Python 我可以使用什么语言快速执行此数据库摘要任务?
所以我写了一个Python程序来处理一些数据处理 任务 下面是我想要的一个非常简短的计算语言规范:Python 我可以使用什么语言快速执行此数据库摘要任务?,python,sql,lisp,ocaml,apache-pig,Python,Sql,Lisp,Ocaml,Apache Pig,所以我写了一个Python程序来处理一些数据处理 任务 下面是我想要的一个非常简短的计算语言规范: parse "%s %lf %s" aa bb cc | group_by aa | quickselect --key=bb 0:5 | \ flatten | format "%s %lf %s" aa bb cc 也就是说,对于每一行,解析出一个单词、一个浮点数和另一个单词。可以将它们视为球员ID、分数和日期。我要每个球员的前五名分数和日期。数据量不是很小,但也不是很大;大约630
parse "%s %lf %s" aa bb cc | group_by aa | quickselect --key=bb 0:5 | \
flatten | format "%s %lf %s" aa bb cc
也就是说,对于每一行,解析出一个单词、一个浮点数和另一个单词。可以将它们视为球员ID、分数和日期。我要每个球员的前五名分数和日期。数据量不是很小,但也不是很大;大约630兆字节
我想知道我应该用什么真正的可执行语言来编写它
让它同样简短(如下面的Python),但要快得多
#!/usr/bin/python
# -*- coding: utf-8; -*-
import sys
top_5 = {}
for line in sys.stdin:
aa, bb, cc = line.split()
# We want the top 5 for each distinct value of aa. There are
# hundreds of thousands of values of aa.
bb = float(bb)
if aa not in top_5: top_5[aa] = []
current = top_5[aa]
current.append((bb, cc))
# Every once in a while, we drop the values that are not in
# the top 5, to keep our memory footprint down, because some
# values of aa have thousands of (bb, cc) pairs.
if len(current) > 10:
current.sort()
current[:-5] = []
for aa in top_5:
current = top_5[aa]
current.sort()
for bb, cc in current[-5:]:
print aa, bb, cc
以下是一些示例输入数据:
3 1.5 a
3 1.6 b
3 0.8 c
3 0.9 d
4 1.2 q
3 1.5 e
3 1.8 f
3 1.9 g
以下是我从中得到的输出:
3 1.5 a
3 1.5 e
3 1.6 b
3 1.8 f
3 1.9 g
4 1.2 q
3
有七个值,因此我们删除c
和d
值
因为他们的bb
值将他们排除在前五名之外。因为4
已经
只有一个值,其“前五名”仅由该值组成
这比在MySQL中执行相同的查询运行得更快(至少
我们找到的查询方式)但我很确定这是在花钱
它的大部分时间都在Python字节码解释器中。我认为这是事实
另一种语言,我可能可以让它处理数百个
每秒数千行,而不是每分钟数千行。所以我想
用实现速度更快的语言编写
但我不确定该选择哪种语言
我还没有弄明白如何用SQL将其表示为一个查询
事实上,我对MySQL的能力甚至仅仅是
选择*从foo到outfile'bar'代码>输入数据
C是一个明显的选择,但类似于排序列表的line.split()
创建一个哈希表需要编写一些
不在标准库中,因此我将得到100行代码
或者更多,而不是14
C++似乎是一个更好的选择(它有字符串、映射、,
但它看起来像是代码
STL会更混乱
OCaml可以,但它是否有一个与line.split()等效的,
我会为它的地图的表现感到悲伤吗
通用Lisp可能会工作吗
对于这样的数据库计算,是否有类似于Matlab的方法
这样我就可以将循环下推到快速代码中?有人试过吗
(编辑:回应davethegr8的评论,提供了一些示例输入和输出数据,并修复了Python程序中的一个bug!)
(额外编辑:哇,到目前为止,这个评论帖子真的非常棒。谢谢大家!)
