hastic
/
hastic-server
4
0
Fork 0
Code Issues Pull Requests Projects Releases 1 Wiki Activity
Browse Source

Move repeating code from models to utils #270 (#272) 

peak / trough / jump / drop / general common code to and utils refactoring
pull/1/head
Alexandr Velikiy 6 years ago committed by Alexey Velikiy
parent
bd1e151ef4
commit
d389cf3adb
7 changed files with 135 additions and 183 deletions
Whitespace
Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL
Unified View
Diff Options
Show Stats Download Patch File Download Diff File
  1. 70
      analytics/analytics/models/drop_model.py
  2. 32
      analytics/analytics/models/general_model.py
  3. 67
      analytics/analytics/models/jump_model.py
  4. 33
      analytics/analytics/models/peak_model.py
  5. 33
      analytics/analytics/models/trough_model.py
  6. 79
      analytics/analytics/utils/common.py
  7. 2
      analytics/analytics/utils/segments.py

70
analytics/analytics/models/drop_model.py
Unescape View File

@ -36,78 +36,32 @@ class DropModel(Model):
patterns_list = [] patterns_list = []
for segment in segments: for segment in segments:
if segment['labeled']: if segment['labeled']:
segment_from_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms')) segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
segment_to_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms'))
segment_data = data[segment_from_index: segment_to_index + 1]
percent_of_nans = segment_data.isnull().sum() / len(segment_data) percent_of_nans = segment_data.isnull().sum() / len(segment_data)
if percent_of_nans > 0 or len(segment_data) == 0: if percent_of_nans > 0 or len(segment_data) == 0:
continue continue
segment_min = min(segment_data) confidence = utils.find_confidence(segment_data)
segment_max = max(segment_data) confidences.append(confidence)
confidences.append(0.20 * (segment_max - segment_min)) segment_cent_index, drop_height, drop_length = utils.find_drop_parameters(segment_data, segment_from_index)
flat_segment = segment_data.rolling(window = 5).mean()
pdf = gaussian_kde(flat_segment.dropna())
max_drop = max(flat_segment.dropna())
min_drop = min(flat_segment.dropna())
x = np.linspace(flat_segment.dropna().min() - 1, flat_segment.dropna().max() + 1, len(flat_segment.dropna()))
y = pdf(x)
ax_list = list(zip(x, y))
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]
try:
min_peak_index = peaks_kde[0]
segment_min_line = ax_list[min_peak_index, 0]
max_peak_index = peaks_kde[1]
segment_max_line = ax_list[max_peak_index, 0]
segment_median = ax_list[antipeaks_kde[0], 0]
except IndexError:
segment_max_line = max_drop
segment_min_line = min_drop
segment_median = (max_drop - min_drop) / 2 + min_drop
drop_height = 0.95 * (segment_max_line - segment_min_line)
drop_height_list.append(drop_height) drop_height_list.append(drop_height)
drop_length = utils.find_drop_length(segment_data, segment_min_line, segment_max_line)
drop_length_list.append(drop_length) drop_length_list.append(drop_length)
cen_ind = utils.drop_intersection(flat_segment.tolist(), segment_median) #finds all interseprions with median
drop_center = cen_ind[0]
segment_cent_index = drop_center - 5 + segment_from_index
self.idrops.append(segment_cent_index) self.idrops.append(segment_cent_index)
labeled_drop = data[segment_cent_index - self.state['WINDOW_SIZE']: segment_cent_index + self.state['WINDOW_SIZE'] + 1] labeled_drop = utils.get_interval(data, segment_cent_index, self.state['WINDOW_SIZE'])
