pax_global_header 0000666 0000000 0000000 00000000064 14037246614 0014521 g ustar 00root root 0000000 0000000 52 comment=d725c1c4c9ee9b23f054d3f616d7fb418e544247
Alpenglow-1.0.6/ 0000775 0000000 0000000 00000000000 14037246614 0013455 5 ustar 00root root 0000000 0000000 Alpenglow-1.0.6/.editorconfig 0000775 0000000 0000000 00000000274 14037246614 0016140 0 ustar 00root root 0000000 0000000 root = true
[*]
end_of_line = lf
insert_final_newline = false
[*.{py,cpp,h}]
charset = utf-8
[*.py]
indent_style = space
indent_size = 4
[*.{cpp,h}]
indent_style = space
indent_size = 2 Alpenglow-1.0.6/.gitignore 0000775 0000000 0000000 00000000420 14037246614 0015444 0 ustar 00root root 0000000 0000000 build
.scon*
config.log
python/alpenglow/__pycache__
python/alpenglow/cpp/__pycache__
python/.ipynb_checkpoints
python/.cache
.cache
.parallel
alpenglow.egg-info
python/alpenglow/cpp.*.so
cpp/bin
cpp/dep/*
!cpp/dep/empty
python/test_alpenglow/tmp/*
.pytest_cache
sip_build Alpenglow-1.0.6/.travis.yml 0000664 0000000 0000000 00000003546 14037246614 0015576 0 ustar 00root root 0000000 0000000 jobs:
include:
- name: "cpp unit tests"
language: cpp
before_install:
#scons
- sudo apt-get install -y scons
#dependencies
- pushd cpp/dep
#eigen
- wget https://gitlab.com/libeigen/eigen/-/archive/3.3.7/eigen-3.3.7.tar.gz
- tar -xzf eigen-3.3.7.tar.gz
- rm eigen-3.3.7.tar.gz
- mkdir eigen
- mv eigen-3.3.7 eigen/eigen3
- export CPATH="$CPATH:$(pwd)/eigen"
#gtest
- wget https://github.com/google/googletest/archive/release-1.7.0.zip
- unzip -q release-1.7.0.zip
- rm -rf gtest
- mv googletest-release-1.7.0 gtest
- rm release-1.7.0.zip
- cd gtest
- GTEST_DIR=`pwd`
- mkdir build
- cd build
- g++ -isystem ${GTEST_DIR}/include -I${GTEST_DIR} -pthread -c ${GTEST_DIR}/src/gtest-all.cc
- ar -rv libgtest.a gtest-all.o
- popd
- cd cpp/src
install: scons -j10 --mode=travis
script: ./run_tests.sh
- name: "python integration tests"
language: python
python:
# We don't actually use the Travis Python, but this keeps it organized.
- "3.6"
install:
- wget https://repo.continuum.io/miniconda/Miniconda3-latest-Linux-x86_64.sh -O miniconda.sh;
- bash miniconda.sh -b -p $HOME/miniconda
- export PATH="$HOME/miniconda/bin:$PATH"
- hash -r
- conda config --set always_yes yes --set changeps1 no
- conda update -q conda
# Useful for debugging any issues with conda
- conda info -a
- conda create -q -n test-environment python=$TRAVIS_PYTHON_VERSION libgcc
- source activate test-environment
- conda install -c conda-forge eigen
- ./install_alpenglow_sip.sh
- pip install .
- pip install pytest
script:
- pytest
Alpenglow-1.0.6/LICENSE 0000664 0000000 0000000 00000026135 14037246614 0014471 0 ustar 00root root 0000000 0000000
Apache License
Version 2.0, January 2004
http://www.apache.org/licenses/
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
1. Definitions.
"License" shall mean the terms and conditions for use, reproduction,
and distribution as defined by Sections 1 through 9 of this document.
"Licensor" shall mean the copyright owner or entity authorized by
the copyright owner that is granting the License.
"Legal Entity" shall mean the union of the acting entity and all
other entities that control, are controlled by, or are under common
control with that entity. For the purposes of this definition,
"control" means (i) the power, direct or indirect, to cause the
direction or management of such entity, whether by contract or
otherwise, or (ii) ownership of fifty percent (50%) or more of the
outstanding shares, or (iii) beneficial ownership of such entity.
"You" (or "Your") shall mean an individual or Legal Entity
exercising permissions granted by this License.
"Source" form shall mean the preferred form for making modifications,
including but not limited to software source code, documentation
source, and configuration files.
