requirements.txt

gradio
pandas
numpy
joblib
scikit-learn

app.py

@@ -0,0 +1,94 @@
+import gradio as gr
+import pandas as pd
+import joblib
+import numpy as np
+
+# =========================================================
+# Load trained model
+# =========================================================
+# Upload your trained model file in the same Hugging Face Space
+# Example model name: biomass_model.pkl
+
+try:
+    model = joblib.load("biomass_model.pkl")
+    model_loaded = True
+except:
+    model_loaded = False
+
+
+# =========================================================
+# Prediction Function
+# =========================================================
+def predict_composition(cellulose, hemicellulose, lignin, moisture, ash):
+
+    # Input array
+    input_data = np.array([
+        [cellulose, hemicellulose, lignin, moisture, ash]
+    ])
+
+    # If model exists
+    if model_loaded:
+        prediction = model.predict(input_data)
+
+        return {
+            "Predicted Biomass Composition": float(prediction[0])
+        }
+
+    # Dummy calculation if model not uploaded yet
+    biomass_score = (
+        0.35 * cellulose +
+        0.25 * hemicellulose +
+        0.20 * lignin -
+        0.10 * moisture -
+        0.10 * ash
+    )
+
+    return {
+        "Estimated Biomass Score": round(biomass_score, 2)
+    }
+
+
+# =========================================================
+# Gradio Interface
+# =========================================================
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+
+    gr.Markdown(
+        """
+        # Biomass Composition Finder
+
+        Enter biomass properties to estimate biomass composition.
+        """
+    )
+
+    with gr.Row():
+        cellulose = gr.Slider(0, 100, value=40, label="Cellulose (%)")
+        hemicellulose = gr.Slider(0, 100, value=25, label="Hemicellulose (%)")
+
+    with gr.Row():
+        lignin = gr.Slider(0, 100, value=20, label="Lignin (%)")
+        moisture = gr.Slider(0, 100, value=10, label="Moisture Content (%)")
+
+    ash = gr.Slider(0, 50, value=5, label="Ash Content (%)")
+
+    output = gr.JSON(label="Prediction Result")
+
+    predict_btn = gr.Button("Predict")
+
+    predict_btn.click(
+        fn=predict_composition,
+        inputs=[
+            cellulose,
+            hemicellulose,
+            lignin,
+            moisture,
+            ash
+        ],
+        outputs=output
+    )
+
+
+# =========================================================
+# Launch App
+# =========================================================
+demo.launch()