修改readme

evaluate-0.4.2/.github/hub/push_evaluations_to_hub.py

+from pathlib import Path
+from huggingface_hub import create_repo, Repository
+import tempfile
+import subprocess
+import os
+import shutil
+import logging
+import re
+from urllib.parse import urlparse
+
+logger = logging.getLogger(__name__)
+
+GIT_UP_TO_DATE = "On branch main\nYour branch is up to date with 'origin/main'.\
+\n\nnothing to commit, working tree clean\n"
+
+COMMIT_PLACEHOLDER = "{COMMIT_PLACEHOLDER}"
+
+def get_git_tag(lib_path, commit_hash):
+    # check if commit has a tag, see: https://stackoverflow.com/questions/1474115/how-to-find-the-tag-associated-with-a-given-git-commit
+    command = f"git describe --exact-match {commit_hash}"
+    output = subprocess.run(command.split(),
+            stderr=subprocess.PIPE,
+            stdout=subprocess.PIPE,
+            encoding="utf-8",
+            cwd=lib_path,
+            env=os.environ.copy(),
+        )
+    tag = output.stdout.strip()
+    if re.match(r"v\d*\.\d*\.\d*", tag) is not None:
+        return tag
+    else:
+        return None
+
+
+def copy_recursive(source_base_path, target_base_path):
+    """Copy directory recursively and overwrite existing files."""
+    for item in source_base_path.iterdir():
+        target_path = target_base_path / item.name
+        if item.is_dir():
+            target_path.mkdir(exist_ok=True)
+            copy_recursive(item, target_path)
+        else:
+            shutil.copy(item, target_path)
+
+def update_evaluate_dependency(requirements_path, commit_hash):
+    """Updates the evaluate requirement with the latest commit."""
+    with open(requirements_path, "r") as f:
+        file_content = f.read()
+    file_content = file_content.replace(COMMIT_PLACEHOLDER, commit_hash)
+    with open(requirements_path, "w") as f:
+        f.write(file_content)
+
+def push_module_to_hub(module_path, type, token, commit_hash, tag=None):
+    module_name = module_path.stem
+    org = f"evaluate-{type}"
+    
+    repo_url = create_repo(org + "/" + module_name, repo_type="space", space_sdk="gradio", exist_ok=True, token=token)    
+    repo_path = Path(tempfile.mkdtemp())
+    
+    scheme = urlparse(repo_url).scheme
+    repo_url = repo_url.replace(f"{scheme}://", f"{scheme}://user:{token}@")
+    clean_repo_url = re.sub(r"(https?)://.*@", r"\1://", repo_url)
+    
+    try:
+        subprocess.run(
+            f"git clone {repo_url}".split(),
+            stderr=subprocess.PIPE,
+            stdout=subprocess.PIPE,
+            check=True,
+            encoding="utf-8",
+            cwd=repo_path,
+            env=os.environ.copy(),
+        )
+    except OSError:
+        # make sure we don't accidentally expose token
+        raise OSError(f"Could not clone from '{clean_repo_url}'")
+
+    repo = Repository(local_dir=repo_path / module_name, use_auth_token=token)
+    
+    copy_recursive(module_path, repo_path / module_name)
+    update_evaluate_dependency(repo_path / module_name / "requirements.txt", commit_hash)
+    
+    repo.git_add()
+    try:
+        repo.git_commit(f"Update Space (evaluate main: {commit_hash[:8]})")
+        repo.git_push()
+        logger.info(f"Module '{module_name}' pushed to the hub")
+    except OSError as error:
+        if str(error) == GIT_UP_TO_DATE:
+            logger.info(f"Module '{module_name}' is already up to date.")
+        else:
+            raise error
+
+    if tag is not None:
+        repo.add_tag(tag, message="add evaluate tag", remote="origin")
+    
+    shutil.rmtree(repo_path)
+
+
+if __name__ == "__main__":
+    evaluation_paths = ["metrics", "comparisons", "measurements"]
+    evaluation_types = ["metric", "comparison", "measurement"]
+
+    token = os.getenv("HF_TOKEN")
+    evaluate_lib_path = Path(os.getenv("EVALUATE_LIB_PATH"))
+    commit_hash = os.getenv("GIT_HASH")
+    git_tag = get_git_tag(evaluate_lib_path, commit_hash)
+    if git_tag is not None:
+        logger.info(f"Found tag: {git_tag}.")
+
+    for type, dir in zip(evaluation_types, evaluation_paths):
+        if (evaluate_lib_path/dir).exists():
+            for module_path in (evaluate_lib_path/dir).iterdir():
+                if module_path.is_dir():
+                    logger.info(f"Updating: module {module_path.name}.")
+                    push_module_to_hub(module_path, type, token, commit_hash, tag=git_tag)
+        else:
+            logger.warning(f"No folder {str(evaluate_lib_path/dir)} for {type} found.")