"Object" form shall mean any form resulting from mechanical
transformation or translation of a Source form, including but
not limited to compiled object code, generated documentation,
and conversions to other media types.
"Work" shall mean the work of authorship, whether in Source or
Object form, made available under the License, as indicated by a
copyright notice that is included in or attached to the work
(an example is provided in the Appendix below).
"Derivative Works" shall mean any work, whether in Source or Object
form, that is based on (or derived from) the Work and for which the
editorial revisions, annotations, elaborations, or other modifications
represent, as a whole, an original work of authorship. For the purposes
of this License, Derivative Works shall not include works that remain
separable from, or merely link (or bind by name) to the interfaces of,
the Work and Derivative Works thereof.
"Contribution" shall mean any work of authorship, including
the original version of the Work and any modifications or additions
to that Work or Derivative Works thereof, that is intentionally
submitted to Licensor for inclusion in the Work by the copyright owner
or by an individual or Legal Entity authorized to submit on behalf of
the copyright owner. For the purposes of this definition, "submitted"
means any form of electronic, verbal, or written communication sent
to the Licensor or its representatives, including but not limited to
communication on electronic mailing lists, source code control systems,
and issue tracking systems that are managed by, or on behalf of, the
Licensor for the purpose of discussing and improving the Work, but
excluding communication that is conspicuously marked or otherwise
designated in writing by the copyright owner as "Not a Contribution."
"Contributor" shall mean Licensor and any individual or Legal Entity
on behalf of whom a Contribution has been received by Licensor and
subsequently incorporated within the Work.
2. Grant of Copyright License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
copyright license to reproduce, prepare Derivative Works of,
publicly display, publicly perform, sublicense, and distribute the
Work and such Derivative Works in Source or Object form.
3. Grant of Patent License. Subject to the terms and conditions of
this License, each Contributor hereby grants to You a perpetual,
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
(except as stated in this section) patent license to make, have made,
use, offer to sell, sell, import, and otherwise transfer the Work,
where such license applies only to those patent claims licensable
by such Contributor that are necessarily infringed by their
Contribution(s) alone or by combination of their Contribution(s)
with the Work to which such Contribution(s) was submitted. If You
institute patent litigation against any entity (including a
cross-claim or counterclaim in a lawsuit) alleging that the Work
or a Contribution incorporated within the Work constitutes direct
or contributory patent infringement, then any patent licenses
granted to You under this License for that Work shall terminate
as of the date such litigation is filed.
4. Redistribution. You may reproduce and distribute copies of the
Work or Derivative Works thereof in any medium, with or without
modifications, and in Source or Object form, provided that You
meet the following conditions:
(a) You must give any other recipients of the Work or
Derivative Works a copy of this License; and
(b) You must cause any modified files to carry prominent notices
stating that You changed the files; and
(c) You must retain, in the Source form of any Derivative Works
that You distribute, all copyright, patent, trademark, and
attribution notices from the Source form of the Work,
excluding those notices that do not pertain to any part of
the Derivative Works; and
(d) If the Work includes a "NOTICE" text file as part of its
distribution, then any Derivative Works that You distribute must
include a readable copy of the attribution notices contained
within such NOTICE file, excluding those notices that do not
pertain to any part of the Derivative Works, in at least one
of the following places: within a NOTICE text file distributed
as part of the Derivative Works; within the Source form or
documentation, if provided along with the Derivative Works; or,
within a display generated by the Derivative Works, if and
wherever such third-party notices normally appear. The contents
of the NOTICE file are for informational purposes only and
do not modify the License. You may add Your own attribution
notices within Derivative Works that You distribute, alongside
or as an addendum to the NOTICE text from the Work, provided
that such additional attribution notices cannot be construed
as modifying the License.
You may add Your own copyright statement to Your modifications and
may provide additional or different license terms and conditions
for use, reproduction, or distribution of Your modifications, or
for any such Derivative Works as a whole, provided Your use,
reproduction, and distribution of the Work otherwise complies with
the conditions stated in this License.
5. Submission of Contributions. Unless You explicitly state otherwise,
any Contribution intentionally submitted for inclusion in the Work
by You to the Licensor shall be under the terms and conditions of
this License, without any additional terms or conditions.
Notwithstanding the above, nothing herein shall supersede or modify
the terms of any separate license agreement you may have executed
with Licensor regarding such Contributions.
