def extract_features_with_param(time_series, window):
## type: (object, object) -> object
## type: (object, object) -> object
"""
Extracts three types of features from the time series.
:param time_series: the time series to extract the feature of
:type time_series: pandas.Series
:param window: the length of window
:type window: int
:return: the value of features
:return type: list with float
"""
# if not tsd_common.is_standard_time_series(time_series, window):
# # add your report of this error here...
#
# return []
# spilt time_series
split_time_series = tsd_common.split_time_series(time_series, window)
normalized_split_time_series = tsd_common.normalize_time_series(
split_time_series)
max_min_normalized_time_series = tsd_common.normalize_time_series_by_max_min(
split_time_series)
s_features_with_parameter1 = statistical_features.get_parameters_features(
max_min_normalized_time_series)
# s_features_with_parameter2 = statistical_features.get_parameters_features(normalized_split_time_series)
features = s_features_with_parameter1
return features
def extract_features(time_series, window):
"""
Extracts three types of features from the time series.
:param time_series: the time series to extract the feature of
:type time_series: pandas.Series
:param window: the length of window
:type window: int
:return: the value of features
:return type: list with float
"""
if not tsd_common.is_standard_time_series(time_series, window):
# add your report of this error here...
return []
# spilt time_series
split_time_series = tsd_common.split_time_series(time_series, window)
# nomalize time_series
normalized_split_time_series = tsd_common.normalize_time_series(split_time_series)
max_min_normalized_time_series = tsd_common.normalize_time_series_by_max_min(split_time_series)
s_features = statistical_features.get_statistical_features(normalized_split_time_series[4])
f_features = fitting_features.get_fitting_features(normalized_split_time_series)
c_features = classification_features.get_classification_features(max_min_normalized_time_series)
# combine features with types
features = s_features + f_features + c_features
return features
def time_series_window_parts_value_distribution_with_threshold(x):
"""
Split the whole time series into five parts.
Given a threshold = 0.01, return the percentage of elements of time series
which are less than threshold
:param x: normalized time series
:type x: pandas.Series
:return: 5 values of this feature
:return type: list
"""
threshold = 0.01
split_value_list = split_time_series(x, DEFAULT_WINDOW)
count_list = []
for value_list in split_value_list:
nparray_threshold = np.array(value_list)
nparray_threshold[nparray_threshold < threshold] = -1
count_list.append((nparray_threshold == -1).sum())
if sum(count_list) == 0:
features = [0, 0, 0, 0, 0]
else:
features = list(np.array(count_list) / float((DEFAULT_WINDOW + 1)))
return features
def extract_features(time_series, window):
"""
Extracts three types of features from the time series.
:param time_series: the time series to extract the feature of
:type time_series: pandas.Series
:param window: the length of window
:type window: int
:return: the value of features
:return type: list with float
"""
if not tsd_common.is_standard_time_series(time_series, window):
# add your report of this error here...
return []
# spilt time_series
split_time_series = tsd_common.split_time_series(time_series, window)
# nomalize time_series
normalized_split_time_series = tsd_common.normalize_time_series(
split_time_series)
max_min_normalized_time_series = tsd_common.normalize_time_series_by_max_min(
split_time_series)
s_features = statistical_features.get_statistical_features(
normalized_split_time_series[4])
f_features = fitting_features.get_fitting_features(
normalized_split_time_series)
c_features = classification_features.get_classification_features(
max_min_normalized_time_series)
# combine features with types
features = s_features + f_features + c_features
return features
def time_series_window_parts_value_distribution_with_threshold(x):
"""
Split the whole time series into five parts.
Given a threshold = 0.01, return the percentage of elements of time series
which are less than threshold
:param x: normalized time series
:type x: pandas.Series
:return: 5 values of this feature
:return type: list
"""
threshold = 0.01
split_value_list = split_time_series(x, DEFAULT_WINDOW)
count_list = []
for value_list in split_value_list:
nparray_threshold = np.array(value_list)
nparray_threshold[nparray_threshold < threshold] = -1
count_list.append((nparray_threshold == -1).sum())
if sum(count_list) == 0:
features = [0, 0, 0, 0, 0]
else:
features = list(np.array(count_list) / float((DEFAULT_WINDOW + 1)))
return features
def calculate_all_features(time_series, window):
"""
Extracts three types of features from the time series.
