Start pplus-library: 16 verified routines in six modules
Routines written once in pseudo and checked at every level, so programs can use them by name instead of rewriting and re-verifying them: - stats: Mean, Variance (two-pass) - numerics: KahanSum, LinearInterp, Trapezoid - align: LinearGapPenalty, AffineGapPenalty, MatchScore, NeedlemanWunschScore - md: LennardJones, LennardJonesForce, MinimumImage, PairDistance - seq: GCContent, HammingDistance - special: ErfApprox (Abramowitz and Stegun 7.1.26) Each has contracts, cases, reference implementations in Python, Mojo and (for the numerical ones) C at more than one level, and nine have a Dafny proof over exact numbers. status.json and STATUS.md are written by pplus-core's library-check: every check passes or is open/unverified as listed there. The Mojo references still need the pinned compiler's answers (library-verify-mojo, network). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FgvbRdoEheAHqsRmr2WuKZ
This commit is contained in:
103 files changed
+3025
No files matched your search
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"tool": "dafny",
|
||||
"version": "4.11.0",
|
||||
"flags": [
|
||||
"verify",
|
||||
"--resource-limit",
|
||||
"20000000"
|
||||
],
|
||||
"source_sha256": "2c1cfe5cfd7f6a1f1d930e526ab91e381efef2b847ff56cef529d111c7e97fad",
|
||||
"verdict": "verified",
|
||||
"summary": "9 verified, 0 errors"
|
||||
}
|
||||
@@ -0,0 +1,49 @@
|
||||
// Mean, over real numbers. The FLOAT version rounds; this one does not.
|
||||
function Sum(x: seq<real>): real
|
||||
{
|
||||
if |x| == 0 then 0.0 else Sum(x[..|x| - 1]) + x[|x| - 1]
|
||||
}
|
||||
|
||||
method Mean(x: seq<real>) returns (m: real)
|
||||
requires |x| > 0
|
||||
ensures m == Sum(x) / (|x| as real)
|
||||
{
|
||||
var total := 0.0;
|
||||
var i := 0;
|
||||
while i < |x|
|
||||
invariant 0 <= i <= |x|
|
||||
invariant total == Sum(x[..i])
|
||||
{
|
||||
assert x[..i + 1][..i] == x[..i];
|
||||
total := total + x[i];
|
||||
i := i + 1;
|
||||
}
|
||||
assert x[..|x|] == x;
|
||||
m := total / (|x| as real);
|
||||
}
|
||||
|
||||
// Every value at most hi: the sum is at most |x| * hi.
|
||||
lemma SumAtMost(x: seq<real>, hi: real)
|
||||
requires forall i :: 0 <= i < |x| ==> x[i] <= hi
|
||||
ensures Sum(x) <= (|x| as real) * hi
|
||||
{
|
||||
if |x| > 0 { SumAtMost(x[..|x| - 1], hi); }
|
||||
}
|
||||
|
||||
// Every value at least lo: the sum is at least |x| * lo.
|
||||
lemma SumAtLeast(x: seq<real>, lo: real)
|
||||
requires forall i :: 0 <= i < |x| ==> lo <= x[i]
|
||||
ensures (|x| as real) * lo <= Sum(x)
|
||||
{
|
||||
if |x| > 0 { SumAtLeast(x[..|x| - 1], lo); }
|
||||
}
|
||||
|
||||
// In exact arithmetic the mean lies between any lower and upper bound of the values.