6. Trademarks. This License does not grant permission to use the trade
names, trademarks, service marks, or product names of the Licensor,
except as required for reasonable and customary use in describing the
origin of the Work and reproducing the content of the NOTICE file.
7. Disclaimer of Warranty. Unless required by applicable law or
agreed to in writing, Licensor provides the Work (and each
Contributor provides its Contributions) on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
implied, including, without limitation, any warranties or conditions
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
PARTICULAR PURPOSE. You are solely responsible for determining the
appropriateness of using or redistributing the Work and assume any
risks associated with Your exercise of permissions under this License.
8. Limitation of Liability. In no event and under no legal theory,
whether in tort (including negligence), contract, or otherwise,
unless required by applicable law (such as deliberate and grossly
negligent acts) or agreed to in writing, shall any Contributor be
liable to You for damages, including any direct, indirect, special,
incidental, or consequential damages of any character arising as a
result of this License or out of the use or inability to use the
Work (including but not limited to damages for loss of goodwill,
work stoppage, computer failure or malfunction, or any and all
other commercial damages or losses), even if such Contributor
has been advised of the possibility of such damages.
9. Accepting Warranty or Additional Liability. While redistributing
the Work or Derivative Works thereof, You may choose to offer,
and charge a fee for, acceptance of support, warranty, indemnity,
or other liability obligations and/or rights consistent with this
License. However, in accepting such obligations, You may act only
on Your own behalf and on Your sole responsibility, not on behalf
of any other Contributor, and only if You agree to indemnify,
defend, and hold each Contributor harmless for any liability
incurred by, or claims asserted against, such Contributor by reason
of your accepting any such warranty or additional liability.
END OF TERMS AND CONDITIONS
APPENDIX: How to apply the Apache License to your work.
To apply the Apache License to your work, attach the following
boilerplate notice, with the fields enclosed by brackets "[]"
replaced with your own identifying information. (Don't include
the brackets!) The text should be enclosed in the appropriate
comment syntax for the file format. We also recommend that a
file or class name and description of purpose be included on the
same "printed page" as the copyright notice for easier
identification within third-party archives.
Copyright [yyyy] [name of copyright owner]
Licensed under the Apache License, Version 2.0 (the "License");
you may not use this file except in compliance with the License.
You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing, software
distributed under the License is distributed on an "AS IS" BASIS,
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
See the License for the specific language governing permissions and
limitations under the License. Alpenglow-1.0.6/NOTICE 0000664 0000000 0000000 00000000044 14037246614 0014357 0 ustar 00root root 0000000 0000000 Alpenglow
Copyright 2017 MTA SZTAKI. Alpenglow-1.0.6/README.md 0000664 0000000 0000000 00000006217 14037246614 0014742 0 ustar 00root root 0000000 0000000
[](https://travis-ci.com/rpalovics/Alpenglow)
[](https://alpenglow.readthedocs.io/en/latest/)
- Alpenglow is a free and open source C++ framework with easy-to-use Python API.
- Alpenglow is capable of training and evaluating industry standard recommendation algorithms including variants of popularity, nearest neighbor, and factorization models.
- Besides batch training and evaluation, Alpenglow supports *online training* of recommendation models capable of adapting to concept drift in non-stationary environments.
### Requirements
- Anaconda + Python 3.5+
### Conda package:
[](https://anaconda.org/conda-forge/alpenglow) [](https://anaconda.org/conda-forge/alpenglow) [](https://circleci.com/gh/conda-forge/alpenglow-feedstock)
[](https://travis-ci.org/conda-forge/alpenglow-feedstock)
[](https://ci.appveyor.com/project/conda-forge/alpenglow-feedstock/branch/master)
### Installation from conda repositories
- `conda install -c conda-forge alpenglow`
In case you also intend to run sample code and tutorials, you should install matplotlib as well:
`conda install matplotlib`
If you encounter any conflict or error, try installing Alpenglow in a clean conda environment.
