Duplicate from ICML2022/ICML2022_papers

Co-authored-by: hysts <hysts@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,28 @@
+*.csv filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.pre-commit-config.yaml

@@ -0,0 +1,35 @@
+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: 5.10.1
+  hooks:
+    - id: isort
+- repo: https://github.com/pre-commit/mirrors-mypy
+  rev: v0.812
+  hooks:
+    - id: mypy
+      args: ['--ignore-missing-imports']
+- repo: https://github.com/google/yapf
+  rev: v0.32.0
+  hooks:
+  - id: yapf
+    args: ['--parallel', '--in-place']

.style.yapf

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

README.md

@@ -0,0 +1,13 @@
+---
+title: ICML2022 Papers
+emoji: 🦀
+colorFrom: green
+colorTo: gray
+sdk: gradio
+sdk_version: 3.0.24
+app_file: app.py
+pinned: true
+duplicated_from: ICML2022/ICML2022_papers
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,70 @@
+#!/usr/bin/env python
+
+from __future__ import annotations
+
+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" />'
+
+
+def main():
+    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',
+            '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)
+
+
+if __name__ == '__main__':
+    main()

paper_list.py

@@ -0,0 +1,122 @@
+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.table = pd.read_csv('papers.csv')
+        self._preprcess_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>
+            </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)
+        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>'
+            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_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 ''
+            row = f'''
+                <tr>
+                    <td>{paper}</td>
+                    <td>{row.authors}</td>
+                    <td>{pdf}</td>
+                    <td>{arxiv}</td>
+                    <td>{github}</td>
+                    <td>{hf_space}</td>
+                    <td>{hf_model}</td>
+                    <td>{hf_dataset}</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[int, str]:
+        df = self.add_spaces_to_table(self.organization_name, 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 = 'HF Space' in filter_names
+        has_hf_model = 'HF Model' in filter_names
+        has_hf_dataset = 'HF Dataset' in filter_names
+        df = self.filter_table(df, has_arxiv, has_github, has_hf_space,
+                               has_hf_model, has_hf_dataset)
+        return len(df), 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

papers.csv

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ddf0077cfd7ce2b23ad1813e47fc3f3efcdeefb25d50447d51da9e3bdea6e3f4
+size 335527

style.css

@@ -0,0 +1,22 @@
+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;
+}