Create app.y

app.y

@@ -0,0 +1,38 @@
+import gradio as gr
+from transformers import pipeline
+
+# Load the Hugging Face model for income prediction
+model = pipeline("text-classification", model="distilbert-base-uncased-finetuned-sst-2-english")
+
+def predict_income(features):
+    # Preprocess the input features
+    job_title = features['job_title']
+    years_of_experience = features['years_of_experience']
+    education_level = features['education_level']
+
+    # Combine the input features into a text string
+    input_text = f"Job Title: {job_title}\nYears of Experience: {years_of_experience}\nEducation Level: {education_level}"
+
+    # Use the Hugging Face model to predict the income
+    prediction = model(input_text)[0]
+
+    # Return the predicted income
+    return prediction['label']
+
+# Define the input fields for the Gradio interface
+job_title_input = gr.inputs.Textbox(label="Job Title")
+years_of_experience_input = gr.inputs.Number(label="Years of Experience")
+education_level_input = gr.inputs.Dropdown(label="Education Level", choices=["High School", "Bachelor's Degree", "Master's Degree", "PhD"])
+
+# Define the output field for the Gradio interface
+income_output = gr.outputs.Textbox(label="Predicted Income")
+
+# Create the Gradio interface
+interface = gr.Interface(fn=predict_income,
+                         inputs=[job_title_input, years_of_experience_input, education_level_input],
+                         outputs=income_output,
+                         title="Income Prediction",
+                         description="Predict income for female and male employees based on job-related features.")
+
+# Launch the Gradio interface
+interface.launch()