-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
Showing
4 changed files
with
98 additions
and
13 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Original file line | Diff line number | Diff line change |
---|---|---|---|
@@ -0,0 +1,40 @@ | |||
# Compiled source # | |||
################### | |||
*.com | |||
*.class | |||
*.dll | |||
*.exe | |||
*.o | |||
*.so | |||
*.pyc | |||
*.stream | |||
*.gr | |||
# Packages # | |||
############ | |||
# it's better to unpack these files and commit the raw source | |||
# git has its own built in compression methods | |||
*.7z | |||
*.dmg | |||
*.iso | |||
*.jar | |||
*.rar | |||
*.tar | |||
*.zip | |||
|
|||
# Logs and databases # | |||
###################### | |||
*.log | |||
*.sql | |||
*.sqlite | |||
*.bbl | |||
*.aux | |||
*.blg | |||
*.dvi | |||
|
|||
# OS generated files # | |||
###################### | |||
.DS_Store? | |||
ehthumbs.db | |||
Icon? | |||
Thumbs.db |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Original file line | Diff line number | Diff line change |
---|---|---|---|
@@ -0,0 +1,31 @@ | |||
''' | |||
Created on Nov 19, 2011 | |||
@author: kykamath | |||
''' | |||
from settings import hdfsInputFolder, hashtagsWithoutEndingWindowFile, hashtagsWithEndingWindowFile | |||
from datetime import datetime | |||
from dateutil.relativedelta import relativedelta | |||
from library.mrjobwrapper import runMRJob | |||
from mr_analysis import MRAnalysis | |||
from hashtags_for_locations.mr_analysis import PARAMS_DICT | |||
from library.file_io import FileIO | |||
|
|||
def getInputFiles(startTime, endTime, folderType='world'): | |||
current=startTime | |||
while current<=endTime: | |||
yield hdfsInputFolder%folderType+'%s_%s'%(current.year, current.month) | |||
current+=relativedelta(months=1) | |||
|
|||
def mr_analysis(startTime, endTime, outputFolder): | |||
outputFile = hashtagsWithEndingWindowFile%outputFolder | |||
runMRJob(MRAnalysis, outputFile, getInputFiles(startTime, endTime), jobconf={'mapred.reduce.tasks':300}) | |||
FileIO.writeToFileAsJson(PARAMS_DICT, outputFile) | |||
|
|||
if __name__ == '__main__': | |||
startTime, endTime, outputFolder = datetime(2011, 4, 1), datetime(2012, 1, 31), 'complete' # Complete duration | |||
# startTime, endTime, outputFolder = datetime(2011, 5, 1), datetime(2011, 12, 31), 'complete_prop' # Complete propagation duration | |||
# startTime, endTime, outputFolder = datetime(2011, 5, 1), datetime(2011, 10, 31), 'training' # Training duration | |||
# startTime, endTime, outputFolder = datetime(2011, 11, 1), datetime(2011, 12, 31), 'testing' # Testing duration | |||
|
|||
mr_analysis(startTime, endTime, outputFolder) |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Original file line | Diff line number | Diff line change |
---|---|---|---|
@@ -0,0 +1,10 @@ | |||
''' | |||
Created on Feb 12, 2012 | |||
@author: kykamath | |||
''' | |||
hdfsInputFolder = 'hdfs:///user/kykamath/geo/hashtags/%s/' | |||
|
|||
analysisFolder = '/mnt/chevron/kykamath/data/geo/hashtags/hashtags_for_locations/%s/' | |||
hashtagsWithoutEndingWindowFile = analysisFolder+'hashtagsWithoutEndingWindow' | |||
hashtagsWithEndingWindowFile = analysisFolder+'hashtagsWithEndingWindow' |