Update app.py

app.py

@@ -1,92 +1,62 @@
 import streamlit as st
 import numpy as np
-import pandas as pd
-from sklearn.preprocessing import StandardScaler
-from sklearn.decomposition import PCA
 import pickle
 from sklearn.linear_model import LinearRegression
-import os
+from sklearn.preprocessing import StandardScaler
+from sklearn.decomposition import PCA
 
-# 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)
+def load_data():
+    # Replace this with your actual data loading logic
+    X_train = np.random.rand(100, 5)
+    y_train = np.random.rand(100)
+    return X_train, y_train
 
-# 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
-    if X.shape[1] != 8:
-        raise ValueError("The input data should have 8 features (cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, flow).")
-
-    try:
-        # Scale the input data using the loaded scaler
-        X_scaled = scaler.transform(X)
-
-        # Apply PCA using the loaded PCA transformer
-        X_pca = pca.transform(X_scaled)
-
-        return X_pca
-    except Exception as e:
-        raise ValueError(f"Error preprocessing the data: {str(e)}")
-
-def predict_slump_app():
-    with st.expander("Concrete Mix Parameters"):
-        cement = st.number_input("Cement (kg/m^3)", min_value=0.0, step=0.1)
-        blast_furnace_slag = st.number_input("Blast Furnace Slag (kg/m^3)", min_value=0.0, step=0.1)
-        fly_ash = st.number_input("Fly Ash (kg/m^3)", min_value=0.0, step=0.1)
-        water = st.number_input("Water (kg/m^3)", min_value=0.0, step=0.1)
-        superplasticizer = st.number_input("Superplasticizer (kg/m^3)", min_value=0.0, step=0.1)
-        coarse_aggregate = st.number_input("Coarse Aggregate (kg/m^3)", min_value=0.0, step=0.1)
-        fine_aggregate = st.number_input("Fine Aggregate (kg/m^3)", min_value=0.0, step=0.1)
-        flow = st.number_input("FLOW (cm)", min_value=0.0, step=0.1)
-
-    # Prepare the input data
-    total_mix = cement + blast_furnace_slag + fly_ash + water
-    if total_mix > 1000:
-        raise ValueError("The total mix quantity should not exceed 1000 kg/m^3.")
-
-    X = np.array([[cement, blast_furnace_slag, fly_ash, water, superplasticizer, coarse_aggregate, fine_aggregate, flow]])
-
-    # Preprocess the data
-    try:
-        X_preprocessed = preprocess_data(X)
-    except ValueError as e:
-        st.error(str(e))
+def save_model_artifacts(regressor, scaler, pca):
+    with open('slump_regressor.pkl', 'wb') as f:
+        pickle.dump(regressor, f, protocol=pickle.HIGHEST_PROTOCOL)
+    with open('scaler.pkl', 'wb') as f:
+        pickle.dump(scaler, f, protocol=pickle.HIGHEST_PROTOCOL)
+    with open('pca.pkl', 'wb') as f:
+        pickle.dump(pca, f, protocol=pickle.HIGHEST_PROTOCOL)
+
+def predict_slump_app(regressor, scaler, pca):
+    st.subheader("Enter Concrete Mix Parameters")
+    cement = st.number_input("Cement (kg/m³)", min_value=0.0, step=1.0)
+    slag = st.number_input("Slag (kg/m³)", min_value=0.0, step=1.0)
+    flyash = st.number_input("Fly Ash (kg/m³)", min_value=0.0, step=1.0)
+    water = st.number_input("Water (kg/m³)", min_value=0.0, step=1.0)
+    superplasticizer = st.number_input("Superplasticizer (kg/m³)", min_value=0.0, step=0.1)
+    coarseaggregate = st.number_input("Coarse Aggregate (kg/m³)", min_value=0.0, step=1.0)
+    fineaggregate = st.number_input("Fine Aggregate (kg/m³)", min_value=0.0, step=1.0)
+
+    if st.button("Predict Slump Strength"):
+        X_new = np.array([cement, slag, flyash, water, superplasticizer, coarseaggregate, fineaggregate])
+        X_new = scaler.transform([X_new])
+        X_new = pca.transform(X_new)
+        slump_prediction = regressor.predict(X_new)[0]
+        return slump_prediction
+    else:
         return None
 
-    # Make the prediction
-    slump_prediction = regressor.predict(X_preprocessed)[0]
-
-    return slump_prediction
-
 def main():
     st.set_page_config(page_title="Concrete Slump Strength Prediction")
     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
+    except (FileNotFoundError, UnpicklingError):
+        X_train, y_train = load_data()
         regressor = LinearRegression()
-        # Train the model using the data
         regressor.fit(X_train, y_train)
         scaler = StandardScaler()
         scaler.fit(X_train)
@@ -94,7 +64,7 @@ def main():
         pca.fit(scaler.transform(X_train))
         save_model_artifacts(regressor, scaler, pca)
 
-    slump_prediction = predict_slump_app()
+    slump_prediction = predict_slump_app(regressor, scaler, pca)
     if slump_prediction is not None:
         st.subheader("Predicted Slump Strength")
         st.markdown(f"The predicted slump strength is **{slump_prediction:.2f} MPa**.")