FranKGraphBench 0.0.1a0__py2.py3-none-any.whl

FranKGraphBench-0.0.1a0.dist-info/LICENSE

@@ -0,0 +1,201 @@
+                                 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.

FranKGraphBench-0.0.1a0.dist-info/METADATA

@@ -0,0 +1,189 @@
+Metadata-Version: 2.1
+Name: FranKGraphBench
+Version: 0.0.1a0
+Summary: pip install package for frankgraphbench.
+Home-page: https://github.com/AKSW/frankgraphbench/tree/master/
+Author: Paulo do Carmo and Alvaro Lopes
+Author-email: paulo.carmo@htwk-leipzig.de
+License: Apache-2.0
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Programming Language :: Python :: 3
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: gensim
+Requires-Dist: joblib
+Requires-Dist: networkx
+Requires-Dist: numpy
+Requires-Dist: pandas
+Requires-Dist: python-dateutil
+Requires-Dist: pytz
+Requires-Dist: PyYAML
+Requires-Dist: scikit-learn
+Requires-Dist: scipy
+Requires-Dist: six
+Requires-Dist: smart-open
+Requires-Dist: threadpoolctl
+Requires-Dist: tqdm
+Requires-Dist: tzdata
+Requires-Dist: pykeen
+Requires-Dist: torch ==2.1.2
+Requires-Dist: py-cpuinfo
+Requires-Dist: gputil
+Requires-Dist: psutil
+Requires-Dist: sentence-transformers
+Requires-Dist: graph-walker
+Requires-Dist: isodate ==0.6.1
+Requires-Dist: Levenshtein ==0.21.0
+Requires-Dist: pyparsing ==3.0.9
+Requires-Dist: python-Levenshtein ==0.21.0
+Requires-Dist: rapidfuzz ==3.0.0
+Requires-Dist: rdflib ==6.3.2
+Requires-Dist: SPARQLWrapper ==2.0.0
+Requires-Dist: thefuzz ==0.19.0
+Requires-Dist: tzdata ==2023.3
+Requires-Dist: beautifulsoup4
+
+# FranKGraphBench: Knowledge Graph Aware Recommender Systems Framework for Benchmarking
+
+The FranKGraphBench is a framework to allow KG Aware RSs to be benchmarked in a reproducible and easy to implement manner. 
+It was first created on Google Summer of Code 2023 for Data Integration between DBpedia and some standard RS datasets in a reproducible framework.
+
+Check the [docs](https://frankgraphbench.readthedocs.io/en/latest/index.html) for more information.
+
+* This repository was first created for Data Integration between DBpedia and some standard Recommender Systems datasets and a framework for reproducible experiments. For more info, check the [project proposal](https://github.com/AlvaroJoseLopes/GSoC-2023) and the project progress with weekly (as possible) [updates](https://github.com/AKSW/frankgraphbench/wiki).
+
+# Data Integration Usage
+Install the required packages using python [virtualenv](https://docs.python.org/3/library/venv.html), using:
+
+```shell
+python3 -m venv venv_data_integration/
+source venv_data_integration/bin/activate
+pip3 install -r requirements_data_integration.txt 
+```
+
+Install the full dataset using bash scripts located at `datasets/`:
+
+```shell
+cd datasets
+bash ml-100k.sh # Downloaded at `datasets/ml-100k` folder
+bash ml-1m.sh   # Downloaded at `datasets/ml-1m` folder
+```
+
+## Usage
+```shell
+python3 data_integration.py [-h] -d DATASET -i INPUT_PATH -o OUTPUT_PATH [-ci] [-cu] [-cr] [-cs] [-map] [-w]
+```
+
+Arguments:
+- **-h:** Shows the help message.
+- **-d:** Name of a supported dataset. It will be the same name of the folder created by the bash script provided for the dataset. For now, check `data_integration/dataset2class.py` to see the supported ones.
+- **-i:** Input path where the full dataset is placed.
+- **-o:** Output path where the integrated dataset will be placed.
+- **-ci:** Use this flag if you want to convert item data.
+- **-cu:** Use this flag if you want to convert user data.
+- **-cr:** Use this flag if you want to convert rating data.
+- **-cs:** Use this flag if you want to convert social link data.
+- **-map:** Use this flag if you want to map dataset items with DBpedia. At least the item data should be already converted.
+- **-w:** Choose the number of workers(threads) to be used for parallel queries.
+
+Usage Example:
+
+```shell
+python3 data_integration.py -d 'ml-100k' -i 'datasets/ml-100k' -o 'datasets/ml-100k/processed' \
+    -ci -cu -cr -map -w 8
+```
+
+Check [Makefile](Makefile) for more examples.
+
+## Supported datasets
+
+| Dataset | #items matched | #items |
+|---------|---------------|---|
+|[MovieLens-100k](https://grouplens.org/datasets/movielens/100k/)|1462|1681|
+|[MovieLens-1M](https://grouplens.org/datasets/movielens/1m/)|3356|3883|
+|[LastFM-hetrec-2011](https://grouplens.org/datasets/hetrec-2011/)|11815|17632|
+|[Douban-Movie-Short-Comments-Dataset](https://www.kaggle.com/datasets/utmhikari/doubanmovieshortcomments/data)|---|28|douban-movie|
+|[Yelp-Dataset](https://www.yelp.com/dataset/download)|---|150348|yelp|
+|[Amazon-Video-Games-5](https://nijianmo.github.io/amazon/index.html)|---|21106|amazon-video_games-5|
+
+# Framework for reproducible experiments usage
+Install the require packages using python [virtualenv](https://docs.python.org/3/library/venv.html), using:
+
+```shell
+python3 -m venv venv_framework/
+source venv_framework/bin/activate
+pip3 install -r requirements_framework.txt 
+```
+
+## Usage 
+
+```shell
+python3 framework.py -c 'config_files/test.yml'
+```
+Arguments:
+- **-c:** Experiment configuration file path.
+
+The experiment config file should be a .yaml file like this:
+
+```yaml
+experiment:
+  dataset: 
+    name: ml-100k
+    item:
+      path: datasets/ml-100k/processed/item.csv 
+      extra_features: [movie_year, movie_title] 
+    user:
+      path: datasets/ml-100k/processed/user.csv 
+      extra_features: [gender, occupation] 
+    ratings: 
+      path: datasets/ml-100k/processed/rating.csv 
+      timestamp: True
+    enrich:
+      map_path: datasets/ml-100k/processed/map.csv
+      enrich_path: datasets/ml-100k/processed/enriched.csv
+      remove_unmatched: False
+      properties:
+        - type: subject
+          grouped: True
+          sep: "::"
+        - type: director
+          grouped: True
+          sep: "::"
+
+  preprocess:
+    - method: filter_kcore
+      parameters:
+        k: 20
+        iterations: 1
+        target: user
+
+  split:
+    seed: 42
+    test:
+      method: k_fold
+      k: 2
+      level: 'user'
+
+
+  models:
+    - name: deepwalk_based
+      config:
+        save_weights: True
+      parameters:
+        walk_len: 10
+        p: 1.0
+        q: 1.0
+        n_walks: 50
+        embedding_size: 64
+        epochs: 1
+  
+  evaluation:
+    k: 5
+    relevance_threshold: 3
+    metrics: [MAP, nDCG]
+
+  report:
+    file: 'experiment_results/ml100k_enriched/run1.csv'
+```
+
+See the [config_files/](/config_files/) directory for more examples.

