Update app.py

app.py

@@ -6,13 +6,13 @@ import matplotlib.pyplot as plt
 from sklearn.model_selection import train_test_split
 from sklearn.impute import SimpleImputer
 from sklearn.preprocessing import LabelEncoder, StandardScaler
-from sklearn.ensemble import RandomForestClassifier
-from sklearn.linear_model import LogisticRegression
-from sklearn.svm import SVC
-from sklearn.neighbors import KNeighborsClassifier
-from sklearn.tree import DecisionTreeClassifier
+from sklearn.ensemble import RandomForestClassifier, RandomForestRegressor
+from sklearn.linear_model import LogisticRegression, LinearRegression
+from sklearn.svm import SVC, SVR
+from sklearn.neighbors import KNeighborsClassifier, KNeighborsRegressor
+from sklearn.tree import DecisionTreeClassifier, DecisionTreeRegressor
 from sklearn.naive_bayes import GaussianNB
-from sklearn.metrics import accuracy_score, classification_report
+from sklearn.metrics import accuracy_score, mean_squared_error, classification_report
 from scipy import stats
 
 # File uploader
@@ -77,7 +77,7 @@ if uploaded_file is not None:
         y = df_cleaned[target]
         
         # Determine if the target is continuous or categorical
-        is_classification = len(y.unique()) <= 10  # If target has fewer than or equal to 10 unique values, treat as classification
+        is_classification = y.dtype == 'object' or len(y.unique()) <= 10  # If target is categorical or has few unique values, treat as classification
         
         # Ensure there is enough data before proceeding with train-test split
         if len(X) == 0 or len(y) == 0:
@@ -113,9 +113,27 @@ if uploaded_file is not None:
                 st.markdown(f"**Model Performance Results**")
                 st.dataframe(results_df)
             
-            # If it's not classification (i.e., regression)
+            # For Regression
             else:
-                st.warning("Regression models are not implemented in this version. Please select a classification target.")
+                model_choices = [
+                    ("Random Forest", RandomForestRegressor(n_estimators=50)),
+                    ("Linear Regression", LinearRegression()),
+                    ("SVR", SVR()),
+                    ("K-Nearest Neighbors", KNeighborsRegressor(n_neighbors=5)),
+                    ("Decision Tree", DecisionTreeRegressor()),
+                ]
+                
+                for name, model in model_choices:
+                    model.fit(X_train, y_train)
+                    y_pred = model.predict(X_test)
+                    mse = mean_squared_error(y_test, y_pred)
+                    results.append([name, mse])
+                
+                # Display results in a table
+                st.subheader("Model Performance Results")
+                results_df = pd.DataFrame(results, columns=["Model", "Mean Squared Error"])
+                st.markdown(f"**Model Performance Results**")
+                st.dataframe(results_df)
 
             # Option to download the model performance metrics (Results Table)
             st.download_button(