WIP: Jump and drop v1 (#119)

* new jump model with height

* antipeak

* universal n/w jumps

* jump and drop models

* rm unneeded lines and trailing spaces

analytics/models/jump_model.py

@@ -10,7 +10,7 @@ from scipy.stats import gaussian_kde
 from scipy.stats import norm
 
 
-WINDOW_SIZE = 240
+WINDOW_SIZE = 400
 
 class JumpModel(Model):
 
@@ -32,7 +32,6 @@ class JumpModel(Model):
         convolve_list = []
         jump_height_list = []
         jump_length_list = []
-        print(segments)
         for segment in segments:
             if segment['labeled']:
                 segment_data = data.loc[segment['from'] : segment['to'] + 1].reset_index(drop=True)
@@ -100,17 +99,16 @@ class JumpModel(Model):
         return result
 
     def __predict(self, data):
-        window_size = 24
-        all_max_flatten_data = data.rolling(window=window_size).mean()
-        all_mins = argrelextrema(np.array(all_max_flatten_data), np.less)[0]        
-       
+        #window_size = 24
+        #all_max_flatten_data = data.rolling(window=window_size).mean()
+        #all_mins = argrelextrema(np.array(all_max_flatten_data), np.less)[0]
         possible_jumps = utils.find_jump(data, self.state['JUMP_HEIGHT'], self.state['JUMP_LENGTH'] + 1)
 
-        return [(x - 1, x + 1) for x in self.__filter_prediction(possible_jumps, all_max_flatten_data)]
+        return [(x - 1, x + 1) for x in self.__filter_prediction(possible_jumps, data)]
 
-    def __filter_prediction(self, segments, all_max_flatten_data):
+    def __filter_prediction(self, segments, data):
         delete_list = []
-        variance_error = int(0.004 * len(all_max_flatten_data))
+        variance_error = int(0.004 * len(data))
         if variance_error > 50:
             variance_error = 50
         for i in range(1, len(segments)):
@@ -122,10 +120,12 @@ class JumpModel(Model):
         if len(segments) == 0 or len(self.ijumps) == 0 :
             segments = []
             return segments
-        pattern_data = all_max_flatten_data[self.ijumps[0] - WINDOW_SIZE : self.ijumps[0] + WINDOW_SIZE]
+
+        pattern_data = data[self.ijumps[0] - WINDOW_SIZE : self.ijumps[0] + WINDOW_SIZE]
         for segment in segments:
-            if segment > WINDOW_SIZE:
-                convol_data = all_max_flatten_data[segment - WINDOW_SIZE : segment + WINDOW_SIZE]
+            if segment > WINDOW_SIZE and segment < (len(data) - WINDOW_SIZE):
+                convol_data = data[segment - WINDOW_SIZE : segment + WINDOW_SIZE]
+
                 conv = scipy.signal.fftconvolve(pattern_data, convol_data)
                 if max(conv) > self.state['convolve_max'] * 1.2 or max(conv) < self.state['convolve_max'] * 0.8:
                     delete_list.append(segment)
@@ -137,4 +137,5 @@ class JumpModel(Model):
         for ijump in self.ijumps:
             segments.append(ijump)
 
+
         return segments

analytics/models/step_model.py

@@ -3,11 +3,13 @@ from models import Model
 import scipy.signal
 from scipy.fftpack import fft
 from scipy.signal import argrelextrema
+from scipy.stats import gaussian_kde
 
 import utils
 import numpy as np
 import pandas as pd
 
+WINDOW_SIZE = 400
 
 class StepModel(Model):
     def __init__(self):
@@ -16,31 +18,61 @@ class StepModel(Model):
         self.idrops = []
         self.state = {
             'confidence': 1.5,
-            'convolve_max': 570000
+            'convolve_max': WINDOW_SIZE,
+            'DROP_HEIGHT': 1,
+            'DROP_LENGTH': 1,
         }
 
     def fit(self, dataframe, segments):
         self.segments = segments
-        #dataframe = dataframe.iloc[::-1]
         d_min = min(dataframe['value'])
         for i in range(0,len(dataframe['value'])):
             dataframe.loc[i, 'value'] = dataframe.loc[i, 'value'] - d_min
         data = dataframe['value']
+
         confidences = []
         convolve_list = []
+        drop_height_list = []
+        drop_length_list = []
         for segment in segments:
             if segment['labeled']:
                 segment_from_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['from']))
                 segment_to_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['to']))
 