FranKGraphBench-0.0.1a0.dist-info/RECORD

@@ -0,0 +1,70 @@
+data_integration/__init__.py,sha256=x3eh4cRQSiiZNeIvVo5UVeoTgDWBhsY0klrMkXmcUIk,2505
+data_integration/__main__.py,sha256=qkvm2rn7aqJbghtAGGXDsw67sbha2RM9GYBhGBu4g_s,84
+data_integration/dataset.py,sha256=JlAhmIm3E-xDEcvXkQXd0V2P6-19kW5JS82hlfodsO8,9954
+data_integration/dataset2class.py,sha256=m2SdFDpQ2JFONK7GyUj_usA2XZ86dFd95FNZ0ewvt6o,834
+data_integration/datasets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+data_integration/datasets/amazon.py,sha256=2MQb_ZXGK6Gjw8R8wlfws_hlkpqRI_QZFX1i8zHJtlo,5403
+data_integration/datasets/book-crossing.py,sha256=jEzLYGi7FT4ysgWN_tmufILgQ6riTzfktHg6xz-eEnM,3677
+data_integration/datasets/douban-movie.py,sha256=4A402rwJzM33jF42bxI_wycFYN18eD8UDoWRqFJi7WY,2693
+data_integration/datasets/lastfm.py,sha256=Ro0-6M0R6ZaPx1_d9nwzw54eSGpucZpo-pTbH90xK5U,8579
+data_integration/datasets/movielens.py,sha256=sdGwSCdwXRL4GAcV4Cc428B3O-Dg9OSObWrHP-Ew2-A,13971
+data_integration/datasets/steam.py,sha256=CGO9p4PW2EbFiFKN2bFIi3s8EKN9LpwPzHfF1MebeR0,3620
+data_integration/datasets/worker.py,sha256=IJ4-FmX6Y_Pe0uHp57591rlzHOS_xM0WdR01MhYN0sQ,1075
+data_integration/datasets/yelp.py,sha256=RlOiZvRZxSbvfT05d_wqL3ELGV8zhe26Vlw_OzlNprc,6063
+framework/__init__.py,sha256=ReEsL7-MoA3UjCH3kLtKJywq_6BzmOAJ4a12AG4j6Z8,518
+framework/__main__.py,sha256=Ft0oM50z9vFrCFjoIeYyIVMkYgp3SkdOCArx8Ygx1Jw,70
+framework/experiment.py,sha256=pKfvL8VNLmzqOCdyZBi9Vb80dPu2yoMailVTwly9gfQ,4615
+framework/utils.py,sha256=TE9PvcTBUEBdkFqFwpJKE2O9ZH7zFHnbhXZsj3X71r4,255
+framework/dataloader/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/dataloader/dataloader.py,sha256=sRmhWQEt6VMoJzuEKBVfNQcIwIkRFi8mtt1RmWXp3-E,2107
+framework/dataloader/dataset/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/dataloader/dataset/dataset.py,sha256=q-UpdS2LHX5pXPjRiKaR8C-Vb9TfuWL_eReYOT8NAiI,1107
+framework/dataloader/edge_splitter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/dataloader/edge_splitter/edge_splitter.py,sha256=wxTUsB4pH2geriSFiTl10qN9zrc9lYEnEHMuVqjYdGE,6035
+framework/dataloader/graph/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/dataloader/graph/graph.py,sha256=n0TilMzQ0LsIsE5UU7GQrndjKfy379imkDmd-ww7sA8,12544
+framework/dataloader/graph/node.py,sha256=8YJJI-vM5W4eWj134cSAmNsgUBxi2MjAIH0eHjCvwf0,1972
+framework/dataloader/preprocess/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/dataloader/preprocess/methods.py,sha256=xxtmQoctp7jkzivT4rJj8kANAqWkBOJvLi9IbJ_BNEo,1457
+framework/evaluator/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/evaluator/metric.py,sha256=Pfl31nKmcZbchxQm4JGAX9wkQJDLL7kjnwyXUD4pFOA,1560
+framework/evaluator/metric2class.py,sha256=xv8TrzFKM6bTdcvTmXGlN9mN3gROLep_GHyz7zKmFkc,187
+framework/evaluator/metrics/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/evaluator/metrics/map.py,sha256=IQdz-Gnq93hqWQSkooEA96TKHdETdQzVJUGE27eo6uA,1107
+framework/evaluator/metrics/ndcg.py,sha256=eNjgZ6g3DXDWOOwaKEU57B4etWs6Bs5iqrb4ffwCxPY,1638
