|
import gradio as gr |
|
import pandas as pd |
|
|
|
data = [ |
|
["Category", "Value", "Percentage"], |
|
["Total Reviews", 50000, None], |
|
["Total Sentences", 621647, None], |
|
["Pronouns in Sentences", None, None], |
|
["Male Pronouns", 85615, None], |
|
["Female Pronouns", 39372, None], |
|
["Both Male and Female Pronouns", 7765, None], |
|
["Exclusive Usage of Pronouns", None, None], |
|
["Only Male Pronouns", 77860, 13.77], |
|
["Only Female Pronouns", 31617, 6.33], |
|
["Pronouns and Professions in Sentences", None, None], |
|
["Male Pronouns with Professions", 5580, 0.9], |
|
["Female Pronouns with Professions", 2618, 0.42], |
|
["Exclusive Usage of Pronouns with Professions", None, None], |
|
["Only Male Pronouns with Professions", 5011, 0.81], |
|
["Only Female Pronouns with Professions", 2049, 0.33], |
|
["Pronouns and Professions in Combination", None, None], |
|
["Male or Female Pronouns with Professions", 7629, 1.23], |
|
["Male and Female Pronouns with Professions", 569, 0.09] |
|
] |
|
|
|
|
|
def display_methodology(methodology): |
|
title = methodology |
|
description = "" |
|
details = "" |
|
if methodology == "Term Identity Diversity Analysis": |
|
description = "111" |
|
details = "222" |
|
elif methodology == "Textual Gender Label Evaluation": |
|
description = "333" |
|
details = "444" |
|
elif methodology == "GenBit": |
|
description = "555" |
|
details = "666" |
|
|
|
return title, description, details |
|
|
|
|
|
def run_evaluation(dataset, methodology): |
|
return f"Running evaluation for {dataset} with {methodology}" |
|
|
|
if methodology == "A": |
|
run_a(dataset) |
|
elif methodology == "B": |
|
run_b(dataset) |
|
elif methodology == "C": |
|
run_c(dataset) |
|
|
|
|
|
demo = gr.Blocks(title="BiasAware: Dataset Bias Detection", |
|
theme=gr.themes.Soft()) |
|
|
|
with demo: |
|
gr.Markdown("# BiasAware: Dataset Bias Detection") |
|
gr.Markdown( |
|
"Natural Language Processing (NLP) training datasets often reflect the biases present in the data sources they are compiled from, leading to the **perpetuation of stereotypes, underrepresentation, and skewed perspectives in AI models**. BiasAware is designed to **identify and quantify biases present in text data**, making it an invaluable resource for data scientists, machine learning practitioners, and organizations committed to **mitigating bias in AI systems**." |
|
) |
|
|
|
with gr.Row(): |
|
with gr.Column(scale=1): |
|
gr.Markdown("Select a dataset to analyze") |
|
|
|
dataset = gr.Text(label="Dataset") |
|
gr.Examples( |
|
examples=["imdb", "amazon_reviews_multi", "tweet_eval"], |
|
fn=run_evaluation, |
|
inputs=[dataset], |
|
) |
|
|
|
methodology = gr.Radio( |
|
[ |
|
"Term Identity Diversity Analysis", |
|
"Textual Gender Label Evaluation", |
|
"GenBit", |
|
], |
|
label="Methodology", |
|
) |
|
|
|
button = gr.Button("Run Evaluation") |
|
|
|
with gr.Column(scale=4): |
|
gr.Markdown("### Results") |
|
|
|
with gr.Box(): |
|
methodology_title = gr.Markdown("### Title") |
|
methodology_description = gr.Markdown("lorem ipsum") |
|
|
|
methodology_details = gr.Markdown("lorem ipsum") |
|
|
|
outputs = gr.DataFrame(pd.DataFrame(data), headers=[ |
|
"", "Count", "Percentage"]) |
|
|
|
gr.Error("No results to display") |
|
|
|
with gr.Column(scale=1): |
|
gr.Markdown("### Leaderboard") |
|
gr.DataFrame( |
|
headers=["Dataset", "Score"], |
|
value=[ |
|
["imdb", 0.9], |
|
["amazon_reviews_multi", 0.8], |
|
["tweet_eval", 0.7], |
|
], |
|
interactive=False, |
|
) |
|
|
|
methodology.change( |
|
fn=display_methodology, |
|
inputs=[methodology], |
|
outputs=[ |
|
methodology_title, |
|
methodology_description, |
|
methodology_details, |
|
], |
|
) |
|
|
|
button.click(fn=run_evaluation, inputs=[ |
|
dataset, methodology], outputs=[outputs]) |
|
|
|
demo.launch() |
|
|
