Drops pattern ValueError: All elements of patterns_list should have same length #414 (#418)

analytics/analytics/models/model.py

@@ -79,11 +79,6 @@ class Model(ABC):
             self.state['WINDOW_SIZE'] = math.ceil(max_length / 2) if max_length else 0
         model, model_type = self.get_model_type()
         learning_info = self.get_parameters_from_segments(dataframe, labeled, deleted, model, model_type)
-        if self.state.get('pattern_center') and self.state.get('pattern_model'):
-            for center in self.state['pattern_center']:
-                aligned_segment = utils.get_interval(data, center, self.state['WINDOW_SIZE'])
-                aligned_segment = utils.subtract_min_without_nan(aligned_segment)
-                learning_info['patterns_list'].append(aligned_segment)
         self.do_fit(dataframe, labeled, deleted, learning_info)
         return self.state
 

analytics/analytics/utils/common.py

@@ -80,21 +80,23 @@ def ar_mean(numbers):
     return float(sum(numbers)) / max(len(numbers), 1)
 
 def get_av_model(patterns_list):
-    if len(patterns_list) == 0:
-        return []
-    x = len(patterns_list[0])
-    if len(patterns_list) > 1 and len(patterns_list[1]) != x:
-        raise ValueError('All elements of patterns_list should have same length')
-
-    model_pat = []
-    for i in range(x):
-        av_val = []
-        for val in patterns_list:
-            if type(val) == pd.Series:
-                val = val.values
-        av_val.append(val[i])
-        model_pat.append(ar_mean(av_val))
-    return model_pat
+    if not patterns_list:  return []
+    patterns_list = get_same_length(patterns_list)
+    value_list = list(map(list, zip(*patterns_list)))
+    return list(map(ar_mean, value_list))
+
+def get_same_length(patterns_list):
+    for index in range(len(patterns_list)):
+        if type(patterns_list[index]) == pd.Series:
+            patterns_list[index] = patterns_list[index].tolist()
+    patterns_list = list(filter(None, patterns_list))
+    max_length = max(map(len, patterns_list))
+    for pat in patterns_list:
+        if len(pat) < max_length:
+            length_difference = max_length - len(pat)
+            added_values = list(0 for _ in range(length_difference))
+            pat.extend(added_values)
+    return patterns_list
 
 def close_filtering(pattern_list, win_size):
     if len(pattern_list) == 0:

analytics/tests/test_dataset.py

@@ -229,11 +229,31 @@ class TestDataset(unittest.TestCase):
         }
         data_val = [1.0, 1.0, 1.0, 4.0, 4.0, 0.0, 0.0, 5.0, 5.0, 0.0, 0.0, 4.0, 4.0, 4.0, 4.0]
         dataframe = create_dataframe(data_val)
-        segments = [{'_id': 'Esl7uetLhx4lCqHa', 'analyticUnitId': 'opnICRJwOmwBELK8', 'from': 1523889000010, 'to': 1523889000012, 'labeled': True, 'deleted': False}]
+        segments = [{'_id': 'Esl7uetLhx4lCqHa', 'analyticUnitId': 'opnICRJwOmwBELK8', 'from': 152388900009, 'to': 1523889000013, 'labeled': True, 'deleted': False}]
         model = models.JumpModel()
         result = model.fit(dataframe, segments, cache)
         self.assertEqual(len(result['pattern_center']), 3)
 
+    def test_models_for_pattern_model_cache(self):
+        cache = {
+            'pattern_center': [4, 12],
+            'pattern_model': [],
+            'confidence': 2,
+            'convolve_max': 8,
+            'convolve_min': 7,
+            'WINDOW_SIZE': 2,
+            'conv_del_min': 0,
+            'conv_del_max': 0,
+        }
+        data_val = [5.0, 5.0, 5.0, 5.0, 1.0, 1.0, 1.0, 1.0, 9.0, 9.0, 9.0, 9.0, 0, 0, 0, 0, 0, 0, 6.0, 6.0, 6.0, 1.0, 1.0, 1.0, 1.0, 1.0]
+        dataframe = create_dataframe(data_val)
+        segments = [{'_id': 'Esl7uetLhx4lCqHa', 'analyticUnitId': 'opnICRJwOmwBELK8', 'from': 1523889000019, 'to': 1523889000024, 'labeled': True, 'deleted': False}]
+        try:
+            model = models.DropModel()
+            model_name = model.__class__.__name__
+            model.fit(dataframe, segments, cache)
+        except ValueError:
+            self.fail('Model {} raised unexpectedly'.format(model_name))
 
 if __name__ == '__main__':
     unittest.main()

analytics/tests/test_utils.py

@@ -129,7 +129,12 @@ class TestUtils(unittest.TestCase):
         patterns_list = []
         result = []
         self.assertEqual(utils.get_av_model(patterns_list), result)
-    
+
+    def test_get_av_model_normal_data(self):
+        patterns_list = [[1, 1, 1], [2, 2, 2],[3,3,3]]
+        result = [2.0, 2.0, 2.0]
+        self.assertEqual(utils.get_av_model(patterns_list), result)
+
     def test_find_jump_nan_data(self):
         data = [np.NaN, np.NaN, np.NaN, np.NaN]
         data = pd.Series(data)
@@ -207,6 +212,13 @@ class TestUtils(unittest.TestCase):
             utils.get_convolve(segemnts, av_model, data, window_size)
         except ValueError:
             self.fail('Method get_convolve raised unexpectedly')
+    
+    def test_get_av_model_for_different_length(self):
+        patterns_list = [[1.0, 1.0, 2.0], [4.0, 4.0], [2.0, 2.0, 2.0], [3.0, 3.0], []]
+        try:
+            utils.get_av_model(patterns_list)
+        except ValueError:
+            self.fail('Method get_convolve raised unexpectedly')
 
 if __name__ == '__main__':
     unittest.main()