:param time_series: the time series to extract the feature of
:type time_series: pandas.Series
:param window: the length of window
:type window: int
:return: the value of features
:return type: list with float
"""
split_time_series = tsd_common.split_time_series(time_series, window)
normalized_split_time_series = tsd_common.normalize_time_series(
split_time_series)
max_min_normalized_time_series = tsd_common.normalize_time_series_by_max_min(
split_time_series)
# s_features = statistical_features.get_statistical_features(normalized_split_time_series[4])
# c_features = classification_features.get_classification_features(max_min_normalized_time_series)
# f_features = fitting_features.get_fitting_features(normalized_split_time_series)
# s_features_with_parameter1 = feature_calculate.get_parameters_features(max_min_normalized_time_series)
# features = s_features + c_features + f_features + s_features_with_parameter1
anom_feature = feature_calculate.get_classification_features_test(
normalized_split_time_series)
pattern_feature = feature_calculate.get_classification_feature_pattern(
max_min_normalized_time_series)
stat_feature = feature_calculate.get_classification_feature_stat(
max_min_normalized_time_series)
features = stat_feature + anom_feature + pattern_feature
return features
def time_series_daily_parts_value_distribution_with_threshold(x):
"""
Split the whole time series into three parts: c, b, a.
Given a threshold = 0.01, return the percentage of elements of time series
which are less than threshold
:param x: normalized time series
:type x: pandas.Series
:return: 6 values of this feature
:return type: list
"""
threshold = 0.01
split_value_list = split_time_series(x, DEFAULT_WINDOW)
data_c = split_value_list[0] + split_value_list[1][1:]
data_b = split_value_list[2] + split_value_list[3][1:]
data_a = split_value_list[4]
# the number of elements in time series which is less than threshold:
nparray_data_c_threshold = np.array(data_c)
nparray_data_c_threshold[nparray_data_c_threshold < threshold] = -1
nparray_data_b_threshold = np.array(data_b)
nparray_data_b_threshold[nparray_data_b_threshold < threshold] = -1
nparray_data_a_threshold = np.array(data_a)
nparray_data_a_threshold[nparray_data_a_threshold < threshold] = -1
# the total number of elements in time series which is less than threshold:
nparray_threshold_count = (nparray_data_c_threshold == -1).sum() + (
nparray_data_b_threshold == -1).sum() + (nparray_data_a_threshold
== -1).sum()
if nparray_threshold_count == 0:
features = [0, 0, 0]
else:
features = [(nparray_data_c_threshold == -1).sum() /
float(nparray_threshold_count),
(nparray_data_b_threshold == -1).sum() /
float(nparray_threshold_count),
(nparray_data_a_threshold == -1).sum() /
float(nparray_threshold_count)]
features.extend([
(nparray_data_c_threshold == -1).sum() / float(len(data_c)),
(nparray_data_b_threshold == -1).sum() / float(len(data_b)),
(nparray_data_a_threshold == -1).sum() / float(len(data_a))
])
return features
def time_series_window_parts_value_distribution_with_threshold(x):
"""
Split the whole time series into five parts.
