Skip to content
This repository was archived by the owner on Nov 21, 2025. It is now read-only.
This repository was archived by the owner on Nov 21, 2025. It is now read-only.

Radon Short Time Average is not a real moving average over last 24hr #17

@mariusg0000

Description

@mariusg0000

Hello,

I use a pseudo-inversing algo from numpy in order to obtain original values from a moving average series. When i use this script on movig average from randomly generated number, everyting is ok, i can obtain original values with a small error but when I use the same script on STA values from last 7 days, the result not as expected, many negative values, high volatility which makes me think that STA in not a real moving (rolling) average, but something else. Can you provide the algorithm used for obtaining STA values or can you provide the raw, instant radon values over the last hour ?

Here is the python script I use:

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from scipy.ndimage import shift
import random

def reconstruct_orig(sm_x:np.ndarray, win_size:int=7):

    arr_size = sm_x.shape[0]+win_size
    # get A and its inverse     
    A = (np.tril(np.ones((arr_size,arr_size)),-1) - np.tril(np.ones((arr_size,arr_size)),-(win_size+1)))/win_size
    A = A[win_size:,:]
    pA = np.linalg.pinv(A) #pseudo inverse
    return np.dot(pA, sm_x)

if __name__=="__main__":

    data = np.loadtxt("sta.csv", delimiter=",",dtype='float')
    orig = pd.DataFrame(data)
    
    re_x = reconstruct_orig(orig, win_size=24)
    
    data = np.concatenate([np.zeros((23)), data]) # right shift 24 values  

    plt.plot(data,label='original x')
    plt.plot(re_x, label='reconstructed x')
    plt.legend()
    plt.show()

REVERSE_RND
reverse_sta

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions