Add .gitignore file and main application script

This commit introduces a .gitignore file that ignores various file types and directories related to Python, PyCharm, and venv. Additionally, the main application script, app.py, is added, which uses gradio for interface, loads data using the 'datasets' package, and includes functionality for user feedback and navigation.

.gitignore

@@ -0,0 +1,282 @@
+# Created by https://www.toptal.com/developers/gitignore/api/pycharm+all,venv,python
+# Edit at https://www.toptal.com/developers/gitignore?templates=pycharm+all,venv,python
+
+### PyCharm+all ###
+# Covers JetBrains IDEs: IntelliJ, RubyMine, PhpStorm, AppCode, PyCharm, CLion, Android Studio, WebStorm and Rider
+# Reference: https://intellij-support.jetbrains.com/hc/en-us/articles/206544839
+
+# User-specific stuff
+.idea/**/workspace.xml
+.idea/**/tasks.xml
+.idea/**/usage.statistics.xml
+.idea/**/dictionaries
+.idea/**/shelf
+
+# AWS User-specific
+.idea/**/aws.xml
+
+# Generated files
+.idea/**/contentModel.xml
+
+# Sensitive or high-churn files
+.idea/**/dataSources/
+.idea/**/dataSources.ids
+.idea/**/dataSources.local.xml
+.idea/**/sqlDataSources.xml
+.idea/**/dynamic.xml
+.idea/**/uiDesigner.xml
+.idea/**/dbnavigator.xml
+
+# Gradle
+.idea/**/gradle.xml
+.idea/**/libraries
+
+# Gradle and Maven with auto-import
+# When using Gradle or Maven with auto-import, you should exclude module files,
+# since they will be recreated, and may cause churn.  Uncomment if using
+# auto-import.
+# .idea/artifacts
+# .idea/compiler.xml
+# .idea/jarRepositories.xml
+# .idea/modules.xml
+# .idea/*.iml
+# .idea/modules
+# *.iml
+# *.ipr
+
+# CMake
+cmake-build-*/
+
+# Mongo Explorer plugin
+.idea/**/mongoSettings.xml
+
+# File-based project format
+*.iws
+
+# IntelliJ
+out/
+
+# mpeltonen/sbt-idea plugin
+.idea_modules/
+
+# JIRA plugin
+atlassian-ide-plugin.xml
+
+# Cursive Clojure plugin
+.idea/replstate.xml
+
+# SonarLint plugin
+.idea/sonarlint/
+
+# Crashlytics plugin (for Android Studio and IntelliJ)
+com_crashlytics_export_strings.xml
+crashlytics.properties
+crashlytics-build.properties
+fabric.properties
+
+# Editor-based Rest Client
+.idea/httpRequests
+
+# Android studio 3.1+ serialized cache file
+.idea/caches/build_file_checksums.ser
+
+### PyCharm+all Patch ###
+# Ignore everything but code style settings and run configurations
+# that are supposed to be shared within teams.
+
+.idea/*
+
+!.idea/codeStyles
+!.idea/runConfigurations
+
+### 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/
+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
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__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 maintained 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/
+
+### Python Patch ###
+# Poetry local configuration file - https://python-poetry.org/docs/configuration/#local-configuration
+poetry.toml
+
+# ruff
+.ruff_cache/
+
+# LSP config files
+pyrightconfig.json
+
+### venv ###
+# Virtualenv
+# http://iamzed.com/2009/05/07/a-primer-on-virtualenv/
+[Bb]in
+[Ii]nclude
+[Ll]ib
+[Ll]ib64
+[Ll]ocal
+[Ss]cripts
+pyvenv.cfg
+pip-selfcheck.json
+
+# End of https://www.toptal.com/developers/gitignore/api/pycharm+all,venv,python
+
+.idea
+
+data
+feedback
+flagged

