Update

.pre-commit-config.yaml

@@ -1,36 +1,60 @@
 repos:
-- repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.2.0
-  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: double-quote-string-fixer
-  - 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: v1.4
-  hooks:
-  - id: docformatter
-    args: ['--in-place']
-- repo: https://github.com/pycqa/isort
-  rev: 5.12.0
-  hooks:
-    - id: isort
-- repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v0.991
-  hooks:
-    - id: mypy
-      args: ['--ignore-missing-imports']
-      additional_dependencies: ['types-python-slugify']
-- repo: https://github.com/google/yapf
-  rev: v0.32.0
-  hooks:
-  - id: yapf
-    args: ['--parallel', '--in-place']
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.6.0
+    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: 5.13.2
+    hooks:
+      - id: isort
+        args: ["--profile", "black"]
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.10.0
+    hooks:
+      - id: mypy
+        args: ["--ignore-missing-imports"]
+        additional_dependencies:
+          [
+            "types-python-slugify",
+            "types-requests",
+            "types-PyYAML",
+            "types-pytz",
+          ]
+  - repo: https://github.com/psf/black
+    rev: 24.4.2
+    hooks:
+      - id: black
+        language_version: python3.10
+        args: ["--line-length", "119"]
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.7.1
+    hooks:
+      - id: nbstripout
+        args:
+          [
+            "--extra-keys",
+            "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
+          ]
+  - repo: https://github.com/nbQA-dev/nbQA
+    rev: 1.8.5
+    hooks:
+      - id: nbqa-black
+      - id: nbqa-pyupgrade
+        args: ["--py37-plus"]
+      - id: nbqa-isort
+        args: ["--float-to-top"]

.style.yapf

@@ -1,5 +0,0 @@
-[style]
-based_on_style = pep8
-blank_line_before_nested_class_or_def = false
-spaces_before_comment = 2
-split_before_logical_operator = true

README.md

@@ -4,7 +4,7 @@ emoji: 🦀
 colorFrom: green
 colorTo: gray
 sdk: gradio
-sdk_version: 3.39.0
+sdk_version: 4.36.1
 app_file: app.py
 pinned: true
 duplicated_from: ICML2022/ICML2022_papers

app.py

@@ -6,30 +6,30 @@ import gradio as gr
 
 from paper_list import PaperList
 
-DESCRIPTION = '# ICML 2023 Papers'
+DESCRIPTION = "# ICML 2023 Papers"
 
 paper_list = PaperList()
 
-with gr.Blocks(css='style.css') as demo:
+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'
+        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')
+    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')
+    number_of_papers = gr.Textbox(label="Number of Papers Found")
     table = gr.HTML(show_label=False)
 
     demo.load(

paper_list.py

@@ -6,11 +6,11 @@ import pandas as pd
 
 class PaperList:
     def __init__(self):
-        self.organization_name = 'ICML2023'
-        self.table = pd.read_csv('papers.csv')
+        self.organization_name = "ICML2023"
+        self.table = pd.read_csv("papers.csv")
         self._preprocess_table()
 
-        self.table_header = '''
+        self.table_header = """
             <tr>
                 <td width="38%">Title</td>
                 <td width="25%">Authors</td>
@@ -21,33 +21,29 @@ class PaperList:
                 <td width="5%">Models</td>
                 <td width="5%">Datasets</td>
                 <td width="5%">Claimed</td>
-            </tr>'''
+            </tr>"""
 
     def _preprocess_table(self) -> None:
-        self.table['title_lowercase'] = self.table.title.str.lower()
+        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'''
+            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>
@@ -58,33 +54,35 @@ class PaperList:
                     <td>{hf_model}</td>
                     <td>{hf_dataset}</td>
                     <td>{claimed_paper}</td>
-                </tr>'''
+                </tr>"""
             rows.append(row)
-        self.table['html_table_content'] = rows
+        self.table["html_table_content"] = rows
 
-    def render(self, search_query: str, case_sensitive: bool,
-               filter_names: list[str]) -> tuple[str, str]:
+    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)
+        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)
+        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:
+    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:
@@ -99,10 +97,10 @@ class PaperList:
 
     @staticmethod
     def to_html(df: pd.DataFrame, table_header: str) -> str:
-        table_data = ''.join(df.html_table_content)
-        html = f'''
+        table_data = "".join(df.html_table_content)
+        html = f"""
         <table>
             {table_header}
             {table_data}
-        </table>'''
+        </table>"""
         return html

requirements.txt

@@ -1 +1 @@
-pandas==2.0.3
+pandas==2.2.2

style.css

@@ -1,5 +1,6 @@
 h1 {
   text-align: center;
+  display: block;
 }
 table a {
   background-color: transparent;
@@ -16,7 +17,3 @@ a:hover {
 table, th, td {
   border: 1px solid;
 }
-img#visitor-badge {
-  display: block;
-  margin: auto;
-}