+framework/recommender/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/model2class.py,sha256=RrAYp1kea2JzWfi8JNOpp18kc6R-9QE6aJKiGgAq-6w,1037
+framework/recommender/recommender.py,sha256=EL53qCN9u7Zj0abBnjsN6B3VehjYHQDGCc9kmoahCrI,1235
+framework/recommender/models/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/models/complEx/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/models/complEx/model.py,sha256=uCu4d3eXegUtBYhbK4o2dTaZMPvV7vhrQ2neD814TV4,7479
+framework/recommender/models/deep_walk_based/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/models/deep_walk_based/model.py,sha256=MyJAkVndtvDdYOcjdvJTAZPac8CEW0YlzoOEdABrP1c,5400
+framework/recommender/models/distMult/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/models/distMult/model.py,sha256=uD0lY-aF2I8wiJn__PkJVNn8VoLlnNi2LYaoSMsZVNE,7115
+framework/recommender/models/ePHEN/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/models/ePHEN/model.py,sha256=n9rXpMzTJhLtKm4cQGIQc6asz7smhxXX7SVTTfWVKZw,6323
+framework/recommender/models/rESCAL/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/models/rESCAL/model.py,sha256=74qKoOBop7bYPV-Vf2lymKKqiF4rX1M_aorqCMeMAjk,6915
+framework/recommender/models/rotatE/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/models/rotatE/model.py,sha256=Y8adL3jqnoISrMwN1lkyCJyAGpQ7YjFGbOszYU8PnZo,7698
+framework/recommender/models/transD/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/models/transD/model.py,sha256=ntPzCu9sxuYj4w7ef7YZhq0wj8SHp783opaE0-R0knM,7328
+framework/recommender/models/transE/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/models/transE/model.py,sha256=KwbXvSmKR3VHYhnU8nPlR7QE89S8sIXtAJyzWqCLyLU,7450
+framework/recommender/models/transH/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/models/transH/model.py,sha256=iDIVHcTuTaQcmn_Tb4MEY4KrV9nZioOwn6KLmLzQTiU,7513
+framework/recommender/models/transR/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/models/transR/model.py,sha256=Hd1nLPYscltTBTPrvBdCUIjmKXM07Iy9D5dQwX2oOCE,7364
+framework/recommender/models/tuckER/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/models/tuckER/model.py,sha256=ZEk2innTsljJTFKsbQC2UtG5wRVNJNyN5qVaanTacgM,7843
+framework/recommender/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/recommender/utils/walker.py,sha256=hj00ML1ZooVV8qcCon2rhnfKYa_FYHuyuFtOLQ-fCaw,5603
+framework/reporter/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+framework/reporter/report.py,sha256=8YlQpd_gdbldXQZUYR0OgyGQFa3Onko7X044ktXy48k,3831
+FranKGraphBench-0.0.1a0.dist-info/LICENSE,sha256=HrhfyXIkWY2tGFK11kg7vPCqhgh5DcxleloqdhrpyMY,11558
+FranKGraphBench-0.0.1a0.dist-info/METADATA,sha256=-LXoOcURZVo-5fsrHbScZhKEEKDZelAE6LZKil8ZiGU,6382
+FranKGraphBench-0.0.1a0.dist-info/WHEEL,sha256=DZajD4pwLWue70CAfc7YaxT1wLUciNBvN_TTcvXpltE,110
+FranKGraphBench-0.0.1a0.dist-info/entry_points.txt,sha256=cXDIJ8OHjypcsMfYc41oCtAvsSBjsRMWz5d6LSjuCOA,103
+FranKGraphBench-0.0.1a0.dist-info/top_level.txt,sha256=RoD7dhJJkBgu0NKFQ1k_mY6wU05S65SE0gLx3jg9dI8,27
+FranKGraphBench-0.0.1a0.dist-info/RECORD,,

