mongodb mapreduce小试
最近由于产品业务的需求，需要使用一些数据量比较相对有点大的计算，顺便试试mongodb的mapreduce功能，感觉还不错下面是官方提供的一个例子：
$ ./mongo
> db.things.insert( { _id : 1, tags : ['dog', 'cat'] } );
> db.things.insert( { _id : 2, tags : ['cat'] } );
> db.things.insert( { _id : 3, tags : ['mouse', 'cat', 'dog'] } );
> db.things.insert( { _id : 4, tags : []} );
> // map function
> m = function(){
... this.tags.forEach(
... function(z){
... emit( z , { count : 1 } );
... }
... );
...};
> // reduce function
> r = function( key , values ){
... var total = 0;
... for ( var i=0; i res = db.things.mapReduce(m,r);
> res
{"timeMillis.emit" : 9 , "result" : "mr.things.1254430454.3" ,
"numObjects" : 4 , "timeMillis" : 9 , "errmsg" : "" , "ok" : 0}
> db.find()
{"_id" : "cat" , "value" : {"count" : 3}}
{"_id" : "dog" , "value" : {"count" : 2}}
{"_id" : "mouse" , "value" : {"count" : 1}}
> db.drop()
mapreduce参数说明
db.runCommand(
{
mapreduce : ,
map : ,
reduce :
[, query : ]
[, sort : ]
[, limit : ]
[, out : ]
[, keeptemp: ]
[, finalize : ]
[, scope : ]
[, verbose : true]
});
mapreduce：指定要进行mapreduce处理的collection
map：map函数
reduce：reduce函数
query：一个筛选条件，只有满足条件的行才会加入mapreduce集合，而这个筛选过程是先于整个mapreduce流程而执行的
sort：和query结合的sort排序参数，这是唯一可以优化分组机制的地方
limit：同上
out：结果输出的collection的名字，不指定会默认创建一个随机名字的collection
keytemp：true或false，表明结果输出到的collection是否是临时的，如果为true，则会在客户端连接中断后自动删除，如果你用的是MongoDB的mongo客户端连接，那必须exit后才会删除。如果是脚本执行，脚本退出或调用close会自动删除结果collection
finalize：和map，reduce一样是一个函数，它可以在reduce得出一个结果后再对key和value进行一次计算并返回一个最终结果
scope：设置参数值，在这里设置的值在map，reduce，finalize函数中可见
verbose：在执行过程中打印调试信息。
返回格式：
{
result : ,
counts : {input :, emit: , output : } ,
timeMillis : ,
ok : ,
[, err : ]
}
下面来一个略微复杂一点的例子，下面是统计房源列表页房源的曝光量：
mongodb数据格式：
{ "_id" : ObjectId("50364d9fdec7d5ce4000198d"), "pn" : "Listing_V2_IndexPage_All", "guid" : "E200F425-30E7-0D97-9B3A-E047A08CE47C", "uguid" : "4455754C-B2A0-7EDA-6387-A50F0228DE7F", "url" : "http://shanghai.haozu.com/listing/pudong/?from=in_area", "referer" : "http://shanghai.haozu.com/", "site" : "haozu", "stamp" : "1345691212948", "cip" : "116.231.123.184", "sessid" : "B1197AA0-976C-F6EF-BB6F-9401D8E983DD", "cid" : "11", "cstamp" : "1345691178421", "cstparam" : "{\"found\":\"37695\",\"proids\":\"10290023|10353348|8448223|10310737|10311720|10250125|10320886|8507299|10332158|10341287|10266002|10322302|9185878|10273552|10272872|10282252|10270250|10336122|9350169|10196350|8533446|10250019|10335617|10222489\"}", "rfpn" : "Home_Index8Page", "agent" : "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; 360SE; 360SE)" }
房源id保存在cstparam字段里面，是一个字符串，因此需要正则进行一下匹配，然后取出进行统计
，因此对应的map,reduce的写法为：
map方法：
var m=function () {
var arr = this.cstparam.split("\"");
var str_ids = arr;
var arr_ids = str_ids.split("|");
for (var i in arr_ids) {
emit(arr_ids, 1);
}
}
reduce方法：
var reduce=function (key, emits) {
var count = 0;
for (var i in emits) {
count += emits;
}
return count;
}
执行：
db.log_soj.mapReduce(map,reduce,{out:'result_tmp',query:{'cstparam':{'$exists':true},'cstparam':/proids/}});
