Spaces:
Running
Running
import pandas as pd | |
from typing import List, Dict, Optional | |
import gradio as gr | |
from datasets import load_dataset | |
import numpy as np | |
class AuthorLeaderboard: | |
""" | |
A class to manage and process author leaderboard data for display in a Gradio Dataframe component. | |
""" | |
# Class-level constants defining columns and their data types | |
COLUMNS_ORDER: List[str] = [ | |
'Rank', | |
'Author', | |
'Total Artifacts', | |
'Avg Artifacts per Paper', | |
'Total Papers', | |
'Total Models', | |
'Total Datasets', | |
'Total Spaces', | |
'Upvotes', | |
'Comments', | |
] | |
DATATYPES: Dict[str, str] = { | |
'Rank': 'str', | |
'Author': 'markdown', | |
'Total Artifacts': 'int', | |
'Avg Artifacts per Paper': 'float', | |
'Total Papers': 'int', | |
'Total Models': 'int', | |
'Total Datasets': 'int', | |
'Total Spaces': 'int', | |
'Upvotes': 'int', | |
'Comments': 'int', | |
} | |
EMOTICONS = { | |
1: '🥇', | |
2: '🥈', | |
3: '🥉' | |
} | |
def __init__(self): | |
""" | |
Initialize the AuthorLeaderboard class by loading and processing the dataset. | |
""" | |
self.df_raw: pd.DataFrame = self.get_df() | |
self.df_prettified: pd.DataFrame = self.prettify(self.df_raw) | |
def get_df() -> pd.DataFrame: | |
""" | |
Load and process the leaderboard dataset. | |
Returns: | |
pd.DataFrame: The processed DataFrame. | |
""" | |
# Load the dataset from the Hugging Face Hub | |
dataset = load_dataset('IAMJB/paper-central-leaderboard', split='train') | |
df = dataset.to_pandas() | |
# Calculate total artifacts | |
df['Total Artifacts'] = df['num_models'] + df['num_datasets'] + df['num_spaces'] | |
# Calculate average artifacts per paper | |
df['Avg Artifacts per Paper'] = df['Total Artifacts'] / df['num_papers'] | |
df['Avg Artifacts per Paper'] = df['Avg Artifacts per Paper'].round(2) | |
# Rename columns for clarity | |
df.rename(columns={ | |
'name': 'Author', | |
'num_papers': 'Total Papers', | |
'num_models': 'Total Models', | |
'num_datasets': 'Total Datasets', | |
'num_spaces': 'Total Spaces', | |
'upvotes': 'Upvotes', | |
'num_comments': 'Comments', | |
}, inplace=True) | |
return df | |
def prettify(self, df: pd.DataFrame) -> pd.DataFrame: | |
""" | |
Prettify the DataFrame by adding rankings, emoticons, and markdown links. | |
Args: | |
df (pd.DataFrame): The DataFrame to prettify. | |
Returns: | |
pd.DataFrame: The prettified DataFrame. | |
""" | |
df = df.copy() | |
# Sort authors by Total Artifacts descending | |
df.sort_values(by='Total Artifacts', ascending=False, inplace=True) | |
# Reset index to get ranks | |
df.reset_index(drop=True, inplace=True) | |
df.index += 1 # Start ranks from 1 | |
# Add Rank column | |
df['Rank'] = df.index | |
# Add emoticons for top 3 ranks | |
df['Rank'] = df['Rank'].apply(lambda x: f"{self.EMOTICONS.get(x, '')} {x}" if x <= 3 else f"{x}") | |
# Convert 'Author' to markdown with profile links if 'username' is available | |
df['Author'] = df.apply(self._create_author_link, axis=1) | |
# Select columns to display | |
df = df[self.COLUMNS_ORDER] | |
return df | |
def _create_author_link(self, row: pd.Series) -> str: | |
""" | |
Create a markdown link for the author's profile. | |
Args: | |
row (pd.Series): A row from the DataFrame. | |
Returns: | |
str: The markdown link for the author. | |
""" | |
if pd.notna(row.get('username')) and row['username']: | |
profile_url = f"https://huggingface.co/{row['username']}" | |
return f"[{row['Author']}]({profile_url})" | |
else: | |
return row['Author'] | |
def filter(self, author_search_input: Optional[str] = None) -> gr.update: | |
""" | |
Filter the DataFrame based on the author search input. | |
Args: | |
author_search_input (Optional[str]): The author name to search for. | |
Returns: | |
gr.Update: An update object for the Gradio Dataframe component. | |
""" | |
filtered_df: pd.DataFrame = self.df_prettified.copy() | |
if author_search_input: | |
search_string = author_search_input.lower() | |
filtered_df = filtered_df[filtered_df['Author'].str.lower().str.contains(search_string)] | |
# Get the corresponding data types for the columns | |
datatypes: List[str] = [self.DATATYPES.get(col, 'str') for col in filtered_df.columns] | |
return gr.update(value=filtered_df, datatype=datatypes) | |