【发布时间】：2019-02-15 04:55:39
【问题描述】：
我目前正在尝试通过解决一些 Hackerrank 问题来更新我的 Haskell 知识。
例如：
https://www.hackerrank.com/challenges/maximum-palindromes/problem
我已经在 C++ 中实现了一个命令式解决方案，该解决方案已被所有测试用例接受。现在我正在尝试在（合理地惯用的）Haskell 中提出一个纯函数式解决方案。
我当前的代码是
module Main where
import Control.Monad
import qualified Data.ByteString.Char8 as C
import Data.Bits
import Data.List
import qualified Data.Map.Strict as Map
import qualified Data.IntMap.Strict as IntMap
import Debug.Trace
-- precompute factorials
compFactorials :: Int -> Int -> IntMap.IntMap Int
compFactorials n m = go 0 1 IntMap.empty
where
go a acc map
| a < 0 = map
| a < n = go a' acc' map'
| otherwise = map'
where
map' = IntMap.insert a acc map
a' = a + 1
acc' = (acc * a') `mod` m
-- precompute invs
compInvs :: Int -> Int -> IntMap.IntMap Int -> IntMap.IntMap Int
compInvs n m facts = go 0 IntMap.empty
where
go a map
| a < 0 = map
| a < n = go a' map'
| otherwise = map'
where
map' = IntMap.insert a v map
a' = a + 1
v = (modExp b (m-2) m) `mod` m
b = (IntMap.!) facts a
modExp :: Int -> Int -> Int -> Int
modExp b e m = go b e 1
where
go b e r
| (.&.) e 1 == 1 = go b' e' r'
| e > 0 = go b' e' r
| otherwise = r
where
r' = (r * b) `mod` m
b' = (b * b) `mod` m
e' = shift e (-1)
-- precompute frequency table
initFreqMap :: C.ByteString -> Map.Map Char (IntMap.IntMap Int)
initFreqMap inp = go 1 map1 map2 inp
where
map1 = Map.fromList $ zip ['a'..'z'] $ repeat 0
map2 = Map.fromList $ zip ['a'..'z'] $ repeat IntMap.empty
go idx m1 m2 inp
| C.null inp = m2
| otherwise = go (idx+1) m1' m2' $ C.tail inp
where
m1' = Map.update (\v -> Just $ v+1) (C.head inp) m1
m2' = foldl' (\m w -> Map.update (\v -> liftM (\c -> IntMap.insert idx c v) $ Map.lookup w m1') w m)
m2 ['a'..'z']
query :: Int -> Int -> Int -> Map.Map Char (IntMap.IntMap Int)
-> IntMap.IntMap Int -> IntMap.IntMap Int -> Int
query l r m freqMap facts invs
| x > 1 = (x * y) `mod` m
| otherwise = y
where
calcCnt cs = cr - cl
where
cl = IntMap.findWithDefault 0 (l-1) cs
cr = IntMap.findWithDefault 0 r cs
f1 acc cs
| even cnt = acc
| otherwise = acc + 1
where
cnt = calcCnt cs
f2 (acc1,acc2) cs
| cnt < 2 = (acc1 ,acc2)
| otherwise = (acc1',acc2')
where
cnt = calcCnt cs
n = cnt `div` 2
acc1' = acc1 + n
r = choose acc1' n
acc2' = (acc2 * r) `mod` m
-- calc binomial coefficient using Fermat's little theorem
choose n k
| n < k = 0
| otherwise = (f1 * t) `mod` m
where
f1 = (IntMap.!) facts n
i1 = (IntMap.!) invs k
i2 = (IntMap.!) invs (n-k)
t = (i1 * i2) `mod` m
x = Map.foldl' f1 0 freqMap
y = snd $ Map.foldl' f2 (0,1) freqMap
main :: IO()
main = do
inp <- C.getLine
q <- readLn :: IO Int
let modulo = 1000000007
let facts = compFactorials (C.length inp) modulo
let invs = compInvs (C.length inp) modulo facts
let freqMap = initFreqMap inp
forM_ [1..q] $ \_ -> do
line <- getLine
let [s1, s2] = words line
let l = (read s1) :: Int
let r = (read s2) :: Int
let result = query l r modulo freqMap facts invs
putStrLn $ show result
它通过了所有中小型测试用例，但我在大型测试用例中超时。 解决这个问题的关键是在一开始就预先计算一些东西，然后用它们来有效地回答各个查询。
现在，我需要帮助的主要问题是：
初始分析显示IntMap 的lookup 操作似乎是主要瓶颈。有没有更好的替代IntMap 来记忆？或者我应该看看Vector 或Array，我相信这会导致更多“丑陋”的代码。
即使在当前状态下，代码看起来也不好看（按功能标准），并且像我的 C++ 解决方案一样冗长。有什么技巧可以让它更地道吗？除了IntMap 用于记忆化之外，您是否发现任何其他可能导致性能问题的明显问题？
还有什么好的资源可以让我学习如何更有效地使用 Haskell 进行竞争性编程？
一个大型测试用例示例，当前代码超时：
为了比较我的 C++ 解决方案：
#include <vector>
#include <iostream>
#define MOD 1000000007L
long mod_exp(long b, long e) {
long r = 1;
while (e > 0) {
if ((e & 1) == 1) {
r = (r * b) % MOD;
}
b = (b * b) % MOD;
e >>= 1;
}
return r;
}
long n_choose_k(int n, int k, const std::vector<long> &fact_map, const std::vector<long> &inv_map) {
if (n < k) {
return 0;
}
long l1 = fact_map[n];
long l2 = (inv_map[k] * inv_map[n-k]) % MOD;