编辑:
有一个(谢谢,Rainer!),下面是Will Hartung的awk
脚本,用于生成一些测试数据(尽管它没有真实数据的齐普夫分布):
开始{
对于(i=0;i<27000000;i++){
v=兰德();
k=int(rand()*100);
打印k“v”i;
}
出口
}
我很难相信任何事先不知道数据的脚本(不像MySql那样预先加载了这些信息)都会比SQL方法更快
除了解析输入所花费的时间外,脚本还需要“保持”按数组排序等
假设表的aa、bb、cc列上有一个索引(*),那么下面是关于什么应该在SQL中运行得非常快的第一个猜测。(一个可能的替代方案是“aa、bb DESC、cc”索引
(*)此索引可以是聚集索引,也可以不聚集索引,但不影响以下查询。是否聚集索引以及是否需要“aa、bb、cc”单独索引取决于用例、表中行的大小等
SELECT T1.aa, T1.bb, T1.cc , COUNT(*)
FROM tblAbc T1
LEFT OUTER JOIN tblAbc T2 ON T1.aa = T2.aa AND
(T1.bb < T2.bb OR(T1.bb = T2.bb AND T1.cc < T2.cc))
GROUP BY T1.aa, T1.bb, T1.cc
HAVING COUNT(*) < 5 -- trick, remember COUNT(*) goes 1,1,2,3,...
ORDER BY T1.aa, T1.bb, T1.cc, COUNT(*) DESC
关于是否需要索引的问题(参见OP的评论)
当仅仅运行“SELECT*FROM myTable”时,表扫描实际上是最快的方法,不需要麻烦索引(除了作为首先积累数据的存储库之外,任何外部解决方案都需要考虑导出相关数据的时间),这是因为它可以依靠索引来避免扫描。许多通用语言更适合处理原始处理,但它们正在与SQL进行不公平的斗争,因为它们需要重建SQL在其数据收集/导入阶段收集的数据的任何先验知识。因为排序通常是SQL及其相对较慢的处理能力往往比其他解决方案更具时间和空间消耗性
此外,即使没有预先构建的索引,现代查询优化器也可能决定一个涉及创建临时索引的计划。而且,由于排序是DDMS的固有部分,SQL Server在这方面通常是高效的
那么……SQL更好吗?
也就是说,如果我们试图比较SQL和其他语言的纯ETL作业,即处理堆(未索引的表)作为执行各种转换和过滤的输入,使用C语言编写的多线程实用程序可能会更快,并利用高效的排序库。决定SQL与非SQL方法的决定性问题是数据位于何处以及它最终应该驻留在何处。如果我们只想vert一个文件从“链”向下提供,外部程序更适合。如果我们在SQL server中拥有或需要数据,只有极少数情况下值得从外部导出和处理。这不是很简单吗
SELECT DISTINCT aa, bb, cc FROM tablename ORDER BY bb DESC LIMIT 5
?
当然,如果不对数据进行测试,很难判断什么是最快的。如果这是您需要快速运行的东西,那么优化数据库以加快查询速度可能是有意义的,而不是优化查询
及
DECLARE @aa AS VARCHAR(10), @bb AS INT, @cc AS VARCHAR(10)
DECLARE @curAa AS VARCHAR(10)
DECLARE @Ctr AS INT
DROP TABLE tblResults;
CREATE TABLE tblResults
( aa VARCHAR(10),
bb INT,
cc VARCHAR(10)
);
DECLARE abcCursor CURSOR
FOR SELECT aa, bb, cc
FROM tblABC
ORDER BY aa, bb DESC, cc
FOR READ ONLY;
OPEN abcCursor;
SET @curAa = ''
FETCH NEXT FROM abcCursor INTO @aa, @bb, @cc;
WHILE @@FETCH_STATUS = 0
BEGIN
IF @curAa <> @aa
BEGIN
SET @Ctr = 0
SET @curAa = @aa
END
IF @Ctr < 5
BEGIN
SET @Ctr = @Ctr + 1;
INSERT tblResults VALUES(@aa, @bb, @cc);
END
FETCH NEXT FROM AbcCursor INTO @aa, @bb, @cc;
END;
CLOSE abcCursor;
DEALLOCATE abcCursor;
SELECT * from tblResults
ORDER BY aa, bb, cc -- OR .. bb DESC ... for a more traditional order.
