First commit

.github/dependabot.yml

@@ -0,0 +1,93 @@
+# Dependabot configuration file
+# See: https://docs.github.com/en/code-security/supply-chain-security/keeping-your-dependencies-updated-automatically/configuration-options-for-dependency-updates#allow
+
+version: 2
+
+updates:
+
+  # We're using Poetry
+  - package-ecosystem: pip
+
+    # The root directory of the project
+    directory: "/"
+
+    # Check every day for updates at 08:00 UTC
+    schedule:
+      interval: "daily"
+      time: "08:00"
+      timezone: "UTC"
+
+    # Do not alert for indirect dependencies, as there may be too many
+    allow:
+      - dependency-type: direct
+
+    # Use Gitmoji in the commit message
+    commit-message:
+      prefix: "⬆️ "
+      include: "scope"
+
+    # Set the pull request label
+    labels:
+      - "dependencies"
+
+    # Stay updated to the main branch
+    rebase-strategy: auto
+
+    # Pip does not support any other versioning strategy
+    versioning-strategy: lockfile-only
+
+  # Additionally, keep GitHub Actions updated
+  - package-ecosystem: github-actions
+
+    # The root directory of the actions
+    directory: "/"
+
+    # Check every day for updates at 08:00 UTC
+    schedule:
+      interval: "daily"
+      time: "08:00"
+      timezone: "UTC"
+
+    # GitHub Actions only has direct dependencies
+    allow:
+      - dependency-type: direct
+
+    # Use Gitmoji in the commit message
+    commit-message:
+      prefix: "🔨️ "
+      include: "scope"
+
+    # Set the pull request label
+    labels:
+      - "automation"
+
+    # Stay updated to the main branch
+    rebase-strategy: auto
+
+  # Finally, keep Git submodules updated
+  - package-ecosystem: gitsubmodule
+
+    # The root directory of the repository
+    directory: "/"
+
+    # Check every day for updates at 08:00 UTC
+    schedule:
+      interval: "daily"
+      time: "08:00"
+      timezone: "UTC"
+
+    # GitHub Actions only has direct dependencies
+    allow:
+      - dependency-type: direct
+
+    # Use Gitmoji in the commit message
+    commit-message:
+      prefix: "⬆️ "
+      include: "scope"
+
+    # Set the pull request label
+    labels:
+      - "dependencies"
+
+    # Stay updated to the main branch
+    rebase-strategy: auto

.gitignore

@@ -0,0 +1,169 @@
+# Gitignore file
+# See https://git-scm.com/docs/gitignore for more details
+
+###################
+# Project ignores #
+###################
+
+# Add your own ignores here!
+
+
+
+##################
+# Python ignores #
+##################
+
+# From https://github.com/github/gitignore/blob/main/Python.gitignore
+
+# 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/
+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/
+cover/
+
+# 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/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .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
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.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/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintainted in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/

.idea/.gitignore

@@ -0,0 +1,8 @@
+# Default ignored files
+/shelf/
+/workspace.xml
+# Editor-based HTTP Client requests
+/httpRequests/
+# Datasource local storage ignored files
+/dataSources/
+/dataSources.local.xml

.idea/compiler.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="TypeScriptCompiler">
+    <option name="recompileOnChanges" value="true" />
+  </component>
+</project>

.idea/discord.xml

@@ -0,0 +1,7 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="DiscordProjectSettings">
+    <option name="show" value="ASK" />
+    <option name="description" value="" />
+  </component>
+</project>

.idea/markdown.xml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="MarkdownSettings">
+    <enabledExtensions>
+      <entry key="MermaidLanguageExtension" value="false" />
+      <entry key="PlantUMLLanguageExtension" value="false" />
+    </enabledExtensions>
+    <option name="splitLayout" value="SHOW_EDITOR" />
+  </component>
+</project>

.idea/misc.xml

@@ -0,0 +1,10 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="DiscordProjectSettings">
+    <option name="show" value="ASK" />
+    <option name="description" value="" />
+  </component>
+  <component name="ProjectRootManager">
+    <output url="file://$PROJECT_DIR$/out" />
+  </component>
+</project>

.idea/modules.xml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/unimore-bda-6.iml" filepath="$PROJECT_DIR$/unimore-bda-6.iml" />
+    </modules>
+  </component>
+</project>

.idea/vcs.xml

@@ -0,0 +1,6 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="VcsDirectoryMappings">
+    <mapping directory="$PROJECT_DIR$" vcs="Git" />
+  </component>
+</project>

.readthedocs.yml

@@ -0,0 +1,10 @@
+version: 2
+
+python:
+   install:
+      - path: "."
+
+build:
+   os: "ubuntu-20.04"
+   tools:
+      python: "3.10"