labeled_drop = labeled_drop - min(labeled_drop) labeled_drop = utils.subtract_min_without_nan(labeled_drop)
patterns_list.append(labeled_drop) patterns_list.append(labeled_drop)
self.model_drop = utils.get_av_model(patterns_list) self.model_drop = utils.get_av_model(patterns_list)
for idrop in self.idrops: convolve_list = utils.get_convolve(self.idrops, self.model_drop, data, self.state['WINDOW_SIZE'])
labeled_drop = data[idrop - self.state['WINDOW_SIZE']: idrop + self.state['WINDOW_SIZE'] + 1]
labeled_drop = labeled_drop - min(labeled_drop)
auto_convolve = scipy.signal.fftconvolve(labeled_drop, labeled_drop)
convolve_drop = scipy.signal.fftconvolve(labeled_drop, self.model_drop)
convolve_list.append(max(auto_convolve))
convolve_list.append(max(convolve_drop))
del_conv_list = [] del_conv_list = []
for segment in segments: for segment in segments:
if segment['deleted']: if segment['deleted']:
segment_from_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms')) segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
segment_to_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms'))
segment_data = data[segment_from_index: segment_to_index + 1]
if len(segment_data) == 0: if len(segment_data) == 0:
continue continue
flat_segment = segment_data.rolling(window = 5).mean() segment_cent_index = utils.find_drop_parameters(segment_data, segment_from_index)[0]
flat_segment_dropna = flat_segment.dropna() deleted_drop = utils.get_interval(data, segment_cent_index, self.state['WINDOW_SIZE'])
pdf = gaussian_kde(flat_segment_dropna) deleted_drop = utils.subtract_min_without_nan(deleted_drop)
x = np.linspace(flat_segment_dropna.min() - 1, flat_segment_dropna.max() + 1, len(flat_segment_dropna))
y = pdf(x)
ax_list = list(zip(x, y))
ax_list = np.array(ax_list, np.float32)
antipeaks_kde = argrelextrema(np.array(ax_list), np.less)[0]
segment_median = ax_list[antipeaks_kde[0], 0]
cen_ind = utils.intersection_segment(flat_segment.tolist(), segment_median) #finds all interseprions with median
drop_center = cen_ind[0] # or -1? test
segment_cent_index = drop_center - 5 + segment_from_index
deleted_drop = data[segment_cent_index - self.state['WINDOW_SIZE'] : segment_cent_index + self.state['WINDOW_SIZE'] + 1]
deleted_drop = deleted_drop - min(labeled_drop)
del_conv_drop = scipy.signal.fftconvolve(deleted_drop, self.model_drop) del_conv_drop = scipy.signal.fftconvolve(deleted_drop, self.model_drop)
del_conv_list.append(max(del_conv_drop)) del_conv_list.append(max(del_conv_drop))
@ -163,7 +117,7 @@ class DropModel(Model):
pattern_data = self.model_drop pattern_data = self.model_drop
for segment in segments: for segment in segments:
if segment > self.state['WINDOW_SIZE'] and segment < (len(data) - self.state['WINDOW_SIZE']): if segment > self.state['WINDOW_SIZE'] and segment < (len(data) - self.state['WINDOW_SIZE']):
convol_data = data[segment - self.state['WINDOW_SIZE'] : segment + self.state['WINDOW_SIZE'] + 1] convol_data = utils.get_interval(data, segment, self.state['WINDOW_SIZE'])
percent_of_nans = convol_data.isnull().sum() / len(convol_data) percent_of_nans = convol_data.isnull().sum() / len(convol_data)
if percent_of_nans > 0.5: if percent_of_nans > 0.5:
delete_list.append(segment) delete_list.append(segment)