Given a threshold = 0.01, return the percentage of elements of time series
which are less than threshold
:param x: normalized time series
:type x: pandas.Series
:return: 5 values of this feature
:return type: list
"""
threshold = 0.01
split_value_list = split_time_series(x, DEFAULT_WINDOW)
count_list = []
for value_list in split_value_list:
nparray_threshold = np.array(value_list)
nparray_threshold[nparray_threshold < threshold] = -1
count_list.append((nparray_threshold == -1).sum())
if sum(count_list) == 0:
features = [0, 0, 0, 0, 0]
else:
features = list(np.array(count_list) / float((DEFAULT_WINDOW + 1)))
return features
#
# def get_classification_features(x):
# """
# :param x: splited time series normalized by maximun and minimum value
# :return: list of some local anomaly features and morphological features
# """
# classification_features =[
#
# {"time_series_autocorrelation_classification":time_series_autocorrelation(x)},
# {"time_series_coefficient_of_variation_classification":time_series_coefficient_of_variation(x)},
# ]
# classification_features.extend(time_series_value_distribution(x))
# # classification_features.extend(time_series_daily_parts_value_distribution(x))
# # classification_features.extend(time_series_daily_parts_value_distribution_with_threshold(x))
# # classification_features.extend(time_series_window_parts_value_distribution_with_threshold(x))
# # classification_features.extend(time_series_binned_entropy(x))
# # add yourself classification features here...
#
# return classification_features
def time_series_daily_parts_value_distribution(x):
"""
Given buckets, calculate the percentage of elements in three subsequences
of the whole time series in different buckets
:param x: normalized time series
:type x: pandas.Series
:return: the values of this feature
:return type: list
"""
thresholds = [0, 0.01, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.99, 1.0, 1.0]
split_value_list = split_time_series(x, DEFAULT_WINDOW)
data_c = split_value_list[0] + split_value_list[1][1:]
data_b = split_value_list[2] + split_value_list[3][1:]
data_a = split_value_list[4]
count_c = list(np.histogram(data_c, bins=thresholds)[0])
count_b = list(np.histogram(data_b, bins=thresholds)[0])
count_a = list(np.histogram(data_a, bins=thresholds)[0])
return list(np.array(count_c) / float(len(data_c))) + list(np.array(count_b) / float(len(data_b))) + list(np.array(count_a) / float(len(data_a)))
def time_series_daily_parts_value_distribution(x):
"""
Given buckets, calculate the percentage of elements in three subsequences
of the whole time series in different buckets
:param x: normalized time series
:type x: pandas.Series
:return: the values of this feature
:return type: list
"""
thresholds = [0, 0.01, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.99, 1.0, 1.0]
split_value_list = split_time_series(x, DEFAULT_WINDOW)
data_c = split_value_list[0] + split_value_list[1][1:]
data_b = split_value_list[2] + split_value_list[3][1:]
data_a = split_value_list[4]
count_c = list(np.histogram(data_c, bins=thresholds)[0])
count_b = list(np.histogram(data_b, bins=thresholds)[0])
count_a = list(np.histogram(data_a, bins=thresholds)[0])
return list(np.array(count_c) / float(len(data_c))) + list(np.array(count_b) / float(len(data_b))) + list(np.array(count_a) / float(len(data_a)))
def time_series_daily_parts_value_distribution_with_threshold(x):
"""
Split the whole time series into three parts: c, b, a.
Given a threshold = 0.01, return the percentage of elements of time series
which are less than threshold
:param x: normalized time series
:type x: pandas.Series
:return: 6 values of this feature
:return type: list
"""
threshold = 0.01
split_value_list = split_time_series(x, DEFAULT_WINDOW)
data_c = split_value_list[0] + split_value_list[1][1:]
data_b = split_value_list[2] + split_value_list[3][1:]
data_a = split_value_list[4]
# the number of elements in time series which is less than threshold:
nparray_data_c_threshold = np.array(data_c)
nparray_data_c_threshold[nparray_data_c_threshold < threshold] = -1
nparray_data_b_threshold = np.array(data_b)
nparray_data_b_threshold[nparray_data_b_threshold < threshold] = -1
nparray_data_a_threshold = np.array(data_a)
nparray_data_a_threshold[nparray_data_a_threshold < threshold] = -1
# the total number of elements in time series which is less than threshold:
nparray_threshold_count = (nparray_data_c_threshold == -1).sum() + (nparray_data_b_threshold == -1).sum() + (nparray_data_a_threshold == -1).sum()
if nparray_threshold_count == 0:
features = [0, 0, 0]
else:
features = [
(nparray_data_c_threshold == -1).sum() / float(nparray_threshold_count),
(nparray_data_b_threshold == -1).sum() / float(nparray_threshold_count),
(nparray_data_a_threshold == -1).sum() / float(nparray_threshold_count)
]
features.extend([
(nparray_data_c_threshold == -1).sum() / float(len(data_c)),
(nparray_data_b_threshold == -1).sum() / float(len(data_b)),
(nparray_data_a_threshold == -1).sum() / float(len(data_a))
])
return features
def extract_features_without_param(time_series, window):
## type: (object, object) -> object
## type: (object, object) -> object
"""
Extracts three types of features from the time series.
