Merge branch 'develop' into feature/refactor

.travis.yml

@@ -1,7 +1,6 @@
 language: python
 python:
   - 2.7
-  - 3.3
   - 3.4
   - 3.5
 install:
@@ -12,7 +11,7 @@ script:
   # Normal unit tests.
   - coverage run --source=apyori setup.py test
   # Code quality check.
-  - pylint apyori.py test/*.py
+  - pyflakes apyori.py test/*.py
   # Integration test
   - apyori-run data/integration_test_input_1.tsv > result.txt
   - diff result.txt data/integration_test_output_1.txt

apyori.py

@@ -208,14 +208,16 @@ def gen_ordered_statistics(transaction_manager, record):
         record -- A support record as a SupportRecord instance.
     """
     items = record.items
-    for combination_set in combinations(sorted(items), len(items) - 1):
-        items_base = frozenset(combination_set)
-        items_add = frozenset(items.difference(items_base))
-        confidence = (
-            record.support / transaction_manager.calc_support(items_base))
-        lift = confidence / transaction_manager.calc_support(items_add)
-        yield OrderedStatistic(
-            frozenset(items_base), frozenset(items_add), confidence, lift)
+    sorted_items = sorted(items)
+    for base_length in range(len(items)):
+        for combination_set in combinations(sorted_items, base_length):
+            items_base = frozenset(combination_set)
+            items_add = frozenset(items.difference(items_base))
+            confidence = (
+                record.support / transaction_manager.calc_support(items_base))
+            lift = confidence / transaction_manager.calc_support(items_add)
+            yield OrderedStatistic(
+                frozenset(items_base), frozenset(items_add), confidence, lift)
 
 
 def filter_ordered_statistics(ordered_statistics, **kwargs):