32
analytics/analytics/models/general_model.py
Unescape View File

@ -34,39 +34,28 @@ class GeneralModel(Model):
patterns_list = [] patterns_list = []
for segment in segments: for segment in segments:
if segment['labeled']: if segment['labeled']:
segment_from_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms')) segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
segment_to_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms'))
segment_data = data[segment_from_index: segment_to_index + 1]
percent_of_nans = segment_data.isnull().sum() / len(segment_data) percent_of_nans = segment_data.isnull().sum() / len(segment_data)
if percent_of_nans > 0 or len(segment_data) == 0: if percent_of_nans > 0 or len(segment_data) == 0:
continue continue
x = segment_from_index + math.ceil((segment_to_index - segment_from_index) / 2) center_ind = segment_from_index + math.ceil((segment_to_index - segment_from_index) / 2)
self.ipats.append(x) self.ipats.append(center_ind)
segment_data = data[x - self.state['WINDOW_SIZE'] : x + self.state['WINDOW_SIZE']] segment_data = utils.get_interval(data, center_ind, self.state['WINDOW_SIZE'])
segment_min = min(segment_data) segment_data = utils.subtract_min_without_nan(segment_data)
segment_data = segment_data - segment_min
patterns_list.append(segment_data) patterns_list.append(segment_data)
self.model_gen = utils.get_av_model(patterns_list) self.model_gen = utils.get_av_model(patterns_list)
for ipat in self.ipats: #labeled segments convolve_list = utils.get_convolve(self.ipats, self.model_gen, data, self.state['WINDOW_SIZE'])
labeled_data = data[ipat - self.state['WINDOW_SIZE']: ipat + self.state['WINDOW_SIZE'] + 1]
labeled_data = labeled_data - min(labeled_data)
auto_convolve = scipy.signal.fftconvolve(labeled_data, labeled_data)
convolve_data = scipy.signal.fftconvolve(labeled_data, self.model_gen)
convolve_list.append(max(auto_convolve))
convolve_list.append(max(convolve_data))
del_conv_list = [] del_conv_list = []
for segment in segments: for segment in segments:
if segment['deleted']: if segment['deleted']:
segment_from_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms')) segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
segment_to_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms'))
segment_data = data[segment_from_index: segment_to_index + 1]
if len(segment_data) == 0: if len(segment_data) == 0:
continue continue
del_mid_index = segment_from_index + math.ceil((segment_to_index - segment_from_index) / 2) del_mid_index = segment_from_index + math.ceil((segment_to_index - segment_from_index) / 2)
deleted_pat = data[del_mid_index - self.state['WINDOW_SIZE']: del_mid_index + self.state['WINDOW_SIZE'] + 1] deleted_pat = utils.get_interval(data, del_mid_index, self.state['WINDOW_SIZE'])
deleted_pat = deleted_pat - min(deleted_pat) deleted_pat = utils.subtract_min_without_nan(segment_data)
del_conv_pat = scipy.signal.fftconvolve(deleted_pat, self.model_gen) del_conv_pat = scipy.signal.fftconvolve(deleted_pat, self.model_gen)
del_conv_list.append(max(del_conv_pat)) del_conv_list.append(max(del_conv_pat))
@ -97,8 +86,7 @@ class GeneralModel(Model):
for i in range(self.state['WINDOW_SIZE'] * 2, len(data)): for i in range(self.state['WINDOW_SIZE'] * 2, len(data)):
watch_data = data[i - self.state['WINDOW_SIZE'] * 2: i] watch_data = data[i - self.state['WINDOW_SIZE'] * 2: i]
w = min(watch_data) watch_data = utils.subtract_min_without_nan(watch_data)
watch_data = watch_data - w
conv = scipy.signal.fftconvolve(watch_data, pat_data) conv = scipy.signal.fftconvolve(watch_data, pat_data)
self.all_conv.append(max(conv)) self.all_conv.append(max(conv))
all_conv_peaks = utils.peak_finder(self.all_conv, self.state['WINDOW_SIZE'] * 2) all_conv_peaks = utils.peak_finder(self.all_conv, self.state['WINDOW_SIZE'] * 2)