evaluate-0.4.2/.github/hub/requirements.txt

+huggingface_hub
\ No newline at end of file

evaluate-0.4.2/.github/workflows/build_documentation.yml

+name: Build documentation
+
+on:
+  push:
+    branches:
+      - main
+      - doc-builder*
+      - v*-release
+
+jobs:
+   build:
+    uses: huggingface/doc-builder/.github/workflows/build_main_documentation.yml@main
+    with:
+      commit_sha: ${{ github.sha }}
+      package: evaluate

evaluate-0.4.2/.github/workflows/build_pr_documentation.yml

+name: Build PR Documentation
+
+on:
+  pull_request:
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
+  cancel-in-progress: true
+
+jobs:
+  build:
+    uses: huggingface/doc-builder/.github/workflows/build_pr_documentation.yml@main
+    with:
+      commit_sha: ${{ github.event.pull_request.head.sha }}
+      pr_number: ${{ github.event.number }}
+      package: evaluate
\ No newline at end of file

evaluate-0.4.2/.github/workflows/ci.yml

+name: CI
+
+on:
+  pull_request:
+    branches:
+      - main
+  push:
+    branches:
+      - main
+      - ci-*
+
+env:
+  HF_ALLOW_CODE_EVAL: 1
+
+jobs:
+
+  check_code_quality:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set up Python
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install .[quality]
+      - name: Check quality
+        run: |
+          black --check --line-length 119 --target-version py36 tests src metrics comparisons measurements
+          isort --check-only tests src metrics comparisons measurements
+          flake8 tests src metrics
+
+  test:
+    needs: check_code_quality
+    strategy:
+      fail-fast: false
+      matrix:
+        test: ['unit', 'parity']
+        os: [ubuntu-latest, windows-latest]
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - name: Set up Python 3.8
+        uses: actions/setup-python@v4
+        with:
+          python-version: "3.8"
+      - name: Upgrade pip
+        run: python -m pip install --upgrade pip
+      - name: Install dependencies
+        run: |
+          pip install .[tests]
+          pip install -r additional-tests-requirements.txt --no-deps
+      - name: Test with pytest
+        if: ${{ matrix.test == 'unit' }}
+        run: |
+          python -m pytest -n 2 --dist loadfile -sv ./tests/ --ignore=./tests/test_trainer_evaluator_parity.py
+      - name: Integration test with transformers
+        if: ${{ matrix.test == 'parity' }}
+        run: |
+          python -m pytest -n 2 --dist loadfile -sv ./tests/test_trainer_evaluator_parity.py

evaluate-0.4.2/.github/workflows/delete_doc_comment.yml

+name: Delete dev documentation
+
+on:
+  pull_request:
+    types: [ closed ]
+
+
+jobs:
+  delete:
+    uses: huggingface/doc-builder/.github/workflows/delete_doc_comment.yml@main
+    with:
+      pr_number: ${{ github.event.number }}
+      package: evaluate
\ No newline at end of file

