szilard/benchm-ml
A minimal benchmark for scalability, speed and accuracy of commonly used open source implementations (R packages, Python scikit-learn, H2O, xgboost, Spark MLlib etc.) of the top machine learning algorithms for binary classification (random forests, gradient boosted trees, deep neural networks etc.).
RMIT
Issues
- 0
License for datasets
#60 opened by Li0ness - 6
- 1
- 1
Question on the metric of AUC
#56 opened by kyhhdm - 3
maybe add libfm and libffm to benchmark
#9 opened by lihang00 - 1
- 21
Spark random forest issues
#19 opened by szilard - 1
How to time the algorithms?
#54 opened by jakobmoeller - 4
More datasets and regression problems
#53 opened by PhilippPro - 20
Update Latest version of XGBoost
#37 opened by tqchen - 1
Request to add License
#52 opened by ravi9 - 18
LightGBM results
#46 opened by szilard - 3
DL with mxnet
#29 opened by szilard - 14
DL with h2o
#28 opened by szilard - 1
benchmarking with autosklearn (zeroconf)
#50 opened by Motorrat - 12
- 0
Spark Random forest accuracy --spam?
#49 opened by am9090 - 0
RandomForest Example
#47 opened by Mega4alik - 0
issue deleted
#44 opened by szilard - 0
test new spark 1-hot ecoding
#40 opened by szilard - 2
5-spark.txt: spark-train-10m.csv
#39 opened by xhudik - 3
- 1
- 0
Linear & Random Forests TODOs
#12 opened by szilard - 7
ranger - R RF package
#34 opened by szilard - 3
Possible data leakage
#33 opened by arogozhnikov - 30
- 2
sklearn using sparse data representation
#27 opened by szilard - 1
running your benchmarks from beginning to end
#35 opened by vinhdizzo - 4
Add MLPACK to comparisons?
#31 opened by jjallaire - 9
- 3
mxnet sparse data format
#30 opened by szilard - 5
upgrade H2O to 3.0
#13 opened by szilard - 14
Datacratic MLDB results
#25 opened by nicolaskruchten - 2
Upgrade to VW v8.0
#23 opened by trufanov-nok - 7
Spark logistic regression issues
#17 opened by szilard - 1
Spark random forest low AUC etc
#16 opened by szilard - 6
- 2
- 21
best boosting AUC?
#15 opened by szilard - 4
xgboost RF bump for n=10M
#14 opened by szilard - 15
add xgboost to benchmark
#2 opened by tqchen - 5
other dataset of such type for benchmarking?
#11 opened by szilard - 3
- 2
Add Rborist
#6 opened by eddelbuettel