app.py

@@ -0,0 +1,128 @@
+import uuid
+
+import gradio as gr
+from datasets import load_dataset
+
+configuration = "commitchronicle-py-long"  # select a configuration
+dataset = load_dataset("JetBrains-Research/lca-cmg",
+                       configuration,
+                       split="test",
+                       cache_dir="data")
+n_samples = len(dataset)
+
+saver = gr.CSVLogger()
+
+
+def get_github_link(repo, hash):
+    repo_url = f"https://github.com/{repo}/commit/{hash}"
+    return repo_url
+
+
+def update_commit_view(sample_ind):
+    if sample_ind >= n_samples:
+        return None
+
+    record = dataset[sample_ind]
+    github_link_md = f"[See the commit on GitHub]({get_github_link(record['repo'], record['hash'])})"
+    diff_json = record['mods']
+    commit_msg = record['message']
+    repo_val = record['repo']
+    hash_val = record['hash']
+    return github_link_md, diff_json, commit_msg, repo_val, hash_val
+
+
+def next_sample(current_sample_ind):
+    if current_sample_ind == n_samples:
+        return None
+
+    current_sample_ind += 1
+    updated_view = update_commit_view(current_sample_ind)
+    return (current_sample_ind,) + updated_view
+
+
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    with gr.Row():
+        current_sample_sld = gr.Slider(minimum=0, maximum=n_samples, step=1,
+                                       value=0,
+                                       interactive=False,
+                                       label='sample_ind',
+                                       info=f"Samples labeled/skipped (out of {n_samples})",
+                                       show_label=False,
+                                       container=False,
+                                       scale=5)
+        with gr.Column(scale=1):
+            repo_val = gr.Textbox(interactive=False, container=False, label='repo', visible=False)
+            hash_val = gr.Textbox(interactive=False, container=False, label='hash', visible=False)
+            skip_btn = gr.Button("Skip the current sample")
+    with gr.Row():
+        with gr.Column(scale=2):
+            github_link = gr.Markdown()
+            diff_view = gr.JSON()
+        with gr.Column(scale=1):
+            commit_msg = gr.Textbox(label="AI-generated commit message",
+                                    interactive=False,
+                                    )
+            gr.Markdown("## Please, answer the questions below")
+            verbosity_feedback = gr.Radio(info='How can you describe the length of the commit message above?',
+                                          label='verbosity',
+                                          show_label=False,
+                                          choices=[
+                                              ('Too short', 0),
+                                              ('Just right', 1),
+                                              ('Too verbose', 2)])
+            correctness_feedback = gr.Radio(info='Is the commit message factually correct?',
+                                            label='is_correct',
+                                            show_label=False,
+                                            choices=[
+                                                ('Yes', True),
+                                                ('No', False)])
+            format_feedback = gr.Slider(info='Rate the commit message\'s format (1 - very bad, 5 - very good)',
+                                        label='format_score',
+                                        show_label=False,
+                                        minimum=1,
+                                        step=1,
+                                        interactive=True,
+                                        maximum=5)
+            submit_btn = gr.Button("Submit and continue")
+            session_val = gr.Textbox(info='Session', interactive=False, container=True, show_label=False,
+                                     label='session')
+
+    commit_view = [
+        github_link,
+        diff_view,
+        commit_msg,
+        repo_val,
+        hash_val
+    ]
+
+    feedback_form = [
+        current_sample_sld,
+        session_val,
+        repo_val,
+        hash_val,
+        verbosity_feedback,
+        correctness_feedback,
+        format_feedback
+    ]
+
+    saver.setup(feedback_form, "feedback")
+
+    skip_btn.click(next_sample, inputs=[current_sample_sld], outputs=[current_sample_sld] + commit_view)
+
+
+    def submit(*args):
+        saver.flag(args)
+        return next_sample(args[0])
+
+
+    submit_btn.click(submit, inputs=feedback_form, outputs=[current_sample_sld] + commit_view)
+
+
+    def init_session(*args):
+        session = str(uuid.uuid4())
+        return (session,) + update_commit_view(*args)
+
+
+    demo.load(init_session, inputs=[current_sample_sld], outputs=[session_val] + commit_view)
+
+demo.launch()