FranKGraphBench-0.0.1a0.dist-info/WHEEL

@@ -0,0 +1,6 @@
+Wheel-Version: 1.0
+Generator: bdist_wheel (0.43.0)
+Root-Is-Purelib: true
+Tag: py2-none-any
+Tag: py3-none-any
+

FranKGraphBench-0.0.1a0.dist-info/entry_points.txt

@@ -0,0 +1,3 @@
+[console_scripts]
+data_integration = data_integration:data_integration
+framework = framework:framework

FranKGraphBench-0.0.1a0.dist-info/top_level.txt

@@ -0,0 +1,2 @@
+data_integration
+framework

data_integration/__init__.py

@@ -0,0 +1,47 @@
+import argparse
+import importlib
+
+from data_integration.dataset2class import dataset2class
+
+__version__ = "0.0.1-alpha"
+__author__ = "Paulo do Carmo and Alvaro Lopes"
+
+def get_dataset_class(dataset):
+    module_name = f'data_integration.{dataset2class[dataset]["submodule"]}'
+    class_name = dataset2class[dataset]['class']
+    return module_name, class_name
+
+def data_integration():
+    parser = argparse.ArgumentParser(
+        description="Script for Data Integration between DBpedia and some standard Recommender System datasets."
+    )
+
+    parser.add_argument('-d',   '--dataset',  type=str, required=True, help='Choose a supported RS dataset.')
+    parser.add_argument('-i',   '--input_path', type=str, required=True, help='Path where the dataset is located.')
+    parser.add_argument('-o',   '--output_path', type=str, required=True, help='Path where the processed dataset will be placed.')
+    parser.add_argument('-ci',  '--convert_item', action='store_true', help='Use this flag if you want to convert item data.')
+    parser.add_argument('-cu',  '--convert_user', action='store_true', help='Use this flag if you want to convert user data.')
+    parser.add_argument('-cr',  '--convert_rating', action='store_true', help='Use this flag if you want to convert rating data.')
+    parser.add_argument('-cs',  '--convert_social', action='store_true', help='Use this flag if you want to convert social links data.')
+    parser.add_argument('-map', '--map_URIs', action='store_true', help='Use this flag if you want to map dataset items with DBpedia.')
+    parser.add_argument('-enrich',  '--enrich_data', action='store_true', help='Use this flag if you want to enrich dataset with DBpedia.')
+    parser.add_argument('-w',   '--n_workers', type=int, default=1, help='Choose the number of workers(threads) to be used for parallel queries.')
+
+
+    args = parser.parse_args()
+    module_name, class_name = get_dataset_class(args.dataset)
+    dataset = getattr(importlib.import_module(module_name), class_name)
+    dataset = dataset(args.input_path, args.output_path, n_workers=args.n_workers)
+    
+    if args.convert_item:
+        dataset.convert_item_data()
+    if args.convert_user:
+        dataset.convert_user_data()
+    if args.convert_rating:
+        dataset.convert_rating_data()
+    if args.convert_social:
+        dataset.convert_social_data()
+    if args.map_URIs:
+        dataset.map_URIs()
+    if args.enrich_data:
+        dataset.enrich_data()

data_integration/__main__.py

@@ -0,0 +1,4 @@
+from . import data_integration
+
+if __name__ == '__main__':
+    data_integration()