Upload model_train.py

model_train.py

@@ -0,0 +1,47 @@
+import pandas as pd
+import numpy as np
+import tensorflow as tf
+from sklearn.model_selection import train_test_split
+from sklearn.preprocessing import StandardScaler
+import joblib
+
+# 1. Data Acquisition (Using the standard insurance dataset)
+url = "https://raw.githubusercontent.com/stedy/Machine-Learning-with-R-datasets/master/insurance.csv"
+df = pd.read_csv(url)
+
+# 2. Preparation: Encoding Categorical Data
+df['sex'] = df['sex'].map({'female': 0, 'male': 1})
+df['smoker'] = df['smoker'].map({'no': 0, 'yes': 1})
+# One-hot encode the 'region' column
+df = pd.get_dummies(df, columns=['region'])
+
+# 3. Splitting Features and Target
+X = df.drop('charges', axis=1)
+y = df['charges']
+
+X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
+
+# 4. Feature Scaling
+scaler = StandardScaler()
+X_train_scaled = scaler.fit_transform(X_train)
+X_test_scaled = scaler.transform(X_test)
+
+# Save the scaler for use in the app
+joblib.dump(scaler, 'scaler.pkl')
+
+# 5. Model Building (ANN Architecture)
+model = tf.keras.Sequential([
+    tf.keras.layers.Dense(128, activation='relu', input_shape=(X_train_scaled.shape[1],)),
+    tf.keras.layers.Dropout(0.2),
+    tf.keras.layers.Dense(64, activation='relu'),
+    tf.keras.layers.Dense(32, activation='relu'),
+    tf.keras.layers.Dense(1) # Regression output
+])
+
+# 6. Compilation & Training
+model.compile(optimizer='adam', loss='mae', metrics=['mse'])
+model.fit(X_train_scaled, y_train, epochs=150, batch_size=32, validation_split=0.1, verbose=1)
+
+# 7. Save the Model
+model.save('insurance_model.h5')
+print("Model and Scaler saved successfully!")