### Installation from source (linux only at the moment)
- `cd Alpenglow`
- `conda activate [your_cond_env_name]`
- `./install_alpenglow_sip.sh`
- `conda install libgcc`
- `conda install -c conda-forge eigen`
- `pip install .`
### Getting Started
```python
from alpenglow.experiments import FactorExperiment
from alpenglow.evaluation import DcgScore
import pandas as pd
import matplotlib
import matplotlib.pyplot as plt
data = pd.read_csv("http://info.ilab.sztaki.hu/~fbobee/alpenglow/alpenglow_sample_dataset")
factor_model_experiment = FactorExperiment(
top_k=100,
seed=254938879,
dimension=10,
learning_rate=0.14,
negative_rate=100
)
rankings = factor_model_experiment.run(data, verbose=True)
rankings['dcg'] = DcgScore(rankings)
day = 86400
averages = rankings['dcg'].groupby((rankings['time']-rankings['time'].min())//day).mean()
plt.plot(averages)
```
- Online documentation: https://alpenglow.readthedocs.io/en/latest/
### Development
- For faster recompilation, use `export CC="ccache cc"`
- E.g. to enable compilation on 4 threads, use `echo 4 > .parallel`
- Reinstall modified version using `pip install --upgrade --force-reinstall --no-deps .`
- To build and use in the current folder, use `pip install --upgrade --force-reinstall --no-deps -e .` and `export PYTHONPATH="$(pwd)/python:$PYTHONPATH"` Alpenglow-1.0.6/cpp/ 0000775 0000000 0000000 00000000000 14037246614 0014237 5 ustar 00root root 0000000 0000000 Alpenglow-1.0.6/cpp/dep/ 0000775 0000000 0000000 00000000000 14037246614 0015007 5 ustar 00root root 0000000 0000000 Alpenglow-1.0.6/cpp/dep/gtest/ 0000775 0000000 0000000 00000000000 14037246614 0016135 5 ustar 00root root 0000000 0000000 Alpenglow-1.0.6/cpp/dep/gtest/include/ 0000775 0000000 0000000 00000000000 14037246614 0017560 5 ustar 00root root 0000000 0000000 Alpenglow-1.0.6/cpp/dep/gtest/include/gtest/ 0000775 0000000 0000000 00000000000 14037246614 0020706 5 ustar 00root root 0000000 0000000 Alpenglow-1.0.6/cpp/dep/gtest/include/gtest/gtest_prod.h 0000775 0000000 0000000 00000004424 14037246614 0023240 0 ustar 00root root 0000000 0000000 // Copyright 2006, Google Inc.
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are
// met:
//
// * Redistributions of source code must retain the above copyright
// notice, this list of conditions and the following disclaimer.
// * Redistributions in binary form must reproduce the above
// copyright notice, this list of conditions and the following disclaimer
// in the documentation and/or other materials provided with the
// distribution.
// * Neither the name of Google Inc. nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
// "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
// LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
// A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
// OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
// LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
// THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
// (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
//
// Author: wan@google.com (Zhanyong Wan)
//
// Google C++ Testing Framework definitions useful in production code.
#ifndef GTEST_INCLUDE_GTEST_GTEST_PROD_H_
#define GTEST_INCLUDE_GTEST_GTEST_PROD_H_
// When you need to test the private or protected members of a class,
// use the FRIEND_TEST macro to declare your tests as friends of the
// class. For example:
//
// class MyClass {
// private:
// void MyMethod();
// FRIEND_TEST(MyClassTest, MyMethod);
// };
//
// class MyClassTest : public testing::Test {
// // ...
// };
//
// TEST_F(MyClassTest, MyMethod) {
// // Can call MyClass::MyMethod() here.
