Last active
December 24, 2015 02:25
-
-
Save jinhoyoo/b6f3b22ab0f9401b8d3a to your computer and use it in GitHub Desktop.
Spark clustering example code
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from pyspark import SparkContext | |
from subprocess import call, check_output | |
import numpy as np #Spark has numpy for python. | |
def run(sc): | |
data = [np.arange(0, 99), np.arange(100, 200) ] | |
distData=sc.parallelize(data) | |
sc.addFile("/master/sum_of_numbers") | |
def sumData(x): | |
strCmd = map(str, x) | |
strCmd.insert(0, "./sum_of_numbers") | |
strResult=check_output(strCmd) | |
return int(strResult) | |
return distData.map(sumData).reduce(lambda a, b: a + b) | |
if __name__ == '__main__': | |
print run(SparkContext()) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from pyspark import SparkContext | |
import numpy as np #Spark has numpy for python. | |
def run(sc): | |
data = [np.arange(0, 99), np.arange(100, 200) ] | |
distData = sc.parallelize(data) | |
def sumData(x): | |
return np.sum(x) | |
mappedSum = distData.map( sumData ) | |
return mappedSum.reduce(lambda a, b: a + b) | |
if __name__ == '__main__': | |
print run(SparkContext() ) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from pyspark import SparkContext | |
from subprocess import call, check_output | |
import numpy as np #Spark has numpy for python. | |
def run(sc): | |
data = [np.arange(0, 99), np.arange(100, 200) ] | |
distData=sc.parallelize(data) | |
sc.addFile("/master/sum_of_numbers") | |
def sumData(x): | |
strCmd = map(str, x) | |
strCmd.insert(0, "./sum_of_numbers") | |
strResult=check_output(strCmd) | |
return int(strResult) | |
return distData.map(sumData).reduce(lambda a, b: a + b) | |
if __name__ == '__main__': | |
print run(SparkContext()) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from pyspark import SparkContext | |
from sklearn import datasets, svm | |
def run(sc): | |
iris = datasets.load_iris() | |
digits = [ datasets.load_digits(), datasets.load_digits()] | |
def learn(x): | |
clf = svm.SVC(gamma=0.001, C=100.) | |
clf.fit(x.data[:-1], x.target[:-1] ) | |
return clf.predict(x.data[-1]) | |
return sc.parallelize(digits).map(learn).collect() | |
if __name__ == '__main__': | |
print run(SparkContext() ) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#include <stdio.h> | |
int main(int argc, char *argv[]) | |
{ | |
int count, s = 0; | |
int i; | |
count = argc; | |
for (i = 1; i < argc; i++) | |
{ | |
s += atoi(argv[i]); | |
} | |
printf("%d", s); | |
return 0; | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment