Update to ICML 2023

.pre-commit-config.yaml

@@ -20,14 +20,15 @@ repos:
   - id: docformatter
     args: ['--in-place']
 - repo: https://github.com/pycqa/isort
-  rev: 5.10.1
+  rev: 5.12.0
   hooks:
     - id: isort
 - repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v0.812
+  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:

.vscode/settings.json

@@ -0,0 +1,18 @@
+{
+    "python.linting.enabled": true,
+    "python.linting.flake8Enabled": true,
+    "python.linting.pylintEnabled": false,
+    "python.linting.lintOnSave": true,
+    "python.formatting.provider": "yapf",
+    "python.formatting.yapfArgs": [
+        "--style={based_on_style: pep8, indent_width: 4, blank_line_before_nested_class_or_def: false, spaces_before_comment: 2, split_before_logical_operator: true}"
+    ],
+    "[python]": {
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "source.organizeImports": true
+        }
+    },
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": true
+}

README.md

@@ -1,10 +1,10 @@
 ---
-title: ICML2022 Papers
+title: ICML2023 Papers
 emoji: 🦀
 colorFrom: green
 colorTo: gray
 sdk: gradio
-sdk_version: 3.0.24
+sdk_version: 3.34.0
 app_file: app.py
 pinned: true
 duplicated_from: ICML2022/ICML2022_papers

app.py

@@ -6,65 +6,67 @@ import gradio as gr
 
 from paper_list import PaperList
 
-DESCRIPTION = '# ICML 2022 Papers'
-NOTES = '''
-- [ICML 2022](https://icml.cc/Conferences/2022/)
-- [Proceedings](https://proceedings.mlr.press/v162/)
-'''
-FOOTER = '<img id="visitor-badge" alt="visitor badge" src="https://visitor-badge.glitch.me/badge?page_id=hysts.icml2022_papers" />'
+DESCRIPTION = '# ICML 2023 Papers'
 
+paper_list = PaperList()
 
-def main():
-    paper_list = PaperList()
+with gr.Blocks(css='style.css') as demo:
+    gr.Markdown(DESCRIPTION)
 
-    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')
 
-        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',
-            'HF Space',
-            'HF Model',
-            'HF Dataset',
-        ],
-                                        label='Filter')
-        search_button = gr.Button('Search')
-
-        number_of_papers = gr.Textbox(label='Number of Papers Found')
-        table = gr.HTML(show_label=False)
-
-        gr.Markdown(NOTES)
-        gr.Markdown(FOOTER)
-
-        demo.load(paper_list.render,
-                  inputs=[
-                      search_box,
-                      case_sensitive,
-                      filter_names,
-                  ],
-                  outputs=[
-                      number_of_papers,
-                      table,
-                  ])
-        search_button.click(paper_list.render,
-                            inputs=[
-                                search_box,
-                                case_sensitive,
-                                filter_names,
-                            ],
-                            outputs=[
-                                number_of_papers,
-                                table,
-                            ])
-
-    demo.launch(enable_queue=True, share=False)
+    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,
+        ],
+    )
 
-if __name__ == '__main__':
-    main()
+    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

@@ -1,59 +1,31 @@
 from __future__ import annotations
 
-import numpy as np
 import pandas as pd
-import requests
-from huggingface_hub.hf_api import SpaceInfo
 
 
 class PaperList:
     def __init__(self):
-        self.organization_name = 'ICML2022'
+        self.organization_name = 'ICML2023'
         self.table = pd.read_csv('papers.csv')
-        self._preprcess_table()
+        self._preprocess_table()
 
         self.table_header = '''
             <tr>
-                <td width="50%">Paper</td>
-                <td width="26%">Authors</td>
-                <td width="4%">pdf</td>
-                <td width="4%">arXiv</td>
-                <td width="4%">GitHub</td>
-                <td width="4%">HF Spaces</td>
-                <td width="4%">HF Models</td>
-                <td width="4%">HF Datasets</td>
+                <td width="40%">Paper</td>
+                <td width="30%">Authors</td>
+                <td width="6%">arXiv</td>
+                <td width="6%">GitHub</td>
+                <td width="6%">Spaces</td>
+                <td width="6%">Models</td>
+                <td width="6%">Datasets</td>
             </tr>'''
 
-    @staticmethod
-    def load_space_info(author: str) -> list[SpaceInfo]:
-        path = 'https://huggingface.co/api/spaces'
-        r = requests.get(path, params={'author': author})
-        d = r.json()
-        return [SpaceInfo(**x) for x in d]
-
-    def add_spaces_to_table(self, organization_name: str,
-                            df: pd.DataFrame) -> pd.DataFrame:
-        spaces = self.load_space_info(organization_name)
-        name2space = {
-            s.id.split('/')[1].lower(): f'https://huggingface.co/spaces/{s.id}'
-            for s in spaces
-        }
-        df['hf_space'] = df.loc[:, ['hf_space', 'github']].apply(
-            lambda x: x[0] if isinstance(x[0], str) else name2space.get(
-                x[1].split('/')[-1].lower()
-                if isinstance(x[1], str) else '', np.nan),
-            axis=1)
-        return df
-
-    def _preprcess_table(self) -> None:
-        self.table = self.add_spaces_to_table(self.organization_name,
-                                              self.table)
+    def _preprocess_table(self) -> None:
         self.table['title_lowercase'] = self.table.title.str.lower()
 
         rows = []
         for row in self.table.itertuples():
-            paper = f'<a href="{row.url}" target="_blank">{row.title}</a>'
-            pdf = f'<a href="{row.pdf}" target="_blank">pdf</a>'
+            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(
@@ -66,9 +38,8 @@ class PaperList:
                 row.hf_dataset, str) else ''
             row = f'''
                 <tr>
-                    <td>{paper}</td>
+                    <td>{title}</td>
                     <td>{row.authors}</td>
-                    <td>{pdf}</td>
                     <td>{arxiv}</td>
                     <td>{github}</td>
                     <td>{hf_space}</td>
@@ -80,7 +51,7 @@ class PaperList:
 
     def render(self, search_query: str, case_sensitive: bool,
                filter_names: list[str]) -> tuple[int, str]:
-        df = self.add_spaces_to_table(self.organization_name, self.table)
+        df = self.table
         if search_query:
             if case_sensitive:
                 df = df[df.title.str.contains(search_query)]

papers.csv

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ddf0077cfd7ce2b23ad1813e47fc3f3efcdeefb25d50447d51da9e3bdea6e3f4
-size 335527
+oid sha256:b585cf6312b7e58c0801a3a00d83e4dcde09bc99618b5bbd6e73d02e724118f9
+size 301993

requirements.txt

@@ -0,0 +1 @@
+pandas==2.0.2