def calculate_peak(self, file_index=-1, is_horizontal=True):
if is_horizontal:
label = 'horizontal'
else:
label = 'vertical'
_profile = self.roi[label]['profiles'][str(file_index)]
yaxis = _profile['profile']
if self.peak_algorithm == 'change_point':
var = np.mean(yaxis)
result = pelt(normal_var(yaxis, var), len(yaxis))
if len(result) > 2:
peak = np.mean(result[2:])
else:
peak = np.mean(result[1:])
else: # sliding average
_o_range = MeanRangeCalculation(data=yaxis)
nbr_pixels = len(yaxis)
delta_array = []
for _pixel in np.arange(0, nbr_pixels-5):
_o_range.calculate_left_right_mean(pixel=_pixel)
_o_range.calculate_delta_mean_square()
delta_array.append(_o_range.delta_square)
peak_value = delta_array.index(max(delta_array[0: nbr_pixels -5]))
self.peak[label][file_index] = np.int(peak_value)
def test_pelt_normal_var_small(self):
""" Test normal changing variance, with smaller dataset
"""
data = [
-1.82348457, -0.13819782, 1.25618544, -0.54487136, -2.24769311,
9.82204284, -1.0181088, 3.93764179, -8.73177678, 5.99949843
]
result = pelt(normal_var(np.array(data), 0), len(data))
self.assertEqual(result, [0, 5])
def test_pelt_normal_var_big(self):
""" Test normal changing variance, with bigger dataset
"""
size = 100
mean = 0.0
var_a = 1.0
var_b = 10.0
np.random.seed(19348)
data_a = np.random.normal(mean, var_a, size)
data_b = np.random.normal(mean, var_b, size)
data = np.append(data_a, data_b)
result = pelt(normal_var(data, mean), len(data))
self.assertEqual(result, [0, 100, 198])
def _pelt_change_point_detection(self,
df=None,
metric=None,
min_ts_length=None,
max_ts_length=None):
"""
This function computes the significant change points based on PELT and the Kullback-Leibler divergence method.
:param pandas.dataframe df: A pandas dataframe containing the time series
:param pandas.dataframe metric: The metric in the dataframe that contains the time series
:param int min_ts_length: Specifying the minimum required length of the time series for training
:param int max_ts_length: Specifying the maximum required length of the time series for training.
The training time series length truncates accordingly based on minimum between max_ts_length and the
length of the input time series.
:return: A pandas dataframe containing the time series after the last changepoint
>>> df
raw interpolated
2016-01-02 1753421.0 14.377080
2016-01-03 1879108.0 14.446308
2016-01-04 1462725.0 14.195812
2016-01-05 1525162.0 14.237612
2016-01-06 1424264.0 14.169166
... ... ...
2018-10-14 2185230.0 14.597232
2018-10-15 1825539.0 14.417386
2018-10-16 1776778.0 14.390313
2018-10-17 1792899.0 14.399345
2018-10-18 1738657.0 14.368624
>>> copy_df, change_point_list
( raw interpolated
2016-01-02 1753421.0 14.377080
2016-01-03 1879108.0 14.446308
2016-01-04 1462725.0 14.195812
2016-01-05 1525162.0 14.237612
2016-01-06 1424264.0 14.169166
... ... ...
2018-10-14 2185230.0 14.597232
2018-10-15 1825539.0 14.417386
2018-10-16 1776778.0 14.390313
2018-10-17 1792899.0 14.399345
2018-10-18 1738657.0 14.368624
[1021 rows x 2 columns], ['2016-12-26 00:00:00', '2018-09-10 00:00:00'])
"""
import numpy as np
import pandas as pd
from changepy import pelt
from changepy.costs import normal_var
change_point_threshold = self.change_point_threshold
df_copy = pd.DataFrame(df[metric])
counts = df_copy[metric].values
mean = np.mean(counts)
# Performing changepoint detection with respect to the data variablity shift through PELT
cdate = pelt(normal_var(counts, mean), len(counts))
# If PELT detects the first datapoint to be a change point, then we ignore that change point
if cdate:
if cdate[0] == 0:
cdate.remove(0)
if len(cdate) > 0:
# Finding the magnitude of divergence around every change point (detected by PELT) by comparing the
# distributions of the data points on the left and the right side of the change point
entrp = self._shift_intensity(change_points=cdate,
df=df_copy,
metric=metric)
df_change_points = pd.DataFrame({
'c_point': cdate,
'entropy': entrp
})
# Narrowing down to the change points which satisfies a required lower bound of divergence
df_change_points = df_change_points[
df_change_points['entropy'] > change_point_threshold]
cdate = df_change_points['c_point'].values
# Set the start date of the time series based on the min_ts_length and the max_ts_length and the change
# points
if len(cdate) > 0:
df_subset = df_copy.iloc[cdate]
change_point_list = [i.__str__() for i in df_subset.index]
index = df_subset.index[-1]
copy_df = df.loc[index:df.last_valid_index(
)] if self.data_shift_truncate else df
if copy_df.shape[0] < min_ts_length:
# Return None, If time series after the change point contains less number of data points
# than the minimum required length
return None, change_point_list
elif copy_df.shape[0] < max_ts_length:
# Return the time series after the change point if it's length lies between the minimum and the
# maximum required length
pass
elif copy_df.shape[0] > max_ts_length:
# Truncate the time series after change point if it contains more than required data for
# training
copy_df = df.iloc[-max_ts_length:]
else:
change_point_list = None
if df.shape[0] < min_ts_length:
return None, change_point_list
else:
if df.shape[0] < max_ts_length:
copy_df = df
else:
copy_df = df.iloc[-max_ts_length:]
else:
change_point_list = None
if df.shape[0] < min_ts_length:
return None, change_point_list
else:
if df.shape[0] < max_ts_length:
copy_df = df
else:
copy_df = df.iloc[-max_ts_length:]
return copy_df, change_point_list