// }
#define FRIEND_TEST(test_case_name, test_name)\
friend class test_case_name##_##test_name##_Test
#endif // GTEST_INCLUDE_GTEST_GTEST_PROD_H_
Alpenglow-1.0.6/cpp/src/ 0000775 0000000 0000000 00000000000 14037246614 0015026 5 ustar 00root root 0000000 0000000 Alpenglow-1.0.6/cpp/src/.gitignore 0000664 0000000 0000000 00000000073 14037246614 0017016 0 ustar 00root root 0000000 0000000 #coverage report generated by lcov script
.coverage.*
html
Alpenglow-1.0.6/cpp/src/SConscript 0000664 0000000 0000000 00000005103 14037246614 0017037 0 ustar 00root root 0000000 0000000 import os
extra_cpppath = []
if 'CPATH' in os.environ:
extra_cpppath = filter(bool, os.environ['CPATH'].split(os.pathsep))
env = Environment(
CXX="g++",
CCFLAGS=[
'-std=c++11',
'-Wall',
#'-O3',
#'-ggdb',
'-fPIC',
'-Wno-deprecated',
'-Wno-reorder',
#'-Wsuggest-override',
'-mfpmath=sse,387',
'-funroll-loops',
'-fomit-frame-pointer',
'-lpthread',
'-msse3',
'-D_LARGEFILE_SOURCE',
'-D_FILE_OFFSET_BITS=64'
#, '-fprofile-arcs',
#'-ftest-coverage'
],
#LDFLAGS=[
# '-lgcov',
# '-fprofile-arcs'
#],
CPPPATH=['#.', '#../dep/gtest/include','#../dep']+extra_cpppath,
LIBPATH=['#../dep/gtest/build', '/usr/local/lib'],
LIBS=[
'gtest',
'pthread'
#, 'gcov'
]
)
AddOption('--mode',
dest='mode',
type='string',
nargs=1,
default='debug',
action='store',
metavar='DIR',
help='modifies compile flags, possible values: debug (default), optimized, coverage')
mode_raw = GetOption('mode')
mode = mode_raw if mode_raw is not None else "debug"
#documentation: compile in coverage mode using
#scons [-j30] --mode=coverage
#available modes: coverage, debug (default), optimized
if mode=="debug":
env.Append(CCFLAGS = '-ggdb')
if mode=="optimized":
env.Append(CCFLAGS = '-O3')
if mode=="coverage":
env.Append(CCFLAGS = '-fprofile-arcs')
env.Append(CCFLAGS = '-ftest-coverage')
env.Append(LIBS = 'gcov')
env.Append(LDFLAGS='-lgcov')
env.Append(LDFLAGS='-fprofile-arcs')
cpp = Glob("main/*/*.cpp")
cpp.extend(Glob("main/*/*/*.cpp"))
cpp.extend(Glob("main/*/*/*/*.cpp"))
objs = env.Object(cpp)
cpp_test = Glob("test/*/*.cpp")
cpp_test.extend(Glob("test/*/*/*.cpp"))
cpp_test.extend(Glob("test/*/*/*/*.cpp"))
AddOption('--test-filter',
dest='test-filter',
type='string',
nargs=1,
action='store',
metavar='DIR',
help='filter to these tests, comma separated (no space)')
test_filter_raw = GetOption('test-filter')
test_filter = set(test_filter_raw.split(',')) if test_filter_raw is not None else None
for src in cpp_test:
src_str = str(src)
relative_path = os.path.relpath(src_str, os.path.commonprefix([src_str, Dir('#').abspath]))
env.Object(relative_path)
program_name = os.path.basename(os.path.splitext(relative_path)[0])
if test_filter is None or program_name in test_filter:
env.Program("test/"+program_name, [relative_path]+['#../bin/'+str(i) for i in objs])
Alpenglow-1.0.6/cpp/src/SConstruct 0000664 0000000 0000000 00000000074 14037246614 0017061 0 ustar 00root root 0000000 0000000 SConscript('SConscript', variant_dir='../bin', duplicate=0)
Alpenglow-1.0.6/cpp/src/main/ 0000775 0000000 0000000 00000000000 14037246614 0015752 5 ustar 00root root 0000000 0000000 Alpenglow-1.0.6/cpp/src/main/data_generators/ 0000775 0000000 0000000 00000000000 14037246614 0021114 5 ustar 00root root 0000000 0000000 Alpenglow-1.0.6/cpp/src/main/data_generators/CompletePastDataGenerator.cpp 0000664 0000000 0000000 00000001104 14037246614 0026655 0 ustar 00root root 0000000 0000000 #include "CompletePastDataGenerator.h"
RecommenderData* CompletePastDataGenerator::generate_recommender_data(RecDat*){
local_recommender_data_.clear();
vector* train_data = local_recommender_data_.get_rec_data();
for(int counter = recommender_data_iterator_->get_counter();counter>=0;counter--){
RecDat* rec_dat = recommender_data_iterator_->get(counter);
train_data->push_back(*rec_dat);
}
if (!local_recommender_data_.initialize()) throw runtime_error("Initialization of local_recommender_data was unsuccesful.");
return &local_recommender_data_;