.vscode/extensions.json

@@ -0,0 +1,5 @@
+{
+    "recommendations": [
+        "ms-python.python"
+    ]
+}

.vscode/settings.json

@@ -0,0 +1,13 @@
+{
+    "files.exclude": {
+        ".idea/": true,
+        "**/*.iml": true,
+        "**/.pytest_cache/": true,
+        "**/__pycache__/": true,
+        ".venv/": true,
+        "dist/": true,
+        "out/": true,
+        "poetry.lock": true,
+    },
+    "python.analysis.extraPaths": ["./unimore_bda_6"],
+}

Dockerfile

@@ -0,0 +1,24 @@
+FROM python AS metadata
+LABEL maintainer="Your Name <you@example.org>"
+
+FROM metadata AS workdir
+WORKDIR /usr/src/PACKAGE_NAME
+
+FROM workdir AS poetry
+RUN pip install "poetry"
+
+FROM poetry AS dependencies
+COPY pyproject.toml ./pyproject.toml
+COPY poetry.lock ./poetry.lock
+RUN poetry install --no-root --no-dev
+
+FROM dependencies AS package
+COPY . .
+RUN poetry install
+
+FROM package AS environment
+ENV PYTHONUNBUFFERED=1
+
+FROM environment AS entrypoint
+ENTRYPOINT ["poetry", "run", "python", "-m", "PACKAGE_NAME"]
+CMD []

README.md

@@ -0,0 +1,27 @@
+[ Stefano Pigozzi | Tema Text Analytics | Big Data Analytics | A.A. 2022/2023 | Unimore ]
+
+# WIP
+
+> ### Sentiment analysis su recensioni Amazon
+> 
+> Modificare l’esercizio di sentiment analysis sulle review Amazon svolto in classe e verificare l’efficacia del metodo effettuando queste varianti: 
+> 
+> 1. Utilizzare come tokenizer il “sentiment tokenizer” di Christopher Potts (link disponibile nelle slide del corso);
+> 2. Modificare il dataset recuperando anche recensioni a 2, 3 e 4 stelle ed effettuare una classificazione a più classi (es. 5 classi di sentiment corrispondenti al numero di stelle delle recensioni). 
+>
+> Effettuare quindi un confronto di efficacia tra queste varianti e la versione originale vista in classe.
+> 
+> Valutare anche l’inclusione di altre feature estratte dai dati, con l’obiettivo di aumentare l’efficacia.
+> 
+> * E’ necessario effettuare tutti i test su un numero significativo di run (es., almeno 50), scegliendo ogni volta in maniera casuale la composizione di test-set e training-set a partire dall’insieme di post estratti (è possibile utilizzare le feature automatiche di cross validation viste per scikit-learn)
+> * E’ possibile (e gradito) estendere in ampiezza la propria analisi:
+>    * utilizzare e confrontare una o più delle librerie di ML viste a lezione (NLTK/scikitlearn/XGBoost/Tensorflow) (NOTA: per le tracce 2 e 3 è necessario sperimentare anche almeno una libreria diversa da NLTK)
+>    * utilizzare e confrontare diversi classificatori tra quelli offerti (es. quelli citati a lezione in scikit-learn) e una o più delle tecniche citate/viste a lezione (es. codifica del testo tramite TF-IDF, word embeddings per tensorflow, hyper-parameter tuning per scikit-learn, tecniche specifiche per sent. analysis, …)
+>    * utilizzare librerie per l’elaborazione del testo alternative (es. SpaCy https://spacy.io/ ) per estrarre feature aggiuntive, valutandone l’effetto sul modello
+>    * in generale: studiare, riassumere brevemente e applicare eventuali altre tecniche o strumenti ritenuti utili all’obiettivo (cioè, migliorare l’efficacia del modello proposto).
+>
+> Consegna: PDF commentato con discussione e codice Python (includere dati e codice anche in un file .txt per facilitarne il testing)
+> 
+> Per quanto riguarda il codice Python, è possibile (e gradito) produrre e consegnare un notebook jupyter .ipynb
+> (https://jupyter.org/) invece di codice .py e relativi commenti separati su PDF (per comodità di consultazione,
+> consegnare comunque anche una stampa PDF del notebook oltre al notebook stesso).

