I am looking into Log2Vec as a TD-IDF alternative to log vectorization. Primarily, I’ll be interested in consuming Sysmon logs later.
Log2Vec
Abstract—Logs are one of the most valuable data sources for large-scale service management. Log representation, which converts unstructured texts to structured vectors or matrices, serves as the the first step towards automated log analysis. However, the current log representation methods neither represent domain-specific semantic information of logs, nor handle the outof-vocabulary (OOV) words of new types of logs at runtime. We propose Log2Vec, a semantic-aware representation framework for log analysis. Log2Vec combines a log-specific word embedding method to accurately extract the semantic information of logs, with an OOV word processor to embed OOV words into vectors at runtime. We present an analysis on the impact of OOV words and evaluate the performance of the OOV word processor. The evaluation experiments on four public production log datasets demonstrate that Log2Vec not only fixes the issue presented by OOV words, but also significantly improves the performance of two popular log-based service management tasks, including log classification and anomaly detection. We have packaged Log2Vec into an open-source toolkit and hope that it can be used for future research.
https://github.com/NetManAIOps/Log2Vec The work was supported by National Key R&D Program of China (Grant No. 2019YFB1802504, 2018YFB1800405), the National Natural Science Foundation of China (Grant Nos. 61772307, 61902200 and 61402257), the China Postdoctoral Science Foundation (2019M651015) and the Beijing National Research Center for Information Science and Technology (BNRist).
Paper Our paper is published on The 29th International Conference on Computer Communications and Networks (ICCCN 2020
Weibin Meng, Ying Liu, Yuheng Huang, Shenglin Zhang, Federico Zaiter, Bingjin Chen, Dan Pei. A Semantic-aware Representation Framework for Online Log Analysis . ICCCN 2020. August 3 - August 6, 2020, Honolulu, Hawaii, USA.
Install Log2Vec on Linux Mint 21 AMD64 in 2024 I use separate conda environments for “older” research-grade software. Software moves at a rapid pace.
It requires a little bit of software engineering skill.
https://conda.io/projects/conda/en/latest/user-guide/tasks/manage-environments.html# The following dependencies need to be present:
1. nltk, nltk.download("wordnet")
2. spacy, spacy.load("en_core_web_md")
3. progressbar
4. dynet (python3)
dynet https://github.com/clab/dynet Last release is from 2020 (state of this information 15 Jan 2024 ). In Python 3.12 disutils became deprecated, which will cause build errors.
https://github.com/Asana/python-asana/issues/80 I chose to use 3.9, but your requirements may be stricter. This way the error can be avoided.
conda create --name log2vec python=3.9
conda activate log2vec
pip install 'setuptools<57.0.0'
pip install --verbose dynet --no-build-isolation
build-essential and cmake (Linux Mint 21) This is straightforward, but I document the compiler version here for the sake of completeness.
apt install build-essential
apt install cmake
(log2vec) marius@mleng:~/source/Log2Vec/code/LRWE/src$ dpkg -l | grep build-essential
ii build-essential 12.9ubuntu3 amd64 Informational list of build-essential packages
(log2vec) marius@mleng:~/source/Log2Vec/code/LRWE/src$ dpkg -l | grep cmake
ii cmake 3.22.1-1ubuntu1.22.04.1 amd64 cross-platform, open-source make system
ii cmake-data 3.22.1-1ubuntu1.22.04.1 all CMake data files (modules, templates and documentation)
Click here to expand...
marius@mleng:~/source/Log2Vec/code/LRWE/src$ gcc -v
Using built-in specs.
COLLECT_GCC=gcc
COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper
OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa
OFFLOAD_TARGET_DEFAULT=1
Target: x86_64-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Ubuntu 11.4.0-1ubuntu1~22.04' --with-bugurl=file:///usr/share/doc/gcc-11/README.Bugs --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --prefix=/usr --with-gcc-major-version-only --program-suffix=-11 --program-prefix=x86_64-linux-gnu- --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --libdir=/usr/lib --enable-nls --enable-bootstrap --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --with-default-libstdcxx-abi=new --enable-gnu-unique-object --disable-vtable-verify --enable-plugin --enable-default-pie --with-system-zlib --enable-libphobos-checking=release --with-target-system-zlib=auto --enable-objc-gc=auto --enable-multiarch --disable-werror --enable-cet --with-arch-32=i686 --with-abi=m64 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --without-cuda-driver --enable-checking=release --build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-build-config=bootstrap-lto-lean --enable-link-serialization=2
Thread model: posix
Supported LTO compression algorithms: zlib zstd
gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04)
marius@mleng:~/source/Log2Vec/code/LRWE/src$ g++ -v
Using built-in specs.