evaluate-0.4.2/.github/workflows/python-release.yml

+name: Python release
+
+on:
+  push:
+    tags:
+      - v*
+
+env:
+  PYPI_TOKEN: ${{ secrets.PYPI_TOKEN_DIST }}
+
+jobs:
+  python_release:
+    runs-on: ubuntu-latest
+
+    steps:
+    - uses: actions/checkout@v2
+    - name: Set up Python
+      uses: actions/setup-python@v2
+      with:
+        python-version: 3.9
+    - name: Install dependencies
+      run: |
+        pip install --upgrade pip
+        pip install setuptools wheel
+    - run: python setup.py sdist bdist_wheel
+
+    - run: |
+        pip install twine
+    - name: Upload to PyPi
+      run: |
+          twine upload dist/* -u __token__ -p "$PYPI_TOKEN"

evaluate-0.4.2/.github/workflows/update_spaces.yml

+name: Update Hub repositories
+
+on:
+  push:
+    branches:
+      - main
+
+jobs:
+  update-hub-repositories:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v2
+        with:
+          fetch-depth: 0
+      - name: Set up Python
+        uses: actions/setup-python@v2
+        with:
+          python-version: "3.8"
+      - name: Set up default Git config
+        run: |
+          git config --global user.name evaluate-bot
+          git config --global user.email leandro@huggingface.co
+      - name: Install dependencies
+        working-directory: ./.github/hub
+        run: |
+          python -m pip install --upgrade pip
+          pip install -r requirements.txt
+      - name: Update Hub repositories
+        working-directory: ./.github/hub
+        run: |
+          export HF_TOKEN=${{ secrets.HF_HUB_TOKEN }}
+          export EVALUATE_LIB_PATH=$GITHUB_WORKSPACE
+          export GIT_HASH=$GITHUB_SHA
+          export GIT_LFS_SKIP_SMUDGE=1
+          python push_evaluations_to_hub.py
\ No newline at end of file

evaluate-0.4.2/.gitignore

+# Locked files
+*.lock
+!dvc.lock
+
+# Extracted dummy data
+datasets/**/dummy_data-zip-extracted/
+
+# Compiled python modules.
+*.pyc
+
+# Byte-compiled
+_pycache__/
+.cache/
+
+# Python egg metadata, regenerated from source files by setuptools.
+*.egg-info
+.eggs/
+
+# PyPI distribution artifacts.
+build/
+dist/
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# pyenv
+.python-version
+
+# Tests
+.pytest_cache/
+
+# Other
+*.DS_Store
+
+# PyCharm/vscode
+.idea
+.vscode
+
+# keep only the empty datasets and metrics directory with it's __init__.py file
+/src/*/datasets/*
+!/src/*/datasets/__init__.py
+
+/src/*/metrics/*
+!/src/*/metrics/__init__.py
+
+# Vim
+.*.swp
+
+# playground
+/playground
+
+# Sphinx documentation
+docs/_build/
+docs/source/_build/
+
+# Benchmark results
+report.json
+report.md
\ No newline at end of file

evaluate-0.4.2/AUTHORS

+# This is the list of HuggingFace Datasets authors for copyright purposes.
+#
+# This does not necessarily list everyone who has contributed code, since in
+# some cases, their employer may be the copyright holder.  To see the full list
+# of contributors, see the revision history in source control.
+
+Google Inc.
+HuggingFace Inc.

evaluate-0.4.2/CODE_OF_CONDUCT.md

+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, caste, color, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+feedback@huggingface.co.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+[https://www.contributor-covenant.org/version/2/0/code_of_conduct.html][v2.0].
+
+Community Impact Guidelines were inspired by 
+[Mozilla's code of conduct enforcement ladder][Mozilla CoC].
+
+For answers to common questions about this code of conduct, see the FAQ at
+[https://www.contributor-covenant.org/faq][FAQ]. Translations are available 
+at [https://www.contributor-covenant.org/translations][translations].
+
+[homepage]: https://www.contributor-covenant.org
+[v2.0]: https://www.contributor-covenant.org/version/2/0/code_of_conduct.html
+[Mozilla CoC]: https://github.com/mozilla/diversity
+[FAQ]: https://www.contributor-covenant.org/faq
+[translations]: https://www.contributor-covenant.org/translations