|
||||
lemma MeanBetween(x: seq<real>, lo: real, hi: real)
|
||||
requires |x| > 0
|
||||
requires forall i :: 0 <= i < |x| ==> lo <= x[i] <= hi
|
||||
ensures lo <= Sum(x) / (|x| as real) <= hi
|
||||
{
|
||||
SumAtMost(x, hi);
|
||||
SumAtLeast(x, lo);
|
||||
}
|
||||
@@ -0,0 +1,5 @@
|
||||
double mean(const double *x, long n) {
|
||||
double total = 0.0;
|
||||
for (long i = 0; i < n; i++) total += x[i];
|
||||
return total / (double)n;
|
||||
}
|
||||
@@ -0,0 +1,5 @@
|
||||
def mean(x: List[Float64]) -> Float64:
|
||||
var total: Float64 = 0.0
|
||||
for i in range(len(x)):
|
||||
total = total + x[i]
|
||||
return total / Float64(len(x))
|
||||
@@ -0,0 +1,17 @@
|
||||
def mean(x: List[Float64]) -> Float64:
|
||||
var s0: Float64 = 0.0
|
||||
var s1: Float64 = 0.0
|
||||
var s2: Float64 = 0.0
|
||||
var s3: Float64 = 0.0
|
||||
var n = len(x)
|
||||
var i = 0
|
||||
while i + 4 <= n:
|
||||
s0 = s0 + x[i]
|
||||
s1 = s1 + x[i + 1]
|
||||
s2 = s2 + x[i + 2]
|
||||
s3 = s3 + x[i + 3]
|
||||
i = i + 4
|
||||
while i < n:
|
||||
s0 = s0 + x[i]
|
||||
i = i + 1
|
||||
return ((s0 + s1) + (s2 + s3)) / Float64(n)
|
||||
@@ -0,0 +1,5 @@
|
||||
import math
|
||||
|
||||
|
||||
def mean(x):
|
||||
return math.fsum(x) / len(x)
|
||||
@@ -0,0 +1,5 @@
|
||||
def mean(x):
|
||||
total = 0.0
|
||||
for v in x:
|
||||
total += v
|
||||
return total / len(x)
|
||||
@@ -0,0 +1,69 @@
|
||||
{
|
||||
"name": "Mean",
|
||||
"summary": "The arithmetic mean of a list of numbers.",
|
||||
"tags": [
|
||||
"statistics",
|
||||
"summation"
|
||||
],
|
||||
"sources": [
|
||||
{
|
||||
"title": "Any statistics text: the sample mean, the sum divided by the count"
|
||||
}
|
||||
],
|
||||
"cases": [
|
||||
{
|
||||
"call": "Mean([1.0, 2.0, 3.0, 4.0])"
|
||||
},
|
||||
{
|
||||
"call": "Mean([0.1, 0.1, 0.1])"
|
||||
},
|
||||
{
|
||||
"call": "Mean([-5.0, 5.0])"
|
||||
},
|
||||
{
|
||||
"call": "Mean([1.0e300, 1.0e300])"
|
||||
},
|
||||
{
|
||||
"call": "Mean([2.5])"
|
||||
}
|
||||
],
|
||||
"references": [
|
||||
{
|
||||
"lang": "python",
|
||||
"level": "plain",
|
||||
"file": "ref/python/plain.py",
|
||||
"note": "The same loop: one running total, added to in order."
|
||||
},
|
||||
{
|
||||
"lang": "python",
|
||||
"level": "fsum",
|
||||
"file": "ref/python/fsum.py",
|
||||
"note": "math.fsum rounds the sum once, exactly; the plain loop rounds at every step, so the two can differ in the last digit.",
|
||||
"rel": 1e-15
|
||||
},
|
||||
{
|
||||
"lang": "c",
|
||||
"level": "plain",
|
||||
"file": "ref/c/plain.c",
|
||||
"note": "The same loop in C. Without -ffast-math the compiler keeps the additions in order at every optimization level."
|
||||
},
|
||||
{
|
||||
"lang": "mojo",
|
||||
"level": "plain",
|
||||
"file": "ref/mojo/plain.mojo",
|
||||
"note": "The same loop in Mojo."
|
||||
},
|
||||
{
|
||||
"lang": "mojo",
|
||||
"level": "unrolled",
|
||||
"file": "ref/mojo/unrolled.mojo",
|
||||
"note": "Four running totals, as a vectorizing compiler keeps them: faster on long lists, and the additions happen in a different order, so the last digit can differ.",
|
||||
"rel": 1e-15
|
||||
}
|
||||
],
|
||||
"proof": {
|
||||
"lang": "dafny",
|
||||
"file": "proof/mean.dfy",
|
||||
"note": "Over real numbers: the loop computes Sum(X) / |X|, and the mean lies between the smallest and largest value (rounding can push the FLOAT result just outside, as Mean([0.1, 0.1, 0.1]) shows)."