return (l1 * l2) % MOD;
}
int main() {
std::string s;
int q;
std::cin >> s >> q;
std::vector<std::vector<long>> freq_map;
std::vector<long> fact_map(s.size()+1);
std::vector<long> inv_map(s.size()+1);
for (int i = 0; i < 26; i++) {
freq_map.emplace_back(std::vector<long>(s.size(), 0));
}
std::vector<long> acc_map(26, 0);
for (int i = 0; i < s.size(); i++) {
acc_map[s[i]-'a']++;
for (int j = 0; j < 26; j++) {
freq_map[j][i] = acc_map[j];
}
}
fact_map[0] = 1;
inv_map[0] = 1;
for (int i = 1; i <= s.size(); i++) {
fact_map[i] = (i * fact_map[i-1]) % MOD;
inv_map[i] = mod_exp(fact_map[i], MOD-2) % MOD;
}
while (q--) {
int l, r;
std::cin >> l >> r;
std::vector<long> x(26, 0);
long t = 0;
long acc = 0;
long result = 1;
for (int i = 0; i < 26; i++) {
auto cnt = freq_map[i][r-1] - (l > 1 ? freq_map[i][l-2] : 0);
if (cnt % 2 != 0) {
t++;
}
long n = cnt / 2;
if (n > 0) {
acc += n;
result *= n_choose_k(acc, n, fact_map, inv_map);
result = result % MOD;
}
}
if (t > 0) {
result *= t;
result = result % MOD;
}
std::cout << result << std::endl;
}
}
更新：
DanielWagner 的回答证实了我的怀疑，即我的代码中的主要问题是使用 IntMap 进行记忆。将 IntMap 替换为 Array 使我的代码执行类似于 DanielWagner 的解决方案。
module Main where
import Control.Monad
import Data.Array (Array)
import qualified Data.Array as A
import qualified Data.ByteString.Char8 as C
import Data.Bits
import Data.List
import Debug.Trace
-- precompute factorials
compFactorials :: Int -> Int -> Array Int Int
compFactorials n m = A.listArray (0,n) $ scanl' f 1 [1..n]
where
f acc a = (acc * a) `mod` m
-- precompute invs
compInvs :: Int -> Int -> Array Int Int -> Array Int Int
compInvs n m facts = A.listArray (0,n) $ map f [0..n]
where
f a = (modExp ((A.!) facts a) (m-2) m) `mod` m
modExp :: Int -> Int -> Int -> Int
modExp b e m = go b e 1
where
go b e r
| (.&.) e 1 == 1 = go b' e' r'
| e > 0 = go b' e' r
| otherwise = r
where
r' = (r * b) `mod` m
b' = (b * b) `mod` m
e' = shift e (-1)
-- precompute frequency table
initFreqMap :: C.ByteString -> Map.Map Char (Array Int Int)
initFreqMap inp = Map.fromList $ map f ['a'..'z']
where
n = C.length inp
f c = (c, A.listArray (0,n) $ scanl' g 0 [0..n-1])
where
g x j
| C.index inp j == c = x+1
| otherwise = x
query :: Int -> Int -> Int -> Map.Map Char (Array Int Int)
-> Array Int Int -> Array Int Int -> Int
query l r m freqMap facts invs
| x > 1 = (x * y) `mod` m
| otherwise = y
where
calcCnt freqMap = cr - cl
where
cl = (A.!) freqMap (l-1)
cr = (A.!) freqMap r
f1 acc cs
| even cnt = acc
| otherwise = acc + 1
where
cnt = calcCnt cs
f2 (acc1,acc2) cs
| cnt < 2 = (acc1 ,acc2)
| otherwise = (acc1',acc2')
where
cnt = calcCnt cs
n = cnt `div` 2
acc1' = acc1 + n
r = choose acc1' n
acc2' = (acc2 * r) `mod` m
-- calc binomial coefficient using Fermat's little theorem
choose n k
| n < k = 0
| otherwise = (f1 * t) `mod` m
where
f1 = (A.!) facts n
i1 = (A.!) invs k
i2 = (A.!) invs (n-k)
t = (i1 * i2) `mod` m
x = Map.foldl' f1 0 freqMap
y = snd $ Map.foldl' f2 (0,1) freqMap
main :: IO()
main = do
inp <- C.getLine
q <- readLn :: IO Int
let modulo = 1000000007
let facts = compFactorials (C.length inp) modulo
let invs = compInvs (C.length inp) modulo facts
let freqMap = initFreqMap inp
replicateM_ q $ do
line <- getLine
let [s1, s2] = words line
let l = (read s1) :: Int
let r = (read s2) :: Int
let result = query l r modulo freqMap facts invs
putStrLn $ show result
【问题讨论】：
-
请将这个问题缩小到可以用几句话完全解释的问题，而不需要链接到 HackerRank 之类的东西。就目前而言，它太开放了。另外，您为什么不展示您的 C++ 代码以及在该版本中运行得更快的是什么？
-
你可能想把它分成几个不同的问题。
-
这不是简单的偶数字母数加一（如果有奇数字母）？
week -> e:2 w:1 k:1 -> 2+1=3 -
@karafka 没有；例如对于
week，只有两个最大长度的回文，即ewe和eke。不，这也不是 odd 字母的数量。想想例如bookmark，其中长回文以ok或ko开头，然后是b、m、a或r，因此有 2*4=8 个最大长度回文。 -
哦，最大长度回文数。不是最大长度！
标签： performance haskell