evaluate-0.4.2/CONTRIBUTING.md

+<!---
+Copyright 2020 The HuggingFace Team. All rights reserved.
+
+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.
+-->
+
+# How to contribute to Evaluate
+
+Everyone is welcome to contribute, and we value everybody's contribution. Code
+is not the only way to help the community. Answering questions, helping
+others, reaching out and improving the documentations are immensely valuable to
+the community.
+
+It also helps us if you spread the word: reference the library from blog posts
+on the awesome projects it made possible, shout out on Twitter every time it has
+helped you, or simply star the repo to say "thank you".
+
+Whichever way you choose to contribute, please be mindful to respect our
+[code of conduct](https://github.com/huggingface/evaluate/blob/main/CODE_OF_CONDUCT.md).
+
+## You can contribute in so many ways!
+
+There are four ways you can contribute to `evaluate`:
+* Fixing outstanding issues with the existing code;
+* Implementing new evaluators and metrics;
+* Contributing to the examples and documentation;
+* Submitting issues related to bugs or desired new features.
+
+Open issues are tracked directly on the repository [here](https://github.com/huggingface/evaluate/issues).
+
+If you would like to work on any of the open issues:
+* Make sure it is not already assigned to someone else. The assignee (if any) is on the top right column of the Issue page. If it's not taken, self-assign it.
+* Work on your self-assigned issue and create a Pull Request!
+
+## Submitting a new issue or feature request
+
+Following these guidelines when submitting an issue or a feature
+request will make it easier for us to come back to you quickly and with good
+feedback.
+
+### Do you want to implement a new metric?
+
+All evaluation modules, be it metrics, comparisons, or measurements live on the 🤗 Hub in a [Space](https://huggingface.co/docs/hub/spaces) (see for example [Accuracy](https://huggingface.co/spaces/evaluate-metric/accuracy)). Evaluation modules can be either **community** or **canonical**. 
+
+* **Canonical** metrics are well-established metrics which already broadly adopted. 
+* **Community** metrics are new or custom metrics. It is simple to add a new community metric to use with `evaluate`. Please see our guide to adding a new evaluation metric [here](https://huggingface.co/docs/evaluate/creating_and_sharing)! 
+
+The only functional difference is that canonical metrics are integrated into the `evaluate` library directly and do not require a namespace when being loaded. 
+
+We encourage contributors to share new evaluation modules they contribute broadly! If they become widely adopted then they will be integrated into the core `evaluate` library as a canonical module.
+
+### Do you want to request a new feature (that is not a metric)?
+
+We would appreciate it if your feature request addresses the following points:
+
+1. Motivation first:
+  * Is it related to a problem/frustration with the library? If so, please explain
+    why. Providing a code snippet that demonstrates the problem is best.
+  * Is it related to something you would need for a project? We'd love to hear
+    about it!
+  * Is it something you worked on and think could benefit the community?
+    Awesome! Tell us what problem it solved for you.
+2. Write a *full paragraph* describing the feature;
+3. Provide a **code snippet** that demonstrates its future use;
+4. In case this is related to a paper, please attach a link;
+5. Attach any additional information (drawings, screenshots, etc.) you think may help.
+
+### Did you find a bug?
+
+Thank you for reporting an issue. If the bug is related to a community metric, please open an issue or pull request directly on the repository of the metric on the Hugging Face Hub. 
+
