Update app.py

app.py

@@ -2,37 +2,37 @@ import numpy as np
 import pandas as pd
 import gradio as gr
 from sklearn.model_selection import train_test_split
-from sklearn.feature_selection import SelectKBest, f_regression
+from sklearn.feature_selection import SelectKBest, f_classif
 from sklearn.preprocessing import StandardScaler
 from sklearn.pipeline import Pipeline
-from sklearn.ensemble import RandomForestRegressor
-from sklearn.metrics import mean_squared_error, r2_score
+from sklearn.ensemble import RandomForestClassifier
+from sklearn.metrics import accuracy_score
 import joblib
 import os
 
 # ---------------------------
 # 1. Train or Load Model
 # ---------------------------
-MODEL_FILE = "turgor_model.pkl"
+MODEL_FILE = "brain_tumor_model.pkl"
 
 if not os.path.exists(MODEL_FILE):
     np.random.seed(42)
     n_samples = 500
 
+    # Simulated dataset (replace with MRI-extracted features later)
     X = pd.DataFrame({
-        "leaf_thickness": np.random.uniform(0.2, 1.0, n_samples),
-        "water_content": np.random.uniform(60, 95, n_samples),
-        "osmotic_pressure": np.random.uniform(0.5, 2.5, n_samples),
-        "temperature": np.random.uniform(15, 40, n_samples),
+        "tumor_size": np.random.uniform(1, 10, n_samples),      # cm
+        "texture_score": np.random.uniform(0, 1, n_samples),    # extracted from MRI texture
+        "age": np.random.randint(20, 80, n_samples),            # patient age
+        "contrast_intensity": np.random.uniform(50, 200, n_samples), # MRI contrast
     })
 
+    # Simulated binary labels: 1 = Tumor present, 0 = No tumor
     y = (
-        0.3 * X["leaf_thickness"]
-        + 0.5 * X["water_content"]
-        - 0.2 * X["temperature"]
-        + 0.8 * X["osmotic_pressure"]
-        + np.random.normal(0, 2, n_samples)
+        (X["tumor_size"] > 5).astype(int) |
+        (X["contrast_intensity"] > 120).astype(int)
     )
+    y = np.where(np.random.rand(n_samples) > 0.9, 1 - y, y)  # add noise
 
     X_train, X_test, y_train, y_test = train_test_split(
         X, y, test_size=0.2, random_state=42
@@ -41,16 +41,15 @@ if not os.path.exists(MODEL_FILE):
     pipeline = Pipeline(
         [
             ("scaler", StandardScaler()),
-            ("select", SelectKBest(score_func=f_regression, k=3)),  # top 3 features
-            ("regressor", RandomForestRegressor(n_estimators=100, random_state=42)),
+            ("select", SelectKBest(score_func=f_classif, k=3)),  # select best 3 features
+            ("classifier", RandomForestClassifier(n_estimators=100, random_state=42)),
         ]
     )
 
     pipeline.fit(X_train, y_train)
 
     y_pred = pipeline.predict(X_test)
-    print("MSE:", mean_squared_error(y_test, y_pred))
-    print("R2 Score:", r2_score(y_test, y_pred))
+    print("Accuracy:", accuracy_score(y_test, y_pred))
 
     joblib.dump(pipeline, MODEL_FILE)
 
@@ -60,32 +59,30 @@ model = joblib.load(MODEL_FILE)
 # ---------------------------
 # 2. Prediction Function
 # ---------------------------
-def predict_turgor(leaf_thickness, water_content, osmotic_pressure, temperature):
-    input_data = np.array(
-        [[leaf_thickness, water_content, osmotic_pressure, temperature]]
-    )
+def predict_brain_tumor(tumor_size, texture_score, age, contrast_intensity):
+    input_data = np.array([[tumor_size, texture_score, age, contrast_intensity]])
     pred = model.predict(input_data)[0]
-    return f"Predicted Turgor Pressure: {pred:.2f} units"
+    return "🧠 Tumor Detected" if pred == 1 else "✅ No Tumor Detected"
 
 # ---------------------------
 # 3. Gradio UI
 # ---------------------------
 with gr.Blocks() as demo:
-    gr.Markdown("# 🌱 Turgor Pressure Detection")
-    gr.Markdown("Predict plant turgor pressure using physiological and environmental features.")
+    gr.Markdown("# 🧠 Brain Tumor Detection")
+    gr.Markdown("Predict brain tumor presence using MRI-based features (simulated demo).")
 
     with gr.Row():
-        leaf_thickness = gr.Slider(0.2, 1.0, value=0.5, step=0.01, label="Leaf Thickness (mm)")
-        water_content = gr.Slider(60, 95, value=80, step=0.1, label="Water Content (%)")
-        osmotic_pressure = gr.Slider(0.5, 2.5, value=1.2, step=0.01, label="Osmotic Pressure (MPa)")
-        temperature = gr.Slider(15, 40, value=25, step=0.5, label="Temperature (°C)")
+        tumor_size = gr.Slider(1, 10, value=4, step=0.1, label="Tumor Size (cm)")
+        texture_score = gr.Slider(0, 1, value=0.5, step=0.01, label="Texture Score")
+        age = gr.Slider(20, 80, value=40, step=1, label="Patient Age")
+        contrast_intensity = gr.Slider(50, 200, value=100, step=1, label="MRI Contrast Intensity")
 
     output = gr.Textbox(label="Prediction")
 
     predict_btn = gr.Button("Predict")
     predict_btn.click(
-        fn=predict_turgor,
-        inputs=[leaf_thickness, water_content, osmotic_pressure, temperature],
+        fn=predict_brain_tumor,
+        inputs=[tumor_size, texture_score, age, contrast_intensity],
         outputs=output,
     )