67
analytics/analytics/models/jump_model.py
Unescape View File

@ -42,73 +42,28 @@ class JumpModel(Model):
percent_of_nans = segment_data.isnull().sum() / len(segment_data) percent_of_nans = segment_data.isnull().sum() / len(segment_data)
if percent_of_nans > 0 or len(segment_data) == 0: if percent_of_nans > 0 or len(segment_data) == 0:
continue continue
segment_min = min(segment_data) confidence = utils.find_confidence(segment_data)
segment_max = max(segment_data) confidences.append(confidence)
confidences.append(0.20 * (segment_max - segment_min)) segment_cent_index, jump_height, jump_length = utils.find_jump_parameters(segment_data, segment_from_index)
flat_segment = segment_data.rolling(window = 5).mean()
flat_segment_dropna = flat_segment.dropna()
min_jump = min(flat_segment_dropna)
max_jump = max(flat_segment_dropna)
pdf = gaussian_kde(flat_segment_dropna)
x = np.linspace(flat_segment_dropna.min() - 1, flat_segment_dropna.max() + 1, len(flat_segment_dropna))
y = pdf(x)
ax_list = list(zip(x, y))
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]
try:
min_peak_index = peaks_kde[0]
segment_min_line = ax_list[min_peak_index, 0]
max_peak_index = peaks_kde[1]
segment_max_line = ax_list[max_peak_index, 0]
segment_median = ax_list[antipeaks_kde[0], 0]
except IndexError:
segment_max_line = max_jump
segment_min_line = min_jump
segment_median = (max_jump - min_jump) / 2 + min_jump
jump_height = 0.95 * (segment_max_line - segment_min_line)
jump_height_list.append(jump_height) jump_height_list.append(jump_height)
jump_length = utils.find_jump_length(segment_data, segment_min_line, segment_max_line)
jump_length_list.append(jump_length) jump_length_list.append(jump_length)
cen_ind = utils.intersection_segment(flat_segment.tolist(), segment_median) #finds all interseprions with median
jump_center = cen_ind[0]
segment_cent_index = jump_center - 5 + segment_from_index
self.ijumps.append(segment_cent_index) self.ijumps.append(segment_cent_index)
labeled_jump = data[segment_cent_index - self.state['WINDOW_SIZE'] : segment_cent_index + self.state['WINDOW_SIZE'] + 1] labeled_jump = utils.get_interval(data, segment_cent_index, self.state['WINDOW_SIZE'])
labeled_jump = labeled_jump - min(labeled_jump) labeled_jump = utils.subtract_min_without_nan(labeled_jump)
patterns_list.append(labeled_jump) patterns_list.append(labeled_jump)
self.model_jump = utils.get_av_model(patterns_list) self.model_jump = utils.get_av_model(patterns_list)
for ijump in self.ijumps: convolve_list = utils.get_convolve(self.ijumps, self.model_jump, data, self.state['WINDOW_SIZE'])
labeled_jump = data[ijump - self.state['WINDOW_SIZE']: ijump + self.state['WINDOW_SIZE'] + 1]
labeled_jump = labeled_jump - min(labeled_jump)
auto_convolve = scipy.signal.fftconvolve(labeled_jump, labeled_jump)
convolve_jump = scipy.signal.fftconvolve(labeled_jump, self.model_jump)
convolve_list.append(max(auto_convolve))
convolve_list.append(max(convolve_jump))
del_conv_list = [] del_conv_list = []
for segment in segments: for segment in segments:
if segment['deleted']: if segment['deleted']:
segment_from_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms')) segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
segment_to_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms'))
segment_data = data[segment_from_index: segment_to_index + 1]
if len(segment_data) == 0: if len(segment_data) == 0:
continue continue
flat_segment = segment_data.rolling(window = 5).mean() segment_cent_index = utils.find_jump_parameters(segment_data, segment_from_index)[0]
flat_segment_dropna = flat_segment.dropna() deleted_jump = utils.get_interval(data, segment_cent_index, self.state['WINDOW_SIZE'])
pdf = gaussian_kde(flat_segment_dropna) deleted_jump = utils.subtract_min_without_nan(labeled_jump)
x = np.linspace(flat_segment_dropna.min() - 1, flat_segment_dropna.max() + 1, len(flat_segment_dropna))
y = pdf(x)
ax_list = list(zip(x, y))
ax_list = np.array(ax_list, np.float32)
antipeaks_kde = argrelextrema(np.array(ax_list), np.less)[0]
segment_median = ax_list[antipeaks_kde[0], 0]
cen_ind = utils.intersection_segment(flat_segment.tolist(), segment_median) #finds all interseprions with median
jump_center = cen_ind[0]
segment_cent_index = jump_center - 5 + segment_from_index
deleted_jump = data[segment_cent_index - self.state['WINDOW_SIZE'] : segment_cent_index + self.state['WINDOW_SIZE'] + 1]
deleted_jump = deleted_jump - min(labeled_jump)
del_conv_jump = scipy.signal.fftconvolve(deleted_jump, self.model_jump) del_conv_jump = scipy.signal.fftconvolve(deleted_jump, self.model_jump)
del_conv_list.append(max(del_conv_jump)) del_conv_list.append(max(del_conv_jump))
@ -169,7 +124,7 @@ class JumpModel(Model):
delete_low_bound = self.state['conv_del_min'] * 0.98 delete_low_bound = self.state['conv_del_min'] * 0.98
for segment in segments: for segment in segments:
if segment > self.state['WINDOW_SIZE'] and segment < (len(data) - self.state['WINDOW_SIZE']): if segment > self.state['WINDOW_SIZE'] and segment < (len(data) - self.state['WINDOW_SIZE']):
convol_data = data[segment - self.state['WINDOW_SIZE'] : segment + self.state['WINDOW_SIZE'] + 1] convol_data = utils.get_interval(data, segment, self.state['WINDOW_SIZE'])
percent_of_nans = convol_data.isnull().sum() / len(convol_data) percent_of_nans = convol_data.isnull().sum() / len(convol_data)
if percent_of_nans > 0.5: if percent_of_nans > 0.5:
delete_list.append(segment) delete_list.append(segment)

