Add 1000 db

app.py

@@ -9,6 +9,12 @@ from scripts.gender_distribution import *
 
 methodologies = json.load(open("config/methodologies.json", "r"))
 
+datasets = [
+    os.path.join(os.path.dirname(__file__), "data", f)
+    for f in os.listdir(os.path.join(os.path.dirname(__file__), "data"))
+    if f.endswith(".csv")
+]
+
 MAX_THRESHOLD = 5000
 DATASET_CACHE = {}
 
@@ -16,7 +22,7 @@ DATASET_CACHE = {}
 def evaluate(dataset, sampling_method, sampling_size, column, methodology):
     try:
         print(
-            f"[{dataset.name.split('/')[-1]}::{column}] - {sampling_method} {sampling_size} entries"
+            f"[{dataset.name.split('/')[-1]}::{column}] - {sampling_method} {sampling_size} entries using {methodology}"
         )
         data = DATASET_CACHE.setdefault(dataset.name, pd.read_csv(dataset.name))[
             [column]
@@ -125,16 +131,12 @@ with BiasAware:
     )
 
     with gr.Row():
-        with gr.Column(scale=2):
+        with gr.Column(scale=1):
             gr.Markdown("## Dataset")
 
             dataset_file = gr.File(label="Dataset", file_types=["csv"])
             dataset_examples = gr.Examples(
-                [
-                    os.path.join(os.path.dirname(__file__), "data/imdb_100.csv"),
-                    os.path.join(os.path.dirname(__file__), "data/z_employee.csv"),
-                    os.path.join(os.path.dirname(__file__), "data/z_sentences.csv"),
-                ],
+                examples=datasets,
                 inputs=dataset_file,
                 label="Example Datasets",
             )
@@ -147,7 +149,7 @@ with BiasAware:
                 row_count=(5, "fixed"), col_count=(1, "fixed"), visible=False
             )
 
-        with gr.Column(scale=2):
+        with gr.Column(scale=1):
             gr.Markdown("## Methodology")
 
             methodology = gr.Radio(
@@ -160,7 +162,7 @@ with BiasAware:
 
             methodology_metadata = gr.Markdown(visible=False)
 
-        with gr.Column(scale=4):
+        with gr.Column(scale=2):
             result = gr.Markdown("## Result")
 
             result_plot = gr.Plot(show_label=False, container=False, visible=False)

data/z_employee.csv

@@ -1,26 +0,0 @@
-EmployeeID,FirstName,LastName,Email,Department,Salary
-101,John,Smith,john.smith@example.com,Finance,60000
-102,Emily,Johnson,emily.johnson@example.com,Marketing,55000
-103,Michael,Williams,michael.williams@example.com,HR,50000
-104,Susan,Anderson,susan.anderson@example.com,IT,65000
-105,David,Martin,david.martin@example.com,Sales,58000
-106,Linda,Davis,linda.davis@example.com,Finance,62000
-107,William,Miller,william.miller@example.com,Marketing,56000
-108,Sarah,Anderson,sarah.anderson@example.com,HR,51000
-109,Robert,Clark,robert.clark@example.com,IT,67000
-110,Karen,Wilson,karen.wilson@example.com,Sales,59000
-111,James,Brown,james.brown@example.com,Finance,61000
-112,Anna,Johnson,anna.johnson@example.com,Marketing,57000
-113,Christopher,Moore,christopher.moore@example.com,HR,52000
-114,Laura,White,laura.white@example.com,IT,68000
-115,Mark,Davis,mark.davis@example.com,Sales,60000
-116,Patricia,Jones,patricia.jones@example.com,Finance,63000
-117,Matthew,Taylor,matthew.taylor@example.com,Marketing,58000
-118,Jennifer,Young,jennifer.young@example.com,HR,53000
-119,Steven,Anderson,steven.anderson@example.com,IT,69000
-120,Elizabeth,Thomas,elizabeth.thomas@example.com,Sales,61000
-121,Kevin,Harris,kevin.harris@example.com,Finance,64000
-122,Deborah,Smith,deborah.smith@example.com,Marketing,59000
-123,Joseph,Walker,joseph.walker@example.com,HR,54000
-124,Cynthia,Jackson,cynthia.jackson@example.com,IT,70000
-125,Daniel,Hall,daniel.hall@example.com,Sales,62000

data/z_sentences.csv

@@ -1,11 +0,0 @@
-ID,Sentences,Gender Bias Test
-1,The doctor examined the patient.,Neutral
-2,The teacher helped the student with their homework.,Neutral
-3,The engineer designed the new software.,Neutral
-4,The nurse cared for the sick child.,Neutral
-5,The chef prepared a delicious meal.,Neutral
-6,The firefighter bravely rescued people from the burning building.,Neutral
-7,The police officer maintained law and order in the city.,Neutral
-8,The scientist conducted groundbreaking research.,Neutral
-9,The artist created a beautiful masterpiece.,Neutral
-10,The CEO made important decisions for the company.,Neutral