}
Alpenglow-1.0.6/cpp/src/main/data_generators/CompletePastDataGenerator.h 0000664 0000000 0000000 00000002240 14037246614 0026324 0 ustar 00root root 0000000 0000000 #ifndef COMPLETE_PAST_DATA_GENERATOR_H
#define COMPLETE_PAST_DATA_GENERATOR_H
//SIP_AUTOCONVERT
#include "DataGenerator.h"
#include "../general_interfaces/NeedsExperimentEnvironment.h"
#include "../general_interfaces/Initializable.h"
class CompletePastDataGenerator : public DataGenerator, public NeedsExperimentEnvironment, public Initializable {
public:
RecommenderData* generate_recommender_data(RecDat*) override;
void set_recommender_data_iterator(RecommenderDataIterator* recommender_data_iterator){
recommender_data_iterator_ = recommender_data_iterator;
}
bool self_test(){
bool ok=DataGenerator::self_test();
if(recommender_data_iterator_==NULL) ok=false;
return ok;
}
protected:
bool autocalled_initialize() override {
if(recommender_data_iterator_==NULL){
if (experiment_environment_==NULL) return false;
recommender_data_iterator_=experiment_environment_->get_recommender_data_iterator();
}
return true;
}
private:
const RecommenderDataIterator* recommender_data_iterator_ = NULL;
RecommenderData local_recommender_data_;
};
#endif /* COMPLETE_PAST_DATA_GENERATOR_H */
Alpenglow-1.0.6/cpp/src/main/data_generators/DataGenerator.cpp 0000664 0000000 0000000 00000000033 14037246614 0024334 0 ustar 00root root 0000000 0000000 #include "DataGenerator.h"
Alpenglow-1.0.6/cpp/src/main/data_generators/DataGenerator.h 0000664 0000000 0000000 00000000442 14037246614 0024005 0 ustar 00root root 0000000 0000000 #ifndef DATA_GENERATOR_H
#define DATA_GENERATOR_H
//SIP_AUTOCONVERT
#include "../recommender_data/RecommenderData.h"
class DataGenerator {
public:
virtual RecommenderData* generate_recommender_data(RecDat*)=0;
bool self_test(){ return true; }
};
#endif /* DATA_GENERATOR_H */
Alpenglow-1.0.6/cpp/src/main/data_generators/SamplingDataGenerator.cpp 0000664 0000000 0000000 00000002341 14037246614 0026033 0 ustar 00root root 0000000 0000000 #include "SamplingDataGenerator.h"
RecommenderData* SamplingDataGenerator::generate_recommender_data(RecDat*){
local_recommender_data_.clear();
int random_index_boundary = recommender_data_iterator_->get_counter()+1;
vector* train_data = local_recommender_data_.get_rec_data();
for(int i=0;iget(index_of_sample);
train_data->push_back(*sample);
}
if (!local_recommender_data_.initialize()) throw runtime_error("Initialization of local_recommender_data was unsuccesful.");
return &local_recommender_data_;
}
Alpenglow-1.0.6/cpp/src/main/data_generators/SamplingDataGenerator.h 0000664 0000000 0000000 00000004076 14037246614 0025507 0 ustar 00root root 0000000 0000000 #ifndef SAMPLING_DATA_GENERATOR_H
#define SAMPLING_DATA_GENERATOR_H
//SIP_AUTOCONVERT
#include "DataGenerator.h"
#include "../general_interfaces/NeedsExperimentEnvironment.h"
#include "../general_interfaces/Initializable.h"
struct SamplingDataGeneratorParameters {
string distribution = "uniform";
int number_of_samples = 1000;
double y = 10; //parameter of arctg random
double geometric_param = 0.5; //parameter of geometric random
int seed = 745578;
};
class SamplingDataGenerator : public DataGenerator, public Initializable, public NeedsExperimentEnvironment {
public:
SamplingDataGenerator(SamplingDataGeneratorParameters* params){
distribution_ = params->distribution;
number_of_samples_ = params->number_of_samples;
y_ = params->y;
geometric_param_ = params->geometric_param;
random_.set(params->seed);
}
RecommenderData* generate_recommender_data(RecDat*) override;
void set_recommender_data_iterator(RecommenderDataIterator* recommender_data_iterator){
recommender_data_iterator_ = recommender_data_iterator;
}
bool self_test(){
bool ok=DataGenerator::self_test();
if(!random_.self_test()) ok=false;
if(recommender_data_iterator_==NULL) ok=false;
if(number_of_samples_<0) ok=false;
if(geometric_param_>1) ok=false; //it's a probability value...
