Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 0 additions & 33 deletions build.gradle

This file was deleted.

Binary file removed gradle/wrapper/gradle-wrapper.jar
Binary file not shown.
6 changes: 0 additions & 6 deletions gradle/wrapper/gradle-wrapper.properties

This file was deleted.

160 changes: 0 additions & 160 deletions gradlew

This file was deleted.

90 changes: 0 additions & 90 deletions gradlew.bat

This file was deleted.

7 changes: 3 additions & 4 deletions pairRdd/aggregation/reducebykey/WordCount.py
Original file line number Diff line number Diff line change
@@ -1,9 +1,8 @@
from pyspark import SparkContext
from pyspark import SparkContext, SparkConf

if __name__ == "__main__":

sc = SparkContext("local", "wordCounts")
sc.setLogLevel("ERROR")
conf = SparkConf().setAppName("wordCounts").setMaster("local[3]")
sc = SparkContext(conf = conf)

lines = sc.textFile("in/word_count.text")
wordRdd = lines.flatMap(lambda line: line.split(" "))
Expand Down
7 changes: 3 additions & 4 deletions pairRdd/create/PairRddFromRegularRdd.py
Original file line number Diff line number Diff line change
@@ -1,9 +1,8 @@
from pyspark import SparkContext
from pyspark import SparkContext, SparkConf

if __name__ == "__main__":

sc = SparkContext("local", "create")
sc.setLogLevel("ERROR")
conf = SparkConf().setAppName("create").setMaster("local")
sc = SparkContext(conf = conf)

inputStrings = ["Lily 23", "Jack 29", "Mary 29", "James 8"]
regularRDDs = sc.parallelize(inputStrings)
Expand Down
7 changes: 3 additions & 4 deletions pairRdd/create/PairRddFromTupleList.py
Original file line number Diff line number Diff line change
@@ -1,9 +1,8 @@
from pyspark import SparkContext
from pyspark import SparkContext, SparkConf

if __name__ == "__main__":

sc = SparkContext("local", "create")
sc.setLogLevel("ERROR")
conf = SparkConf().setAppName("create").setMaster("local")
sc = SparkContext(conf = conf)

tuples = [("Lily", 23), ("Jack", 29), ("Mary", 29), ("James", 8)]
pairRDD = sc.parallelize(tuples)
Expand Down
15 changes: 9 additions & 6 deletions pairRdd/groupbykey/GroupByKeyVsReduceByKey.py
Original file line number Diff line number Diff line change
@@ -1,18 +1,21 @@
from pyspark import SparkContext
from pyspark import SparkContext, SparkConf

if __name__ == "__main__":

sc = SparkContext("local", "GroupByKeyVsReduceByKey")
sc.setLogLevel("ERROR")
conf = SparkConf().setAppName('GroupByKeyVsReduceByKey').setMaster("local[*]")
sc = SparkContext(conf = conf)

words = ["one", "two", "two", "three", "three", "three"]
wordsPairRdd = sc.parallelize(words).map(lambda word: (word, 1))

wordCountsWithReduceByKey = wordsPairRdd.reduceByKey(lambda x, y: x + y).collect()
wordCountsWithReduceByKey = wordsPairRdd \
.reduceByKey(lambda x, y: x + y) \
.collect()
print("wordCountsWithReduceByKey: {}".format(list(wordCountsWithReduceByKey)))

wordCountsWithGroupByKey = wordsPairRdd \
.groupByKey() \
.mapValues(lambda intIterable: len(intIterable)) \
.mapValues(len) \
.collect()
print("wordCountsWithGroupByKey: {}".format(list(wordCountsWithGroupByKey)))


7 changes: 3 additions & 4 deletions pairRdd/join/JoinOperations.py
Original file line number Diff line number Diff line change
@@ -1,9 +1,8 @@
from pyspark import SparkContext
from pyspark import SparkContext, SparkConf

if __name__ == "__main__":

sc = SparkContext("local", "JoinOperations")
sc.setLogLevel("ERROR")
conf = SparkConf().setAppName("JoinOperations").setMaster("local[1]")
sc = SparkContext(conf = conf)

ages = sc.parallelize([("Tom", 29), ("John", 22)])
addresses = sc.parallelize([("James", "USA"), ("John", "UK")])
Expand Down
Loading