33
analytics/analytics/models/peak_model.py
Unescape View File

@ -34,41 +34,30 @@ class PeakModel(Model):
patterns_list = [] patterns_list = []
for segment in segments: for segment in segments:
if segment['labeled']: if segment['labeled']:
segment_from_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms')) segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
segment_to_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms'))
segment_data = data[segment_from_index: segment_to_index + 1]
percent_of_nans = segment_data.isnull().sum() / len(segment_data) percent_of_nans = segment_data.isnull().sum() / len(segment_data)
if percent_of_nans > 0 or len(segment_data) == 0: if percent_of_nans > 0 or len(segment_data) == 0:
continue continue
segment_min = min(segment_data) confidence = utils.find_confidence(segment_data)
segment_max = max(segment_data) confidences.append(confidence)
confidences.append(0.2 * (segment_max - segment_min))
segment_max_index = segment_data.idxmax() segment_max_index = segment_data.idxmax()
self.ipeaks.append(segment_max_index) self.ipeaks.append(segment_max_index)
labeled_peak = data[segment_max_index - self.state['WINDOW_SIZE']: segment_max_index + self.state['WINDOW_SIZE'] + 1] labeled_peak = utils.get_interval(data, segment_max_index, self.state['WINDOW_SIZE'])
labeled_peak = labeled_peak - min(labeled_peak) labeled_peak = utils.subtract_min_without_nan(labeled_peak)
patterns_list.append(labeled_peak) patterns_list.append(labeled_peak)
self.model_peak = utils.get_av_model(patterns_list) self.model_peak = utils.get_av_model(patterns_list)
for ipeak in self.ipeaks: #labeled segments convolve_list = utils.get_convolve(self.ipeaks, self.model_peak, data, self.state['WINDOW_SIZE'])
labeled_peak = data[ipeak - self.state['WINDOW_SIZE']: ipeak + self.state['WINDOW_SIZE'] + 1]
labeled_peak = labeled_peak - min(labeled_peak)
auto_convolve = scipy.signal.fftconvolve(labeled_peak, labeled_peak)
convolve_peak = scipy.signal.fftconvolve(labeled_peak, self.model_peak)
convolve_list.append(max(auto_convolve))
convolve_list.append(max(convolve_peak))
del_conv_list = [] del_conv_list = []
for segment in segments: for segment in segments:
if segment['deleted']: if segment['deleted']:
segment_from_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms')) segment_from_index, segment_to_index, segment_data = parse_segment(segment, dataframe)
segment_to_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms'))
segment_data = data[segment_from_index: segment_to_index + 1]
if len(segment_data) == 0: if len(segment_data) == 0:
continue continue
del_max_index = segment_data.idxmax() del_max_index = segment_data.idxmax()
deleted_peak = data[del_max_index - self.state['WINDOW_SIZE']: del_max_index + self.state['WINDOW_SIZE'] + 1] deleted_peak = utils.get_interval(data, del_max_index, self.state['WINDOW_SIZE'])
deleted_peak = deleted_peak - min(deleted_peak) deleted_peak = utils.subtract_min_without_nan(deleted_peak)
del_conv_peak = scipy.signal.fftconvolve(deleted_peak, self.model_peak) del_conv_peak = scipy.signal.fftconvolve(deleted_peak, self.model_peak)
del_conv_list.append(max(del_conv_peak)) del_conv_list.append(max(del_conv_peak))
@ -124,8 +113,8 @@ class PeakModel(Model):
pattern_data = self.model_peak pattern_data = self.model_peak
for segment in segments: for segment in segments:
if segment > self.state['WINDOW_SIZE']: if segment > self.state['WINDOW_SIZE']:
convol_data = data[segment - self.state['WINDOW_SIZE']: segment + self.state['WINDOW_SIZE'] + 1] convol_data = utils.get_interval(data, segment, self.state['WINDOW_SIZE'])
convol_data = convol_data - min(convol_data) convol_data = utils.subtract_min_without_nan(convol_data)
percent_of_nans = convol_data.isnull().sum() / len(convol_data) percent_of_nans = convol_data.isnull().sum() / len(convol_data)
if percent_of_nans > 0.5: if percent_of_nans > 0.5:
delete_list.append(segment) delete_list.append(segment)

