Add files

.pre-commit-config.yaml

@@ -0,0 +1,50 @@
+repos:
+- repo: https://github.com/pre-commit/pre-commit-hooks
+  rev: v4.4.0
+  hooks:
+  - id: check-executables-have-shebangs
+  - id: check-json
+  - id: check-merge-conflict
+  - id: check-shebang-scripts-are-executable
+  - id: check-toml
+  - id: check-yaml
+  - id: end-of-file-fixer
+  - id: mixed-line-ending
+    args: ["--fix=lf"]
+  - id: requirements-txt-fixer
+  - id: trailing-whitespace
+- repo: https://github.com/myint/docformatter
+  rev: v1.7.5
+  hooks:
+  - id: docformatter
+    args: ["--in-place"]
+- repo: https://github.com/pycqa/isort
+  rev: 5.12.0
+  hooks:
+    - id: isort
+      args: ["--profile", "black"]
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v1.5.1
+  hooks:
+    - id: mypy
+      args: ["--ignore-missing-imports"]
+      additional_dependencies: ["types-python-slugify", "types-requests", "types-PyYAML"]
+- repo: https://github.com/psf/black
+  rev: 23.7.0
+  hooks:
+    - id: black
+      language_version: python3.10
+      args: ["--line-length", "119"]
+- repo: https://github.com/kynan/nbstripout
+  rev: 0.6.1
+  hooks:
+    - id: nbstripout
+      args: ["--extra-keys", "metadata.interpreter metadata.kernelspec cell.metadata.pycharm"]
+- repo: https://github.com/nbQA-dev/nbQA
+  rev: 1.7.0
+  hooks:
+    - id: nbqa-black
+    - id: nbqa-pyupgrade
+      args: ["--py37-plus"]
+    - id: nbqa-isort
+      args: ["--float-to-top"]

.vscode/settings.json

@@ -0,0 +1,21 @@
+{
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "source.organizeImports": true
+        }
+    },
+    "black-formatter.args": [
+        "--line-length=119"
+    ],
+    "isort.args": ["--profile", "black"],
+    "flake8.args": [
+        "--max-line-length=119"
+    ],
+    "ruff.args": [
+        "--line-length=119"
+    ],
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": true
+}

LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2023 hysts
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

README.md

@@ -7,6 +7,7 @@ sdk: gradio
 sdk_version: 3.42.0
 app_file: app.py
 pinned: false
+license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,72 @@
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+import gradio as gr
+
+from paper_list import PaperList
+
+DESCRIPTION = "# ICCV 2023 Papers"
+
+paper_list = PaperList()
+
+with gr.Blocks(css="style.css") as demo:
+    gr.Markdown(DESCRIPTION)
+
+    search_box = gr.Textbox(
+        label="Search Title", placeholder="You can search for titles with regular expressions. e.g. (?<!sur)face"
+    )
+    case_sensitive = gr.Checkbox(label="Case Sensitive")
+    filter_names = gr.CheckboxGroup(
+        choices=[
+            "arXiv",
+            "GitHub",
+            "Space",
+            "Model",
+            "Dataset",
+        ],
+        label="Filter",
+    )
+    search_button = gr.Button("Search")
+
+    number_of_papers = gr.Textbox(label="Number of Papers Found")
+    table = gr.HTML(show_label=False)
+
+    demo.load(
+        fn=paper_list.render,
+        inputs=[
+            search_box,
+            case_sensitive,
+            filter_names,
+        ],
+        outputs=[
+            number_of_papers,
+            table,
+        ],
+    )
+
+    search_box.submit(
+        fn=paper_list.render,
+        inputs=[
+            search_box,
+            case_sensitive,
+            filter_names,
+        ],
+        outputs=[
+            number_of_papers,
+            table,
+        ],
+    )
+    search_button.click(
+        fn=paper_list.render,
+        inputs=[
+            search_box,
+            case_sensitive,
+            filter_names,
+        ],
+        outputs=[
+            number_of_papers,
+            table,
+        ],
+    )
+demo.queue().launch()

