MongoDB映射功能中的多个文件输入
实际上,我想在mongodb中实现一个数据聚类算法。 我有两个文件MongoDB映射功能中的多个文件输入,mongodb,Mongodb,实际上,我想在mongodb中实现一个数据聚类算法。 我有两个文件 数据文件:它有带时间戳的数据点 例: 配置文件(元数据) 维度类别粒度 0, N, 4,0,100 [ 0 th dimesion is numeric has granularity 4 and starts from 0 & goes till 100 i.e. 0-25, 26-50, 51-75,76-100] 1,N,2,0,50 [Ist dimension has gran = 2 thus 0
0, N, 4,0,100 [ 0 th dimesion is numeric has granularity 4 and starts from 0 & goes till 100 i.e. 0-25, 26-50, 51-75,76-100]
1,N,2,0,50 [Ist dimension has gran = 2 thus 0-25, 26-50]
2,C,A,B,C,D [2nd dimension is categorical and as values a,b,c,d therefore granularity 4]
现在,我必须在mongodb中构建一个MAP-REDUCE函数,通过输入上述文件,为时间戳处的数据提供d签名:
6- 1,1,0
7- 3,1,1
等等
我必须运行map reduce,将两个文件都作为输入。。但是我在mongodb map reduce中找不到任何方法来获取输入的多个文件。
如果有人有什么想法,请告诉我怎么做
谢谢mapReduce作业的输入是MongoDB集合,不能是数据文件 但是,在您的情况下,您不需要mapReduce(),因为没有“reduce”部分—您所做的只是将1:1的输入记录转换为输出记录 因此,第一步是将数据文件存储到集合“inp”中——将时间序列作为数组存储在文档中。如果您的数据文件会导致一个大于16MB的文档,那么您必须将其拆分为多个文档-为了示例起见,我将每个文档仅存储2个时间戳元素。我用JavaScript为mongo shell编写了以下示例:
PATH = "/home/ronald/mongotest/";
DATA = "data.file";
ELEMS_PER_DOC = 2; // number of emelements in "series" per document
db.data.drop();
data = cat( PATH + DATA );
lines = data.split("\n")
lines = lines.splice(0,lines.length-1);
series = [];
lines.forEach(function( line ) {
if ( series.length >= ELEMS_PER_DOC ) {
db.data.insert({ "series": series });
series = [];
}
l = line.split("|");
timestamp = l[0];
d = l[1].split(",");
series.push( { "ts": timestamp, "data": d } );
});
db.data.insert({ "series": series });
对于给定的数据文件:
6|46,36,A
7|90,45,B
8|45,12,C
9|34,67,D
这将产生以下集合:
> db.data.find().pretty()
{
"_id" : ObjectId("515e735657a0887a97cc8d23"),
"series" : [
{
"ts" : "6",
"data" : [
"46",
"36",
"A"
]
},
{
"ts" : "7",
"data" : [
"90",
"45",
"B"
]
}
]
}
{
"_id" : ObjectId("515e735657a0887a97cc8d24"),
"series" : [
{
"ts" : "8",
"data" : [
"45",
"12",
"C"
]
},
{
"ts" : "9",
"data" : [
"34",
"67",
"D"
]
}
]
}
db.out.drop();
cursor = db.data.find();
cursor.forEach( function (doc) {
doc.series.forEach( function (serie) {
for ( i=0; i<serie.data.length; i++ ) {
// apply transformation function for each dimension
serie.data[i] = funcs[i]( serie.data[i] );
}
});
db.out.insert( doc );
})
[注意:如果您不想在MongoDB中存储输入数据,那么只需构建“series”数组,并在第三步中将其用作输入。观察客户端计算机上的内存使用情况!]
下一步是从配置文件生成JavaScript函数,这些函数将用于根据规则集转换数据。实际上,这将是一个函数数组,以避免硬编码的三维限制
PATH = "/home/ronald/mongotest/";
CONFIG = "config.file";
config = cat( PATH + CONFIG );
lines = config.split("\n")
lines = lines.splice(0,lines.length-1);
// array of functions - index = dimension
funcs = [];
lines.forEach(function( line ) {
x = line.split(",");
f = "";
if ( x[1] == "N" ) {
// Numeric rule:
// x[2] = granularity
// x[3],x[4] lower,upper range
// the function to be called for the given value looks like:
// function( val ) returns: the interval or "n/a" if outside range
// the interval is given by (val - (val modulo intervalSize)) / intervalSize
// the intervalSize is (max - min) / granularity
intervalSize = (x[4] - x[3]) / x[2];
f = "function (val) {";
f += " if ( val < "+x[3]+" || val > "+x[4]+" ) return 'n/a';";
f += " return (val - val % "+intervalSize+") / "+intervalSize+";";
f += "}";
} else if ( x[1] == "C" ) {
// Categoric rule:
// return the position of value in the array of params
// skip dimension and rule type
x = x.splice(2, x.length-1);
// build parameter array
pa = '[';
x.forEach( function(p) { pa += '"' + p + '",' } );
pa += ']';
// the function will return -1 if value not found in array
f = "function (val) { return "+pa+".indexOf(val) }";
}
else {
// unknown rule type
f = "function (val) { return 'rule err' }";
}
eval( "fx = "+f );
funcs.push( fx );
});
这将生成以下函数数组:
> funcs
[
function (val) { if ( val < 0 || val > 100 ) return 'n/a'; return (val - val % 25) / 25;},
function (val) { if ( val < 0 || val > 50 ) return 'n/a'; return (val - val % 25) / 25;},
function (val) { return ["A","B","C","D",].indexOf(val) }
]
> funcs
[
function (val) { if ( val < 0 || val > 100 ) return 'n/a'; return (val - val % 25) / 25;},
function (val) { if ( val < 0 || val > 50 ) return 'n/a'; return (val - val % 25) / 25;},
function (val) { return ["A","B","C","D",].indexOf(val) }
]
db.out.drop();
cursor = db.data.find();
cursor.forEach( function (doc) {
doc.series.forEach( function (serie) {
for ( i=0; i<serie.data.length; i++ ) {
// apply transformation function for each dimension
serie.data[i] = funcs[i]( serie.data[i] );
}
});
db.out.insert( doc );
})
> db.out.find().pretty()
{
"_id" : ObjectId("515e974c57a0887a97cc8d2f"),
"series" : [
{
"ts" : "6",
"data" : [
1,
1,
0
]
},
{
"ts" : "7",
"data" : [
3,
1,
1
]
}
]
}
{
"_id" : ObjectId("515e974c57a0887a97cc8d30"),
"series" : [
{
"ts" : "8",
"data" : [
1,
0,
2
]
},
{
"ts" : "9",
"data" : [
1,
"n/a",
3
]
}
]
}