33
analytics/analytics/models/trough_model.py
Unescape View File

@ -34,42 +34,31 @@ class TroughModel(Model):
patterns_list = [] patterns_list = []
for segment in segments: for segment in segments:
if segment['labeled']: if segment['labeled']:
segment_from_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms')) segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
segment_to_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms'))
segment_data = data[segment_from_index: segment_to_index + 1]
percent_of_nans = segment_data.isnull().sum() / len(segment_data) percent_of_nans = segment_data.isnull().sum() / len(segment_data)
if percent_of_nans > 0 or len(segment_data) == 0: if percent_of_nans > 0 or len(segment_data) == 0:
continue continue
segment_min = min(segment_data) confidence = utils.find_confidence(segment_data)
segment_max = max(segment_data) confidences.append(confidence)
confidences.append(0.2 * (segment_max - segment_min))
segment_min_index = segment_data.idxmin() segment_min_index = segment_data.idxmin()
self.itroughs.append(segment_min_index) self.itroughs.append(segment_min_index)
labeled_trough = data[segment_min_index - self.state['WINDOW_SIZE'] : segment_min_index + self.state['WINDOW_SIZE'] + 1] labeled_trough = utils.get_interval(data, segment_min_index, self.state['WINDOW_SIZE'])
labeled_trough = labeled_trough - min(labeled_trough) labeled_trough = utils.subtract_min_without_nan(labeled_trough)
patterns_list.append(labeled_trough) patterns_list.append(labeled_trough)
self.model_trough = utils.get_av_model(patterns_list) self.model_trough = utils.get_av_model(patterns_list)
for itrough in self.itroughs: convolve_list = utils.get_convolve(self.itroughs, self.model_trough, data, self.state['WINDOW_SIZE'])
labeled_trough = data[itrough - self.state['WINDOW_SIZE']: itrough + self.state['WINDOW_SIZE'] + 1]
labeled_trough = labeled_trough - min(labeled_trough)
auto_convolve = scipy.signal.fftconvolve(labeled_trough, labeled_trough)
convolve_trough = scipy.signal.fftconvolve(labeled_trough, self.model_trough)
convolve_list.append(max(auto_convolve))
convolve_list.append(max(convolve_trough))
del_conv_list = [] del_conv_list = []
for segment in segments: for segment in segments:
if segment['deleted']: if segment['deleted']:
segment_from_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms')) segment_from_index, segment_to_index, segment_data = utils.parse_segment(segment, dataframe)
segment_to_index = utils.timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms'))
segment_data = data[segment_from_index: segment_to_index + 1]
percent_of_nans = segment_data.isnull().sum() / len(segment_data) percent_of_nans = segment_data.isnull().sum() / len(segment_data)
if percent_of_nans > 0 or len(segment_data) == 0: if percent_of_nans > 0 or len(segment_data) == 0:
continue continue
del_min_index = segment_data.idxmin() del_min_index = segment_data.idxmin()
deleted_trough = data[del_min_index - self.state['WINDOW_SIZE']: del_min_index + self.state['WINDOW_SIZE'] + 1] deleted_trough = utils.get_interval(data, del_min_index, self.state['WINDOW_SIZE'])
deleted_trough = deleted_trough - min(deleted_trough) deleted_trough = utils.subtract_min_without_nan(deleted_trough)
del_conv_trough = scipy.signal.fftconvolve(deleted_trough, self.model_trough) del_conv_trough = scipy.signal.fftconvolve(deleted_trough, self.model_trough)
del_conv_list.append(max(del_conv_trough)) del_conv_list.append(max(del_conv_trough))
@ -125,8 +114,8 @@ class TroughModel(Model):
pattern_data = self.model_trough pattern_data = self.model_trough
for segment in segments: for segment in segments:
if segment > self.state['WINDOW_SIZE']: if segment > self.state['WINDOW_SIZE']:
convol_data = data[segment - self.state['WINDOW_SIZE'] : segment + self.state['WINDOW_SIZE'] + 1] convol_data = utils.get_interval(data, segment, self.state['WINDOW_SIZE'])
convol_data = convol_data - min(convol_data) convol_data = utils.subtract_min_without_nan(convol_data)
percent_of_nans = convol_data.isnull().sum() / len(convol_data) percent_of_nans = convol_data.isnull().sum() / len(convol_data)
if percent_of_nans > 0.5: if percent_of_nans > 0.5:
delete_list.append(segment) delete_list.append(segment)