paper_list.py

@@ -0,0 +1,106 @@
+from __future__ import annotations
+
+import numpy as np
+import pandas as pd
+
+
+class PaperList:
+    def __init__(self):
+        self.organization_name = "ICML2023"
+        self.table = pd.read_csv("papers.csv")
+        self._preprocess_table()
+
+        self.table_header = """
+            <tr>
+                <td width="38%">Title</td>
+                <td width="25%">Authors</td>
+                <td width="5%">arXiv</td>
+                <td width="5%">GitHub</td>
+                <td width="7%">Paper pages</td>
+                <td width="5%">Spaces</td>
+                <td width="5%">Models</td>
+                <td width="5%">Datasets</td>
+                <td width="5%">Claimed</td>
+            </tr>"""
+
+    def _preprocess_table(self) -> None:
+        self.table["title_lowercase"] = self.table.title.str.lower()
+
+        rows = []
+        for row in self.table.itertuples():
+            title = f"{row.title}"
+            arxiv = f'<a href="{row.arxiv}" target="_blank">arXiv</a>' if isinstance(row.arxiv, str) else ""
+            github = f'<a href="{row.github}" target="_blank">GitHub</a>' if isinstance(row.github, str) else ""
+            hf_paper = (
+                f'<a href="{row.hf_paper}" target="_blank">Paper page</a>' if isinstance(row.hf_paper, str) else ""
+            )
+            hf_space = f'<a href="{row.hf_space}" target="_blank">Space</a>' if isinstance(row.hf_space, str) else ""
+            hf_model = f'<a href="{row.hf_model}" target="_blank">Model</a>' if isinstance(row.hf_model, str) else ""
+            hf_dataset = (
+                f'<a href="{row.hf_dataset}" target="_blank">Dataset</a>' if isinstance(row.hf_dataset, str) else ""
+            )
+            author_linked = "✅" if ~np.isnan(row.n_linked_authors) and row.n_linked_authors > 0 else ""
+            n_linked_authors = "" if np.isnan(row.n_linked_authors) else int(row.n_linked_authors)
+            n_authors = "" if np.isnan(row.n_authors) else int(row.n_authors)
+            claimed_paper = "" if n_linked_authors == "" else f"{n_linked_authors}/{n_authors} {author_linked}"
+            row = f"""
+                <tr>
+                    <td>{title}</td>
+                    <td>{row.authors}</td>
+                    <td>{arxiv}</td>
+                    <td>{github}</td>
+                    <td>{hf_paper}</td>
+                    <td>{hf_space}</td>
+                    <td>{hf_model}</td>
+                    <td>{hf_dataset}</td>
+                    <td>{claimed_paper}</td>
+                </tr>"""
+            rows.append(row)
+        self.table["html_table_content"] = rows
+
+    def render(self, search_query: str, case_sensitive: bool, filter_names: list[str]) -> tuple[str, str]:
+        df = self.table
+        if search_query:
+            if case_sensitive:
+                df = df[df.title.str.contains(search_query)]
+            else:
+                df = df[df.title_lowercase.str.contains(search_query.lower())]
+        has_arxiv = "arXiv" in filter_names
+        has_github = "GitHub" in filter_names
+        has_hf_space = "Space" in filter_names
+        has_hf_model = "Model" in filter_names
+        has_hf_dataset = "Dataset" in filter_names
+        df = self.filter_table(df, has_arxiv, has_github, has_hf_space, has_hf_model, has_hf_dataset)
+        n_claimed = len(df[df.n_linked_authors > 0])
+        return f"{len(df)} ({n_claimed} claimed)", self.to_html(df, self.table_header)
+
+    @staticmethod
+    def filter_table(
+        df: pd.DataFrame,
+        has_arxiv: bool,
+        has_github: bool,
+        has_hf_space: bool,
+        has_hf_model: bool,
+        has_hf_dataset: bool,
+    ) -> pd.DataFrame:
+        if has_arxiv:
+            df = df[~df.arxiv.isna()]
+        if has_github:
+            df = df[~df.github.isna()]
+        if has_hf_space:
+            df = df[~df.hf_space.isna()]
+        if has_hf_model:
+            df = df[~df.hf_model.isna()]
+        if has_hf_dataset:
+            df = df[~df.hf_dataset.isna()]
+        return df
+
+    @staticmethod
+    def to_html(df: pd.DataFrame, table_header: str) -> str:
+        table_data = "".join(df.html_table_content)
+        html = f"""
+        <table>
+            {table_header}
+            {table_data}
+        </table>"""
+        return html

requirements.txt

@@ -0,0 +1 @@
+pandas==2.1.0

style.css

@@ -0,0 +1,27 @@
+h1 {
+  text-align: center;
+}
+
+table a {
+  background-color: transparent;
+  color: #58a6ff;
+  text-decoration: none;
+}
+
+a:active,
+a:hover {
+  outline-width: 0;
+}
+
+a:hover {
+  text-decoration: underline;
+}
+
+table, th, td {
+  border: 1px solid;
+}
+
+img#visitor-badge {
+  display: block;
+  margin: auto;
+}