返回结果：
{
"result" : "result_tmp",
"timeMillis" : 18888,
"counts" : {
"input" : 15742,
"emit" : 333011,
"reduce" : 103137,
"output" : 150897
},
"ok" : 1,
}
结果集：
{ "_id" : "10000003", "value" : 1 }
{ "_id" : "10000016", "value" : 2 }
{ "_id" : "10000032", "value" : 1 }
{ "_id" : "10000039", "value" : 1 }
{ "_id" : "10000043", "value" : 1 }
{ "_id" : "10000059", "value" : 1 }
再来一个，和上例类似，但是按照房源所出现的城市进行曝光量的统计
map函数：
function () {
var arr = this.cstparam.split("\"");
var str_ids = arr;
var arr_ids = str_ids.split("|");
for (var i in arr_ids) {
var key = arr_ids + "_" + this.cid;
emit(key, {prop_id:arr_ids, city_id:this.cid, count:1});
}
}
reduce函数：
function (key, emits) {
var total = 0;
for (var i in emits) {
total += emits.count;
}
return {prop_id:emits.prop_id, city_id:emits.city_id, count:total};
}
执行：
db.log_soj.mapReduce(m1,r1,{out:'result_tmp',query:{'cstparam':{'$exists':true},'cstparam':/proids/}});
结果：
{ "_id" : "10000003_undefined", "value" : { "prop_id" : "10000003", "city_id" : null, "count" : 1 } }
{ "_id" : "10000016_14", "value" : { "prop_id" : "10000016", "city_id" : "14", "count" : 2 } }
{ "_id" : "10000032_15", "value" : { "prop_id" : "10000032", "city_id" : "15", "count" : 1 } }
{ "_id" : "10000039_15", "value" : { "prop_id" : "10000039", "city_id" : "15", "count" : 1 } }
{ "_id" : "10000043_11", "value" : { "prop_id" : "10000043", "city_id" : "11", "count" : 1 } }
{ "_id" : "10000059_17", "value" : { "prop_id" : "10000059", "city_id" : "17", "count" : 1 } }
{ "_id" : "10000068_11", "value" : { "prop_id" : "10000068", "city_id" : "11", "count" : 1 } }
{ "_id" : "10000099_15", "value" : { "prop_id" : "10000099", "city_id" : "15", "count" : 1 } }
{ "_id" : "10000100_18", "value" : { "prop_id" : "10000100", "city_id" : "18", "count" : 1 } }
{ "_id" : "10000106_14", "value" : { "prop_id" : "10000106", "city_id" : "14", "count" : 1 } }
{ "_id" : "10000109_18", "value" : { "prop_id" : "10000109", "city_id" : "18", "count" : 3 } }
{ "_id" : "10000112_15", "value" : { "prop_id" : "10000112", "city_id" : "15", "count" : 1 } }
{ "_id" : "10000118_15", "value" : { "prop_id" : "10000118", "city_id" : "15", "count" : 1 } }
{ "_id" : "10000156_11", "value" : { "prop_id" : "10000156", "city_id" : "11", "count" : 1 } }
{ "_id" : "10000224_14", "value" : { "prop_id" : "10000224", "city_id" : "14", "count" : 1 } }
{ "_id" : "10000250_22", "value" : { "prop_id" : "10000250", "city_id" : "22", "count" : 1 } }
{ "_id" : "10000262_25", "value" : { "prop_id" : "10000262", "city_id" : "25", "count" : 1 } }
{ "_id" : "10000267_14", "value" : { "prop_id" : "10000267", "city_id" : "14", "count" : 3 } }
{ "_id" : "10000305_14", "value" : { "prop_id" : "10000305", "city_id" : "14", "count" : 3 } }
{ "_id" : "10000323_11", "value" : { "prop_id" : "10000323", "city_id" : "11", "count" : 1 } }
转载请注明出处：
http://www.iyunv.com/xiazh/archive/2012/09/05/2671730.html
页:
[1]