Movatterモバイル変換

[0]ホーム
URL:

Skip to content

Navigation Menu

Sign in
Appearance settings

Search code, repositories, users, issues, pull requests...

Provide feedback

We read every piece of feedback, and take your input very seriously.

Saved searches

Use saved searches to filter your results more quickly

 Sign up
Appearance settings

Commit76f5cce

Browse files
author
Pedro Bernardo
committed
Changed scripts to use the conf paramenter on the SparkContext constructor & Removed setLogLevel
1 parenta6dc078 commit76f5cce

File tree

14 files changed

+77
-54
lines changed

14 files changed

+77
-54
lines changed

‎pairRdd/aggregation/reducebykey/WordCount.py‎

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,8 @@
1-
frompysparkimportSparkContext
1+
frompysparkimportSparkContext,SparkConf
22

33
if__name__=="__main__":
4-
5-
sc=SparkContext("local","wordCounts")
6-
sc.setLogLevel("ERROR")
4+
conf=SparkConf().setAppName("wordCounts").setMaster("local[3]")
5+
sc=SparkContext(conf=conf)
76

87
lines=sc.textFile("in/word_count.text")
98
wordRdd=lines.flatMap(lambdaline:line.split(" "))

‎pairRdd/create/PairRddFromRegularRdd.py‎

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,8 @@
1-
frompysparkimportSparkContext
1+
frompysparkimportSparkContext,SparkConf
22

33
if__name__=="__main__":
4-
5-
sc=SparkContext("local","create")
6-
sc.setLogLevel("ERROR")
4+
conf=SparkConf().setAppName("create").setMaster("local")
5+
sc=SparkContext(conf=conf)
76

87
inputStrings= ["Lily 23","Jack 29","Mary 29","James 8"]
98
regularRDDs=sc.parallelize(inputStrings)

‎pairRdd/create/PairRddFromTupleList.py‎

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,8 @@
1-
frompysparkimportSparkContext
1+
frompysparkimportSparkContext,SparkConf
22

33
if__name__=="__main__":
4-
5-
sc=SparkContext("local","create")
6-
sc.setLogLevel("ERROR")
4+
conf=SparkConf().setAppName("create").setMaster("local")
5+
sc=SparkContext(conf=conf)
76

87
tuples= [("Lily",23), ("Jack",29), ("Mary",29), ("James",8)]
98
pairRDD=sc.parallelize(tuples)
Lines changed: 9 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -1,18 +1,21 @@
1-
frompysparkimportSparkContext
1+
frompysparkimportSparkContext,SparkConf
22

33
if__name__=="__main__":
4-
5-
sc=SparkContext("local","GroupByKeyVsReduceByKey")
6-
sc.setLogLevel("ERROR")
4+
conf=SparkConf().setAppName('GroupByKeyVsReduceByKey').setMaster("local[*]")
5+
sc=SparkContext(conf=conf)
76

87
words= ["one","two","two","three","three","three"]
98
wordsPairRdd=sc.parallelize(words).map(lambdaword: (word,1))
109

11-
wordCountsWithReduceByKey=wordsPairRdd.reduceByKey(lambdax,y:x+y).collect()
10+
wordCountsWithReduceByKey=wordsPairRdd \
11+
.reduceByKey(lambdax,y:x+y) \
12+
.collect()
1213
print("wordCountsWithReduceByKey: {}".format(list(wordCountsWithReduceByKey)))
1314

1415
wordCountsWithGroupByKey=wordsPairRdd \
1516
.groupByKey() \
16-
.mapValues(lambdaintIterable:len(intIterable)) \
17+
.mapValues(len) \
1718
.collect()
1819
print("wordCountsWithGroupByKey: {}".format(list(wordCountsWithGroupByKey)))
20+
21+

‎pairRdd/join/JoinOperations.py‎

Lines changed: 3 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,8 @@
1-
frompysparkimportSparkContext
1+
frompysparkimportSparkContext,SparkConf
22

33
if__name__=="__main__":
4-
5-
sc=SparkContext("local","JoinOperations")
6-
sc.setLogLevel("ERROR")
4+
conf=SparkConf().setAppName("JoinOperations").setMaster("local[1]")
5+
sc=SparkContext(conf=conf)
76

