9. MapReduceでWord Count
9
Lorem ipsum
dolor sit amet,
consectetur
adipisicing elit,
sed do
eiusmod
tempor
incididunt ut
labore et
dolore magna
aliqua Ut enim
ad minim
veniam, quis
nostrud
exercitation
ullamco
lorem 2
lorem 1
ipsum 1
dolor 1
lorem 1
lorem 1
sit 1
amet 1
consect.. 1
do 1
eiusmod 1
tempor 1
adipisic.. 1
elit 1
sed 1
ipsum 1
ipsum 1
ipsum 1
dolor 1
ipsum 3
sit 1
sit 1
sit 1
dolor 1
sit 3
map shuffle reduce result
lorem 2
ipsum 3
dolor 1
sit 3
:
10. MapReduceでWord Count
10
Lorem ipsum
dolor sit amet,
consectetur
adipisicing elit,
sed do
eiusmod
tempor
incididunt ut
labore et
dolore magna
aliqua Ut enim
ad minim
veniam, quis
nostrud
exercitation
ullamco
lorem 2
lorem 1
ipsum 1
dolor 1
lorem 1
lorem 1
sit 1
amet 1
consect.. 1
do 1
eiusmod 1
tempor 1
adipisic.. 1
elit 1
sed 1
ipsum 1
ipsum 1
ipsum 1
dolor 1
ipsum 3
sit 1
sit 1
sit 1
dolor 1
sit 3
map shuffle reduce result
lorem 2
ipsum 3
dolor 1
sit 3
:
(hadoopの場合)
・中間結果をディスクに書き出す
・正格評価 → 逐次計算
11. MapReduceでWord Count
11
Lorem ipsum
dolor sit amet,
consectetur
adipisicing elit,
sed do
eiusmod
tempor
incididunt ut
labore et
dolore magna
aliqua Ut enim
ad minim
veniam, quis
nostrud
exercitation
ullamco
lorem 2
lorem 1
ipsum 1
dolor 1
lorem 1
lorem 1
sit 1
amet 1
consect.. 1
do 1
eiusmod 1
tempor 1
adipisic.. 1
elit 1
sed 1
ipsum 1
ipsum 1
ipsum 1
dolor 1
ipsum 3
sit 1
sit 1
sit 1
dolor 1
sit 3
map shuffle reduce result
lorem 2
ipsum 3
dolor 1
sit 3
:
(sparkの場合)
RDD
DAG
・中間結果はメモリにキャッシュ
・遅延評価 → 計算量最適化
RDD RDD RDD