DECLARE @aa AS VARCHAR(10)
DECLARE @aaCount INT
DROP TABLE tblResults;
CREATE TABLE tblResults
( aa VARCHAR(10),
bb INT,
cc VARCHAR(10)
);
DECLARE aaCountCursor CURSOR
FOR SELECT aa, COUNT(*)
FROM tblABC
GROUP BY aa
ORDER BY aa
FOR READ ONLY;
OPEN aaCountCursor;
FETCH NEXT FROM aaCountCursor INTO @aa, @aaCount
WHILE @@FETCH_STATUS = 0
BEGIN
INSERT tblResults
SELECT TOP 5 aa, bb, cc
FROM tblproh
WHERE aa = @aa
ORDER BY aa, bb DESC, cc
FETCH NEXT FROM aaCountCursor INTO @aa, @aaCount;
END;
CLOSE aaCountCursor
DEALLOCATE aaCountCursor
SELECT * from tblResults
ORDER BY aa, bb, cc -- OR .. bb DESC ... for a more traditional order.
SELECT DISTINCT aa, bb, cc FROM tablename ORDER BY bb DESC LIMIT 5
(defun read-a-line (stream)
(let ((line (read-line stream nil nil)))
(flet ((delimiter-p (c)
(or (char= c #\space) (char= c #\tab))))
(when line
(let* ((s0 (position-if #'delimiter-p line))
(s1 (position-if-not #'delimiter-p line :start s0))
(s2 (position-if #'delimiter-p line :start (1+ s1)))
(s3 (position-if #'delimiter-p line :from-end t)))
(values (subseq line 0 s0)
(list (read-from-string line nil nil :start s1 :end s2)
(subseq line (1+ s3)))))))))
(defun dbscan (top-5-table stream)
"get triples from each line and put them in the hash table"
(loop with aa = nil and bbcc = nil do
(multiple-value-setq (aa bbcc) (read-a-line stream))
while aa do
(setf (gethash aa top-5-table)
(let ((l (merge 'list (gethash aa top-5-table) (list bbcc)
#'> :key #'first)))
(or (and (nth 5 l) (subseq l 0 5)) l)))))
(defun dbprint (table output)
"print the hashtable contents"
(maphash (lambda (aa value)
(loop for (bb cc) in value
do (format output "~a ~a ~a~%" aa bb cc)))
table))
(defun dbsum (input &optional (output *standard-output*))
"scan and sum from a stream"
(let ((top-5-table (make-hash-table :test #'equal)))
(dbscan top-5-table input)
(dbprint top-5-table output)))
(defun fsum (infile outfile)
"scan and sum a file"
(with-open-file (input infile :direction :input)
(with-open-file (output outfile
:direction :output :if-exists :supersede)
(dbsum input output))))
(defun create-test-data (&key (file "/tmp/test.data") (n-lines 100000))
(with-open-file (stream file :direction :output :if-exists :supersede)
(loop repeat n-lines
do (format stream "~a ~a ~a~%"
(random 1000) (random 100.0) (random 10000)))))
(defun test ()
(time (fsum "/tmp/test.data" "/tmp/result.data")))
(defun fsum (infile outfile)
(let ((top-5-table (make-hash-table :size 50000000 :test #'equal)))
(with-open-file (input infile :direction :input)
(loop for line = (read-line input nil nil)
while line do
(destructuring-bind (aa bb cc) (split-string '(#\space #\tab) line)
(setf bb (parse-float bb))
(let ((v (gethash aa top-5-table)))
(unless v
(setf (gethash aa top-5-table)
(setf v (make-array 6 :fill-pointer 0))))
(vector-push (cons bb cc) v)
(when (> (length v) 5)
(setf (fill-pointer (sort v #'> :key #'car)) 5))))))
(with-open-file (output outfile :direction :output :if-exists :supersede)
(maphash (lambda (aa value)
(loop for (bb . cc) across value do
(format output "~a ~f ~a~%" aa bb cc)))
top-5-table))))
from collections import defaultdict
import sys
def keep_5( aList, aPair ):
minbb= min( bb for bb,cc in aList )
bb, cc = aPair
if bb < minbb: return aList
aList.append( aPair )
min_i= 0
for i in xrange(1,6):
if aList[i][0] < aList[min_i][0]
min_i= i
aList.pop(min_i)
return aList
top_5= defaultdict(list)
for row in sys.stdin:
aa, bb, cc = row.split()
bb = float(bb)
if len(top_5[aa]) < 5:
top_5[aa].append( (bb,cc) )
else:
top_5[aa]= keep_5( top_5[aa], (bb,cc) )
#include <map>
#include <iostream>
#include <functional>
#include <utility>
#include <string>
int main() {
using namespace std;
typedef std::map<string, std::multimap<double, string> > Map;
Map m;
string aa, cc;
double bb;
std::cin.sync_with_stdio(false); // Dunno if this has any effect, but anyways.
