# Extracting chains individual initial step size from Turing chain object saved (serialize) after run

**URL:** <https://discourse.julialang.org/t/extracting-chains-individual-initial-step-size-from-turing-chain-object-saved-serialize-after-run/130272>\
**Category:** New to Julia\
**Tags:** turing, bayesian-inference\
**Created:** [June 27, 2025, 9:33am UTC](https://discourse.julialang.org/t/extracting-chains-individual-initial-step-size-from-turing-chain-object-saved-serialize-after-run/130272 "2025-06-27T09:33:09Z")\
**Posts on this page:** 2\
**Page:** 1

<div class="post-metadata">

**Author:** ![Sahil\_Khan](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/sahil_khan/32/47573_2.png) [@Sahil\_Khan](https://discourse.julialang.org/u/Sahil_Khan)\
**Post date:** [June 27, 2025, 9:33am UTC](https://discourse.julialang.org/t/extracting-chains-individual-initial-step-size-from-turing-chain-object-saved-serialize-after-run/130272/1 "2025-06-27T09:33:09Z")

</div>

Hello,

I was wondering is there any way to extract individual step size for chains I run in parallel ?

I tried `summarize()` but it just gives mean and sd value.

Thank you

---

<div class="post-metadata">

**Author:** ![lunafazio](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/lunafazio/32/217332_2.png) [@lunafazio](https://discourse.julialang.org/u/lunafazio)\
**Post date:** [June 29, 2025, 8:21am UTC](https://discourse.julialang.org/t/extracting-chains-individual-initial-step-size-from-turing-chain-object-saved-serialize-after-run/130272/2 "2025-06-29T08:21:55Z")

</div>

You can turn your chains object into a `DataFrame` to access that information in a convenient manner:

```julia
fit = sample(model, NUTS(), MCMCThreads(), 1_000, 4)
df = DataFrame(fit)
unique(df[:,["chain","step_size"]])
# 4×2 DataFrame
# Row │ chain step_size 
# │ Int64 Float64   
# ─────┼──────────────────
# 1 │ 1 0.242788
# 2 │ 2 0.0965947
# 3 │ 3 0.244368
# 4 │ 4 0.0661436

```