hastic-server/analytics/step_detector.py

import numpy as np
import pickle
from scipy.signal import argrelextrema

def is_intersect(target_segment, segments):
    for segment in segments:
        start = max(segment['start'], target_segment[0])
        finish = min(segment['finish'], target_segment[1])
        if start <= finish:
            return True
    return False

def exponential_smoothing(series, alpha):
    result = [series[0]]
    for n in range(1, len(series)):
        result.append(alpha * series[n] + (1 - alpha) * result[n-1])
    return result

class StepDetector:

    def __init__(self, pattern):
        self.pattern = pattern
        self.segments = []
        self.confidence = 1.5

    def fit(self, dataframe, segments):
        data = dataframe['value']
        confidences = []
        for segment in segments:
            if segment['labeled']:
                segment_data = data[segment['start'] : segment['finish'] + 1]
                segment_min = min(segment_data)
                segment_max = max(segment_data)
                confidences.append(0.24 * (segment_max - segment_min))
        if len(confidences) > 0:
            self.confidence = min(confidences)
        else:
            self.confidence = 1.5


    def predict(self, dataframe):
        data = dataframe['value']

        result = self.__predict(data)
        result.sort()

        if len(self.segments) > 0:
            result = [segment for segment in result if not is_intersect(segment, self.segments)]
        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]
        extrema_list = []

        for i in exponential_smoothing(data - self.confidence, 0.03):
            extrema_list.append(i)

        segments = []
        for i in all_mins:
            if all_max_flatten_data[i] < extrema_list[i]:
                segments.append(i - window_size)

        return [(x - 1, x + 1) for x in self.__filter_prediction(segments, all_max_flatten_data)]

    def __filter_prediction(self, segments, all_max_flatten_data):
        delete_list = []
        for i in segments:
            new_data = all_max_flatten_data[i-50:i+250]
            min_value = 100
            for val in new_data:
                if val < min_value:
                    min_value = val
            if all_max_flatten_data[i] > min_value:
                delete_list.append(i)

        for item in delete_list:
            segments.remove(item)

        return segments

    def save(self, model_filename):
        with open(model_filename, 'wb') as file:
            pickle.dump((self.confidence), file)

    def load(self, model_filename):
        try:
            with open(model_filename, 'rb') as file:
                self.confidence = pickle.load(file)
        except:
            pass