I am looking to implement a rolling window on a list, but instead of a fixed length of window, I would like to provide a rolling window list:
Something like this:
l1 = [5, 3, 8, 2, 10, 12, 13, 15, 22, 28]
l2 = [1, 2, 2, 2, 3, 4, 2, 3, 5, 3]
get_custom_roling( l1, l2, np.average)
and the result would be:
[5, 4, 5.5, 5, 6.67, ....]
6.67 is calculated as average of 3 elements 10, 2, 8.
I implemented a slow solution, and every idea is welcome to make it quicker :):
import numpy as np
def get_the_list(end_point, number_points):
"""
example: get_the_list(6, 3) ==> [4, 5, 6]
example: get_the_list(9, 5) ==> [5, 6, 7, 8, 9]
"""
if np.isnan(number_points):
return []
number_points = int( number_points)
return list(range(end_point, end_point - number_points, -1 ))
def get_idx(s):
ss = list(enumerate(s) )
sss = (get_the_list(*elem) for elem in ss )
return sss
def get_custom_roling(s, ss, funct):
output_get_idx = get_idx(ss)
agg_stuff = [s[elem] for elem in output_get_idx]
res_agg_stuff = [ funct(elem) for elem in agg_stuff ]
res_agg_stuff = eiu.pd.Series(data=res_agg_stuff, index = s.index)
return res_agg_stuff
Pandas custom window rolling allows you to modify size of window.
Simple explanation: start and end arrays hold values of indexes to make slices of your data.
#start = [0 0 1 2 2 2 5 5 4 7]
#end = [1 2 3 4 5 6 7 8 9 10]
Arguments passed to get_window_bounds are given by BaseIndexer.
import pandas as pd
import numpy as np
from pandas.api.indexers import BaseIndexer
from typing import Optional, Tuple
class CustomIndexer(BaseIndexer):
def get_window_bounds(self,
num_values: int = 0,
min_periods: Optional[int] = None,
center: Optional[bool] = None,
closed: Optional[str] = None
) -> Tuple[np.ndarray, np.ndarray]:
end = np.arange(1, num_values+1, dtype=np.int64)
start = end - np.array(self.custom_name_whatever, dtype=np.int64)
return start, end
df = pd.DataFrame({"l1": [5, 3, 8, 2, 10, 12, 13, 15, 22, 28],
"l2": [1, 2, 2, 2, 3, 4, 2, 3, 5, 3]})
indexer = CustomIndexer(custom_name_whatever=df.l2)
df["variable_mean"] = df.l1.rolling(indexer).mean()
print(df)
Outputs:
l1 l2 variable_mean
0 5 1 5.000000
1 3 2 4.000000
2 8 2 5.500000
3 2 2 5.000000
4 10 3 6.666667
5 12 4 8.000000
6 13 2 12.500000
7 15 3 13.333333
8 22 5 14.400000
9 28 3 21.666667