Update app.py

app.py

@@ -44,59 +44,56 @@ def main():
     predictors = st.multiselect(
         'Select predictor variables for regression:',
         options=predictor_options,
-        default=['AveRooms']
+        default=predictor_options  # default to all predictors for MLR
     )
 
-    if not predictors:
-        st.error("Please select at least one predictor variable.")
-        return
-
-    st.write("## Scatter Plot")
-    if len(predictors) == 1:
-        fig, ax = plt.subplots()
-        ax.scatter(df[predictors[0]], df[target])
-        ax.set_xlabel(predictors[0])
-        ax.set_ylabel(target)
-        ax.set_title(f'Relationship between {predictors[0]} and {target}')
-        st.pyplot(fig)
-    else:
-        st.write("Scatter plot is only available for a single predictor.")
-
     # Splitting data for regression
     X = df[predictors]
     y = df[target]
     X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)
 
-    # Perform linear regression
-    model = LinearRegression()
-    model.fit(X_train, y_train)
-    y_pred = model.predict(X_test)
-    rmse = np.sqrt(mean_squared_error(y_test, y_pred))
-    r2 = r2_score(y_test, y_pred)
-
-    st.write(f'## Regression Analysis')
-    st.write(f'RMSE: {rmse}')
-    st.write(f'R-squared: {r2}')
-
-    # Visualizing the regression results
-    if len(predictors) == 1:
-        fig, ax = plt.subplots()
-        ax.scatter(X_train, y_train, color='blue', label='Training data')
-        ax.scatter(X_test, y_test, color='green', label='Testing data')
-        ax.plot(X_test, y_pred, color='red', linewidth=2, label='Regression line')
-        ax.set_xlabel(predictors[0])
-        ax.set_ylabel(target)
-        ax.set_title(f'Linear Regression: {predictors[0]} vs {target}')
-        ax.legend()
-        st.pyplot(fig)
-    else:
-        fig, ax = plt.subplots(figsize=(10, 6))
-        ax.scatter(y_test, y_pred, color='blue', label='Predicted vs Actual')
-        ax.plot([min(y_test), max(y_test)], [min(y_test), max(y_test)], color='red', linewidth=2, label='Ideal fit')
-        ax.set_xlabel('Actual ' + target)
-        ax.set_ylabel('Predicted ' + target)
-        ax.set_title('Multilinear Regression: Actual vs Predicted')
-        ax.legend()
+    # Perform multilinear regression
+    mlr_model = LinearRegression()
+    mlr_model.fit(X_train, y_train)
+    mlr_y_pred = mlr_model.predict(X_test)
+    mlr_rmse = np.sqrt(mean_squared_error(y_test, mlr_y_pred))
+    mlr_r2 = r2_score(y_test, mlr_y_pred)
+
+    # Perform simple linear regression using only one predictor if possible
+    if 'AveRooms' in predictors:
+        slr_model = LinearRegression()
+        slr_X_train = X_train[['AveRooms']]
+        slr_X_test = X_test[['AveRooms']]
+        slr_model.fit(slr_X_train, y_train)
+        slr_y_pred = slr_model.predict(slr_X_test)
+        slr_rmse = np.sqrt(mean_squared_error(y_test, slr_y_pred))
+        slr_r2 = r2_score(y_test, slr_y_pred)
+
+        # Display RMSE and R-squared comparisons
+        st.write("## Regression Performance Comparison")
+        st.write(f"### Multilinear Regression (using all selected predictors)")
+        st.write(f'RMSE: {mlr_rmse}')
+        st.write(f'R-squared: {mlr_r2}')
+        
+        st.write(f"### Simple Linear Regression (using 'AveRooms')")
+        st.write(f'RMSE: {slr_rmse}')
+        st.write(f'R-squared: {slr_r2}')
+
+        # Plotting both regressions
+        fig, ax = plt.subplots(1, 2, figsize=(15, 6))
+        
+        ax[0].scatter(y_test, mlr_y_pred, color='blue')
+        ax[0].plot(y_test, y_test, color='red')
+        ax[0].set_title('Multilinear Regression: Actual vs Predicted')
+        ax[0].set_xlabel('Actual Values')
+        ax[0].set_ylabel('Predicted Values')
+        
+        ax[1].scatter(y_test, slr_y_pred, color='green')
+        ax[1].plot(y_test, y_test, color='red')
+        ax[1].set_title("Simple Linear Regression ('AveRooms'): Actual vs Predicted")
+        ax[1].set_xlabel('Actual Values')
+        ax[1].set_ylabel('Predicted Values')
+        
         st.pyplot(fig)
 
 if __name__ == "__main__":
@@ -105,3 +102,4 @@ if __name__ == "__main__":
 
 
 
+