108 lines
3.0 KiB
Nim
108 lines
3.0 KiB
Nim
import print
|
|
import strutils
|
|
import sequtils
|
|
import std/sugar
|
|
import std/algorithm
|
|
|
|
## Get sequences
|
|
## let file_path = "../data/stripped"
|
|
let file_path = "../data/one_to_three"
|
|
proc getOEIS(): seq[seq[string]] =
|
|
let f = open(file_path)
|
|
var i = 0
|
|
var line : string
|
|
var seqs: seq[seq[string]]
|
|
while f.read_line(line):
|
|
if i > 3:
|
|
let seq = split(line, ",")
|
|
let l = seq.len
|
|
let nums = seq[1..(l-2)]
|
|
seqs.add(nums)
|
|
i = i + 1
|
|
f.close()
|
|
return seqs
|
|
var seqs = getOEIS()
|
|
|
|
## Sequence helpers
|
|
proc startsWithSubsequence(xs: seq[string], ys: seq[string]): bool =
|
|
if xs.len == 0:
|
|
return true
|
|
elif ys.len == 0:
|
|
return false
|
|
elif xs[0] == ys[0]:
|
|
return startsWithSubsequence(xs[1..<xs.len], ys[1..<ys.len])
|
|
else:
|
|
return false
|
|
|
|
proc getSequencesWithStart(seqs: seq[seq[string]], start: seq[string]): seq[seq[string]] =
|
|
var continuations: seq[seq[string]]
|
|
for seq in seqs:
|
|
if startsWithSubsequence(start, seq):
|
|
continuations.add(seq)
|
|
return continuations
|
|
|
|
## Pretty print sequences
|
|
|
|
# var start = @["1", "2", "3", "4", "5"]
|
|
# var continuations = getSequencesWithStart(seqs, start)
|
|
# print continuations
|
|
|
|
## Find index (or -1)
|
|
|
|
proc findIndex(xs: seq[string], y: string): int =
|
|
for i, x in xs:
|
|
if x == y:
|
|
return i
|
|
return -1
|
|
|
|
## Do simple predictions
|
|
proc compareTuple (x: (string, float), y: (string, float)): int =
|
|
let (_, p1) = x
|
|
let (_, p2) = y
|
|
if p1 < p2: return 1
|
|
elif p1 > p2: return -1
|
|
else: return 0
|
|
|
|
proc predictContinuation(seqs: seq[seq[string]], start: seq[string]): seq[(string, float)] =
|
|
let continuations = getSequencesWithStart(seqs, start)
|
|
let l = start.len
|
|
var nexts: seq[string]
|
|
var ps: seq[float]
|
|
for c in continuations:
|
|
let next = c[l]
|
|
let i = findIndex(nexts, next)
|
|
if i == -1:
|
|
nexts.add(next)
|
|
ps.add(1.0)
|
|
else:
|
|
ps[i] = ps[i] + 1.0
|
|
let sum = foldl(ps, a + b, 0.0)
|
|
ps = ps.map( p => p/sum)
|
|
var next_and_ps = zip(nexts, ps)
|
|
# next_and_ps = sort(next_and_ps, compareTuple)
|
|
sort(next_and_ps, compareTuple)
|
|
# ^ sorts in place
|
|
# also, openArray refers to both arrays and sequences.
|
|
return next_and_ps
|
|
|
|
var start = @["1", "2", "3", "4", "5", "6"]
|
|
echo "Initial sequence", start
|
|
print "Full prediction with access to all hypotheses:"
|
|
let continuation_probabilities = predictContinuation(seqs, start)
|
|
print continuation_probabilities
|
|
|
|
## Predict continuation but without access to all oeis sequences
|
|
|
|
proc predictContinuationWithTruncatedHypotheses(seqs: seq[seq[string]], start: seq[string], num_hypotheses: int): seq[(string, float)] =
|
|
let n = if num_hypotheses < seqs.len: num_hypotheses else: seqs.len
|
|
let truncated_seqs = seqs[0..<n]
|
|
return predictContinuation(truncated_seqs, start)
|
|
|
|
let l = seqs.len
|
|
for i in 1..10:
|
|
let n = (l.float * (i.float/10.0)).int
|
|
echo "Predictions with ", (100.0 * i.float/10.0).int, "% of the hypotheses"
|
|
let predictions = predictContinuationWithTruncatedHypotheses(seqs, start, n)
|
|
print predictions
|
|
|