IndexError: list index out of range if segment has NaN #242 (#349)

add threshold in model

analytics/analytics/models/drop_model.py

@@ -37,10 +37,9 @@ class DropModel(Model):
         patterns_list = []
         for segment in segments:
             if segment['labeled']:
-                segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
-                percent_of_nans = segment_data.isnull().sum() / len(segment_data)
-                if percent_of_nans > 0 or len(segment_data) == 0:
-                    continue
+                segment_from_index = segment.get('from')
+                segment_to_index = segment.get('to')
+                segment_data = segment.get('data')
                 confidence = utils.find_confidence(segment_data)
                 confidences.append(confidence)
                 segment_cent_index, drop_height, drop_length = utils.find_parameters(segment_data, segment_from_index, 'drop')
@@ -57,9 +56,9 @@ class DropModel(Model):
         del_conv_list = []
         for segment in segments:
             if segment['deleted']:
-                segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
-                if len(segment_data) == 0:
-                    continue
+                segment_from_index = segment.get('from')
+                segment_to_index = segment.get('to')
+                segment_data = segment.get('data')
                 segment_cent_index = utils.find_parameters(segment_data, segment_from_index, 'drop')[0]
                 deleted_drop = utils.get_interval(data, segment_cent_index, self.state['WINDOW_SIZE'])
                 deleted_drop = utils.subtract_min_without_nan(deleted_drop)

analytics/analytics/models/general_model.py

@@ -34,10 +34,9 @@ class GeneralModel(Model):
         patterns_list = []
         for segment in segments:
             if segment['labeled']:
-                segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
-                percent_of_nans = segment_data.isnull().sum() / len(segment_data)
-                if percent_of_nans > 0 or len(segment_data) == 0:
-                    continue
+                segment_from_index = segment.get('from')
+                segment_to_index = segment.get('to')
+                segment_data = segment.get('data')
                 center_ind = segment_from_index + math.ceil((segment_to_index - segment_from_index) / 2)
                 self.ipats.append(center_ind)
                 segment_data = utils.get_interval(data, center_ind, self.state['WINDOW_SIZE'])
@@ -50,9 +49,9 @@ class GeneralModel(Model):
         del_conv_list = []
         for segment in segments:
             if segment['deleted']:
-                segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
-                if len(segment_data) == 0:
-                    continue
+                segment_from_index = segment.get('from')
+                segment_to_index = segment.get('to')
+                segment_data = segment.get('data')
                 del_mid_index = segment_from_index + math.ceil((segment_to_index - segment_from_index) / 2)
                 deleted_pat = utils.get_interval(data, del_mid_index, self.state['WINDOW_SIZE'])
                 deleted_pat = utils.subtract_min_without_nan(segment_data)

analytics/analytics/models/jump_model.py

@@ -38,10 +38,9 @@ class JumpModel(Model):
         patterns_list = []
         for segment in segments:
             if segment['labeled']:
-                segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
-                percent_of_nans = segment_data.isnull().sum() / len(segment_data)
-                if percent_of_nans > 0 or len(segment_data) == 0:
-                    continue
+                segment_from_index = segment.get('from')
+                segment_to_index = segment.get('to')
+                segment_data = segment.get('data')
                 confidence = utils.find_confidence(segment_data)
                 confidences.append(confidence)
                 segment_cent_index, jump_height, jump_length = utils.find_parameters(segment_data, segment_from_index, 'jump')
@@ -58,9 +57,9 @@ class JumpModel(Model):
         del_conv_list = []
         for segment in segments:
             if segment['deleted']:
-                segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
-                if len(segment_data) == 0:
-                    continue
+                segment_from_index = segment.get('from')
+                segment_to_index = segment.get('to')
+                segment_data = segment.get('data')
                 segment_cent_index = utils.find_parameters(segment_data, segment_from_index, 'jump')[0]
                 deleted_jump = utils.get_interval(data, segment_cent_index, self.state['WINDOW_SIZE'])
                 deleted_jump = utils.subtract_min_without_nan(labeled_jump)

analytics/analytics/models/model.py

@@ -24,18 +24,29 @@ class Model(ABC):
 