while (std::cin >> aa >> bb >> cc)
{
if (m[aa].size() == 5)
{
Map::mapped_type::iterator iter = m[aa].begin();
if (bb < iter->first)
continue;
m[aa].erase(iter);
}
m[aa].insert(make_pair(bb, cc));
}
for (Map::const_iterator iter = m.begin(); iter != m.end(); ++iter)
for (Map::mapped_type::const_iterator iter2 = iter->second.begin();
iter2 != iter->second.end();
++iter2)
std::cout << iter->first << " " << iter2->first << " " << iter2->second <<
std::endl;
}
42 0.49357 0
96 0.48075 1
27 0.640761 2
8 0.389128 3
75 0.395476 4
24 0.212069 5
80 0.121367 6
81 0.271959 7
91 0.18581 8
69 0.258922 9
package top5;
import java.io.BufferedReader;
import java.io.FileReader;
import java.util.Arrays;
import java.util.Map;
import java.util.TreeMap;
public class Main {
public static void main(String[] args) throws Exception {
long start = System.currentTimeMillis();
Map<String, Pair[]> top5map = new TreeMap<String, Pair[]>();
BufferedReader br = new BufferedReader(new FileReader("/tmp/file.dat"));
String line = br.readLine();
while(line != null) {
String parts[] = line.split(" ");
String key = parts[0];
double score = Double.valueOf(parts[1]);
String value = parts[2];
Pair[] pairs = top5map.get(key);
boolean insert = false;
Pair p = null;
if (pairs != null) {
insert = (score > pairs[pairs.length - 1].score) || pairs.length < 5;
} else {
insert = true;
}
if (insert) {
p = new Pair(score, value);
if (pairs == null) {
pairs = new Pair[1];
pairs[0] = new Pair(score, value);
} else {
if (pairs.length < 5) {
Pair[] newpairs = new Pair[pairs.length + 1];
System.arraycopy(pairs, 0, newpairs, 0, pairs.length);
pairs = newpairs;
}
int k = 0;
for(int i = pairs.length - 2; i >= 0; i--) {
if (pairs[i].score <= p.score) {
pairs[i + 1] = pairs[i];
} else {
k = i + 1;
break;
}
}
pairs[k] = p;
}
top5map.put(key, pairs);
}
line = br.readLine();
}
for(Map.Entry<String, Pair[]> e : top5map.entrySet()) {
System.out.print(e.getKey());
System.out.print(" ");
System.out.println(Arrays.toString(e.getValue()));
}
System.out.println(System.currentTimeMillis() - start);
}
static class Pair {
double score;
String value;
public Pair(double score, String value) {
this.score = score;
this.value = value;
}
public int compareTo(Object o) {
Pair p = (Pair) o;
return (int)Math.signum(score - p.score);
}
public String toString() {
return String.valueOf(score) + ", " + value;
}
}
}
BEGIN {
for (i = 0; i < 27000000; i++) {
v = rand();
k = int(rand() * 100);
print k " " v " " i;
}
exit;
}
kragen@inexorable:~/devel$ time LANG=C sort -nr infile -o sorted
real 1m27.476s
user 0m59.472s
sys 0m8.549s
kragen@inexorable:~/devel$ time ./top5_sorted_c < sorted > outfile
real 0m5.515s
user 0m4.868s
sys 0m0.452s
#include <ctype.h>
#include <stdio.h>
#include <string.h>
#include <stdlib.h>
enum { linesize = 1024 };
char buf[linesize];
char key[linesize]; /* last key seen */
int main() {
int n = 0;
char *p;
while (fgets(buf, linesize, stdin)) {