if(distribution_!="uniform"
and distribution_!="linear"
and distribution_!="arctg"
and distribution_!="geometric") ok=false;
return ok;
}
protected:
bool autocalled_initialize() override {
if(recommender_data_iterator_==NULL){
if (experiment_environment_==NULL) return false;
recommender_data_iterator_=experiment_environment_->get_recommender_data_iterator();
}
return true;
}
private:
string distribution_;
int number_of_samples_;
double y_;
double geometric_param_;
const RecommenderDataIterator* recommender_data_iterator_ = NULL;
RecommenderData local_recommender_data_;
Random random_;
};
#endif /* SAMPLING_DATA_GENERATOR_H */
Alpenglow-1.0.6/cpp/src/main/data_generators/TimeframeDataGenerator.cpp 0000664 0000000 0000000 00000001333 14037246614 0026172 0 ustar 00root root 0000000 0000000 #include "TimeframeDataGenerator.h"
RecommenderData* TimeframeDataGenerator::generate_recommender_data(RecDat*){
local_recommender_data_.clear();
double now = recommender_data_iterator_->get_actual()->time;
double timeframe_begin=now-timeframe_length_;
vector* train_data = local_recommender_data_.get_rec_data();
for(int counter = recommender_data_iterator_->get_counter();counter>=0;counter--){
RecDat* rec_dat = recommender_data_iterator_->get(counter);
if(rec_dat->time<=timeframe_begin) break;
train_data->push_back(*rec_dat);
}
if (!local_recommender_data_.initialize()) throw runtime_error("Initialization of local_recommender_data was unsuccesful.");
return &local_recommender_data_;
}
Alpenglow-1.0.6/cpp/src/main/data_generators/TimeframeDataGenerator.h 0000664 0000000 0000000 00000002650 14037246614 0025642 0 ustar 00root root 0000000 0000000 #ifndef TIMEFRAME_DATA_GENERATOR_H
#define TIMEFRAME_DATA_GENERATOR_H
//SIP_AUTOCONVERT
#include "DataGenerator.h"
#include "../general_interfaces/NeedsExperimentEnvironment.h"
#include "../general_interfaces/Initializable.h"
struct TimeframeDataGeneratorParameters {
int timeframe_length = 86400;
};
class TimeframeDataGenerator : public DataGenerator, public NeedsExperimentEnvironment, public Initializable {
public:
TimeframeDataGenerator(TimeframeDataGeneratorParameters* params){
timeframe_length_ = params->timeframe_length;
}
RecommenderData* generate_recommender_data(RecDat*) override;
void set_recommender_data_iterator(RecommenderDataIterator* recommender_data_iterator){
recommender_data_iterator_ = recommender_data_iterator;
}
bool self_test(){
bool ok=DataGenerator::self_test();
if(recommender_data_iterator_==NULL) ok=false;
return ok;
}
protected:
bool autocalled_initialize() override {
if(recommender_data_iterator_==NULL){
if (experiment_environment_==NULL) return false;
if (timeframe_length_<0) return false;
recommender_data_iterator_=experiment_environment_->get_recommender_data_iterator();
}
return true;
}
private:
int timeframe_length_;
const RecommenderDataIterator* recommender_data_iterator_ = NULL;
RecommenderData local_recommender_data_;
};
#endif /* TIMEFRAME_DATA_GENERATOR_H */
Alpenglow-1.0.6/cpp/src/main/filters/ 0000775 0000000 0000000 00000000000 14037246614 0017422 5 ustar 00root root 0000000 0000000 Alpenglow-1.0.6/cpp/src/main/filters/AvailabilityFilter.cpp 0000775 0000000 0000000 00000002354 14037246614 0023715 0 ustar 00root root 0000000 0000000 #include "AvailabilityFilter.h"
bool AvailabilityFilter::active(RecDat* r){
if(experiment_environment_->get_time()!=time_) update();
auto available = available_items_set_.find(r->item);
return available != available_items_set_.end();
}
vector AvailabilityFilter::get_whitelist(int user){
//NOTE: the set of available items does not depend on the user
if(experiment_environment_->get_time()!=time_) update();
return available_items_;
}
void AvailabilityFilter::add_availability(double time, int id, int duration){
availabilites_.push(tuple(time, id, duration));
}
void AvailabilityFilter::update(){
time_=experiment_environment_->get_time();
while(availability_ends_.size() != 0 && get<0>(availability_ends_.top()) <= time_){
auto item = availability_ends_.top();
availability_ends_.pop();
available_items_set_.erase(get<1>(item));
}
while(availabilites_.size() != 0 && get<0>(availabilites_.top()) <= time_){
auto item = availabilites_.top();
availabilites_.pop();
available_items_set_.insert(get<1>(item));
availability_ends_.push(make_pair(get<0>(item)+get<2>(item), get<1>(item)));
}
available_items_ = vector(available_items_set_.begin(), available_items_set_.end());
}
Alpenglow-1.0.6/cpp/src/main/filters/AvailabilityFilter.h 0000775 0000000 0000000 00000002621 14037246614 0023357 0 ustar 00root root 0000000 0000000 #ifndef AVAILABILITY_FILTER_H
#define AVAILABILITY_FILTER_H
//SIP_AUTOCONVERT
#include
#include
#include
#include
#include
#include "WhitelistFilter.h"
#include "../general_interfaces/NeedsExperimentEnvironment.h"
class AvailabilityFilter
: public WhitelistFilter
, public NeedsExperimentEnvironment
{
/**
This filter filters the set of available items based on
(time,itemId,duration) triplets. These have to be preloaded before using
this filter.
