Update app.py

app.py

@@ -1,154 +1,53 @@
 import gradio as gr
+import pandas as pd
 import numpy as np
-import random
+from pycaret.regression import load_model, predict_model  # Change to regression if needed
 
-# import spaces #[uncomment to use ZeroGPU]
-from diffusers import DiffusionPipeline
-import torch
+# Load your dataframe
+df = pd.read_csv("data.csv")  # Replace with your actual data file
 
-device = "cuda" if torch.cuda.is_available() else "cpu"
-model_repo_id = "stabilityai/sdxl-turbo"  # Replace to the model you would like to use
+# Identify columns
+input_columns = df.columns[:-1].tolist()  # First 4 columns as input
+target_column = df.columns[-1]  # Last column as target
 
-if torch.cuda.is_available():
-    torch_dtype = torch.float16
-else:
-    torch_dtype = torch.float32
-
-pipe = DiffusionPipeline.from_pretrained(model_repo_id, torch_dtype=torch_dtype)
-pipe = pipe.to(device)
-
-MAX_SEED = np.iinfo(np.int32).max
-MAX_IMAGE_SIZE = 1024
-
-
-# @spaces.GPU #[uncomment to use ZeroGPU]
-def infer(
-    prompt,
-    negative_prompt,
-    seed,
-    randomize_seed,
-    width,
-    height,
-    guidance_scale,
-    num_inference_steps,
-    progress=gr.Progress(track_tqdm=True),
-):
-    if randomize_seed:
-        seed = random.randint(0, MAX_SEED)
-
-    generator = torch.Generator().manual_seed(seed)
-
-    image = pipe(
-        prompt=prompt,
-        negative_prompt=negative_prompt,
-        guidance_scale=guidance_scale,
-        num_inference_steps=num_inference_steps,
-        width=width,
-        height=height,
-        generator=generator,
-    ).images[0]
-
-    return image, seed
-
-
-examples = [
-    "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k",
-    "An astronaut riding a green horse",
-    "A delicious ceviche cheesecake slice",
-]
-
-css = """
-#col-container {
-    margin: 0 auto;
-    max-width: 640px;
+# Min-Max scaling per column
+min_max_dict = {
+    col: (df[col].min(), df[col].max()) for col in input_columns
 }
-"""
-
-with gr.Blocks(css=css) as demo:
-    with gr.Column(elem_id="col-container"):
-        gr.Markdown(" # Text-to-Image Gradio Template")
-
-        with gr.Row():
-            prompt = gr.Text(
-                label="Prompt",
-                show_label=False,
-                max_lines=1,
-                placeholder="Enter your prompt",
-                container=False,
-            )
-
-            run_button = gr.Button("Run", scale=0, variant="primary")
 
-        result = gr.Image(label="Result", show_label=False)
-
-        with gr.Accordion("Advanced Settings", open=False):
-            negative_prompt = gr.Text(
-                label="Negative prompt",
-                max_lines=1,
-                placeholder="Enter a negative prompt",
-                visible=False,
-            )
-
-            seed = gr.Slider(
-                label="Seed",
-                minimum=0,
-                maximum=MAX_SEED,
-                step=1,
-                value=0,
-            )
-
-            randomize_seed = gr.Checkbox(label="Randomize seed", value=True)
+# Load your PyCaret model
+model = load_model("TVAESynthesizer_best")  # Replace with your actual saved model
+
+def pycaret_predict_function(inputs):
+    # Convert input list to DataFrame
+    input_data = pd.DataFrame([inputs], columns=input_columns)
+
+    # Predict using PyCaret model
+    prediction = predict_model(model, data=input_data)
+    return prediction[target_column].values[0]
+
+# Create Gradio inputs dynamically based on scaled range
+input_components = [
+    gr.Slider(
+        minimum=min_max_dict[col][0],
+        maximum=min_max_dict[col][1],
+        step=(min_max_dict[col][1] - min_max_dict[col][0]) / 100,
+        label=col,
+    ) for col in input_columns
+]
 
-            with gr.Row():
-                width = gr.Slider(
-                    label="Width",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## 🔮 Predict the Target Variable using PyCaret Model")
 
-                height = gr.Slider(
-                    label="Height",
-                    minimum=256,
-                    maximum=MAX_IMAGE_SIZE,
-                    step=32,
-                    value=1024,  # Replace with defaults that work for your model
-                )
+    with gr.Row():
+        inputs = [component.render() for component in input_components]
 
-            with gr.Row():
-                guidance_scale = gr.Slider(
-                    label="Guidance scale",
-                    minimum=0.0,
-                    maximum=10.0,
-                    step=0.1,
-                    value=0.0,  # Replace with defaults that work for your model
-                )
+    output = gr.Textbox(label=f"Predicted: {target_column}")
 
-                num_inference_steps = gr.Slider(
-                    label="Number of inference steps",
-                    minimum=1,
-                    maximum=50,
-                    step=1,
-                    value=2,  # Replace with defaults that work for your model
-                )
+    predict_btn = gr.Button("Predict")
 
-        gr.Examples(examples=examples, inputs=[prompt])
-    gr.on(
-        triggers=[run_button.click, prompt.submit],
-        fn=infer,
-        inputs=[
-            prompt,
-            negative_prompt,
-            seed,
-            randomize_seed,
-            width,
-            height,
-            guidance_scale,
-            num_inference_steps,
-        ],
-        outputs=[result, seed],
-    )
+    predict_btn.click(fn=pycaret_predict_function, inputs=inputs, outputs=output)
 
 if __name__ == "__main__":
     demo.launch()