Coverage for src/cell_abm_pipeline/tasks/calculate_data_bins.py: 0%

1import numpy as np 

2from prefect import task 

3 

4 

5@task 

6def calculate_data_bins( 

7 data: np.ndarray, bounds: tuple[float, float], bandwidth: float 

8) -> list[dict]: 

9 if len(data) == 0: 

10 return [] 

11 

12 total = len(data) * bandwidth 

13 num_bins = int((bounds[1] - bounds[0]) / bandwidth) 

14 lower = bounds[0] - 3 * bandwidth / 2 

15 upper = bounds[1] + 3 * bandwidth / 2 

16 

17 bins = np.linspace(lower, upper, num_bins + 4).tolist() 

18 counts, _ = np.histogram(data, bins) 

19 

20 return [ 

21 {"n": count, "x": x0, "y": count / total, "m": (x0 + x1) / 2} 

22 for count, x0, x1 in zip(counts.tolist(), bins[:-1], bins[1:]) 

23 ]