+If the bug is related to the `evaluate` library and not a community metric, we would really appreciate it if you could **make sure the bug was not already reported** (use the search bar on Github under Issues). If it's not already logged, please open an issue with these details:
+
+* Include your **OS type and version**, the versions of **Python**, **PyTorch** and
+  **Tensorflow** when applicable;
+* A short, self-contained, code snippet that allows us to reproduce the bug in
+  less than 30s;
+* Provide the *full* traceback if an exception is raised.
+
+## Start contributing! (Pull Requests)
+
+Before writing code, we strongly advise you to search through the existing PRs or
+issues to make sure that nobody is already working on the same thing. If you are
+unsure, it is always a good idea to open an issue to get some feedback.
+
+1. Fork the [repository](https://github.com/huggingface/evaluate) by
+   clicking on the 'Fork' button on the repository's page. This creates a copy of the code
+   under your GitHub user account.
+
+2. Clone your fork to your local disk, and add the base repository as a remote:
+
+   ```bash
+   $ git clone git@github.com:<your Github handle>/evaluate.git
+   $ cd evaluate 
+   $ git remote add upstream https://github.com/huggingface/evaluate.git
+   ```
+
+3. Create a new branch to hold your development changes:
+
+   ```bash
+   $ git checkout -b a-descriptive-name-for-my-changes
+   ```
+
+   **Do not** work on the `main` branch.
+
+4. Set up a development environment by running the following command in a virtual environment:
+
+   ```bash
+   $ pip install -e ".[dev]"
+   ```
+
+5. Develop the features on your branch.
+
+   As you work on the features, you should make sure that the test suite
+   passes. You should run the tests impacted by your changes like this:
+
+   ```bash
+   $ pytest tests/<TEST_TO_RUN>.py
+   ```
+   
+   To run a specific test, for example the `test_model_init` test in test_evaluator.py, 
+
+   ```bash
+   python -m pytest ./tests/test_evaluator.py::TestQuestionAnsweringEvaluator::test_model_init
+   ```
+
+   You can also run the full suite with the following command:
+
+   ```bash
+   $ python -m pytest ./tests/ 
+   ```
+
+   🤗 Evaluate relies on `black` and `isort` to format its source code
+   consistently. After you make changes, apply automatic style corrections and code verifications
+   that can't be automated in one go with:
+
+   ```bash
+   $ make quality
+   ```
+
+   This target is also optimized to only work with files modified by the PR you're working on.
+
+   If you prefer to run the checks one after the other, the following command apply the
+   style corrections:
+
+   ```bash
+   $ make style
+   ```
+
+   🤗 Evaluate also uses `flake8` and a few custom scripts to check for coding mistakes. Quality
+   control runs in CI, however you can also run the same checks with:
+
+   ```bash
+   $ make quality
+   ```
+
+   If you're modifying documents under `docs/source`, make sure to validate that
+   they can still be built. This check also runs in CI. To run a local check
+   make sure you have installed the documentation builder requirements. First you will need to clone the
+   repository containing our tools to build the documentation:
+   
+   ```bash
+   $ pip install git+https://github.com/huggingface/doc-builder
+   ```
+
+   Then, make sure you have all the dependencies to be able to build the doc with:
+   
+   ```bash
+   $ pip install ".[docs]"
+   ```
+
+   Finally, run the following command from the root of the repository:
+
+   ```bash
+   $ doc-builder build evaluate docs/source/ --build_dir ~/tmp/test-build
+   ```
+
+   This will build the documentation in the `~/tmp/test-build` folder where you can inspect the generated
+   Markdown files with your favorite editor. You won't be able to see the final rendering on the website
+   before your PR is merged, we are actively working on adding a tool for this.
+
+   Once you're happy with your changes, add changed files using `git add` and
