_cv3', 'y_train_np_cv3', 'x_test_np_cv3', 'y_test_np_cv3',]:
     globals()[i] = np.genfromtxt(temp_path / str(i + ".csv"), delimiter=',')
 print('CSV imported')
 print('start model creation')

src/Class_Mod/UMAP_.py

@@ -17,7 +17,7 @@ class Umap:
         else:
             self.categorical_data_encoded = None
 
-        self.model = UMAP(n_neighbors=20, n_components=3, min_dist=0.0, random_state=42,)
+        self.model = UMAP(n_neighbors=20, n_components=3, min_dist=0.0, )#random_state=42,)
         self.model.fit(self.numerical_data, y = self.categorical_data_encoded)
         self.scores_raw = self.model.transform(self.numerical_data)
         self.scores = pd.DataFrame(self.scores_raw)

src/Report/figures/.gitignore

+*
+!.gitignore
\ No newline at end of file

src/data/models/.gitignore

+*           # git ignore tous les fichiers
+!.gitignore # sauf celui-ci
\ No newline at end of file

src/data/params/.gitignore

+*           # git ignore tous les fichiers
+!.gitignore # sauf celui-ci
\ No newline at end of file

src/data/predictions/.gitignore

+*           # git ignore tous les fichiers
+!.gitignore # sauf celui-ci
\ No newline at end of file

src/form_data.json

-{"meta_project": "Life of Brian", "meta_sample_species": "Life of Brian", "meta_sample_category": "Soil", "meta_sample_pretreatment": "Powder", "meta_machine_ID": "Life of Brian", "meta_sample_sub_category": "Green leave", "meta_sample_humidity": "Dry", "meta_scan_place": "Pace"}
\ No newline at end of file

src/pages/1-samples_selection.py

@@ -119,8 +119,12 @@ if not spectra.empty:
     elif dim_red_method == dim_red_methods[2]:
         if not meta_data.empty:
             filter = md_df_st_.columns
+            filter = filter.insert(0, 'Nothing')
             col = pc.selectbox('Supervised UMAP by:', options= filter, key=108)
-            supervised = md_df_st_[col]
+            if col == 'Nothing':
+                supervised = None
+            else:
+                supervised = md_df_st_[col]
         else:
             supervised = None
         dr_model = Umap(numerical_data = MinMaxScale(spectra), cat_data = supervised)
@@ -156,7 +160,8 @@ if not t.empty:
     # 2- HDBSCAN clustering
     elif clus_method == cluster_methods[2]:
         optimized_hdbscan = Hdbscan(np.array(tcr))
-        all_labels, hdbscan_score, clu_centers = optimized_hdbscan.HDBSCAN_scores_
+        # all_labels, hdbscan_score, clu_centers = optimized_hdbscan.HDBSCAN_scores_
+        all_labels, clu_centers = optimized_hdbscan.HDBSCAN_scores_
         labels = [f'cluster#{i+1}' if i !=-1 else 'Non clustered' for i in all_labels]
 
     # 3- Affinity propagation
@@ -221,9 +226,10 @@ if labels:
             sam1.insert(loc=0, column='index', value=selected_samples_idx)
             sam1.insert(loc=1, column='cluster', value=np.array(labels)[selected_samples_idx])
         sam1.index = np.arange(len(selected_samples_idx))+1
-        st.write(f' - The total number of samples:{tcr.shape[0]}.\n- The number of selected samples for chemical analysis: {sam1.shape[0]}.')
+        st.write(f' - The total number of samples: {tcr.shape[0]}.\n- The number of selected samples for chemical analysis: {sam1.shape[0]}.')
         sam = sam1
-        unclus = st.checkbox("Include non clustered samples (for HDBSCAN clustering)", value=True)
+        if clus_method == cluster_methods[2]:
+            unclus = st.checkbox("Include non clustered samples (for HDBSCAN clustering)", value=True)
 
         if clus_method == cluster_methods[2]:
             if selected_samples_idx:

src/temp/.gitignore

+*           # git ignore tous les fichiers
+!.gitignore # sauf celui-ci
\ No newline at end of file