         self.segments = segments
         segment_length_list = []
+        filtered_segments = []
         for segment in self.segments:
-            if segment['labeled']:
-                segment_from_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms'))
-                segment_to_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms'))
-
+            if segment['labeled'] or segment['deleted']:
+                parse_segment_dict = utils.parse_segment(segment, dataframe)
+                segment_from_index = parse_segment_dict.get('from')
+                segment_to_index = parse_segment_dict.get('to')
+                segment_data = parse_segment_dict.get('data')
+                percent_of_nans = segment_data.isnull().sum() / len(segment_data)
+                if percent_of_nans > 0.1 or len(segment_data) == 0:
+                    continue
+                if percent_of_nans > 0:
+                    nan_list = utils.find_nan_indexes(segment_data)
+                    segment_data = utils.nan_to_zero(segment_data, nan_list)
+                segment.update({'from': segment_from_index, 'to': segment_to_index, 'data': segment_data})
                 segment_length = abs(segment_to_index - segment_from_index)
                 segment_length_list.append(segment_length)
+                filtered_segments.append(segment)
+                    
         if len(segment_length_list) > 0:
             self.state['WINDOW_SIZE'] = math.ceil(max(segment_length_list) / 2)
         else:
             self.state['WINDOW_SIZE'] = 0
-        self.do_fit(dataframe, segments)
+        self.do_fit(dataframe, filtered_segments)
         return self.state
 
     def detect(self, dataframe: pd.DataFrame, cache: Optional[ModelCache]) -> dict:

analytics/analytics/models/peak_model.py

@@ -35,10 +35,9 @@ class PeakModel(Model):
         patterns_list = []
         for segment in segments:
             if segment['labeled']:
-                segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
-                percent_of_nans = segment_data.isnull().sum() / len(segment_data)
-                if percent_of_nans > 0 or len(segment_data) == 0:
-                    continue
+                segment_from_index = segment.get('from')
+                segment_to_index = segment.get('to')
+                segment_data = segment.get('data')
                 confidence = utils.find_confidence(segment_data)
                 confidences.append(confidence)
                 segment_max_index = segment_data.idxmax()
@@ -53,9 +52,9 @@ class PeakModel(Model):
         del_conv_list = []
         for segment in segments:
             if segment['deleted']:
-                segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
-                if len(segment_data) == 0:
-                    continue
+                segment_from_index = segment.get('from')
+                segment_to_index = segment.get('to')
+                segment_data = segment.get('data')
                 del_max_index = segment_data.idxmax()
                 deleted_peak = utils.get_interval(data, del_max_index, self.state['WINDOW_SIZE'])
                 deleted_peak = utils.subtract_min_without_nan(deleted_peak)

analytics/analytics/models/trough_model.py

@@ -35,10 +35,9 @@ class TroughModel(Model):
         patterns_list = []
         for segment in segments:
             if segment['labeled']:
-                segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
-                percent_of_nans = segment_data.isnull().sum() / len(segment_data)
-                if percent_of_nans > 0 or len(segment_data) == 0:
-                    continue
+                segment_from_index = segment.get('from')
+                segment_to_index = segment.get('to')
+                segment_data = segment.get('data')
                 confidence = utils.find_confidence(segment_data)
                 confidences.append(confidence)
                 segment_min_index = segment_data.idxmin()
@@ -53,10 +52,9 @@ class TroughModel(Model):
         del_conv_list = []
         for segment in segments:
             if segment['deleted']:
-                segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
-                percent_of_nans = segment_data.isnull().sum() / len(segment_data)
-                if percent_of_nans > 0 or len(segment_data) == 0:
-                    continue
+                segment_from_index = segment.get('from')
+                segment_to_index = segment.get('to')
+                segment_data = segment.get('data')
                 del_min_index = segment_data.idxmin()
                 deleted_trough = utils.get_interval(data, del_min_index, self.state['WINDOW_SIZE'])
                 deleted_trough = utils.subtract_min_without_nan(deleted_trough)

analytics/analytics/utils/segments.py

@@ -6,4 +6,4 @@ def parse_segment(segment: dict, dataframe: pd.DataFrame):
     start = timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms'))
     end = timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms'))
     data = dataframe['value'][start: end + 1]
-    return start, end, data
+    return {'from': start, 'to': end, 'data': data}