-                segment_data = data[segment_from_index : segment_to_index + 1]
+                segment_data = data[segment_from_index : segment_to_index + 1].reset_index(drop=True)
                 segment_min = min(segment_data)
                 segment_max = max(segment_data)
-                confidences.append( 0.4*(segment_max - segment_min))
-                flat_segment = segment_data #.rolling(window=5).mean()
-                segment_min_index = flat_segment.idxmin() - 5
-                self.idrops.append(segment_min_index)
-                labeled_drop = data[segment_min_index - 240 : segment_min_index + 240]
+                confidences.append(0.20 * (segment_max - segment_min))
+                flat_segment = segment_data.rolling(window=5).mean()
+                pdf = gaussian_kde(flat_segment.dropna())
+                x = np.linspace(flat_segment.dropna().min(), flat_segment.dropna().max(), len(flat_segment.dropna()))
+                y = pdf(x)
+                ax_list = []
+                for i in range(len(x)):
+                    ax_list.append([x[i], y[i]])
+                ax_list = np.array(ax_list, np.float32)
+                antipeaks_kde = argrelextrema(np.array(ax_list), np.less)[0]
+                peaks_kde = argrelextrema(np.array(ax_list), np.greater)[0]
+                min_peak_index = peaks_kde[0]
+                max_peak_index = peaks_kde[1]
+                segment_median = ax_list[antipeaks_kde[0], 0]
+                segment_min_line = ax_list[min_peak_index, 0]
+                segment_max_line = ax_list[max_peak_index, 0]
+                #print(segment_min_line, segment_max_line)
+                drop_height = 0.95 * (segment_max_line - segment_min_line)
+                drop_height_list.append(drop_height)
+                drop_lenght = utils.find_drop_length(segment_data, segment_min_line, segment_max_line)
+                #print(drop_lenght)
+                drop_length_list.append(drop_lenght)
+                cen_ind = utils.drop_intersection(flat_segment, segment_median) #finds all interseprions with median
+                drop_center = cen_ind[0]
+                segment_cent_index = drop_center - 5 + segment['start']
+                self.idrops.append(segment_cent_index)
+                labeled_drop = data[segment_cent_index - WINDOW_SIZE : segment_cent_index + WINDOW_SIZE]
+                labeled_min = min(labeled_drop)
+                for value in labeled_drop:
+                    value = value - labeled_min
+
                 convolve = scipy.signal.fftconvolve(labeled_drop, labeled_drop)
                 convolve_list.append(max(convolve))
 
@@ -52,11 +84,20 @@ class StepModel(Model):
         if len(convolve_list) > 0:
             self.state['convolve_max'] = max(convolve_list)
         else:
-            self.state['convolve_max'] = 570000
+            self.state['convolve_max'] = WINDOW_SIZE
+
+        if len(drop_height_list) > 0:
+            self.state['DROP_HEIGHT'] = min(drop_height_list)
+        else:
+            self.state['DROP_HEIGHT'] = 1
+
+        if len(drop_length_list) > 0:
+            self.state['DROP_LENGTH'] = max(drop_length_list)
+        else:
+            self.state['DROP_LENGTH'] = 1
 
 
     async def predict(self, dataframe):
-        #dataframe = dataframe.iloc[::-1]
         d_min = min(dataframe['value'])
         for i in range(0,len(dataframe['value'])):
             dataframe.loc[i, 'value'] = dataframe.loc[i, 'value'] - d_min
@@ -71,54 +112,42 @@ class StepModel(Model):
         return result
 
