Models with filtering#186 (#218)

analytics/models/drop_model.py

@@ -154,17 +154,9 @@ class DropModel(Model):
 
     def __filter_prediction(self, segments: list, data: list):
         delete_list = []
-        variance_error = int(0.004 * len(data))
-        if variance_error > self.state['WINDOW_SIZE']:
         variance_error = self.state['WINDOW_SIZE']
-
-        for i in range(1, len(segments)):
-            if segments[i] < segments[i - 1] + variance_error:
-                delete_list.append(segments[i])
-        # for item in delete_list:
-        #    segments.remove(item)
-        delete_list = []
-
+        close_patterns = utils.close_filtering(segments, variance_error)
+        segments = utils.best_pat(close_patterns, data, 'min')
         if len(segments) == 0 or len(self.idrops) == 0 :
             segments = []
             return segments
@@ -186,8 +178,8 @@ class DropModel(Model):
                     delete_list.append(segment)
             else:
                 delete_list.append(segment)
-        # TODO: implement filtering
-        # for item in delete_list:
-        #     segments.remove(item)
+
+        for item in delete_list:
+            segments.remove(item)
 
         return set(segments)

analytics/models/jump_model.py

@@ -154,20 +154,13 @@ class JumpModel(Model):
 
     def __filter_prediction(self, segments, data):
         delete_list = []
-        variance_error = int(0.004 * len(data))
-        if variance_error > self.state['WINDOW_SIZE']:
         variance_error = self.state['WINDOW_SIZE']
-        for i in range(1, len(segments)):
-            if segments[i] < segments[i - 1] + variance_error:
-                delete_list.append(segments[i])
-        for item in delete_list:
-            segments.remove(item)
+        close_patterns = utils.close_filtering(segments, variance_error)
+        segments = utils.best_pat(close_patterns, data, 'max')
             
         if len(segments) == 0 or len(self.ijumps) == 0 :
             segments = []
             return segments
-        
-        delete_list = []
         pattern_data = self.model_jump
         upper_bound = self.state['convolve_max'] * 1.2
         lower_bound = self.state['convolve_min'] * 0.8
@@ -186,11 +179,8 @@ class JumpModel(Model):
                     delete_list.append(segment)
             else:
                 delete_list.append(segment)
+
         for item in delete_list:
             segments.remove(item)
 
-        # TODO: implement filtering
-        #for ijump in self.ijumps:
-            #segments.append(ijump)
-
         return set(segments)

analytics/models/peak_model.py

@@ -114,16 +114,10 @@ class PeakModel(Model):
 
     def __filter_prediction(self, segments: list, data: list) -> list:
         delete_list = []
-        variance_error = int(0.004 * len(data))
-        if variance_error > self.state['WINDOW_SIZE']:
         variance_error = self.state['WINDOW_SIZE']
-        for i in range(1, len(segments)):
-            if segments[i] < segments[i - 1] + variance_error:
-                delete_list.append(segments[i])
-        for item in delete_list:
-            segments.remove(item)
+        close_patterns = utils.close_filtering(segments, variance_error)
+        segments = utils.best_pat(close_patterns, data, 'max')
         
-        delete_list = []
         if len(segments) == 0 or len(self.ipeaks) == 0:
             return []
         pattern_data = self.model_peak
@@ -135,11 +129,9 @@ class PeakModel(Model):
                 if max(conv) > self.state['convolve_max'] * 1.05 or max(conv) < self.state['convolve_min'] * 0.95:
                     delete_list.append(segment)
                 elif max(conv) < self.state['conv_del_max'] * 1.02 and max(conv) > self.state['conv_del_min'] * 0.98:
-                    print("this must be deleted: {0}, index: {1}".format(max(conv), segment))
                     delete_list.append(segment)
             else:
                 delete_list.append(segment)
-        # TODO: implement filtering
         for item in delete_list:
             segments.remove(item)
 

analytics/models/trough_model.py

@@ -115,16 +115,9 @@ class TroughModel(Model):
 
     def __filter_prediction(self, segments: list, data: list) -> list:
         delete_list = []
-        variance_error = int(0.004 * len(data))
-        if variance_error > self.state['WINDOW_SIZE']:
         variance_error = self.state['WINDOW_SIZE']
-        for i in range(1, len(segments)):
-            if segments[i] < segments[i - 1] + variance_error:
-                delete_list.append(segments[i])
-        for item in delete_list:
-            segments.remove(item)
-
-        delete_list = []
+        close_patterns = utils.close_filtering(segments, variance_error)
+        segments = utils.best_pat(close_patterns, data, 'min')
         if len(segments) == 0 or len(self.itroughs) == 0 :
             segments = []
             return segments  
@@ -140,7 +133,6 @@ class TroughModel(Model):
                     delete_list.append(segment)
             else:
                 delete_list.append(segment)
-        # TODO: implement filtering
         for item in delete_list:
             segments.remove(item)
 

analytics/utils/common.py

@@ -1,6 +1,7 @@
 import numpy as np
 import pandas as pd
 
+
 def exponential_smoothing(series, alpha):
     result = [series[0]]
     for n in range(1, len(series)):
@@ -211,7 +212,11 @@ def ar_mean(numbers):
 
 def get_av_model(patterns_list):
     x = len(patterns_list[0])
+<<<<<<< HEAD
+    if len(pattern_list) > 1 and len(patterns_list[1]) != x:
+=======
     if len(patterns_list[1]) != x:
+>>>>>>> f3e8de3d4de8748ed7c9eb1b81e2d438e04f5f38
         raise NameError('All elements of patterns_list should have same length')
     model_pat = []
     for i in range(x):
@@ -220,3 +225,35 @@ def get_av_model(patterns_list):
             av_val.append(j.values[i])
         model_pat.append(ar_mean(av_val))
     return model_pat
+<<<<<<< HEAD
+
+def close_filtering(pat_list, win_size):
+    s = [[pat_list[0]]]
+    k = 0
+    for i in range(1, len(pat_list)):
+        if pat_list[i] - win_size <= s[k][-1]:
+            s[k].append(pat_list[i])
+        else:
+            k += 1
+            s.append([pat_list[i]])
+    return s
+
+def best_pat(pat_list, data, dir):
+    new_pat_list = []
+    for val in pat_list:
+        max_val = data[val[0]]
+        min_val = data[val[0]]
+        ind = 0
+        for i in val:
+            if dir == 'max':
+                if data[i] > max_val:
+                    max_val = data[i]
+                    ind = i
+            else:
+                if data[i] < min_val:
+                    min_val = data[i]
+                    ind = i
+        new_pat_list.append(ind)
+    return new_pat_list
+=======
+>>>>>>> f3e8de3d4de8748ed7c9eb1b81e2d438e04f5f38