I am having trouble installing Laurae2/Laurae into Rstudio version 3.5.2. I write into R:
devtools::install_github("Laurae2/Laurae")

And receive the following error:
Error in read.dcf(path) :
Found continuation line starting ' modeling. ...' at begin of record.

I have found another user having trouble with a different package, but am unsure how to apply the solution to my answer: psoerensen/qgg#3

Cheers!

It' s possible to use cascade forest to regression?

Hello Laurae, this is is not an issue per se, but a question/suggestion... is there a way to create the function of daForest using your cascade & MG scanning algorithms? Thank you

daForest.pdf

I'm having trouble figuring out the example in ?lgbm.cv. It looks like it's on the housing price dataset, but I'm not 100% sure. When I try to run it, I get the following error:

Error in outputs[["Models"]][[i]][["Validation"]] : 
  subscript out of bounds

Do you have a working example that runs on your machine I could try out, to make sure my installation is working?

Hi, I try to set validation_data=NULL, but after 1 Layer it stops by this message: Error in alloc.col(dt1, length(colnames(dt1)) + length(cols)) :
alloccol has been passed a NULL dt
Could you help me? Thanks

I have follow you instructions to install the lightgbm, and generate the exe and DLL success. What's next?
I refer to the instructions "

If you are using a precompiled dll/lib locally, you can move the dll/lib into LightGBM root folder, modify LightGBM/R-package/src/install.libs.R's 2nd line (change use_precompile <- FALSE to use_precompile <- TRUE), and install R-package as usual
."

But, it failed.

install("C:\Users\szkxpc056\LightGBM\R-package")
Installing lightgbm
"D:/software/R-331.1/bin/x64/R" --no-site-file --no-environ
--no-save --no-restore --quiet CMD INSTALL
"C:/Users/szkxpc056/LightGBM/R-package"
--library="D:/software/R-3.3.1/library" --install-tests
installing source package 'lightgbm' ...
** libs
*** arch - i386
D:/software/Rtools/mingw_32/bin/g++ -std=c++0x -I"D:/software/R-331.1/include" -DNDEBUG -I../..//include -I -I -I../compute/include -DUSE_SOCKET -DUSE_GPU=1 -I"d:/Compiler/gcc-4.9.3/local330/include" -fopenmp -pthread -std=c++11 -O2 -Wall -mtune=core2 -c lightgbm-all.cpp -o lightgbm-all.o
In file included from ../../src/treelearner/parallel_tree_learner.h:7:0,
from ../../src/treelearner/data_parallel_tree_learner.cpp:1,
from lightgbm-all.cpp:30:
../../src/treelearner/serial_tree_learner.h:24:45: fatal error: boost/align/aligned_allocator.hpp: No such file or directory
#include <boost/align/aligned_allocator.hpp>
compilation terminated.
make: *** [lightgbm-all.o] Error 1
Warning: 运行命令'make -f "Makevars.win" -f "D:/software/R-331.1/etc/i386/Makeconf" -f "D:/software/R-331.1/share/make/winshlib.mk" CXX='$(CXX1X) $(CXX1XSTD)' CXXFLAGS='$(CXX1XFLAGS)' CXXPICFLAGS='$(CXX1XPICFLAGS)' SHLIB_LDFLAGS='$(SHLIB_CXX1XLDFLAGS)' SHLIB_LD='$(SHLIB_CXX1XLD)' SHLIB="lightgbm.dll" '的状态是2
ERROR: compilation failed for package 'lightgbm'
removing 'D:/software/R-3.3.1/library/lightgbm'
Error: Command failed (1)

sessionInfo()
R version 3.3.1 (2016-06-21)
Platform: x86_64-w64-mingw32/x64 (64-bit)
Running under: Windows 7 x64 (build 7601) Service Pack 1
locale:
[1] LC_COLLATE=Chinese (Simplified)_People's Republic of China.936
[2] LC_CTYPE=Chinese (Simplified)_People's Republic of China.936
[3] LC_MONETARY=Chinese (Simplified)_People's Republic of China.936
[4] LC_NUMERIC=C
[5] LC_TIME=Chinese (Simplified)_People's Republic of China.936
attached base packages:
[1] stats graphics grDevices utils datasets methods base
other attached packages:
[1] devtools_1.13.2
loaded via a namespace (and not attached):
[1] httr_1.2.1 R6_2.2.1 tools_3.3.1 withr_1.0.2 curl_2.6 memoise_1.1.0
[7] git2r_0.18.0 digest_0.6.12

data.table is now at 1.10.4 which ships with fread and fwrite so I think you can just point to CRAN.

