Scripts for ASReview paper

Author: J535D165

.gitignore

@@ -0,0 +1,152 @@
+
+# Created by https://www.toptal.com/developers/gitignore/api/python,jupyternotebooks
+# Edit at https://www.toptal.com/developers/gitignore?templates=python,jupyternotebooks
+
+### JupyterNotebooks ###
+# gitignore template for Jupyter Notebooks
+# website: http://jupyter.org/
+
+.ipynb_checkpoints
+*/.ipynb_checkpoints/*
+
+# IPython
+profile_default/
+ipython_config.py
+
+# Remove previous ipynb_checkpoints
+#   git rm -r .ipynb_checkpoints/
+
+### Python ###
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+pytestdebug.log
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+doc/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+
+# IPython
+
+# pyenv
+.python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# End of https://www.toptal.com/developers/gitignore/api/python,jupyternotebooks

.zenodo.json

@@ -0,0 +1,45 @@
+{
+	"description": "",
+	"title": "Scripts for 'ASReview: Open Source Software for Efficient and Transparent Active Learning for Systematic Reviews'",
+	"creators": [
+		{
+			"name": "Ferdinands, Gerbrich",
+			"affiliation": "Utrecht University",
+			"orcid": "0000-0002-4998-3293"
+		},
+		{
+			"name": "Schram, Raoul",
+			"affiliation": "Utrecht University",
+			"orcid": "0000-0001-6616-230X"
+		},
+		{
+			"name": "Van de Schoot, Rens",
+			"affiliation": "Department of Psychology, Utrecht University",
+			"orcid": "0000-0001-7736-2091"
+		},
+		{
+			"name": "De Bruin, Jonathan",
+			"affiliation": "Utrecht University",
+			"orcid": "0000-0002-4297-0502"
+		}
+
+	],
+	"keywords": [
+		"systematic review",
+		"prisma",
+		"active learning",
+		"statistics",
+		"machine learning",
+		"text data",
+		"natural language processing",
+		"human-in-the-loop"
+	],
+	"related_identifiers": [
+		{
+			"relation": "isSupplementTo",
+		 	"identifier": "http://arxiv.org/abs/2006.12166"
+		}
+	],
+	"license": "Apache-2.0",
+	"upload_type": "software"
+}

Hyperparameter_optimization/Data/ace.csv

@@ -0,0 +1,10 @@
+# Hyperparameter optimization
+Optimize hyperparameters for 12 hours, over 6 datasets in the `data` directory for a model with Naive Bayes classifier (B), tfidf feature extraction (T), certainty sampling (max) query strategy (C), double balance strategy (D):
+
+`mpirun -n 2 asreview hyper-active -m nb -b double -e tfidf -q max -t 12:00:00 --mpi`
+
+See the [asreview-hyperopt repository](https://github.com/asreview/asreview-hyperopt) for more information on the optimization of hyperparameters.
+
+After 12 hours of optimizing, a configuration file with optimized hyperparameters is created:
+
+`asreview create-config output/active/nb_max_double_tfidf/nudging_software_wilson_ace_virus/trials.pkl -o config/BCTD.ini`

Hyperparameter_optimization/Data/nudging.csv

@@ -0,0 +1,20 @@
+[global_settings]
+n_instances = 20
+n_prior_included = 1
+n_prior_excluded = 1
+model = nb
+balance_strategy = double
+query_strategy = max
+feature_extraction = tfidf
+
+[balance_param]
+a = 0.7782141491367417
+alpha = 1.39537927110139
+b = 0.9147018292161516
+
+[feature_param]
+ngram_max = 2
+split_ta = 0
+
+[model_param]
+alpha = 2.1292734234216257