Add fix and unfix functions for parameter fixing and unfixing (#109)

* Add fix() and unfix() functions for parameter fixing and unfixing

* bump version and add export

* add to doc

* add sentence following Penny's comment

Author: sunxd3

Project.toml

@@ -3,7 +3,7 @@ uuid = "7a57a42e-76ec-4ea3-a279-07e840d6d9cf"
 keywords = ["probablistic programming"]
 license = "MIT"
 desc = "Common interfaces for probabilistic programming"
-version = "0.9.0"
+version = "0.10.0"
 
 [deps]
 AbstractMCMC = "80f14c24-f653-4e6a-9b94-39d6b0f70001"

docs/src/api.md

@@ -29,6 +29,8 @@ string_to_varname
 AbstractProbabilisticProgram
 condition
 decondition
+fix
+unfix
 logdensityof
 AbstractContext
 evaluate!!

src/AbstractPPL.jl

@@ -18,7 +18,7 @@ export VarName,
 
 
 # Abstract model functions
-export AbstractProbabilisticProgram, condition, decondition, logdensityof, densityof, AbstractContext, evaluate!!
+export AbstractProbabilisticProgram, condition, decondition, fix, unfix, logdensityof, densityof, AbstractContext, evaluate!!
 
 # Abstract traces
 export AbstractModelTrace

src/abstractprobprog.jl

@@ -62,6 +62,47 @@ should hold for generative models `m` and arbitrary `obs`.
 """
 function condition end
 
+"""
+    fix(model, params)
+
+Fix the values of parameters specified in `params` within the probabilistic model `model`. 
+This operation is equivalent to treating the fixed parameters as being drawn from a point mass 
+distribution centered at the values specified in `params`. Thus these parameters no longer contribute
+to the accumulated log density. 
+
+Conceptually, this is similar to Pearl's do-operator in causal inference, where we intervene 
+on variables by setting them to specific values, effectively cutting off their dependencies 
+on their usual causes in the model.
+
+The invariant
+
+```
+m == unfix(fix(m, params))
+```
+
+should hold for any model `m` and parameters `params`.
+"""
+function fix end
+
+
+"""
+    unfix(model)
+
+Remove any fixed parameters from the model `model`, returning a new model without the fixed parameters.
+
+This function reverses the effect of `fix` by removing parameter constraints that were previously set.
+It returns a new model where all previously fixed parameters are allowed to vary according to their 
+original distributions in the model.
+
+The invariant
+
+```
+m == unfix(fix(m, params))
+```
+
+should hold for any model `m` and parameters `params`.
+"""
+function unfix end
 
 """
     rand([rng=Random.default_rng()], [T=NamedTuple], model::AbstractProbabilisticProgram) -> T