def main():
input = sys.argv[1]
output = sys.argv[2]
conf = SparkConf().setAppName('Matrix Multiplication')
sc = SparkContext(conf=conf)
assert sc.version >= '1.5.1'
row = sc.textFile(input).map(lambda row : row.split(' ')).cache()
ncol = len(row.take(1)[0])
intermediateResult = row.map(permutation).reduce(add_tuples)
outputFile = open(output, 'w')
result = [intermediateResult[x:x+3] for x in range(0, len(intermediateResult), ncol)]
for row in result:
for element in row:
outputFile.write(str(element) + ' ')
outputFile.write('\n')
outputFile.close()
# outputResult = sc.parallelize(result).coalesce(1)
# outputResult.saveAsTextFile(output)
matrix_multiply.py 文件源码
python
阅读 18
收藏 0
点赞 0
评论 0
评论列表
文章目录