for (p = buf; *p && !isspace(*p); p++) /* find end of key on this line */
;
if (p - buf != strlen(key) || 0 != memcmp(buf, key, p - buf))
n = 0; /* this is a new key */
n++;
if (n <= 5) /* copy up to five lines for each key */
if (fputs(buf, stdout) == EOF) abort();
if (n == 1) { /* save new key in `key` */
memcpy(key, buf, p - buf);
key[p-buf] = '\0';
}
}
return 0;
}
#include <map>
#include <iostream>
#include <string>
int main() {
using namespace std;
int n = 0;
string prev, aa, bb, cc;
while (cin >> aa >> bb >> cc) {
if (aa != prev) n = 0;
++n;
if (n <= 5) cout << aa << " " << bb << " " << cc << endl;
prev = aa;
}
return 0;
}
Data = LOAD '/my/data' using PigStorage() as (aa:int, bb:float, cc:chararray);
grp = GROUP Data by aa;
topK = FOREACH grp (
sorted = ORDER Data by bb DESC;
lim = LIMIT sorted 5;
GENERATE group as aa, lim;
)
STORE topK INTO '/my/output' using PigStorage();
$ time python ./ref.py < data-large.txt > ref-large.txt
real 1m57.689s
user 1m56.104s
sys 0m0.573s
$ time python ./my.py < data-large.txt > my-large.txt
real 1m35.132s
user 1m34.649s
sys 0m0.261s
$ diff my-large.txt ref-large.txt
$ echo $?
0
#!/usr/bin/python
# -*- coding: utf-8; -*-
import sys
import heapq
top_5 = {}
for line in sys.stdin:
aa, bb, cc = line.split()
# We want the top 5 for each distinct value of aa. There are
# hundreds of thousands of values of aa.
bb = float(bb)
if aa not in top_5: top_5[aa] = []
current = top_5[aa]
if len(current) < 5:
heapq.heappush(current, (bb, cc))
else:
if current[0] < (bb, cc):
heapq.heapreplace(current, (bb, cc))
for aa in top_5:
current = top_5[aa]
while len(current) > 0:
bb, cc = heapq.heappop(current)
print aa, bb, cc
$ time python noop.py < data-large.txt > noop-large.txt
real 1m20.143s
user 1m19.846s
sys 0m0.267s
#!/usr/bin/python
# -*- coding: utf-8; -*-
import sys
import heapq
top_5 = {}
for line in sys.stdin:
aa, bb, cc = line.split()
bb = float(bb)
if aa not in top_5: top_5[aa] = []
current = top_5[aa]
if len(current) < 5:
current.append((bb, cc))
for aa in top_5:
current = top_5[aa]
current.sort()
for bb, cc in current[-5:]:
print aa, bb, cc
fid = fopen('fakedata.txt','r');
tic
A=fscanf(fid,'%d %d %d\n');
A=reshape(A,3,length(A)/3)'; %Matlab reads the data into one long column'
Names = unique(A(:,1));
for i=1:length(Names)
indices = find(A(:,1)==Names(i)); %Grab all instances of key i
[Y,I] = sort(A(indices,2),1,'descend'); %sort in descending order of 2nd record
A(indices(I(1:min([5,length(indices(I))]))),:) %Print the top five
end
toc
fclose(fid)
open Printf
open ExtLib
let (>>) x f = f x
let cmp x y = compare (fst x : float) (fst y)
let wsp = Str.regexp "[ \t]+"
let () =
let all = Hashtbl.create 1024 in
Std.input_lines stdin >> Enum.iter (fun line ->
let [a;b;c] = Str.split wsp line in
let b = float_of_string b in
try
match Hashtbl.find all a with
| [] -> assert false
| (bmin,_) as prev::tl -> if b > bmin then
begin
let m = List.sort ~cmp ((b,c)::tl) in
Hashtbl.replace all a (if List.length tl < 4 then prev::m else m)
end
with Not_found -> Hashtbl.add all a [b,c]
);
all >> Hashtbl.iter (fun a -> List.iter (fun (b,c) -> printf "%s %f %s\n" a b c))
Read data : 80.5 s
My TopN : 34.41 s
HeapTopN : 30.34 s
import random, sys, time, heapq
ROWS = 27000000
def make_data( fname ):
f = open( fname, "w" )
r = random.Random()
for i in xrange( 0, ROWS, 10000 ):
for j in xrange( i,i+10000 ):
f.write( "%d %f %d\n" % (r.randint(0,100), r.uniform(0,1000), j))
print ("write: %d\r" % i),
sys.stdout.flush()
print
def read_data( fname ):
for n, line in enumerate( open( fname ) ):
r = line.strip().split()
yield int(r[0]),float(r[1]),r[2]
if not (n % 10000 ):
print ("read: %d\r" % n),
sys.stdout.flush()
print
def topn( ntop, data ):
ntop -= 1
assert ntop > 0
min_by_key = {}
top_by_key = {}
for key,value,label in data:
tup = (value,label)
if key not in top_by_key:
# initialize
top_by_key[key] = [ tup ]
else:
top = top_by_key[ key ]
l = len( top )
if l > ntop:
# replace minimum value in top if it is lower than current value
idx = min_by_key[ key ]
if top[idx] < tup:
top[idx] = tup
min_by_key[ key ] = top.index( min( top ) )
elif l < ntop:
# fill until we have ntop entries
top.append( tup )
else:
# we have ntop entries in list, we'll have ntop+1
top.append( tup )
# initialize minimum to keep
min_by_key[ key ] = top.index( min( top ) )
# finalize:
return dict( (key, sorted( values, reverse=True )) for key,values in top_by_key.iteritems() )
def grouptopn( ntop, data ):
top_by_key = {}
for key,value,label in data:
if key in top_by_key:
top_by_key[ key ].append( (value,label) )
else:
top_by_key[ key ] = [ (value,label) ]
return dict( (key, sorted( values, reverse=True )[:ntop]) for key,values in top_by_key.iteritems() )
def heaptopn( ntop, data ):
top_by_key = {}
for key,value,label in data:
tup = (value,label)
if key not in top_by_key:
top_by_key[ key ] = [ tup ]
else:
top = top_by_key[ key ]
if len(top) < ntop:
heapq.heappush(top, tup)
else:
if top[0] < tup:
heapq.heapreplace(top, tup)
return dict( (key, sorted( values, reverse=True )) for key,values in top_by_key.iteritems() )
def dummy( data ):
for row in data:
pass
make_data( "data.txt" )
t = time.clock()
dummy( read_data( "data.txt" ) )
t_read = time.clock() - t
t = time.clock()
top_result = topn( 5, read_data( "data.txt" ) )
t_topn = time.clock() - t
t = time.clock()
htop_result = heaptopn( 5, read_data( "data.txt" ) )
t_htopn = time.clock() - t
# correctness checking :
for key in top_result:
print key, " : ", " ".join (("%f:%s"%(value,label)) for (value,label) in top_result[key])
print key, " : ", " ".join (("%f:%s"%(value,label)) for (value,label) in htop_result[key])
print
print "Read data :", t_read
print "TopN : ", t_topn - t_read
print "HeapTopN : ", t_htopn - t_read
for key in top_result:
assert top_result[key] == htop_result[key]
SELECT count( key ) FROM the dataset in the above program
