updated col_cat function from DATA_HANDLING.py. Outputs are now comparable to those of dr_reader

Class_Mod/DATA_HANDLING.py

@@ -5,7 +5,7 @@ from Packages import *
 def find_delimiter(filename):
     sniffer = csv.Sniffer()
     with open(filename) as fp:
-        delimiter = sniffer.sniff(fp.read(5000)).delimiter
+        delimiter = sniffer.sniff(fp.read(200)).delimiter
     return delimiter
 
 def find_col_index(filename):
@@ -17,7 +17,10 @@ def find_col_index(filename):
 
 # detection of columns categories and scaling
 def col_cat(data_import):
-    # detect numerical and categorical columns in the csv
+    """detect numerical and categorical columns in the csv"""
+    # set first column as sample names
+    name_col = pd.DataFrame(list(data_import.index), index = list(data_import.index))
+    name_col=name_col.rename(columns = {0:'name'})
     numerical_columns_list = []
     categorical_columns_list = []
     for i in data_import.columns:
@@ -30,6 +33,7 @@ def col_cat(data_import):
         numerical_columns_list.append(empty)
     if len(categorical_columns_list) > 0:
         categorical_data = pd.concat(categorical_columns_list, axis=1)
+        categorical_data.insert(0, 'name', name_col)
     if len(categorical_columns_list) == 0:
         categorical_data = pd.DataFrame
     # Create numerical data matrix from the numerical columns list and fill na with the mean of the column

pages/1-samples_selection.py

@@ -39,8 +39,9 @@ if data_file:
             else:
                 col = False
             imp = pd.read_csv(data_file, sep=psep, index_col=col)
-            spectra = col_cat(imp)[0]
-            meta_data = col_cat(imp)[1]
+            # spectra = col_cat(imp)[0]
+            # meta_data = col_cat(imp)[1]
+            spectra, meta_data = col_cat(imp)
             st.success("The data have been loaded successfully", icon="✅")
 
     ## Load .dx file
@@ -50,7 +51,7 @@ if data_file:
             tmp.write(data_file.read())
             tmp_path = tmp.name
             with col1:
-                _, spectra, meta_data = read_dx(file =  tmp_path)
+                _, spectra, meta_data = read_dx(file = tmp_path)
                 st.success("The data have been loaded successfully", icon="✅")
         os.unlink(tmp_path)
 
@@ -83,10 +84,11 @@ if not spectra.empty:
     clus_method = pc.selectbox("Clustering techniques: ", options = cluster_methods, key = 38)
     xc = standardize(spectra)
 
+
     if dim_red_method == dim_red_methods[1]:
         dr_model = LinearPCA(xc, Ncomp=5)
     elif dim_red_method == dim_red_methods[2]:
-        dr_model = Umap(data_import = data_import, numerical_data = scaled_values, cat_data = categorical_data)
+        dr_model = Umap(data_import = imp, numerical_data = MinMaxScale(spectra), cat_data = meta_data)
 
     if dr_model:
         axis1 = pc.selectbox("x-axis", options = dr_model.scores_.columns, index=0)