Add docstrings to some of the distributions

src/distributions/add_typos.jl

@@ -1,5 +1,26 @@
 import StringDistances: DamerauLevenshtein, evaluate
 
+"""
+    word_with_typos::String ~ AddTypos(word::String, max_typos=nothing)
+
+Add a random number of random typos to the given string.
+
+The distribution on the of typos added to a word depends on the word
+length. On average there is approximately 1 typo for every 45 characters in the
+input word when max_typos is large or not provided.
+
+The typos can be one of several types:
+
+- insertion: insert a random lower-case letter at a random location
+
+- deletion: delete a random character
+
+- substitution: replace a random character with a random lower-case letter
+
+- transpose: swap a random pair of two consecutive letters
+
+NOTE: The log-density is approximate
+"""
 struct AddTypos <: PCleanDistribution end
 
 has_discrete_proposal(::AddTypos) = false

src/distributions/maybe_swap.jl

@@ -1,3 +1,8 @@
+"""
+    MaybeSwap(val, options, prob)
+
+With probability prob, return a random element from options, otherwise return val.
+"""
 struct MaybeSwap <: PCleanDistribution end
 
 supports_explicitly_missing_observations(::MaybeSwap) = true

src/distributions/string_prior.jl

@@ -1,5 +1,13 @@
 using CSV
 
+"""
+    str::String ~ StringPrior(min_length, max_length, proposal_atoms::Vector{String})
+
+Sample a string of random length froma simple bigram model fit to English text.
+
+The string length is uniformly distributed between min_length and max_length (inclusive).
+The alphabet is {'a', 'b', .., 'z', ' ', '.'}.
+"""
 struct StringPrior <: PCleanDistribution end
 
 letter_probs_file = joinpath(dirname(pathof(PClean)), "distributions", "lmparams", "letter_probabilities.csv")

src/distributions/time_prior.jl

@@ -1,5 +1,12 @@
 using CSV
 
+"""
+    TimePrior(
+
+Return a random time stamp of form @sprintf("%d:%02d %s", hours, minutes, ampm).
+
+The hours, minutes and ampm are drawn uniformly from {1, .., 12}, {0, .., 59}, and {"a.m.", "p.m."} respectively.
+"""
 struct TimePrior <: PCleanDistribution end
 
 has_discrete_proposal(::TimePrior) = true