87
ages=sc.parallelize([("Tom",29), ("John",22)])
98
addresses=sc.parallelize([("James","USA"), ("John","UK")])

‎rdd/WordCount.py‎

Lines changed: 9 additions & 5 deletions
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,15 @@
1-
importsys
2-
frompysparkimportSparkContext
1+
frompysparkimportSparkContext,SparkConf
32

43
if__name__=="__main__":
5-
sc=SparkContext("local","word count")
6-
sc.setLogLevel("ERROR")
4+
conf=SparkConf().setAppName("word count").setMaster("local[3]")
5+
sc=SparkContext(conf=conf)
6+
77
lines=sc.textFile("in/word_count.text")
8+
89
words=lines.flatMap(lambdaline:line.split(" "))
10+
911
wordCounts=words.countByValue()
12+
1013
forword,countinwordCounts.items():
11-
print(word,count)
14+
print("{} : {}".format(word,count))
15+

‎rdd/collect/CollectExample.py‎

Lines changed: 9 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,15 @@
1-
frompysparkimportSparkContext
1+
frompysparkimportSparkContext,SparkConf
22

33
if__name__=="__main__":
4-
sc=SparkContext("local","collect")
5-
sc.setLogLevel("ERROR")
4+
conf=SparkConf().setAppName("collect").setMaster("local[*]")
5+
sc=SparkContext(conf=conf)
6+
67
inputWords= ["spark","hadoop","spark","hive","pig","cassandra","hadoop"]
8+
79
wordRdd=sc.parallelize(inputWords)
10+
811
words=wordRdd.collect()
12+
913
forwordinwords:
10-
print(word)
14+
print(word)
15+

‎rdd/count/CountExample.py‎

Lines changed: 4 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,12 +1,13 @@
1-
frompysparkimportSparkContext
1+
frompysparkimportSparkContext,SparkConf
22

33
if__name__=="__main__":
4-
sc=SparkContext("local","count")
5-
sc.setLogLevel("ERROR")
4+
conf=SparkConf().setAppName("count").setMaster("local[*]")
5+
sc=SparkContext(conf=conf)
66
inputWords= ["spark","hadoop","spark","hive","pig","cassandra","hadoop"]
77
wordRdd=sc.parallelize(inputWords)
88
print("Count: {}".format(wordRdd.count()))
99
worldCountByValue=wordRdd.countByValue()
1010
print("CountByValue: ")
1111
forword,countinworldCountByValue.items():
1212
print("{} : {}".format(word,count))
13+

‎rdd/nasaApacheWebLogs/SameHostsSolution.py‎

Lines changed: 3 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -1,7 +1,8 @@
1-
frompysparkimportSparkContext
1+
frompysparkimportSparkContext,SparkConf
22

33
if__name__=="__main__":
4-
sc=SparkContext("local","sameHosts")
4+
conf=SparkConf().setAppName("sameHosts").setMaster("local[1]")
5+
sc=SparkContext(conf=conf)
56

67
julyFirstLogs=sc.textFile("in/nasa_19950701.tsv")
78
augustFirstLogs=sc.textFile("in/nasa_19950801.tsv")
Lines changed: 5 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -1,10 +1,11 @@
1-
frompysparkimportSparkContext
1+
frompysparkimportSparkContext,SparkConf
22

33
defisNotHeader(line:str):
44
returnnot (line.startswith("host")and"bytes"inline)
55

66
if__name__=="__main__":
7-
sc=SparkContext("local","unionLogs")
7+
conf=SparkConf().setAppName("unionLogs").setMaster("local[*]")
8+
sc=SparkContext(conf=conf)
89

910
julyFirstLogs=sc.textFile("in/nasa_19950701.tsv")
1011
augustFirstLogs=sc.textFile("in/nasa_19950801.tsv")
@@ -14,4 +15,5 @@ def isNotHeader(line: str):
1415
cleanLogLines=aggregatedLogLines.filter(isNotHeader)
1516
sample=cleanLogLines.sample(withReplacement=True,fraction=0.1)
1617

17-
sample.saveAsTextFile("out/sample_nasa_logs.csv")
18+
sample.saveAsTextFile("out/sample_nasa_logs.csv")
19+

0 commit comments

Comments
 (0)
[8]ページ先頭
©2009-2025 Movatter.jp