+   make a commit with `git commit` to record your changes locally:
+
+   ```bash
+   $ git add modified_file.py
+   $ git commit
+   ```
+
+   Please write [good commit
+   messages](https://chris.beams.io/posts/git-commit/).
+
+   It is a good idea to sync your copy of the code with the original
+   repository regularly. This way you can quickly account for changes:
+
+   ```bash
+   $ git fetch upstream
+   $ git rebase upstream/main
+   ```
+
+   Push the changes to your account using:
+
+   ```bash
+   $ git push -u origin a-descriptive-name-for-my-changes
+   ```
+
+6. Once you are satisfied, go to the webpage of your fork on GitHub. Click on 'Pull request' to send your changes
+   to the project maintainers for review.
+
+7. It's ok if maintainers ask you for changes. It happens to core contributors
+   too! So everyone can see the changes in the Pull request, work in your local
+   branch and push the changes to your fork. They will automatically appear in
+   the pull request.
+
+
+### Checklist
+
+1. The title of your pull request should be a summary of its contribution;
+2. If your pull request addresses an issue, please mention the issue number in
+   the pull request description to make sure they are linked (and people
+   consulting the issue know you are working on it);
+3. To indicate a work in progress please prefix the title with `[WIP]`. These
+   are useful to avoid duplicated work, and to differentiate it from PRs ready
+   to be merged;
+4. Make sure existing tests pass;
+5. Add high-coverage tests. No quality testing = no merge.
+6. All public methods must have informative docstrings that work nicely with sphinx. 
+7. Due to the rapidly growing repository, it is important to make sure that no files that would significantly weigh down the repository are added. This includes images, videos and other non-text files. We prefer to leverage a hf.co hosted `dataset` like
+   the ones hosted on [`hf-internal-testing`](https://huggingface.co/hf-internal-testing) in which to place these files and reference 
+   them by URL.
+
+
+### Style guide
+
+For documentation strings, 🤗 Evaluate follows the [google style](https://google.github.io/styleguide/pyguide.html).
+Check our [documentation writing guide](https://github.com/huggingface/transformers/tree/main/docs#writing-documentation---specification)
+for more information.
+
+**This guide was heavily inspired by the awesome [scikit-learn guide to contributing](https://github.com/scikit-learn/scikit-learn/blob/main/CONTRIBUTING.md).**
+
+### Develop on Windows
+
+On Windows, you need to configure git to transform Windows `CRLF` line endings to Linux `LF` line endings:
+
+`git config core.autocrlf input`
+
+One way one can run the make command on Window is to pass by MSYS2:
+
+1. [Download MSYS2](https://www.msys2.org/), we assume to have it installed in C:\msys64
+2. Open the command line C:\msys64\msys2.exe (it should be available from the start menu)
+3. Run in the shell: `pacman -Syu` and install make with `pacman -S make`
+4. Add `C:\msys64\usr\bin` to your PATH environment variable.
+
+You can now use `make` from any terminal (Powershell, cmd.exe, etc) 🎉
+
+### Syncing forked main with upstream (HuggingFace) main
+
+To avoid pinging the upstream repository which adds reference notes to each upstream PR and sends unnecessary notifications to the developers involved in these PRs,
+when syncing the main branch of a forked repository, please, follow these steps:
+1. When possible, avoid syncing with the upstream using a branch and PR on the forked repository. Instead, merge directly into the forked main.
+2. If a PR is absolutely necessary, use the following steps after checking out your branch:
+```
+$ git checkout -b your-branch-for-syncing
+$ git pull --squash --no-commit upstream main
+$ git commit -m '<your message without GitHub references>'
+$ git push --set-upstream origin your-branch-for-syncing
+```