COLLECT_GCC=g++
COLLECT_LTO_WRAPPER=/usr/lib/gcc/x86_64-linux-gnu/11/lto-wrapper
OFFLOAD_TARGET_NAMES=nvptx-none:amdgcn-amdhsa
OFFLOAD_TARGET_DEFAULT=1
Target: x86_64-linux-gnu
Configured with: ../src/configure -v --with-pkgversion='Ubuntu 11.4.0-1ubuntu1~22.04' --with-bugurl=file:///usr/share/doc/gcc-11/README.Bugs --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,m2 --prefix=/usr --with-gcc-major-version-only --program-suffix=-11 --program-prefix=x86_64-linux-gnu- --enable-shared --enable-linker-build-id --libexecdir=/usr/lib --without-included-gettext --enable-threads=posix --libdir=/usr/lib --enable-nls --enable-bootstrap --enable-clocale=gnu --enable-libstdcxx-debug --enable-libstdcxx-time=yes --with-default-libstdcxx-abi=new --enable-gnu-unique-object --disable-vtable-verify --enable-plugin --enable-default-pie --with-system-zlib --enable-libphobos-checking=release --with-target-system-zlib=auto --enable-objc-gc=auto --enable-multiarch --disable-werror --enable-cet --with-arch-32=i686 --with-abi=m64 --with-multilib-list=m32,m64,mx32 --enable-multilib --with-tune=generic --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --without-cuda-driver --enable-checking=release --build=x86_64-linux-gnu --host=x86_64-linux-gnu --target=x86_64-linux-gnu --with-build-config=bootstrap-lto-lean --enable-link-serialization=2
Thread model: posix
Supported LTO compression algorithms: zlib zstd
gcc version 11.4.0 (Ubuntu 11.4.0-1ubuntu1~22.04)
CMake Error: Run 'cmake --help' for all supported options.
marius@mleng:~/source/Log2Vec/code/LRWE/src$ cmake --version
cmake version 3.22.1
CMake suite maintained and supported by Kitware (kitware.com/cmake).
nltk and wordnet
conda install anaconda::nltk
(log2vec) marius@mleng:~/source/Log2Vec/code/LRWE/src$ python
Python 3.9.18 (main, Sep 11 2023, 13:41:44)
[GCC 11.2.0] :: Anaconda, Inc. on linux
Type "help", "copyright", "credits" or "license" for more information.
>>> import nltk
>>> nltk.download("wordnet")
[nltk_data] Downloading package wordnet to /home/marius/nltk_data...
True
>>> quit()
spacy
conda install anaconda::spacy
conda install conda-forge::spacy-model-en_core_web_md
Build the C++ project (make)
(log2vec) marius@mleng:~/source/Log2Vec/code/LRWE/src$ make clean
rm -rf word2vec lrcwe
(log2vec) marius@mleng:~/source/Log2Vec/code/LRWE/src$ make -j 4
g++ word2vec.c -o word2vec -lm -pthread -Ofast -march=native -Wall -funroll-loops -Wno-unused-result
g++ lrcwe.c -o lrcwe -lm -pthread -Ofast -march=native -Wall -funroll-loops -Wno-unused-result
gensim 3.x 4.x introduced changes. Using version 3.x avoids errors with breaking changes.
conda install conda-forge::gensim=3.8.3
Test trace To get familiar with the approach:
Click here to expand...