     def __predict(self, data):
-        window_size = 24
-        all_max_flatten_data = data.rolling(window=window_size).mean()
-        new_flat_data = []
-        for val in all_max_flatten_data:
-            new_flat_data.append(val)
-            
-        all_mins = argrelextrema(np.array(all_max_flatten_data), np.less)[0]
-        
-        extrema_list = []
-        for i in utils.exponential_smoothing(data - self.state['confidence'], 0.01):
-            extrema_list.append(i)
-        #extrema_list = extrema_list[::-1]
-
-        segments = []
-        for i in all_mins:
-            if new_flat_data[i] < extrema_list[i]:
-                segments.append(i) #-window_size
-        
-
-        return [(x - 1, x + 1) for x in self.__filter_prediction(segments, new_flat_data)]
-
-    def __filter_prediction(self, segments, new_flat_data):
+        #window_size = 24
+        #all_max_flatten_data = data.rolling(window=window_size).mean()
+        #all_mins = argrelextrema(np.array(all_max_flatten_data), np.less)[0]
+        #print(self.state['DROP_HEIGHT'],self.state['DROP_LENGTH'] )
+        possible_drops = utils.find_drop(data, self.state['DROP_HEIGHT'], self.state['DROP_LENGTH'] + 1)
+        return [(x - 1, x + 1) for x in self.__filter_prediction(possible_drops, data)]
+
+    def __filter_prediction(self, segments, data):
         delete_list = []
-        variance_error = int(0.004 * len(new_flat_data))
-        if variance_error > 100:
-            variance_error = 100
+        variance_error = int(0.004 * len(data))
+        if variance_error > 50:
+            variance_error = 50
+
         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 = []
-        print(self.idrops[0])
-        pattern_data = new_flat_data[self.idrops[0] - 240 : self.idrops[0] + 240]
-        print(self.state['convolve_max'])
+
+        if len(segments) == 0 or len(self.idrops) == 0 :
+            segments = []
+            return segments
+        pattern_data = data[self.idrops[0] - WINDOW_SIZE : self.idrops[0] + WINDOW_SIZE]
         for segment in segments:
-            if segment > 240:
-                convol_data = new_flat_data[segment - 240 : segment + 240]
+            if segment > WINDOW_SIZE and segment < (len(data) - WINDOW_SIZE):
+                convol_data = data[segment - WINDOW_SIZE : segment + WINDOW_SIZE]
                 conv = scipy.signal.fftconvolve(pattern_data, convol_data)
-                if conv[480] > self.state['convolve_max'] * 1.2 or conv[480] < self.state['convolve_max'] * 0.9:
+                if conv[WINDOW_SIZE*2] > self.state['convolve_max'] * 1.2 or conv[WINDOW_SIZE*2] < self.state['convolve_max'] * 0.8:
                     delete_list.append(segment)
-                    print(segment, conv[480], 0)
-                else:
-                    print(segment, conv[480], 1)
             else:
                 delete_list.append(segment)
         for item in delete_list:
             segments.remove(item)
+        #print(segments)
+        for idrop in self.idrops:
+            segments.append(idrop)
 
         return segments

analytics/utils/__init__.py

@@ -158,6 +158,46 @@ def find_jump(data, height, lenght):
                 j_list.append(i)
     return(j_list)
 
+def find_drop_length(segment_data, min_line, max_line):
+    x = np.arange(0, len(segment_data))
+    f = []
+    l = []
+    for i in range(len(segment_data)):
+        f.append(min_line)
+        l.append(max_line)
+    f = np.array(f)
+    l = np.array(l)
+    g = []    
+    for i in segment_data:
+        g.append(i)
+    g = np.array(g)
+    idx = np.argwhere(np.diff(np.sign(f - g)) != 0).reshape(-1) + 0 #min_line
+    idl = np.argwhere(np.diff(np.sign(l - g)) != 0).reshape(-1) + 0 #max_line
+    if (idx[0] - idl[-1] + 1) > 0:
+        return idx[0] - idl[-1] + 1
+    else:
+        return print("retard alert!")
+
+def drop_intersection(segment_data, median_line):
+    x = np.arange(0, len(segment_data))
+    f = []
+    for i in range(len(segment_data)):
+        f.append(median_line)
+    f = np.array(f)
+    g = []    
+    for i in segment_data:
+        g.append(i)
+    g = np.array(g)
+    idx = np.argwhere(np.diff(np.sign(f - g)) != 0).reshape(-1) + 0 
+    return idx
+
+def find_drop(data, height, lenght):
+    d_list = []
+    for i in range(len(data)-lenght-1):
+        for x in range(1, lenght):
+            if(data[i+x] < data[i] - height):
+                d_list.append(i+36)
+    return(d_list)
 
 def timestamp_to_index(dataframe, timestamp):
     data = dataframe['timestamp']