From bfcea1df02315e7f466d7fe141c3f199aec6679f Mon Sep 17 00:00:00 2001
From: Vyacheslav Matyukhin <me@berekuk.ru>
Date: Sat, 24 Sep 2022 19:08:41 +0400
Subject: [PATCH] implement SampleSet.cdf

---
 .../ReducerInterface_Distribution_test.res    |  1 +
 .../rescript/Distributions/GenericDist.res    | 19 ++++++-------------
 .../SampleSetDist/SampleSetDist.res           |  4 ++++
 3 files changed, 11 insertions(+), 13 deletions(-)

diff --git a/packages/squiggle-lang/__tests__/ReducerInterface/ReducerInterface_Distribution_test.res b/packages/squiggle-lang/__tests__/ReducerInterface/ReducerInterface_Distribution_test.res
index c8207131..46ed4c42 100644
--- a/packages/squiggle-lang/__tests__/ReducerInterface/ReducerInterface_Distribution_test.res
+++ b/packages/squiggle-lang/__tests__/ReducerInterface/ReducerInterface_Distribution_test.res
@@ -98,6 +98,7 @@ describe("eval on distribution functions", () => {
       "log(normal(5,2), normal(10,1))",
       "Error(Distribution Math Error: Logarithm of input error: First input must be completely greater than 0)",
     )
+    testEval("log(2, SampleSet.fromDist(0.0001 to 5))", "Ok(Sample Set Distribution)") // log with low values, see https://github.com/quantified-uncertainty/squiggle/issues/1098
     testEval("log(uniform(5,8))", "Ok(Sample Set Distribution)")
     testEval("log10(uniform(5,8))", "Ok(Sample Set Distribution)")
   })
diff --git a/packages/squiggle-lang/src/rescript/Distributions/GenericDist.res b/packages/squiggle-lang/src/rescript/Distributions/GenericDist.res
index f9f5a5d0..231a893c 100644
--- a/packages/squiggle-lang/src/rescript/Distributions/GenericDist.res
+++ b/packages/squiggle-lang/src/rescript/Distributions/GenericDist.res
@@ -86,6 +86,7 @@ let toFloatOperation = (
       | (SampleSet(sampleSet), #Inv(r)) => SampleSetDist.percentile(sampleSet, r)->Some
       | (SampleSet(sampleSet), #Min) => SampleSetDist.min(sampleSet)->Some
       | (SampleSet(sampleSet), #Max) => SampleSetDist.max(sampleSet)->Some
+      | (SampleSet(sampleSet), #Cdf(r)) => SampleSetDist.cdf(sampleSet, r)->Some
       | _ => None
       }
 
@@ -277,22 +278,14 @@ module AlgebraicCombination = {
      Right now we don't yet have a way of getting probability mass, so I'll leave this for later.
  */
     let getLogarithmInputError = (t1: t, t2: t, ~toPointSetFn: toPointSetFn): option<error> => {
-      let firstOperandIsGreaterThanZero =
+      let isDistGreaterThanZero = t =>
         toFloatOperation(
-          t1,
+          t,
           ~toPointSetFn,
           ~distToFloatOperation=#Cdf(MagicNumbers.Epsilon.ten),
-        ) |> E.R.fmap(r => r > 0.)
-      let secondOperandIsGreaterThanZero =
-        toFloatOperation(
-          t2,
-          ~toPointSetFn,
-          ~distToFloatOperation=#Cdf(MagicNumbers.Epsilon.ten),
-        ) |> E.R.fmap(r => r > 0.)
-      let items = E.A.R.firstErrorOrOpen([
-        firstOperandIsGreaterThanZero,
-        secondOperandIsGreaterThanZero,
-      ])
+        )->E.R2.fmap(r => r > 0.)
+
+      let items = E.A.R.firstErrorOrOpen([isDistGreaterThanZero(t1), isDistGreaterThanZero(t2)])
       switch items {
       | Error(r) => Some(r)
       | Ok([true, _]) =>
diff --git a/packages/squiggle-lang/src/rescript/Distributions/SampleSetDist/SampleSetDist.res b/packages/squiggle-lang/src/rescript/Distributions/SampleSetDist/SampleSetDist.res
index 41856882..17fbe431 100644
--- a/packages/squiggle-lang/src/rescript/Distributions/SampleSetDist/SampleSetDist.res
+++ b/packages/squiggle-lang/src/rescript/Distributions/SampleSetDist/SampleSetDist.res
@@ -131,6 +131,10 @@ let max = t => T.get(t)->E.A.Floats.max
 let stdev = t => T.get(t)->E.A.Floats.stdev
 let variance = t => T.get(t)->E.A.Floats.variance
 let percentile = (t, f) => T.get(t)->E.A.Floats.percentile(f)
+let cdf = (t: t, f: float) => {
+  let countBelowF = t->E.A.reduce(0, (acc, x) => acc + (x <= f ? 1 : 0))
+  countBelowF->Js.Int.toFloat /. t->length->Js.Int.toFloat
+}
 
 let mixture = (values: array<(t, float)>, intendedLength: int) => {
   let totalWeight = values->E.A2.fmap(E.Tuple2.second)->E.A.Floats.sum