data/integration_test_output_1.txt

@@ -4,15 +4,15 @@
 {"items": ["beer", "butter"], "support": 0.25, "ordered_statistics": [{"items_base": ["butter"], "items_add": ["beer"], "confidence": 0.6666666666666666, "lift": 1.0666666666666667}]}
 {"items": ["beer", "cheese"], "support": 0.25, "ordered_statistics": [{"items_base": ["cheese"], "items_add": ["beer"], "confidence": 0.6666666666666666, "lift": 1.0666666666666667}]}
 {"items": ["beer", "jam"], "support": 0.375, "ordered_statistics": [{"items_base": ["beer"], "items_add": ["jam"], "confidence": 0.6, "lift": 1.2}, {"items_base": ["jam"], "items_add": ["beer"], "confidence": 0.75, "lift": 1.2}]}
-{"items": ["beer", "nuts"], "support": 0.5, "ordered_statistics": [{"items_base": ["beer"], "items_add": ["nuts"], "confidence": 0.8, "lift": 1.28}, {"items_base": ["nuts"], "items_add": ["beer"], "confidence": 0.8, "lift": 1.28}]}
+{"items": ["beer", "nuts"], "support": 0.5, "ordered_statistics": [{"items_base": [], "items_add": ["beer", "nuts"], "confidence": 0.5, "lift": 1.0}, {"items_base": ["beer"], "items_add": ["nuts"], "confidence": 0.8, "lift": 1.28}, {"items_base": ["nuts"], "items_add": ["beer"], "confidence": 0.8, "lift": 1.28}]}
 {"items": ["cheese", "nuts"], "support": 0.375, "ordered_statistics": [{"items_base": ["cheese"], "items_add": ["nuts"], "confidence": 1.0, "lift": 1.6}, {"items_base": ["nuts"], "items_add": ["cheese"], "confidence": 0.6, "lift": 1.5999999999999999}]}
 {"items": ["jam", "nuts"], "support": 0.375, "ordered_statistics": [{"items_base": ["jam"], "items_add": ["nuts"], "confidence": 0.75, "lift": 1.2}, {"items_base": ["nuts"], "items_add": ["jam"], "confidence": 0.6, "lift": 1.2}]}
 {"items": ["beer", "butter", "jam"], "support": 0.125, "ordered_statistics": [{"items_base": ["beer", "butter"], "items_add": ["jam"], "confidence": 0.5, "lift": 1.0}, {"items_base": ["butter", "jam"], "items_add": ["beer"], "confidence": 1.0, "lift": 1.6}]}
 {"items": ["beer", "butter", "nuts"], "support": 0.125, "ordered_statistics": [{"items_base": ["beer", "butter"], "items_add": ["nuts"], "confidence": 0.5, "lift": 0.8}, {"items_base": ["butter", "nuts"], "items_add": ["beer"], "confidence": 1.0, "lift": 1.6}]}
 {"items": ["beer", "cheese", "jam"], "support": 0.125, "ordered_statistics": [{"items_base": ["beer", "cheese"], "items_add": ["jam"], "confidence": 0.5, "lift": 1.0}, {"items_base": ["cheese", "jam"], "items_add": ["beer"], "confidence": 1.0, "lift": 1.6}]}
-{"items": ["beer", "cheese", "nuts"], "support": 0.25, "ordered_statistics": [{"items_base": ["beer", "cheese"], "items_add": ["nuts"], "confidence": 1.0, "lift": 1.6}, {"items_base": ["beer", "nuts"], "items_add": ["cheese"], "confidence": 0.5, "lift": 1.3333333333333333}, {"items_base": ["cheese", "nuts"], "items_add": ["beer"], "confidence": 0.6666666666666666, "lift": 1.0666666666666667}]}
-{"items": ["beer", "jam", "nuts"], "support": 0.375, "ordered_statistics": [{"items_base": ["beer", "jam"], "items_add": ["nuts"], "confidence": 1.0, "lift": 1.6}, {"items_base": ["beer", "nuts"], "items_add": ["jam"], "confidence": 0.75, "lift": 1.5}, {"items_base": ["jam", "nuts"], "items_add": ["beer"], "confidence": 1.0, "lift": 1.6}]}
+{"items": ["beer", "cheese", "nuts"], "support": 0.25, "ordered_statistics": [{"items_base": ["cheese"], "items_add": ["beer", "nuts"], "confidence": 0.6666666666666666, "lift": 1.3333333333333333}, {"items_base": ["beer", "cheese"], "items_add": ["nuts"], "confidence": 1.0, "lift": 1.6}, {"items_base": ["beer", "nuts"], "items_add": ["cheese"], "confidence": 0.5, "lift": 1.3333333333333333}, {"items_base": ["cheese", "nuts"], "items_add": ["beer"], "confidence": 0.6666666666666666, "lift": 1.0666666666666667}]}
+{"items": ["beer", "jam", "nuts"], "support": 0.375, "ordered_statistics": [{"items_base": ["beer"], "items_add": ["jam", "nuts"], "confidence": 0.6, "lift": 1.5999999999999999}, {"items_base": ["jam"], "items_add": ["beer", "nuts"], "confidence": 0.75, "lift": 1.5}, {"items_base": ["nuts"], "items_add": ["beer", "jam"], "confidence": 0.6, "lift": 1.5999999999999999}, {"items_base": ["beer", "jam"], "items_add": ["nuts"], "confidence": 1.0, "lift": 1.6}, {"items_base": ["beer", "nuts"], "items_add": ["jam"], "confidence": 0.75, "lift": 1.5}, {"items_base": ["jam", "nuts"], "items_add": ["beer"], "confidence": 1.0, "lift": 1.6}]}
 {"items": ["butter", "jam", "nuts"], "support": 0.125, "ordered_statistics": [{"items_base": ["butter", "jam"], "items_add": ["nuts"], "confidence": 1.0, "lift": 1.6}, {"items_base": ["butter", "nuts"], "items_add": ["jam"], "confidence": 1.0, "lift": 2.0}]}
 {"items": ["cheese", "jam", "nuts"], "support": 0.125, "ordered_statistics": [{"items_base": ["cheese", "jam"], "items_add": ["nuts"], "confidence": 1.0, "lift": 1.6}]}
-{"items": ["beer", "butter", "jam", "nuts"], "support": 0.125, "ordered_statistics": [{"items_base": ["beer", "butter", "jam"], "items_add": ["nuts"], "confidence": 1.0, "lift": 1.6}, {"items_base": ["beer", "butter", "nuts"], "items_add": ["jam"], "confidence": 1.0, "lift": 2.0}, {"items_base": ["butter", "jam", "nuts"], "items_add": ["beer"], "confidence": 1.0, "lift": 1.6}]}
-{"items": ["beer", "cheese", "jam", "nuts"], "support": 0.125, "ordered_statistics": [{"items_base": ["beer", "cheese", "jam"], "items_add": ["nuts"], "confidence": 1.0, "lift": 1.6}, {"items_base": ["beer", "cheese", "nuts"], "items_add": ["jam"], "confidence": 0.5, "lift": 1.0}, {"items_base": ["cheese", "jam", "nuts"], "items_add": ["beer"], "confidence": 1.0, "lift": 1.6}]}
+{"items": ["beer", "butter", "jam", "nuts"], "support": 0.125, "ordered_statistics": [{"items_base": ["beer", "butter"], "items_add": ["jam", "nuts"], "confidence": 0.5, "lift": 1.3333333333333333}, {"items_base": ["butter", "jam"], "items_add": ["beer", "nuts"], "confidence": 1.0, "lift": 2.0}, {"items_base": ["butter", "nuts"], "items_add": ["beer", "jam"], "confidence": 1.0, "lift": 2.6666666666666665}, {"items_base": ["beer", "butter", "jam"], "items_add": ["nuts"], "confidence": 1.0, "lift": 1.6}, {"items_base": ["beer", "butter", "nuts"], "items_add": ["jam"], "confidence": 1.0, "lift": 2.0}, {"items_base": ["butter", "jam", "nuts"], "items_add": ["beer"], "confidence": 1.0, "lift": 1.6}]}
+{"items": ["beer", "cheese", "jam", "nuts"], "support": 0.125, "ordered_statistics": [{"items_base": ["beer", "cheese"], "items_add": ["jam", "nuts"], "confidence": 0.5, "lift": 1.3333333333333333}, {"items_base": ["cheese", "jam"], "items_add": ["beer", "nuts"], "confidence": 1.0, "lift": 2.0}, {"items_base": ["beer", "cheese", "jam"], "items_add": ["nuts"], "confidence": 1.0, "lift": 1.6}, {"items_base": ["beer", "cheese", "nuts"], "items_add": ["jam"], "confidence": 0.5, "lift": 1.0}, {"items_base": ["cheese", "jam", "nuts"], "items_add": ["beer"], "confidence": 1.0, "lift": 1.6}]}