Hi @Laurae2 , I did not find your e-mail address. Just wanted to say I quite like your blog https://sites.google.com/view/lauraepp/blog would you mind adding a feed that an RSS reader could subscribe to it?

Hello Laurae, thanks for your response earlier about my question about emulating daForest.

This time I have a question sort of related to validation_data=NULL #6, in that I want to make sure I understand how to properly do training & testing to try to avoid overfitting. I tried running CascadeForest and got excellent results on training and held out validation data (where I knew the labels), but when I applied the model to test data (exclusive of my train & validation data, and where I did not know the labels but the contest website gave me my score), the model did not perform very well. So, I believe I am overfitting.

Basically, I trained CascadeForest using d_train & d_valid like this:

CascadeForest(training_data = d_train,
validation_data = d_valid,
training_labels = labels_train,
validation_labels = labels_valid, ...)

Where: d_train & labels_train = predictor columns & known labels (65% of my total training data)
d_valid & labels_valid = predictor columns & known labels, exclusive of d_train (the other 35% of my total training data).

My AUC was something like 0.96 when I then predicted on d_train and also when I predicted on d_valid. So, that made me happy, and I then applied the predict function to d_test, which is exclusive of d_train and d_valid, and where I don't know the true labels, but I submitted my predictions to the contest website and got a 0.75 AUC, not nearly as good as 0.96.

So that made me think I should use cross-validation in CascadeForest, like this:

CascadeForest(training_data = d_alltrain,
validation_data = NULL,
training_labels = labels_alltrain,
validation_labels = NULL, ...)

Where: d_alltrain is all my training data (= 65% + 35% = 100%), and labels_alltrain is all my known labels for all my training data.

But, I got the error as noted in validation_data=NULL #6. I have not yet tried the solution you suggest to fix the lines of code to work for cross-validation, but is this the proper way to do cross-val? Then if I get a good AUC indicated by the model (on cross-val d_alltrain), and then apply the model to d_test then that is the proper way to try to avoid overfitting and I should hope for a better score?

Thank you very much.

Hi Laurae,
Congrats with this superb library.
With few observations xgboost some times returns the same probability to each one, and having the same probability with different labels makes get.max_acc report the inverse of accuracy & the max threshold also is incorrect if we assume that positive obs are > threshold (not >=)

To reproduce it:
get.max_acc(rep(0.502,8),c(0,1,1,1,1,1,1,1))

It gives 0.125 accuracy with 0.502 threshold

Thanks for your time

Hi Laurae,

Thanks for the very nice and useful package! I'm having some troubles when using xgb.max_f1 as evaluation metric for xgb.train. The error comes from sum(labels): "invalid 'type' (closure) of argument". This happens because labels is not defined, and thus, it's a function from the "base" package. Is it possibly related to the version of the XGBoost package I'm using (i.e., 1.3.2.1)? I checked the xgb.train function code and no labels object is returned by the function.

Best regards,
Paulo.

Trying to install the Laurae2/sparsity package so i can convert from sparse matrix to SVMLight. however, i keep getting this error message Installation failed: Timeout was reached.
I am behind no proxy, and have all dependent packages installed.
I've also tweaked around with options(download.file.method = "") with various methods but to no avail. Searched the web, tried everything and still no success. Is the package still available for download and installation? I'm using R version:

platform x86_64-w64-mingw32
arch x86_64
os mingw32
system x86_64, mingw32
status
major 3
minor 4.0
year 2017
month 04
day 21
svn rev 72570
language R
version.string R version 3.4.0 (2017-04-21)
nickname You Stupid Darkness

I have a dgCMatrix that I want to send to python. writeMM from the Matrix package is taking forever, so I wanted to try your svmlight writer. Which function should I use?

Thanks! This package looks amazing!