CREATE INDEX topn_key_value ON topn( key, value );
CREATE TEMPORARY TABLE topkeys AS SELECT key FROM topn GROUP BY key;
CREATE TEMPORARY TABLE top AS SELECT (r).* FROM (SELECT (SELECT b AS r FROM topn b WHERE b.key=a.key ORDER BY value DESC LIMIT 1) AS r FROM topkeys a) foo;
INSERT INTO top SELECT (r).* FROM (SELECT (SELECT b AS r FROM topn b WHERE b.key=a.key ORDER BY value DESC LIMIT 1 OFFSET 1) AS r FROM topkeys a) foo;
INSERT INTO top SELECT (r).* FROM (SELECT (SELECT b AS r FROM topn b WHERE b.key=a.key ORDER BY value DESC LIMIT 1 OFFSET 2) AS r FROM topkeys a) foo;
INSERT INTO top SELECT (r).* FROM (SELECT (SELECT b AS r FROM topn b WHERE b.key=a.key ORDER BY value DESC LIMIT 1 OFFSET 3) AS r FROM topkeys a) foo;
INSERT INTO top SELECT (r).* FROM (SELECT (SELECT b AS r FROM topn b WHERE b.key=a.key ORDER BY value DESC LIMIT 1 OFFSET 4) AS r FROM topkeys a) foo;
INSERT INTO top SELECT (r).* FROM (SELECT (SELECT b AS r FROM topn b WHERE b.key=a.key ORDER BY value DESC LIMIT 1 OFFSET 5) AS r FROM topkeys a) foo;
SELECT * FROM top ORDER BY key,value;
for each row (key,score,id) :
create or fetch a list of top scores for the row's key
if len( this list ) < N
append current
else if current score > minimum score in list
replace minimum of list with current row
update minimum of all lists if needed
ocamlopt -pp camlp4o code.ml -o caml
open Printf
let cmp x y = compare (fst x : float) (fst y)
let digit c = Char.code c - Char.code '0'
let rec parse f = parser
| [< a=int; _=spaces; b=float; _=spaces;
c=rest (Buffer.create 100); t >] -> f a b c; parse f t
| [< >] -> ()
and int = parser
| [< ''0'..'9' as c; t >] -> int_ (digit c) t
| [< ''-'; ''0'..'9' as c; t >] -> - (int_ (digit c) t)
and int_ n = parser
| [< ''0'..'9' as c; t >] -> int_ (n * 10 + digit c) t
| [< >] -> n
and float = parser
| [< n=int; t=frem; e=fexp >] -> (float_of_int n +. t) *. (10. ** e)
and frem = parser
| [< ''.'; r=frem_ 0.0 10. >] -> r
| [< >] -> 0.0
and frem_ f base = parser
| [< ''0'..'9' as c; t >] ->
frem_ (float_of_int (digit c) /. base +. f) (base *. 10.) t
| [< >] -> f
and fexp = parser
| [< ''e'; e=int >] -> float_of_int e
| [< >] -> 0.0
and spaces = parser
| [< '' '; t >] -> spaces t
| [< ''\t'; t >] -> spaces t
| [< >] -> ()
and crlf = parser
| [< ''\r'; t >] -> crlf t
| [< ''\n'; t >] -> crlf t
| [< >] -> ()
and rest b = parser
| [< ''\r'; _=crlf >] -> Buffer.contents b
| [< ''\n'; _=crlf >] -> Buffer.contents b
| [< 'c; t >] -> Buffer.add_char b c; rest b t
| [< >] -> Buffer.contents b
let () =
let all = Array.make 200 [] in
let each a b c =
assert (a >= 0 && a < 200);
match all.(a) with
| [] -> all.(a) <- [b,c]
| (bmin,_) as prev::tl -> if b > bmin then
begin
let m = List.sort cmp ((b,c)::tl) in
all.(a) <- if List.length tl < 4 then prev::m else m
end
in
parse each (Stream.of_channel stdin);
Array.iteri
(fun a -> List.iter (fun (b,c) -> printf "%i %f %s\n" a b c))
all