:param time_series: the time series to extract the feature of
:type time_series: pandas.Series
:param window: the length of window
:type window: int
:return: the value of features
:return type: list with float
"""
# if not tsd_common.is_standard_time_series(time_series, window):
# # add your report of this error here...
#
# return []
# spilt time_series
split_time_series = tsd_common.split_time_series(time_series, window)
split_time_series2 = tsd_common.split_time_series2(time_series, window)
# nomalize time_series
normalized_split_time_series = tsd_common.normalize_time_series(
split_time_series)
max_min_normalized_time_series = tsd_common.normalize_time_series_by_max_min(
split_time_series)
s_features = statistical_features.get_statistical_features(
normalized_split_time_series[4])
f_features = fitting_features.get_fitting_features(
normalized_split_time_series)
c_features = classification_features.get_classification_features(
max_min_normalized_time_series)
# combine features with types
# s_features_without_parameter = statistical_features.calculate_nonparameters_features(normalized_split_time_series[4])
# s_features_with_parameter = statistical_features.get_parameters_features(normalized_split_time_series[4])
# s_features_with_parameter = statistical_features.get_parameters_features(time_series)
# features = c_features
# return s_features_with_parameter
features = s_features + c_features + f_features
# features = c_features
return features
def _f():
threshold = 0.01
split_value_list = split_time_series(x, DEFAULT_WINDOW)
count_list = []
a = 0
for value_list in split_value_list:
nparray_threshold = np.array(value_list)
nparray_threshold[nparray_threshold < threshold] = -1
temp = (nparray_threshold == -1).sum()
count_list.append((nparray_threshold == -1).sum())
name = ("time_series_window_parts_value_distribution_with_threshold_{}".format(a))
a =a+1
if sum(count_list) == 0:
# features = [0, 0, 0, 0, 0]
features = [{'time_series_window_parts_value_distribution_with_threshold_Ais0':0}, {'time_series_window_parts_value_distribution_with_threshold_bis0':0}, {'time_series_window_parts_value_distribution_with_threshold_cis0':0}, {'time_series_window_parts_value_distribution_with_threshold_Dis0':0}, {'time_series_window_parts_value_distribution_with_threshold_Eis0':0}]
else:
features = temp/float((DEFAULT_WINDOW + 1))
# list(np.array(count_list) / float((DEFAULT_WINDOW + 1)))
yield {'{}'.format(name):features}
def time_series_daily_parts_value_distribution(
x): ##问题是返回值最后是每行一个list---观察combine部分的数据返回值内容
"""
:param x: normalized time series
:type x: pandas.Series
:return: the values of this feature
:return type: list
"""
thresholds = [
0, 0.01, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 0.99, 1.0,
1.0
]
split_value_list = split_time_series(x, DEFAULT_WINDOW)
data_c = split_value_list[0] + split_value_list[1][1:]
data_b = split_value_list[2] + split_value_list[3][1:]
data_a = split_value_list[4]
count_c = list(np.histogram(data_c, bins=thresholds)[0])
count_b = list(np.histogram(data_b, bins=thresholds)[0])
count_a = list(np.histogram(data_a, bins=thresholds)[0])
return list(np.array(count_c) / float(len(data_c))) + list(
np.array(count_b) / float(len(data_b))) + list(
np.array(count_a) / float(len(data_a)))
