Add files

.gitignore

@@ -0,0 +1,141 @@
+# 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
+
+# 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/
+
+# Secrets
+.env

Makefile

@@ -0,0 +1,75 @@
+.PHONY: style
+
+#################################################################################
+# GLOBALS                                                                       #
+#################################################################################
+DETECTED_OS := $(shell uname)
+
+#################################################################################
+# COMMANDS                                                                      #
+#################################################################################
+
+## Format code
+style:
+	black --line-length 119 . && isort .
+
+#################################################################################
+# Self Documenting Commands                                                     #
+#################################################################################
+
+.DEFAULT_GOAL := help
+
+# Inspired by <http://marmelab.com/blog/2016/02/29/auto-documented-makefile.html>
+# sed script explained:
+# /^##/:
+# 	* save line in hold space
+# 	* purge line
+# 	* Loop:
+# 		* append newline + lin	 to hold space
+# 		* go to next line
+# 		* if line starts with doc comment, strip comment character off and loop
+# 	* remove target prerequisites
+# 	* append hold space (+ newline) to line
+# 	* replace newline plus comments by `---`
+# 	* print line
+# Separate expressions are necessary because labels cannot be delimited by
+# semicolon; see <http://stackoverflow.com/a/11799865/1968>
+.PHONY: help
+help:
+	@echo "$$(tput bold)Available rules:$$(tput sgr0)"
+	@echo
+	@sed -n -e "/^## / { \
+		h; \
+		s/.*//; \
+		:doc" \
+		-e "H; \
+		n; \
+		s/^## //; \
+		t doc" \
+		-e "s/:.*//; \
+		G; \
+		s/\\n## /---/; \
+		s/\\n/ /g; \
+		p; \
+	}" ${MAKEFILE_LIST} \
+	| LC_ALL='C' sort --ignore-case \
+	| awk -F '---' \
+		-v ncol=$$(tput cols) \
+		-v indent=19 \
+		-v col_on="$$(tput setaf 6)" \
+		-v col_off="$$(tput sgr0)" \
+	'{ \
+		printf "%s%*s%s ", col_on, -indent, $$1, col_off; \
+		n = split($$2, words, " "); \
+		line_length = ncol - indent; \
+		for (i = 1; i <= n; i++) { \
+			line_length -= length(words[i]) + 1; \
+			if (line_length <= 0) { \
+				line_length = ncol - indent - length(words[i]) - 1; \
+				printf "\n%*s ", -indent, " "; \
+			} \
+			printf "%s ", words[i]; \
+		} \
+		printf "\n"; \
+	}' \
+	| more $(shell test $(shell uname) = Darwin && echo '--no-init --raw-control-chars')

app.py

@@ -0,0 +1,52 @@
+import os
+from pathlib import Path
+
+import pandas as pd
+import requests
+import streamlit as st
+from dotenv import load_dotenv
+
+if Path(".env").is_file():
+    load_dotenv(".env")
+
+
+def download_submissions():
+    auth_token = os.getenv("HF_HUB_TOKEN")
+    header = {"Authorization": "Bearer " + auth_token}
+    response = requests.get("http://huggingface.co/api/datasets", headers=header)
+    all_datasets = response.json()
+
+    submissions = []
+
+    for dataset in all_datasets:
+        is_benchmark = any([t for t in dataset["tags"] if t.split(":")[1] == "neelalex/raft-test"])
+        if is_benchmark:
+            submissions.append(dataset)
+
+    for submission in submissions:
+        submission_id = submission["id"]
+        response = requests.get(
+            f"http://huggingface.co/api/datasets/{submission_id}?full=true",
+            headers=header,
+        )
+        data = response.json()
+        submission_data = {"Team Name": [data["card_data"]["submission_dataset"].split("/")[0]]}
+        for task in data["card_data"]["model-index"]:
+            for task_name, splits in task.items():
+                for split in splits:
+                    if split["split"] == "test":
+                        for metric in split["metrics"]:
+                            if metric["name"] == "f1":
+                                submission_data[task_name] = [metric["value"]]
+
+    return pd.DataFrame(submission_data)
+
+
+###########
+### APP ###
+###########
+st.set_page_config(layout="wide")
+st.title("RAFT Leaderboard")
+df = download_submissions()
+# hack to remove index column from https://github.com/streamlit/streamlit/issues/641
+st.table(df.assign(hack="").set_index("hack"))

requirements.txt

@@ -0,0 +1,3 @@
+streamlit
+pandas
+python-dotenv