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

Scala to Python - advanced folder#3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to ourterms of service andprivacy statement. We’ll occasionally send you account related emails.

Already on GitHub?Sign in to your account

Merged
jleetutorial merged 3 commits intomasterfrompedromb-scala_to_python
Oct 1, 2017
Merged
Show file tree
Hide file tree
Changes fromall 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
25 changes: 25 additions & 0 deletionsadvanced/accumulator/StackOverFlowSurvey.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,25 @@
from pyspark import SparkContext
from commons.Utils import Utils

def filterResponseFromCanada(response, total, missingSalaryMidPoint):
splits = Utils.COMMA_DELIMITER.split(response)
total.add(1)
if not splits[14]:
missingSalaryMidPoint.add(1)
return splits[2] == "Canada"

if __name__ == "__main__":
sc = SparkContext("local", "StackOverFlowSurvey")
sc.setLogLevel("ERROR")

total = sc.accumulator(0)
missingSalaryMidPoint = sc.accumulator(0)

responseRDD = sc.textFile("in/2016-stack-overflow-survey-responses.csv")

responseFromCanada = responseRDD.filter(lambda response: \
filterResponseFromCanada(response, total, missingSalaryMidPoint))

print("Count of responses from Canada: {}".format(responseFromCanada.count()))
print("Total count of responses: {}".format(total.value))
print("Count of responses missing salary middle point: {}".format(missingSalaryMidPoint.value))
34 changes: 0 additions & 34 deletionsadvanced/accumulator/StackOverFlowSurvey.scala
View file
Open in desktop

This file was deleted.

28 changes: 28 additions & 0 deletionsadvanced/accumulator/StackOverFlowSurveyFollowUp.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,28 @@
from pyspark import SparkContext
from commons.Utils import Utils

def filterResponseFromCanada(response, total, missingSalaryMidPoint, processedBytes):
processedBytes.add(len(response.encode('utf-8')))
splits = Utils.COMMA_DELIMITER.split(response)
total.add(1)
if not splits[14]:
missingSalaryMidPoint.add(1)
return splits[2] == "Canada"

if __name__ == "__main__":
sc = SparkContext("local", "StackOverFlowSurvey")
sc.setLogLevel("ERROR")

total = sc.accumulator(0)
missingSalaryMidPoint = sc.accumulator(0)
processedBytes = sc.accumulator(0)

responseRDD = sc.textFile("in/2016-stack-overflow-survey-responses.csv")

responseFromCanada = responseRDD.filter(lambda response: \
filterResponseFromCanada(response, total, missingSalaryMidPoint, processedBytes))

print("Count of responses from Canada: {}".format(responseFromCanada.count()))
print("Number of bytes processed: {}".format(processedBytes.value))
print("Total count of responses: {}".format(total.value))
print("Count of responses missing salary middle point: {}".format(missingSalaryMidPoint.value))
39 changes: 0 additions & 39 deletionsadvanced/accumulator/StackOverFlowSurveyFollowUp.scala
View file
Open in desktop

This file was deleted.

29 changes: 29 additions & 0 deletionsadvanced/broadcast/UkMakerSpaces.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,29 @@
from pyspark import SparkContext
from commons.Utils import Utils

def getPostPrefix(line: str):
splits = Utils.COMMA_DELIMITER.split(line)
postcode = splits[4]
return None if not postcode else postcode.split(" ")[0]

def loadPostCodeMap():
lines = open("in/uk-postcode.csv", "r").read().split("\n")
splitsForLines = [Utils.COMMA_DELIMITER.split(line) for line in lines if line != ""]
return {splits[0]: splits[7] for splits in splitsForLines}

if __name__ == "__main__":
sc = SparkContext("local", "UkMakerSpaces")
sc.setLogLevel("ERROR")

postCodeMap = sc.broadcast(loadPostCodeMap())

makerSpaceRdd = sc.textFile("in/uk-makerspaces-identifiable-data.csv")

regions = makerSpaceRdd \
.filter(lambda line: Utils.COMMA_DELIMITER.split(line)[0] != "Timestamp") \
.filter(lambda line: getPostPrefix(line) is not None) \
.map(lambda line: postCodeMap.value[getPostPrefix(line)] \
if getPostPrefix(line) in postCodeMap.value else "Unknow")

for region, count in regions.countByValue().items():
print("{} : {}".format(region, count))
40 changes: 0 additions & 40 deletionsadvanced/broadcast/UkMakerSpaces.scala
View file
Open in desktop

This file was deleted.

26 changes: 26 additions & 0 deletionsadvanced/broadcast/UkMakerSpacesWithoutBroadcast.py
View file
Open in desktop
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,26 @@
from pyspark import SparkContext
from commons.Utils import Utils

def getPostPrefixes(line: str):
postcode = Utils.COMMA_DELIMITER.split(line)[4]
cleanedPostCode = postcode.replace("\\s+", "")
return [cleanedPostCode[0:i] for i in range(0,len(cleanedPostCode)+1)]

def loadPostCodeMap():
lines = open("in/uk-postcode.csv", "r").read().split("\n")
splitsForLines = [Utils.COMMA_DELIMITER.split(line) for line in lines if line != ""]
return {splits[0]: splits[7] for splits in splitsForLines}

if __name__ == "__main__":
sc = SparkContext("local", "UkMakerSpaces")
sc.setLogLevel("ERROR")
postCodeMap = loadPostCodeMap()
makerSpaceRdd = sc.textFile("in/uk-makerspaces-identifiable-data.csv")

regions = makerSpaceRdd \
.filter(lambda line: Utils.COMMA_DELIMITER.split(line)[0] != "Timestamp") \
.map(lambda line: next((postCodeMap[prefix] for prefix in getPostPrefixes(line) \
if prefix in postCodeMap), "Unknow"))

for region, count in regions.countByValue().items():
print("{} : {}".format(region, count))
40 changes: 0 additions & 40 deletionsadvanced/broadcast/UkMakerSpacesWithoutBroadcast.scala
View file
Open in desktop

This file was deleted.

[8]ページ先頭
©2009-2025 Movatter.jp