cutcutcodec.core.edit.factor.proba.compute_cumhist

cutcutcodec.core.edit.factor.proba.compute_cumhist(expr: Basic | Real | str, n_per_bars: Integral = 3) → Tensor[source]

Calculate the cumulative histogram of a law combination of reduced uniform probability.

Parameters

exprstr or sympy.Basic: The combination expression of uniform laws. The free_symbols variables correspond to the draws of these independent reduced uniform distributions.
n_per_barsint: The average number of samples by bars if there is enouth memory.

Returns

minfloat: The minimum value of the output of the expression expr.
maxfloat: The maximum value of the output of the expression expr.
cumhisttorch.Tensor: The float 32 cumulative histogram (1d vector) constitued of 256 bins. the min and max of the histograms match with the min and max of the expr.

Notes

This function can use some Gio of RAM.

Examples

>>> from cutcutcodec.core.edit.factor.proba import compute_cumhist
>>> min_, max_, cum = compute_cumhist("1 + x1 + x2")
>>> round(min_), round(max_)
(1, 3)
>>> cum.round(decimals=3)
tensor([0.0000, 0.0000, 0.0000, 0.0010, 0.0010, 0.0010, 0.0020, 0.0020, 0.0030,
        0.0030, 0.0040, 0.0040, 0.0050, 0.0060, 0.0070, 0.0080, 0.0090, 0.0100,
        0.0110, 0.0120, 0.0140, 0.0150, 0.0160, 0.0180, 0.0190, 0.0210, 0.0220,
        0.0240, 0.0260, 0.0280, 0.0290, 0.0310, 0.0330, 0.0350, 0.0380, 0.0400,
        0.0420, 0.0440, 0.0470, 0.0490, 0.0510, 0.0540, 0.0570, 0.0590, 0.0620,
        0.0650, 0.0680, 0.0700, 0.0730, 0.0760, 0.0800, 0.0830, 0.0860, 0.0890,
        0.0930, 0.0960, 0.0990, 0.1030, 0.1060, 0.1100, 0.1140, 0.1180, 0.1210,
        0.1250, 0.1290, 0.1330, 0.1370, 0.1410, 0.1460, 0.1500, 0.1540, 0.1580,
        0.1630, 0.1670, 0.1720, 0.1770, 0.1810, 0.1860, 0.1910, 0.1960, 0.2010,
        0.2060, 0.2110, 0.2160, 0.2210, 0.2260, 0.2310, 0.2370, 0.2420, 0.2480,
        0.2530, 0.2590, 0.2640, 0.2700, 0.2760, 0.2820, 0.2880, 0.2930, 0.2990,
        0.3060, 0.3120, 0.3180, 0.3240, 0.3300, 0.3370, 0.3430, 0.3500, 0.3560,
        0.3630, 0.3700, 0.3760, 0.3830, 0.3900, 0.3970, 0.4040, 0.4110, 0.4180,
        0.4250, 0.4330, 0.4400, 0.4470, 0.4550, 0.4620, 0.4700, 0.4770, 0.4850,
        0.4930, 0.5000, 0.5070, 0.5150, 0.5230, 0.5300, 0.5380, 0.5450, 0.5530,
        0.5600, 0.5670, 0.5750, 0.5820, 0.5890, 0.5960, 0.6030, 0.6100, 0.6170,
        0.6240, 0.6300, 0.6370, 0.6440, 0.6500, 0.6570, 0.6630, 0.6700, 0.6760,
        0.6820, 0.6880, 0.6940, 0.7010, 0.7070, 0.7120, 0.7180, 0.7240, 0.7300,
        0.7360, 0.7410, 0.7470, 0.7520, 0.7580, 0.7630, 0.7690, 0.7740, 0.7790,
        0.7840, 0.7890, 0.7940, 0.7990, 0.8040, 0.8090, 0.8140, 0.8190, 0.8230,
        0.8280, 0.8330, 0.8370, 0.8420, 0.8460, 0.8500, 0.8540, 0.8590, 0.8630,
        0.8670, 0.8710, 0.8750, 0.8790, 0.8820, 0.8860, 0.8900, 0.8940, 0.8970,
        0.9010, 0.9040, 0.9070, 0.9110, 0.9140, 0.9170, 0.9200, 0.9240, 0.9270,
        0.9300, 0.9320, 0.9350, 0.9380, 0.9410, 0.9430, 0.9460, 0.9490, 0.9510,
        0.9530, 0.9560, 0.9580, 0.9600, 0.9620, 0.9650, 0.9670, 0.9690, 0.9710,
        0.9720, 0.9740, 0.9760, 0.9780, 0.9790, 0.9810, 0.9820, 0.9840, 0.9850,
        0.9860, 0.9880, 0.9890, 0.9900, 0.9910, 0.9920, 0.9930, 0.9940, 0.9950,
        0.9960, 0.9960, 0.9970, 0.9970, 0.9980, 0.9980, 0.9990, 0.9990, 0.9990,
        1.0000, 1.0000, 1.0000, 1.0000])
>>>