evaluate-0.4.2/LICENSE

+
+                                 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.

evaluate-0.4.2/Makefile

+.PHONY: quality style test
+
+# Check that source code meets quality standards
+
+quality:
+	black --check --line-length 119 --target-version py36 tests src metrics comparisons measurements
+	isort --check-only tests src metrics measurements
+	flake8 tests src metrics
+
+# Format source code automatically
+
+style:
+	black --line-length 119 --target-version py36 tests src metrics comparisons measurements
+	isort tests src metrics measurements
+
+# Run tests for the library
+
+test:
+	python -m pytest -n auto --dist=loadfile -s -v ./tests/

evaluate-0.4.2/README.md

+<p align="center">
+    <br>
+    <img src="https://huggingface.co/datasets/evaluate/media/resolve/main/evaluate-banner.png" width="400"/>
+    <br>
+</p>
+
+<p align="center">
+    <a href="https://github.com/huggingface/evaluate/actions/workflows/ci.yml?query=branch%3Amain">
+        <img alt="Build" src="https://github.com/huggingface/evaluate/actions/workflows/ci.yml/badge.svg?branch=main">
+    </a>
+    <a href="https://github.com/huggingface/evaluate/blob/master/LICENSE">
+        <img alt="GitHub" src="https://img.shields.io/github/license/huggingface/evaluate.svg?color=blue">
+    </a>
+    <a href="https://huggingface.co/docs/evaluate/index">
+        <img alt="Documentation" src="https://img.shields.io/website/http/huggingface.co/docs/evaluate/index.svg?down_color=red&down_message=offline&up_message=online">
+    </a>
+    <a href="https://github.com/huggingface/evaluate/releases">
+        <img alt="GitHub release" src="https://img.shields.io/github/release/huggingface/evaluate.svg">
+    </a>
+    <a href="CODE_OF_CONDUCT.md">
+        <img alt="Contributor Covenant" src="https://img.shields.io/badge/Contributor%20Covenant-2.0-4baaaa.svg">
+    </a>
+</p>
+
+🤗 Evaluate is a library that makes evaluating and comparing models and reporting their performance easier and more standardized. 
+
+It currently contains:
+
+- **implementations of dozens of popular metrics**: the existing metrics cover a variety of tasks spanning from NLP to Computer Vision, and include dataset-specific metrics for datasets. With a simple command like `accuracy = load("accuracy")`, get any of these metrics ready to use for evaluating a ML model in any framework (Numpy/Pandas/PyTorch/TensorFlow/JAX).
+- **comparisons and measurements**: comparisons are used to measure the difference between models and measurements are tools to evaluate datasets.
+- **an easy way of adding new evaluation modules to the 🤗 Hub**: you can create new evaluation modules and push them to a dedicated Space in the 🤗 Hub with `evaluate-cli create [metric name]`, which allows you to see easily compare different metrics and their outputs for the same sets of references and predictions.
+
+[🎓 **Documentation**](https://huggingface.co/docs/evaluate/)
+
+🔎 **Find a [metric](https://huggingface.co/evaluate-metric), [comparison](https://huggingface.co/evaluate-comparison), [measurement](https://huggingface.co/evaluate-measurement) on the Hub**
+
+[🌟 **Add a new evaluation module**](https://huggingface.co/docs/evaluate/)
+
+🤗 Evaluate also has lots of useful features like:
+
+- **Type checking**: the input types are checked to make sure that you are using the right input formats for each metric
+- **Metric cards**: each metrics comes with a card that describes the values, limitations and their ranges, as well as providing examples of their usage and usefulness.
+- **Community metrics:** Metrics live on the Hugging Face Hub and you can easily add your own metrics for your project or to collaborate with others.
+
+
+# Installation
+
+## With pip
+
+🤗 Evaluate can be installed from PyPi and has to be installed in a virtual environment (venv or conda for instance)
+
+```bash
+pip install evaluate
+```
+
+# Usage
+
+🤗 Evaluate's main methods are:
+
+- `evaluate.list_evaluation_modules()` to list the available metrics, comparisons and measurements
+- `evaluate.load(module_name, **kwargs)` to instantiate an evaluation module
+- `results = module.compute(*kwargs)` to compute the result of an evaluation module
+
+# Adding a new evaluation module
+
+First install the necessary dependencies to create a new metric with the following command:
+```bash
+pip install evaluate[template]
+```
+Then you can get started with the following command which will create a new folder for your metric and display the necessary steps:
+```bash
+evaluate-cli create "Awesome Metric"
+```
+See this [step-by-step guide](https://huggingface.co/docs/evaluate/creating_and_sharing) in the documentation for detailed instructions.
+
+## Credits
+
+Thanks to [@marella](https://github.com/marella) for letting us use the `evaluate` namespace on PyPi previously used by his [library](https://github.com/marella/evaluate).

evaluate-0.4.2/additional-tests-requirements.txt

+unbabel-comet>=1.0.0;python_version>'3.6'
+git+https://github.com/google-research/bleurt.git
+git+https://github.com/ns-moosavi/coval.git
+git+https://github.com/hendrycks/math.git
+git+https://github.com/google-research/rl-reliability-metrics
+gin-config
\ No newline at end of file