Sample code
.. code-block:: python
:linenos:
f = rs.AvailabilityFilter()
f.add_availability(20,1,10) #item 1 is available in the time interval (20,30)
*/
public:
bool active(RecDat*) override;
vector get_whitelist(int user) override;
bool self_test(){
bool OK = true;
return OK;
}
void add_availability(double time, int id, int duration);
protected:
priority_queue,
vector>,
greater>> availabilites_;
priority_queue,
vector>,
greater>> availability_ends_;
set available_items_set_;
vector available_items_;
private:
double time_ = -1;
void update();
FRIEND_TEST(TestAvailabilityFilter, test);
};
#endif /* AVAILABILITY_FILTER_H */
Alpenglow-1.0.6/cpp/src/main/filters/LabelFilter.cpp 0000775 0000000 0000000 00000001447 14037246614 0022324 0 ustar 00root root 0000000 0000000 #include "LabelFilter.h"
bool LabelFilter::active(RecDat* rec_dat){
LABEL actual_label = label_container_.get_label(rec_dat->item);
resize_last_labels(rec_dat->user);
LABEL last_label_of_active_user = last_labels_[rec_dat->user];
return (actual_label == last_label_of_active_user);
}
vector LabelFilter::get_whitelist(int user){
resize_last_labels(user);
int last_label = last_labels_[user];
vector active_items = label_container_.get_entities(last_label);
return active_items;
}
void LabelFilter::update(RecDat* rec_dat){
LABEL label = label_container_.get_label(rec_dat->item);
resize_last_labels(rec_dat->user);
last_labels_[rec_dat->user]=label;
}
void LabelFilter::resize_last_labels(int user){
if((int)last_labels_.size()<=user) last_labels_.resize(user+1,-1);
}
Alpenglow-1.0.6/cpp/src/main/filters/LabelFilter.h 0000775 0000000 0000000 00000003626 14037246614 0021772 0 ustar 00root root 0000000 0000000 #ifndef LABEL_FILTER_H
#define LABEL_FILTER_H
#include "WhitelistFilter.h"
#include "../utils/LabelContainer.h"
#include "../models/ModelUpdater.h"
#include
//SIP_AUTOCONVERT
struct LabelFilterParameters {
string label_file_name;
};
class LabelFilter
: public WhitelistFilter
, public Updater
{
/**
White list filter class that allows items having the same label (e.g. artist)
as the item that was previously interacted by the user. Requires updates
(i.e., add the object to the online experiment as an updater).
Sample usage:
.. code-block:: python
import alpenglow as ag
model = ag.PopularityModel()
updater = ag.PopularityModelUpdater()
updater.set_model(model)
label_filter = ag.LabelFilter(
label_file_name = "/path/to/file/"
)
adapter = ag.WhitelistFilter2ModelAdapter()
adapter.set_model(model)
adapter.set_whitelist_filter(label_filter)
*/
public:
LabelFilter(LabelFilterParameters* params){
label_file_name_ = params->label_file_name;
ifstream file(label_file_name_);
label_container_.read_from_file(file);
}
bool active(RecDat*) override;
/**
active(RecDat*)
Implements :py:meth:`alpenglow.cpp.WhitelistFilter.active`.
*/
vector get_whitelist(int user) override;
/**
get_whitelist(int user)
Implements :py:meth:`alpenglow.cpp.WhitelistFilter.get_whitelist`.
*/
void update(RecDat* rec_dat) override;
/**
update(RecDat* rec_dat)
Implements :py:meth:`alpenglow.cpp.Updater.update`.
*/
bool self_test(){
bool ok = true;
return ok;
}
private:
void resize_last_labels(int user);
LabelContainer label_container_;
string label_file_name_;
//state
vector