pyproject.toml

@@ -0,0 +1,167 @@
+[build-system]
+#######################
+# Python build system #
+#######################
+# The build system to use when installing this package.
+# Used when installing the package with `pip install .`.
+# See also: https://www.python.org/dev/peps/pep-0517/
+
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
+
+
+
+[tool.poetry]
+###################
+# Poetry settings #
+###################
+# See https://python-poetry.org/docs/pyproject/ for more details!
+
+# The name of your project.
+# Ensure that it is available on PyPI: https://pypi.org/
+name = "unimore_bda_6"
+
+# The version of the package.
+version = "0.1.0"
+
+# A brief, one-sentence description about your project.
+description = "Sesto progetto di Big Data Analytics"
+
+# A list of the authors of the project.
+authors = [
+    "Stefano Pigozzi <me@steffo.eu>",
+]
+
+# A list of maintainers of the project.
+# Often, it is the same as the authors list.
+maintainers = [
+    "Stefano Pigozzi <me@steffo.eu>",
+]
+
+# The license of the package.
+# Uses SPDX format: https://spdx.org/licenses/
+license = ""
+
+# The README file.
+readme = "README.md"
+
+# The URL of the project website.
+# Not the GitHub repository!
+# homepage = "https://example.org/"
+
+# The URL of the project repository.
+repository = "https://github.com/Steffo99/unimore-bda-6"
+
+# The URL of the project documentation location.
+# documentation = "https://example.org/docs"
+
+# Up to five keywords related to your project.
+# See also: https://packaging.python.org/en/latest/guides/distributing-packages-using-setuptools/#keywords
+keywords = [
+    "unimore",
+    "big data analytics",
+    "sentiment analysis",
+    "amazon reviews",
+    "university project",
+]
+
+# Any number of trove classifiers that apply to your project.
+# See the list at: https://pypi.org/classifiers/
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.10",
+]
+
+# ADVANCED: specify the packages exported by your project
+# See also: https://python-poetry.org/docs/pyproject/#packages
+# packages = [
+#     # Regular packages
+#     { include = "OTHER_PACKAGE_NAME" },
+#     # Namespace packages
+#     { include = "EXTEND/OTHER/NAMESPACE/**/*.py" }
+# ]
+
+# ADVANCED: include additional files in the build
+# include = [
+#     "FILENAME.txt"
+# ]
+
+# ADVANCED: exclude files from the build
+# exclude = [
+#     "PACKAGE_NAME/test.py"
+# ]
+
+
+
+[tool.poetry.urls]
+##################
+# URLs           #
+##################
+# Additional project URLs in a name → link mapping.
+
+
+
+[tool.poetry.scripts]
+#####################
+# Scripts           #
+#####################
+# Poetry can create "binaries" to add to the PATH when the project is installed.
+# They are specified in the form of a mapping with the command name as key and the function to execute as value.
+
+# If you are building a library, comment this.
+# If you are building an application, replace PACKAGE-NAME and PACKAGE_NAME with your package name in kebab-case and snake_case respectively.
+
+# PACKAGE-NAME = "PACKAGE_NAME.__main__:main"
+
+
+
+[tool.poetry.dependencies]
+##########################
+# Dependencies           #
+##########################
+# A mapping of dependencies of the project
+# It should be maintained by `poetry add` / `poetry remove`, but it currently adds things after all comments...
+# You can manually specify allowed version numbers:
+# * means "any release"
+#         *        →  any
+# ^X.X.X means "newer releases with this major version"
+#         ^3.10.1  →  == 3      && >= 3.10.1
+# ~X.X.X means "newer releases with this minor version"
+#         ~3.10.1  →  == 3.10   && >= 3.10.1
+# nothing means "this specific release"
+#          3.10.1  →  == 3.10.1
+
+python = "^3.10"
+
+
+
+[tool.poetry.dev-dependencies]
+##############################
+# Development dependencies   #
+##############################
+# Same as above, but these dependencies are installed only if the project is being installed in development mode.
+# They are excluded from the final build.
+
+
+[tool.poetry.extras]
+####################
+# Package extras   #
+####################
+# ADVANCED: specify optional dependency groups.
+# See: https://python-poetry.org/docs/pyproject/#extras
+
+
+
+[tool.poetry.plugins]
+#####################
+# Poetry plugins    #
+#####################
+# ADVANCED: extend Poetry's functionality.
+# See: https://python-poetry.org/docs/pyproject/#plugins
+
+
+
+[tool.pytest.ini_options]
+#########################
+# Pytest configuration  #
+#########################

unimore-bda-6.iml

@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="GENERAL_MODULE" version="4">
+  <component name="NewModuleRootManager" inherit-compiler-output="true">
+    <exclude-output />
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+</module>

unimore_bda_6/__init__.py

@@ -0,0 +1,5 @@
+# If you are building a **library**, use this file to export objects!
+
+__all__ = (
+    # "",
+)

unimore_bda_6/__main__.py

@@ -0,0 +1,8 @@
+# If you are building an **application**, use this file to run code!
+
+def main():
+    pass
+
+
+if __name__ == "__main__":
+    main()