-
-
Save RedBeard0531/1886960 to your computer and use it in GitHub Desktop.
| // derived from http://en.wikipedia.org/wiki/Algorithms_for_calculating_variance#Parallel_algorithm | |
| function map() { | |
| emit(1, // Or put a GROUP BY key here | |
| {sum: this.value, // the field you want stats for | |
| min: this.value, | |
| max: this.value, | |
| count:1, | |
| diff: 0, // M2,n: sum((val-mean)^2) | |
| }); | |
| } | |
| function reduce(key, values) { | |
| var a = values[0]; // will reduce into here | |
| for (var i=1/*!*/; i < values.length; i++){ | |
| var b = values[i]; // will merge 'b' into 'a' | |
| // temp helpers | |
| var delta = a.sum/a.count - b.sum/b.count; // a.mean - b.mean | |
| var weight = (a.count * b.count)/(a.count + b.count); | |
| // do the reducing | |
| a.diff += b.diff + delta*delta*weight; | |
| a.sum += b.sum; | |
| a.count += b.count; | |
| a.min = Math.min(a.min, b.min); | |
| a.max = Math.max(a.max, b.max); | |
| } | |
| return a; | |
| } | |
| function finalize(key, value){ | |
| value.avg = value.sum / value.count; | |
| value.variance = value.diff / value.count; | |
| value.stddev = Math.sqrt(value.variance); | |
| return value; | |
| } |
| > load('functions.js') | |
| > db.stuff.drop() | |
| false | |
| > db.stuff.insert({value:1}) | |
| > db.stuff.insert({value:2}) | |
| > db.stuff.insert({value:2}) | |
| > db.stuff.insert({value:2}) | |
| > db.stuff.insert({value:3}) | |
| > db.stuff.mapReduce(map, reduce, {finalize:finalize, out:{inline:1}}).results[0] | |
| { | |
| "_id" : 1, | |
| "value" : { | |
| "sum" : 10, | |
| "min" : 1, | |
| "max" : 3, | |
| "count" : 5, | |
| "diff" : 2, | |
| "avg" : 2, | |
| "variance" : 0.4, | |
| "stddev" : 0.6324555320336759 | |
| } | |
| } |
Thank you for posting this!
Thank you, It's very useful for me.
Can we merge two groups if there are duplicate entries in them
example I have two groups group1 and group2 having userName and usage
group1
user1 10
user2 12
user3 15
group2
user2 14
user3 13
user4 16
merged
user1 10
user2 26
user3 28
user4 16
stdev - 7.3485
i want to find st dev of merged group, but problem is because of high data volume I can't maintain userName , so i am maintaining sum and user count, and by probablistic counting algorithm I can find unique users also
group1
count-3, sum-37, diff-9.935
group2
count-3, sum-43, diff-7.919
merged group
unique- 4
group1:: count-3, sum-37, diff-9.935
group2:: count-3, sum-43, diff-7.919
now with this information available, can i find standard deviation of merged group??
Thanks!!
What is the license on this code?
Word of warning, this is doing population standard dev and variance, NOT SAMPLE.
I cleaned up the code and included sample variance and standard dev.
Very useful code
Thank you!
You sir, rock!
Thanks so much :)