79
analytics/analytics/utils/common.py
Unescape View File

@ -1,6 +1,10 @@
import numpy as np import numpy as np
import pandas as pd import pandas as pd
import scipy.signal
from scipy.fftpack import fft
from scipy.signal import argrelextrema
from scipy.stats import gaussian_kde
import utils
def exponential_smoothing(series, alpha): def exponential_smoothing(series, alpha):
result = [series[0]] result = [series[0]]
@ -276,3 +280,76 @@ def nan_to_zero(segment, nan_list):
segment[val] = 0 segment[val] = 0
return segment return segment
def find_confidence(segment: pd.Series) -> float:
segment_min = min(segment)
segment_max = max(segment)
return 0.2 * (segment_max - segment_min)
def get_interval(data: pd.Series, center: int, window_size: int) -> pd.Series:
left_bound = center - window_size
right_bound = center + window_size + 1
return data[left_bound: right_bound]
def subtract_min_without_nan(segment: list) -> list:
if not np.isnan(min(segment)):
segment = segment - min(segment)
return segment
def get_convolve(segments: list, av_model: list, data: pd.Series, window_size: int) -> list:
labeled_segment = []
convolve_list = []
for segment in segments:
labeled_segment = utils.get_interval(data, segment, window_size)
labeled_segment = utils.subtract_min_without_nan(labeled_segment)
auto_convolve = scipy.signal.fftconvolve(labeled_segment, labeled_segment)
convolve_segment = scipy.signal.fftconvolve(labeled_segment, av_model)
convolve_list.append(max(auto_convolve))
convolve_list.append(max(convolve_segment))
return convolve_list
def find_jump_parameters(segment_data: pd.Series, segment_from_index: int):
flat_segment = segment_data.rolling(window=5).mean()
flat_segment_dropna = flat_segment.dropna()
segment_median, segment_max_line, segment_min_line = utils.get_distribution_density(flat_segment_dropna)
jump_height = 0.95 * (segment_max_line - segment_min_line)
jump_length = utils.find_jump_length(segment_data, segment_min_line, segment_max_line) # finds all interseprions with median
cen_ind = utils.intersection_segment(flat_segment.tolist(), segment_median)
jump_center = cen_ind[0]
segment_cent_index = jump_center - 5 + segment_from_index
return segment_cent_index, jump_height, jump_length
def find_drop_parameters(segment_data: pd.Series, segment_from_index: int):
flat_segment = segment_data.rolling(window=5).mean()
flat_segment_dropna = flat_segment.dropna()
segment_median, segment_max_line, segment_min_line = utils.get_distribution_density(flat_segment_dropna)
drop_height = 0.95 * (segment_max_line - segment_min_line)
drop_length = utils.find_drop_length(segment_data, segment_min_line, segment_max_line)
cen_ind = utils.drop_intersection(flat_segment.tolist(), segment_median)
drop_center = cen_ind[0]
segment_cent_index = drop_center - 5 + segment_from_index
return segment_cent_index, drop_height, drop_length
def get_distribution_density(segment: pd.Series) -> float:
min_jump = min(segment)
max_jump = max(segment)
pdf = gaussian_kde(segment)
x = np.linspace(segment.min() - 1, segment.max() + 1, len(segment))
y = pdf(x)
ax_list = list(zip(x, y))
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]
try:
min_peak_index = peaks_kde[0]
segment_min_line = ax_list[min_peak_index, 0]
max_peak_index = peaks_kde[1]
segment_max_line = ax_list[max_peak_index, 0]
segment_median = ax_list[antipeaks_kde[0], 0]
except IndexError:
segment_max_line = max_jump
segment_min_line = min_jump
segment_median = (max_jump - min_jump) / 2 + min_jump
return segment_median, segment_max_line, segment_min_line

2
analytics/analytics/utils/segments.py
Unescape View File

@ -2,7 +2,7 @@ import pandas as pd
from utils.common import timestamp_to_index from utils.common import timestamp_to_index
def parse_segment(segment, dataframe): def parse_segment(segment: dict, dataframe: pd.DataFrame):
start = timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms')) start = timestamp_to_index(dataframe, pd.to_datetime(segment['from'], unit='ms'))
end = timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms')) end = timestamp_to_index(dataframe, pd.to_datetime(segment['to'], unit='ms'))
data = dataframe['value'][start: end + 1] data = dataframe['value'][start: end + 1]

Write Preview
Loading…
Cancel
Save