issues
search
ahfoss
/
kamilaStreamingHadoop
k-means and KAMILA algorithms written for MyHadoop on a SLURM batch scheduler
GNU General Public License v3.0
0
stars
0
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
Sqlite3 for kmeans data preprocessing
#32
ahfoss
opened
8 years ago
0
Python script for generating SLURM header
#31
ahfoss
opened
8 years ago
0
Rnw summary doc for KAMILA results
#30
ahfoss
closed
8 years ago
0
KAMILA algorithm slurm script and r scripts
#29
ahfoss
closed
8 years ago
2
Preprocessing script for KAMILA input
#28
ahfoss
closed
8 years ago
0
sqlite3 for data preprocessing
#27
ahfoss
closed
8 years ago
2
Logfile records real time, not total time spent by all individual tasks
#26
ahfoss
closed
8 years ago
1
Rnw summary doc gives relative size of clusters in percent
#25
ahfoss
closed
8 years ago
0
More descriptive preprocessing script names
#24
ahfoss
closed
8 years ago
2
Rnw summary doc handles categorical data gracefully
#23
ahfoss
closed
8 years ago
0
Implement Hennig-Liao coding in preprocessing step
#22
ahfoss
closed
8 years ago
1
Add unit testing
#21
ahfoss
opened
8 years ago
0
Fails for 10 reducers in certain cases
#20
ahfoss
closed
8 years ago
1
kmeans.slurm logs job stats in local data base
#19
ahfoss
closed
8 years ago
2
Sturm output filenames have dataset name
#18
ahfoss
closed
8 years ago
2
Rnw summary doc: principal components calculated on means rather than data?
#17
ahfoss
opened
8 years ago
2
README file revisions
#16
ahfoss
opened
8 years ago
0
Rnw doc: PC plot centroids should be numbered beginning at 0, not 1
#15
ahfoss
closed
8 years ago
0
Number of mappers
#14
ahfoss
closed
8 years ago
0
Improve some details in preprocessing pipeline
#13
ahfoss
closed
8 years ago
0
Assorted improvements to summary Rnw doc
#12
ahfoss
closed
8 years ago
0
Modified box plots for cluster X variable stats in summary Rnw doc
#11
ahfoss
opened
8 years ago
0
Replace R code with Rcpp/C
#10
ahfoss
opened
8 years ago
2
Summary map-reduce step breaks up clusters among different reducers
#9
ahfoss
closed
8 years ago
1
Change initialization/reseeding strategy from uniform to sampling data points
#8
ahfoss
closed
8 years ago
0
Properly seeding random mean initializations
#7
ahfoss
closed
8 years ago
3
Outer loop, where each iteration is a new initialization of a k-means run
#6
ahfoss
closed
8 years ago
0
Summary run: gives descriptive stats for clusters
#5
ahfoss
closed
8 years ago
2
Problem with empty clusters
#4
ahfoss
closed
8 years ago
3
Progress updates for proc1.py and proc2.py
#3
ahfoss
closed
8 years ago
0
The algorithm and helper functions handle csv files with a header row
#2
ahfoss
closed
8 years ago
0
Premature conversion of counts to means in reducer step
#1
ahfoss
closed
8 years ago
4