R + Hadoop = Big Data Analytics
66
77
88
99
library(rmr)
mapreduce(…)
lapply(data, function)
mapreduce(big.data, map = function)
Rmr
Hive, Pig
Rmr, Rhipe, Dumbo, Pydoop,
Hadoopy
Java, C++
Cascalog, Scalding, Scrunch
Cascading, Crunch
Expose MR Hide MR
mapreduce(input, output, map, reduce)
x = from.dfs(hdfs.object)
hdfs.object = to.dfs(x)
small.ints = 1:1000lapply(small.ints, function(x) x^2)
small.ints = to.dfs(1:1000)mapreduce(input = small.ints,
map = function(k,v) keyval(v, v^2))
groups = rbinom(32, n = 50, prob = 0.4)tapply(groups, groups, length)
groups = to.dfs(groups)mapreduce(input = groups,
map = function(k, v) keyval(v,1),reduce = function(k,vv)
keyval(k, length(vv)))
condition = function(x) x > 10
out = mapreduce(input = input, map = function(k,v)
if (condition(v)) keyval(k,v))
kmeans =function(points, ncenters, iterations = 10, distfun = function(a,b) norm(as.matrix(a-b), type = 'F')) {
newCenters = kmeans.iter(points, distfun, ncenters = ncenters) for(i in 1:iterations) { newCenters = kmeans.iter(points, distfun, centers = newCenters)} newCenters}
kmeans.iter = function(points, distfun, ncenters = dim(centers)[1], centers = NULL) { from.dfs(mapreduce(
input = points, map = if (is.null(centers)) { function(k,v) keyval(sample(1:ncenters,1),v)} else { function(k,v) { distances = apply(centers, 1, function(c) distfun(c,v)) keyval(centers[which.min(distances),], v)}}, reduce = function(k,vv) keyval(NULL, apply(do.call(rbind, vv), 2, mean))), to.data.frame = T)}
#!/usr/bin/pythonimport sysfrom math import fabsfrom org.apache.pig.scripting import Pig
filename = "student.txt"k = 4tolerance = 0.01
MAX_SCORE = 4MIN_SCORE = 0MAX_ITERATION = 100
# initial centroid, equally divide the spaceinitial_centroids = ""last_centroids = [None] * kfor i in range(k):
last_centroids[i] = MIN_SCORE + float(i)/k*(MAX_SCORE-MIN_SCORE)initial_centroids = initial_centroids + str(last_centroids[i])if i!=k-1:
initial_centroids = initial_centroids + ":"
P = Pig.compile("""register udf.jarDEFINE find_centroid FindCentroid('$centroids');raw = load 'student.txt' as (name:chararray, age:int, gpa:double);centroided = foreach raw generate gpa, find_centroid(gpa) as centroid;grouped = group centroided by centroid;result = foreach grouped generate group, AVG(centroided.gpa);store result into 'output';
""")
converged = Falseiter_num = 0while iter_num<MAX_ITERATION:
Q = P.bind({'centroids':initial_centroids})results = Q.runSingle()
if results.isSuccessful() == "FAILED":raise "Pig job failed"
iter = results.result("result").iterator()centroids = [None] * kdistance_move = 0# get new centroid of this iteration, caculate the moving distance with last iterationfor i in range(k):
tuple = iter.next()centroids[i] = float(str(tuple.get(1)))distance_move = distance_move + fabs(last_centroids[i]-centroids[i])
distance_move = distance_move / k;Pig.fs("rmr output")print("iteration " + str(iter_num))print("average distance moved: " + str(distance_move))if distance_move<tolerance:
sys.stdout.write("k-means converged at centroids: [")sys.stdout.write(",".join(str(v) for v in centroids))sys.stdout.write("]\n")converged = Truebreak
last_centroids = centroids[:]initial_centroids = ""for i in range(k):
initial_centroids = initial_centroids + str(last_centroids[i])if i!=k-1:
initial_centroids = initial_centroids + ":"iter_num += 1
if not converged:print("not converge after " + str(iter_num) + " iterations")sys.stdout.write("last centroids: [")sys.stdout.write(",".join(str(v) for v in last_centroids))sys.stdout.write("]\n")
import java.io.IOException;
import org.apache.pig.EvalFunc;import org.apache.pig.data.Tuple;
public class FindCentroid extends EvalFunc<Double> {double[] centroids;public FindCentroid(String initialCentroid) {
String[] centroidStrings = initialCentroid.split(":");centroids = new double[centroidStrings.length];for (int i=0;i<centroidStrings.length;i++)
centroids[i] = Double.parseDouble(centroidStrings[i]);}@Overridepublic Double exec(Tuple input) throws IOException {
double min_distance = Double.MAX_VALUE;double closest_centroid = 0;for (double centroid : centroids) {
double distance = Math.abs(centroid - (Double)input.get(0));if (distance < min_distance) {
min_distance = distance;closest_centroid = centroid;
}}return closest_centroid;
}
}
mapreduce(mapreduce(…
mapreduce(input = c(input1, input2), …)
equijoin = function(left.input, right.input, input,output,outer, map.left, map.right,reduce, reduce.all)
out1 = mapreduce(…)mapreduce(input = out1, <xyz>)mapreduce(input = out1, <abc>)
abstract.job = function(input, output, …) {…result = mapreduce(input = input,
output = output)…result}
input.format, output.format, formatreduce.on.data.frame, to.data.framelocal, hadoop backendsprofiling