fixed major bug with assoc rule mining. refs #1

bartdag · Aug 10, 2015 · b71eb40 · b71eb40
1 parent a7a5696
commit b71eb40
Show file tree

Hide file tree

Showing 2 changed files with 24 additions and 10 deletions.
diff --git a/pymining/assocrules.py b/pymining/assocrules.py
@@ -7,8 +7,8 @@ def mine_assoc_rules(isets, min_support=2, min_confidence=0.5):
             continue
 
         for item in key:
-            left = frozenset([item])
-            right = key.difference([item])
+            left = key.difference([item])
+            right = frozenset([item])
             _mine_assoc_rules(left, right, support, visited, isets,
                     min_support, min_confidence, rules)
 
@@ -17,7 +17,7 @@ def mine_assoc_rules(isets, min_support=2, min_confidence=0.5):
 
 def _mine_assoc_rules(left, right, rule_support, visited, isets, min_support,
         min_confidence, rules):
-    if (left, right) in visited or len(right) < 1:
+    if (left, right) in visited or len(left) < 1:
         return
     else:
         visited.add((left, right))
@@ -26,9 +26,9 @@ def _mine_assoc_rules(left, right, rule_support, visited, isets, min_support,
     confidence = float(rule_support) / float(support_a)
     if confidence >= min_confidence:
         rules.append((left, right, rule_support, confidence))
-        # We can try to increase left!
-        for item in right:
-            new_left = left.union([item])
-            new_right = right.difference([item])
+        # We can try to increase right!
+        for item in left:
+            new_left = left.difference([item])
+            new_right = right.union([item])
             _mine_assoc_rules(new_left, new_right, rule_support, visited, isets,
                     min_support, min_confidence, rules)
diff --git a/tests/assocrules_tests.py b/tests/assocrules_tests.py
@@ -8,7 +8,7 @@ def testDefaultSupportConf(self):
         relim_input = itemmining.get_relim_input(ts1)
         report = itemmining.relim(relim_input, 2)
         rules = assocrules.mine_assoc_rules(report, min_support=2)
-        self.assertEqual(20, len(rules))
+        self.assertEqual(23, len(rules))
 
         a_rule = (frozenset(['b', 'e']), frozenset(['d']), 2, 1.0)
         self.assertTrue(a_rule in rules)
@@ -17,7 +17,7 @@ def testDefaultSupportConf(self):
         relim_input = itemmining.get_relim_input(ts2)
         report = itemmining.relim(relim_input, 2)
         rules = assocrules.mine_assoc_rules(report, min_support=2)
-        self.assertEqual(20, len(rules))
+        self.assertEqual(29, len(rules))
 
         a_rule = (frozenset(['e']), frozenset(['a', 'd']), 2, 2.0/3.0)
         self.assertTrue(a_rule in rules)
@@ -28,7 +28,7 @@ def testConfidence075(self):
         report = itemmining.relim(relim_input, 2)
         rules = assocrules.mine_assoc_rules(report, min_support=2,
                 min_confidence=0.75)
-        self.assertEqual(5, len(rules))
+        self.assertEqual(8, len(rules))
 
         a_rule = (frozenset(['b']), frozenset(['d']), 6, 0.75)
         self.assertTrue(a_rule in rules)
@@ -42,3 +42,17 @@ def testSupport5(self):
 
         a_rule = (frozenset(['d']), frozenset(['b']), 6, 0.75)
         self.assertTrue(a_rule in rules)
+
+    def testConfidenceForComplexRules(self):
+        transab = (('a', 'b'), ) * 1000
+        transac = (('a', 'c'), ) * 1000
+        transabc = (('a', 'b', 'c'), ) * 5
+        trans = transab + transac + transabc
+        relim_input = itemmining.get_relim_input(trans)
+        report = itemmining.relim(relim_input, 5)
+        rules = assocrules.mine_assoc_rules(
+            report, min_support=5, min_confidence=0.9)
+        self.assertEqual(3, len(rules))
+
+        a_rule = (frozenset(['b', 'c']), frozenset(['a']), 5, 1.0)
+        self.assertTrue(a_rule in rules)