def apply_moving_entropy(self,
input_column,
dest_column=None,
row_range=(0, None),
window=10,
no_of_bins=5):
'''
Apply moving entropy as another column
:param input_column: Required column to add feature engineering
:param dest_column: Destination column name
:param row_range: Range of rows that need to modify
:param window: Window size of the calculation takes part
:param no_of_bins: Number of discrete levels
:return: None
'''
if dest_column == None:
dest_column = input_column + '_mentr_' + str(window) + '_' + str(
no_of_bins)
full_series = list(self._pd_frame[input_column])
filtered_series = full_series[row_range[0]:row_range[1]]
result = Features.moving_entropy(series=filtered_series,
window=window,
no_of_bins=no_of_bins,
default=True)
full_series[row_range[0]:row_range[1]] = result
self.add_column(column_name=dest_column, series=full_series)
def apply_moving_median(self,
input_column,
dest_column=None,
row_range=(0, None),
window=5):
'''
Add moving median as another column
:param input_column: Required column to add feature engineering
:param row_range: Range of rows that need to modify
:param window: Window size of the calculation takes part
:param dest_column: Destination column name
:return: None
'''
if dest_column == None:
dest_column = input_column + '_mm_' + str(window)
full_series = list(self._pd_frame[input_column])
filtered_series = full_series[row_range[0]:row_range[1]]
result = Features.moving_median(series=filtered_series,
window=window,
default=True)
full_series[row_range[0]:row_range[1]] = result
self.add_column(column_name=dest_column, series=full_series)
def apply_moving_median_centered_average(self,
input_column,
dest_column=None,
row_range=(0, None),
window=5,
boundary=1):
'''
Apply moving median centered average as another column
:param input_column: Required column to add feature engineering
:param dest_column: Destination column name
:param row_range: Range of rows that need to modify
:param window: Window size of the calculation takes part
:param boundary: number of values that need to be removed from both ends of the sorted window
:return: None
'''
if dest_column == None:
dest_column = input_column + '_mmca_' + str(window)
full_series = list(self._pd_frame[input_column])
filtered_series = full_series[row_range[0]:row_range[1]]
result = Features.moving_median_centered_average(
series=filtered_series,
window=window,
boundary=boundary,
default=True)
full_series[row_range[0]:row_range[1]] = result
self.add_column(column_name=dest_column, series=full_series)
def apply_moving_weighted_average(self,
input_column,
dest_column=None,
row_range=(0, None),
window=5,
weights=[1, 2, 3, 4, 5]):
'''
Apply moving weighted average as another column
:param input_column: Required column to add feature engineering
:param dest_column: Destination column name
:param row_range: Range of rows that need to modify
:param window: Window size of the calculation takes part
:param weights: list of integers
:return: None
'''
if dest_column == None:
dest_column = input_column + '_mwa_' + str(window)
full_series = list(self._pd_frame[input_column])
filtered_series = full_series[row_range[0]:row_range[1]]
result = Features.moving_weighted_average(series=filtered_series,
window=window,
weights=weights,
default=True)
full_series[row_range[0]:row_range[1]] = result
self.add_column(column_name=dest_column, series=full_series)
def apply_moving_k_closest_average(self,
input_column,
dest_column=None,
row_range=(0, None),
window=5,
kclosest=3):
'''
Apply moving k closest average as another column
:param input_column: Required column to add feature engineering
:param dest_column: Destination column name
:param row_range: Range of rows that need to modify
:param window: Window size of the calculation takes part
:param kclosest: k number of closest values to the recent occurrence including itself
:return: None
'''
if dest_column == None:
dest_column = input_column + '_kca_' + str(window)
full_series = list(self._pd_frame[input_column])
filtered_series = full_series[row_range[0]:row_range[1]]
result = Features.moving_k_closest_average(series=filtered_series,
window=window,
kclosest=kclosest,
default=True)
full_series[row_range[0]:row_range[1]] = result
self.add_column(column_name=dest_column, series=full_series)