evaluate-0.4.2/comparisons/exact_match/README.md

+---
+title: Exact Match 
+emoji: 🤗 
+colorFrom: blue
+colorTo: green
+sdk: gradio
+sdk_version: 3.0.2
+app_file: app.py
+pinned: false
+tags:
+- evaluate
+- comparison
+description: >-
+  Returns the rate at which the predictions of one model exactly match those of another model.
+---
+
+
+# Comparison Card for Exact Match
+
+## Comparison description
+
+ Given two model predictions the exact match score is 1 if they are the exact same, and is 0 otherwise. The overall exact match score is the average.
+
+- **Example 1**: The exact match score if prediction 1.0 is [0, 1] is 0, given prediction 2 is [0, 1].
+- **Example 2**: The exact match score if prediction 0.0 is [0, 1] is 0, given prediction 2 is [1, 0].
+- **Example 3**: The exact match score if prediction 0.5 is [0, 1] is 0, given prediction 2 is [1, 1].
+
+## How to use 
+
+At minimum, this metric takes as input predictions and references:
+```python
+>>> exact_match = evaluate.load("exact_match", module_type="comparison")
+>>> results = exact_match.compute(predictions1=[0, 1, 1], predictions2=[1, 1, 1])
+>>> print(results)
+{'exact_match': 0.66}
+```
+
+## Output values
+
+Returns a float between 0.0 and 1.0 inclusive.
+
+## Examples 
+
+```python
+>>> exact_match = evaluate.load("exact_match", module_type="comparison")
+>>> results = exact_match.compute(predictions1=[0, 0, 0], predictions2=[1, 1, 1])
+>>> print(results)
+{'exact_match': 1.0}
+```
+
+```python
+>>> exact_match = evaluate.load("exact_match", module_type="comparison")
+>>> results = exact_match.compute(predictions1=[0, 1, 1], predictions2=[1, 1, 1])
+>>> print(results)
+{'exact_match': 0.66}
+```
+
+
+## Limitations and bias
+
+## Citations

evaluate-0.4.2/comparisons/exact_match/app.py

+import evaluate
+from evaluate.utils import launch_gradio_widget
+
+
+module = evaluate.load("exact_match", module_type="comparison")
+launch_gradio_widget(module)

evaluate-0.4.2/comparisons/exact_match/exact_match.py

+# Copyright 2022 The HuggingFace Evaluate Authors
+#
+# 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.
+"""Exact match test for model comparison."""
+
+import datasets
+import numpy as np
+
+import evaluate
+
+
+_DESCRIPTION = """
+Returns the rate at which the predictions of one model exactly match those of another model.
+"""
+
+
+_KWARGS_DESCRIPTION = """
+Args:
+    predictions1 (`list` of `int`): Predicted labels for model 1.
+    predictions2 (`list` of `int`): Predicted labels for model 2.
+
+Returns:
+    exact_match (`float`): Dictionary containing exact_match rate. Possible values are between 0.0 and 1.0, inclusive.
+
+Examples:
+    >>> exact_match = evaluate.load("exact_match", module_type="comparison")
+    >>> results = exact_match.compute(predictions1=[1, 1, 1], predictions2=[1, 1, 1])
+    >>> print(results)
+    {'exact_match': 1.0}
+"""
+
+
+_CITATION = """
+"""
+
+
+@evaluate.utils.file_utils.add_start_docstrings(_DESCRIPTION, _KWARGS_DESCRIPTION)
+class ExactMatch(evaluate.Comparison):
+    def _info(self):
+        return evaluate.ComparisonInfo(
+            module_type="comparison",
+            description=_DESCRIPTION,
+            citation=_CITATION,
+            inputs_description=_KWARGS_DESCRIPTION,
+            features=datasets.Features(
+                {
+                    "predictions1": datasets.Value("int64"),
+                    "predictions2": datasets.Value("int64"),
+                }
+            ),
+        )
+
+    def _compute(self, predictions1, predictions2):
+        score_list = [p1 == p2 for p1, p2 in zip(predictions1, predictions2)]
+        return {"exact_match": np.mean(score_list)}

evaluate-0.4.2/comparisons/exact_match/requirements.txt

+git+https://github.com/huggingface/evaluate@{COMMIT_PLACEHOLDER}
+scipy
\ No newline at end of file