Update app.py

app.py

@@ -4,14 +4,30 @@ import pandas as pd
 from sklearn.preprocessing import StandardScaler
 from sklearn.decomposition import PCA
 import pickle
+from sklearn.linear_model import LinearRegression
+import os
 
-# Load the trained model, scaler, and PCA
-with open('slump_regressor.pkl', 'rb') as f:
-    regressor = pickle.load(f)
-with open('scaler.pkl', 'rb') as f:
-    scaler = pickle.load(f)
-with open('pca.pkl', 'rb') as f:
-    pca = pickle.load(f)
+# Function to save the trained model, scaler, and PCA
+def save_model_artifacts(regressor, scaler, pca):
+    # Save the trained model, scaler, and PCA to pickle files
+    with open('slump_regressor.pkl', 'wb') as f:
+        pickle.dump(regressor, f)
+    with open('scaler.pkl', 'wb') as f:
+        pickle.dump(scaler, f)
+    with open('pca.pkl', 'wb') as f:
+        pickle.dump(pca, f)
+
+# Function to load the trained model, scaler, and PCA
+def load_model_artifacts():
+    # Load the trained model, scaler, and PCA
+    with open('slump_regressor.pkl', 'rb') as f:
+        regressor = pickle.load(f)
+    with open('scaler.pkl', 'rb') as f:
+        scaler = pickle.load(f)
+    with open('pca.pkl', 'rb') as f:
+        pca = pickle.load(f)
+
+    return regressor, scaler, pca
 
 def preprocess_data(X):
     # Check if the input has 8 features
@@ -64,6 +80,20 @@ def main():
     st.title("Concrete Slump Strength Prediction")
     st.write("Enter the concrete mix parameters to predict the slump.")
 
+    # Load the trained model, scaler, and PCA
+    try:
+        regressor, scaler, pca = load_model_artifacts()
+    except FileNotFoundError:
+        # Train the model, scaler, and PCA and save the artifacts
+        regressor = LinearRegression()
+        # Train the model using the data
+        regressor.fit(X_train, y_train)
+        scaler = StandardScaler()
+        scaler.fit(X_train)
+        pca = PCA(n_components=4)
+        pca.fit(scaler.transform(X_train))
+        save_model_artifacts(regressor, scaler, pca)
+
     slump_prediction = predict_slump_app()
     if slump_prediction is not None:
         st.subheader("Predicted Slump Strength")