(log2vec) marius@mleng:~/source/Log2Vec$ python pipeline.py -i data/HDFS.log -t HDFS -o results/
rawlogs:/home/marius/source/Log2Vec/data/HDFS.log
variables have been removed
logs without variables:/home/marius/source/Log2Vec/results/HDFS/without_variables.log
input: /home/marius/source/Log2Vec/results/HDFS/without_variables.log
syn_file /home/marius/source/Log2Vec/results/HDFS/sys.txt
ant_file /home/marius/source/Log2Vec/results/HDFS/ants.txt
delete is added
INFO is added
dfs Got exception
thread transfer block
python code/getTempLogs.py -input /home/marius/source/Log2Vec/results/HDFS/without_variables.log -output /home/marius/source/Log2Vec/results/HDFS/for_training.log
input: /home/marius/source/Log2Vec/results/HDFS/without_variables.log
output: /home/marius/source/Log2Vec/results/HDFS/for_training.log
alpha:0.050000, alpha_syn:0.025000, alpha_ant:0.300000, alpha_rel:0.010000
belta_syn:0.700000, belta_ant:0.200000, belta_rel:0.800000
Starting training using file /home/marius/source/Log2Vec/results/HDFS/for_training.log
train_file: /home/marius/source/Log2Vec/results/HDFS/for_training.log
word_num:54
Vocab size: 55
Words in train file: 16350
triplet file total line: 5, relation num: 3, match: 5
synonyms file total line: 21, words: 20, ignore words: 0
antonyms file total line: 1, words: 1, ignore words: 0
------
code/LRWE/src/lrcwe -train /home/marius/source/Log2Vec/results/HDFS/for_training.log -synonym /home/marius/source/Log2Vec/results/HDFS/sys.txt -antonym /home/marius/source/Log2Vec/results/HDFS/ants.txt -output /home/marius/source/Log2Vec/results/HDFS/embedding.model -save-vocab /home/marius/source/Log2Vec/results/HDFS/embedding.vocab -belta-rel 0.8 -alpha-rel 0.01 -alpha-ant 0.3 -size 32 -min-count 1 -window 2 -triplet triples.txt
Total in Embeddings vocabulary: 55
Training set character count: 41
------
python code/mimick/make_dataset.py --vectors /home/marius/source/Log2Vec/results/HDFS/embedding.model --w2v-format --output /home/marius/source/Log2Vec/results/HDFS/words.pkl
[dynet] random seed: 3040219324
[dynet] allocating memory: 512MB
[dynet] memory allocation done.
The dy.parameter(...) call is now DEPRECATED. |
There is no longer need to explicitly add parameters to the computation graph.
Any used parameter will be added automatically.
100% |############################################################################################|
[lr=0.006 clips=13 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=0 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=0 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=0 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=0 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=0 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=0 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=0 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=0 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=5 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=6 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=9 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=11 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=3 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=4 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=4 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=5 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=4 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=3 updates=54] None
100% |############################################################################################|
100% |############################################################################################|
[lr=0.006 clips=3 updates=54] None
100% |############################################################################################|
------
python code/mimick/model.py --dataset /home/marius/source/Log2Vec/results/HDFS/words.pkl --vocab /home/marius/source/Log2Vec/results/HDFS/changed_log/vocab.txt --output /home/marius/source/Log2Vec/results/HDFS/oov.vector --num-epochs 20 --learning-rate 0.006000 --num-lstm-layers 1 --cosine --dropout -1.000000 --all-from-mimick --hidden-dim 250 --char-dim 36
log input: /home/marius/source/Log2Vec/results/HDFS/without_variables.log
word vectors input: /home/marius/source/Log2Vec/results/HDFS/embedding.model
log vectors output: /home/marius/source/Log2Vec/results/HDFS/log.vector
end~~
------
python code/Log2Vec.py -logs /home/marius/source/Log2Vec/results/HDFS/without_variables.log -word_model /home/marius/source/Log2Vec/results/HDFS/embedding.model -log_vector_file /home/marius/source/Log2Vec/results/HDFS/log.vector -dimension 32
---------
0.9438120169363016