dev-requirements.txt

@@ -3,4 +3,4 @@ nose
 mock
 
 # Code quality utilities.
-pylint
+pyflakes

setup.py

@@ -32,7 +32,6 @@
         'License :: OSI Approved :: MIT License',
         'Programming Language :: Python',
         'Programming Language :: Python :: 2.7',
-        'Programming Language :: Python :: 3.3',
         'Programming Language :: Python :: 3.4',
         'Programming Language :: Python :: 3.5',
         'Topic :: Scientific/Engineering :: Mathematics',

test/test_gen_ordered_statistics.py

@@ -17,17 +17,43 @@ def test_normal():
     """
     transaction_manager = Mock(spec=TransactionManager)
     transaction_manager.calc_support.side_effect = lambda key: {
+        frozenset([]): 1.0,
         frozenset(['A']): 0.8,
         frozenset(['B']): 0.4,
         frozenset(['C']): 0.2,
         frozenset(['A', 'B']): 0.2,
         frozenset(['A', 'C']): 0.1,
         frozenset(['B', 'C']): 0.01,
+        frozenset(['A', 'B', 'C']): 0.001,
     }.get(key, 0.0)
 
     test_data = SupportRecord(frozenset(['A', 'B', 'C']), 0.001)
     results = list(gen_ordered_statistics(transaction_manager, test_data))
     eq_(results, [
+        OrderedStatistic(
+            frozenset([]),
+            frozenset(['A', 'B', 'C']),
+            0.001 / 1.0,
+            0.001 / 1.0 / 0.001,
+        ),
+        OrderedStatistic(
+            frozenset(['A']),
+            frozenset(['B', 'C']),
+            0.001 / 0.8,
+            0.001 / 0.8 / 0.01,
+        ),
+        OrderedStatistic(
+            frozenset(['B']),
+            frozenset(['A', 'C']),
+            0.001 / 0.4,
+            0.001 / 0.4 / 0.1,
+        ),
+        OrderedStatistic(
+            frozenset(['C']),
+            frozenset(['A', 'B']),
+            0.001 / 0.2,
+            0.001 / 0.2 / 0.2,
+        ),
         OrderedStatistic(
             frozenset(['A', 'B']),
             frozenset(['C']),