Lint

Author: AndrejaKovacic

Orange/widgets/visualize/owvenndiagram.py

@@ -376,17 +376,21 @@ def extract_new_table(self, var_dict):
         domain = defaultdict(lambda: [])
         values = defaultdict(lambda: [])
         atr_vals = {'metas': 'metas', 'attributes': 'X', 'class_vars': 'Y'}
+        renamed = []
         for atr_type, vars_dict in var_dict.items():
             for var_name, var_data in vars_dict.items():
                 if var_data[0]:
                     #columns are different, copy all, rename them
                     for var, table_key in var_data[1]:
                         idx = list(self.data.keys()).index(table_key) + 1
-                        domain[atr_type].append(var.copy(name='{} ({})'.format(var_name, idx)))
+                        domain[atr_type].append(var.copy(name='{} ({})'.format(var_name.name, idx)))
+                        renamed.append(var_name.name)
                         values[atr_type].append(getattr(self.data[table_key].table[:, var_name], atr_vals[atr_type]).reshape(-1, 1))
                 else:
                     domain[atr_type].append(deepcopy(var_data[1][0][0]))
                     values[atr_type].append(getattr(self.data[var_data[1][0][1]].table[:, var_name], atr_vals[atr_type]).reshape(-1, 1))
+        if renamed:
+            self.Warning.renamed_vars(', '.join(renamed))
         return self.merge_data(domain, values)
 
     def curry_merge(self, table_key, atr_type, ids=None, selection=False):
@@ -490,15 +494,21 @@ def extract_rowwise(self, var_dict, ids=None, selection=False):
         domain = defaultdict(lambda: [])
         values = defaultdict(lambda: [])
         atr_vals = {'metas': 'metas', 'attributes': 'X', 'class_vars': 'Y'}
+        renamed = []
         for atr_type, vars_dict in var_dict.items():
             for var_name, var_data in vars_dict.items():
                 different = var_data[0]
                 if different:
-                    #columns are different, copy all, rename them
+                    """
+                    Columns are different, copy and rename them.
+                    Renaming is done here to mark appropriately the source table.
+                    Additional strange clashes are checked later in merge_data
+                    """
                     for var, table_key in var_data[1]:
                         temp = self.data[table_key].table
                         idx = list(self.data.keys()).index(table_key) + 1
                         domain[atr_type].append(var.copy(name='{} ({})'.format(var_name, idx)))
+                        renamed.append(var_name.name)
                         v = getattr(temp[list(ids[table_key].values()), var_name],
                                     atr_vals[atr_type])
                         perm = permutations[table_key]
@@ -522,6 +532,8 @@ def extract_rowwise(self, var_dict, ids=None, selection=False):
                         value[perm] = v
                     values[atr_type].append(value)
 
+        if renamed:
+            self.Warning.renamed_vars(', '.join(renamed))
         table = self.merge_data(domain, values)
         mask = [idx in self.selected_items for idx in all_ids]
         if selection:
@@ -533,9 +545,9 @@ def get_indices(self, table, selection):
         if self.selected_feature:
             if self.output_duplicates and selection:
                 items, inverse = np.unique(getattr(table[:, self.selected_feature], 'metas'),
-                                            return_inverse=True)
-                ids = [np.nonzero(inverse == idx)[0] for idx in range(len(items))]                    
-            else:                                
+                                           return_inverse=True)
+                ids = [np.nonzero(inverse == idx)[0] for idx in range(len(items))]
+            else:
                 items, ids = np.unique(getattr(table[:, self.selected_feature], 'metas'),
                                        return_index=True)
 
@@ -588,19 +600,15 @@ def expand_tables(self, table, atrs, metas, cv):
             array.fill(np.nan)
             b = getattr(table, self.atr_vals[atr_type])
             array[:, perm] = self.make_it_fit(array[:, perm].shape, b)
-            #array[:, perm] = np.atleast_2d(getattr(table, self.atr_vals[atr_type]))
             exp.append(array)
-        #TODO: maybe this could be smarter
         return exp[0], exp[1], exp[2]
 
     def extract_rowwise_duplicates(self, var_dict, ids, relevant_keys):
-        #za vsak id v vsakemu stolpcu rabimo indekse
-        #extractamo celo podtabelo, vstavimo morebitne manjkajoče stolpce, na koncu vstack
         all_ids = sorted(list(reduce(set.union, [set(val.keys()) for val in ids.values()], set())))
         sort_key = lambda var: var.name
-        all_atrs = sorted([var for var in var_dict['attributes'].keys()], key=sort_key)
-        all_metas = sorted([var for var in var_dict['metas'].keys()], key=sort_key)
-        all_cv = sorted([var for var in var_dict['class_vars'].keys()], key=sort_key)
+        all_atrs = sorted((var for var in var_dict['attributes'].keys()), key=sort_key)
+        all_metas = sorted((var for var in var_dict['metas'].keys()), key=sort_key)
+        all_cv = sorted((var for var in var_dict['class_vars'].keys()), key=sort_key)
 
         all_x, all_y, all_m = [], [], []
         for idx in all_ids:

Orange/widgets/visualize/tests/test_owvenndiagram.py

@@ -4,6 +4,7 @@
 import unittest
 from unittest.mock import patch
 from collections import defaultdict
+from copy import deepcopy
 
 import numpy as np
 import scipy.sparse as sp
@@ -35,7 +36,29 @@ def _select_data(self):
         self.widget.vennwidget.vennareas()[1].setSelected(True)
         return list(range(len(self.signal_data)))
 
-    def test_multiple_input(self):
+    def test_rows_id(self):
+        data = Table('zoo')
+        data1 = deepcopy(data)
+        data1[:, 1] = 1
+        self.widget.rowwise = True
+        self.send_signal(self.signal_name, data1[:10], 1)
+        self.widget.selected_feature = 'name'
+        self.send_signal(self.signal_name, data[5:10], 2)
+
+        self.assertIsNone(self.get_output(self.widget.Outputs.selected_data))
+        self.assertTrue(self.widget.Warning.renamed_vars.is_shown())
+
+        self.widget.vennwidget.vennareas()[3].setSelected(True)
+        selected = self.get_output(self.widget.Outputs.selected_data)
+        sel_atrs = [atr.name for atr in selected.domain.attributes]
+        true_atrs = ['hair', 'feathers (1)', 'feathers (2)', 'eggs', 'milk', 'airborne', 'aquatic',
+                     'predator', 'toothed', 'backbone', 'breathes', 'venomous', 'fins', 'legs',
+                     'tail', 'domestic', 'catsize']
+        self.assertEqual(sel_atrs, true_atrs)
+        self.assertEqual(selected.domain.metas, data.domain.metas)
+        self.assertEqual(selected.domain.class_vars, data.domain.class_vars)
+
+    def test_multiple_input_rows_id(self):
         """Over rows"""
         self.widget.rowwise = True
         self.send_signal(self.signal_name, self.data[:100], 1)