(log2vec) marius@mleng:~/source/Log2Vec$ python log2vec.py -i results -t HDFS
# no errors
(log2vec) marius@mleng:~/source/Log2Vec$ python code/preprocessing.py -rawlog ./code/data/BGL.log
rawlogs:./code/data/BGL.log
variables have been removed
logs without variables:./code/data/BGL_without_variables.log
(log2vec) marius@mleng:~/source/Log2Vec$ python code/get_syn_ant.py -logs ./code/data/BGL_without_variables.log -ant_file ./middle/ants.txt
input: ./code/data/BGL_without_variables.log
syn_file ./middle/syns.txt
ant_file ./middle/ants.txt
(log2vec) marius@mleng:~/source/Log2Vec$ python code/get_triplet.py data/BGL_without_variables.log middle/bgl_triplet.txt
(log2vec) marius@mleng:~/source/Log2Vec$
(log2vec) marius@mleng:~/source/Log2Vec$ python code/getTempLogs.py -input data/BGL_without_variables.log -output middle/BGL_without_variables_for_training.log
input: data/BGL_without_variables.log
output: middle/BGL_without_variables_for_training.log
(log2vec) marius@mleng:~/source/Log2Vec/code/LRWE/src$ ./lrcwe -train ../../../middle/BGL_without_variables_for_training.log
alpha:0.050000, alpha_syn:0.025000, alpha_ant:0.001000, alpha_rel:0.010000
belta_syn:0.700000, belta_ant:0.200000, belta_rel:0.800000
Starting training using file ../../../middle/BGL_without_variables_for_training.log
train_file: ../../../middle/BGL_without_variables_for_training.log
word_num:0
Vocab size: 1
Words in train file: 1
(log2vec) marius@mleng:~/source/Log2Vec/code/LRWE/src$ ./lrcwe -train /home/marius/source/Log2Vec/middle/BGL_without_variables_for_training.log -synonym /home/marius/source/Log2Vec/middle/syns.txt -antonym /home/marius/source/Log2Vec/middle/ants.txt -output /home/marius/source/Log2Vec/middle/bgl_words.model -save-vocab /home/marius/source/Log2Vec/middle/bgl.vocab -belta-rel 0.8 - alpha-rel 0.01 -alpha-ant 0.3 -size 32 -min-count 1 /home/marius/source/Log2Vec/middle/bgl_triplet.txt
alpha:0.050000, alpha_syn:0.025000, alpha_ant:0.300000, alpha_rel:0.010000
belta_syn:0.700000, belta_ant:0.200000, belta_rel:0.800000
Starting training using file /home/marius/source/Log2Vec/middle/BGL_without_variables_for_training.log
train_file: /home/marius/source/Log2Vec/middle/BGL_without_variables_for_training.log
word_num:0
Vocab size: 1
Words in train file: 1
synonyms file total line: 0, words: 0, ignore words: 407
antonyms file total line: 0, words: 0, ignore words: 10
(log2vec) marius@mleng:~/source/Log2Vec$ python code/mimick/make_dataset.py --vectors /home/marius/source/Log2Vec/middle/bgl_words.model --w2v-format --output /home/marius/source/Log2Vec/middle/bgl_words.pkl
Total in Embeddings vocabulary: 1
Training set character count: 4
(log2vec) marius@mleng:~/source/Log2Vec$ python code/mimick/model.py --dataset /home/marius/source/Log2Vec/middle/bgl_words.pkl --vocab code/mimick/testdir/testvocab.txt --output middle/oov.vector
[dynet] random seed: 1179517440
[dynet] allocating memory: 512MB
[dynet] memory allocation done.
100% | |
[lr=0.01 clips=0 updates=0] None
The dy.parameter(...) call is now DEPRECATED. |
There is no longer need to explicitly add parameters to the computation graph.
Any used parameter will be added automatically.
100% |############################################################################################|
100% | |
[lr=0.01 clips=0 updates=0] None
100% |############################################################################################|
100% | |
[lr=0.01 clips=0 updates=0] None
100% |############################################################################################|
100% | |
[lr=0.01 clips=0 updates=0] None
100% |############################################################################################|
100% | |
[lr=0.01 clips=0 updates=0] None
100% |############################################################################################|
100% | |
[lr=0.01 clips=0 updates=0] None
100% |############################################################################################|
100% | |
[lr=0.01 clips=0 updates=0] None
100% |############################################################################################|
100% | |
[lr=0.01 clips=0 updates=0] None
100% |############################################################################################|
100% | |
[lr=0.01 clips=0 updates=0] None
100% |############################################################################################|
100% | |
[lr=0.01 clips=0 updates=0] None
100% |############################################################################################|
Very interesting. This appears to be a multistaged and very advanced vectorization technique.