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,12 @@
|
||||
// Mean: the arithmetic mean of a list of numbers.
|
||||
// The running total is a FLOAT, rounded at every addition, so the mean of
|
||||
// [0.1, 0.1, 0.1] comes out a little above 0.1. For long lists of values of
|
||||
// very different sizes, sum with numerics.KahanSum instead.
|
||||
FUNCTION Mean(X : LIST OF FLOAT) RETURNS FLOAT
|
||||
REQUIRE LENGTH(X) > 0
|
||||
DECLARE Total : FLOAT <- 0.0
|
||||
FOR I <- 0 TO LENGTH(X)
|
||||
Total <- Total + X[I]
|
||||
NEXT I
|
||||
RETURN Total / LENGTH(X)
|
||||
ENDFUNCTION
|
||||
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"name": "stats",
|
||||
"title": "Statistics",
|
||||
"summary": "Summaries of a list of measurements: where it sits and how far it spreads."
|
||||
}
|
||||
@@ -0,0 +1,9 @@
|
||||
def variance(x: List[Float64]) -> Float64:
|
||||
var m: Float64 = 0.0
|
||||
for i in range(len(x)):
|
||||
m = m + x[i]
|
||||
m = m / Float64(len(x))
|
||||
var total: Float64 = 0.0
|
||||
for i in range(len(x)):
|
||||
total = total + (x[i] - m) * (x[i] - m)
|
||||
return total / Float64(len(x) - 1)
|
||||
@@ -0,0 +1,9 @@
|
||||
def variance(x):
|
||||
m = 0.0
|
||||
for v in x:
|
||||
m += v
|
||||
m /= len(x)
|
||||
total = 0.0
|
||||
for v in x:
|
||||
total += (v - m) * (v - m)
|
||||
return total / (len(x) - 1)
|
||||
@@ -0,0 +1,5 @@
|
||||
import statistics
|
||||
|
||||
|
||||
def variance(x):
|
||||
return statistics.variance(x)
|
||||
@@ -0,0 +1,46 @@
|
||||
{
|
||||
"name": "Variance",
|
||||
"summary": "The sample variance of a list of numbers (dividing by N - 1), computed in two passes.",
|
||||
"tags": [
|
||||
"statistics",
|
||||
"cancellation"
|
||||
],
|
||||
"sources": [
|
||||
{
|
||||
"title": "Chan, Golub and LeVeque, Algorithms for computing the sample variance (1983)",
|
||||
"url": "https://doi.org/10.1080/00031305.1983.10483115"
|
||||
}
|
||||
],
|
||||
"cases": [
|
||||
{
|
||||
"call": "Variance([2.0, 4.0, 4.0, 4.0, 5.0, 5.0, 7.0, 9.0])"
|
||||
},
|
||||
{
|
||||
"call": "Variance([1.0, 2.0])"
|
||||
},
|
||||
{
|
||||
"call": "Variance([1.0e9 + 4.0, 1.0e9 + 7.0, 1.0e9 + 13.0, 1.0e9 + 16.0])"
|
||||
}
|
||||
],
|
||||
"references": [
|
||||
{
|
||||
"lang": "python",
|
||||
"level": "plain",
|
||||
"file": "ref/python/plain.py",
|
||||
"note": "The same two passes."
|
||||
},
|
||||
{
|
||||
"lang": "python",
|
||||
"level": "statistics",
|
||||
"file": "ref/python/statistics.py",
|
||||
"note": "The standard library's statistics.variance, which works with exact fractions inside: a different method, held to agree to 12 digits.",
|
||||
"rel": 1e-12
|
||||
},
|
||||
{
|
||||
"lang": "mojo",
|
||||
"level": "plain",
|
||||
"file": "ref/mojo/plain.mojo",
|
||||
"note": "The same two passes in Mojo."
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,14 @@
|
||||
// Variance: the sample variance (dividing by N - 1), in two passes: the mean
|
||||
// first, then the squared distances from it. The one-pass formula
|
||||
// (SUM X^2 - N * MEAN^2) / (N - 1) subtracts two nearly equal large numbers
|
||||
// and loses every digit when the values sit far from 0, as the third case shows.
|
||||
USE stats.Mean
|
||||
FUNCTION Variance(X : LIST OF FLOAT) RETURNS FLOAT
|
||||
REQUIRE LENGTH(X) >= 2
|
||||
DECLARE M : FLOAT <- Mean(X)
|
||||
DECLARE Total : FLOAT <- 0.0
|
||||
FOR I <- 0 TO LENGTH(X)
|
||||
Total <- Total + (X[I] - M) * (X[I] - M)
|
||||
NEXT I
|
||||
RETURN Total / (LENGTH(X) - 1)
|
||||
ENDFUNCTION
|
||||
Reference in new issue
Block a user