pymc

pymc copied to clipboard

### Description The following example illustrates a restriction in the current logp derivations, when branch includes constants ```python import pytensor.tensor as pt import pymc as pm t = pt.arange(10) cat...

ricardoV94

seed flaky test GARCH11::test_batched_size

3

seed flaky test GARCH11::test_batched_size ## Description `TestGARCH11::test_batched_size` is flaky in CI, seeded previously non-deterministic rng function. ## Related Issue - [x] Closes #7674 - [x] Related to #7684 (alternative solution,...

nataziel

BUG: Missing `constant_data` in `InferenceData` when defining observed data with same dims.

2

### Describe the issue: I have defined my data in a `pm.Data` container along with its dimensionality `(dims=)` but when i use these points as likelihood and also pass the...

bhroben

JAX backend fails for latent scan variables

14

### Describe the issue: Not sure if this belongs here or in the pytensor repo. Putting it here because the minimal example I can come up with uses PyMC. If...

jessegrabowski

ENH: progressbar=False should silence all sampling output

3

Turning off the progress bar via `progressbar=False` does remove the progress bar, but other sampling-related initialization output is still printed. This results in a lot of output when sampling is...

fonnesbeck

Raise when trying to sample a Multinomial variable

4

## Description Added an error when trying to sample a Multinomial variable ## Related Issue - [x] Closes #7548 - [x] Related to #7548 ## Checklist - [x] Checked that...

Rishab87

Increase tolerance in TestGARCH11::test_batched_size to reduce flakiness

4

## Description Increased the absolute (`atol=1e-3`) and relative (`rtol=1e-2`) tolerances in `np.testing.assert_allclose` within `TestGARCH11::test_batched_size`. This should help reduce test flakiness caused by minor numerical variations. ## Related Issue - [x]...

JigyasuRajput

Warn or raise when trying to sample a Multinomial variable

1

### Description https://discourse.pymc.io/t/inference-issue-using-a-model-with-multinomial-latent-variables-on-multidimensional-observations/16022/4?u=ricardov94

ricardoV94

Add jitter_scale parameter for initial point generation

1

## Description Add jitter_scale parameter to control the bounds of uniform jitter in initial points. This allows users to adjust the width of random initialisation, which is useful for the...

aphc14

ENH: Option to adjust the uniform distribution bounds for jitter/initialisation

5

### Before ```python def make_initial_point_fn( *, free_rvs: Sequence[TensorVariable], rvs_to_transforms: dict[TensorVariable, Transform], initval_strategies: dict[TensorVariable, np.ndarray | Variable | str | None], jitter_rvs: set[TensorVariable] | None = None, default_strategy: str = "support_point",...

aphc14