Update app.py

app.py

@@ -3,6 +3,7 @@ import pandas as pd
 from sklearn.linear_model import LinearRegression, LogisticRegression
 from sklearn.impute import SimpleImputer
 from sklearn.preprocessing import LabelEncoder
+from sklearn.metrics import r2_score, accuracy_score
 
 # Streamlit başlığı
 st.title("Data Corrector with AI")
@@ -35,7 +36,7 @@ if train_file and test_file:
         is_null_train = train_df[train_df[column].isnull()]
 
         if is_null_train.empty:
-            return train_df, test_df
+            return train_df, test_df, None
 
         if model_type == "numeric":
             model = LinearRegression()
@@ -71,10 +72,16 @@ if train_file and test_file:
         # Tahmin edilen değerlerle eksik değerleri doldurma
         train_df.loc[train_df[column].isnull(), column] = predictions
 
+        # Model performansını değerlendirme
+        if model_type == "numeric":
+            performance = r2_score(y_train, model.predict(X_train))
+        else:
+            performance = accuracy_score(y_train, model.predict(X_train))
+
         # Aynı işlemi test verileri için yapma
         X_test = test_df[test_df[column].isnull()].drop(columns=[column])
         if X_test.empty:
-            return train_df, test_df
+            return train_df, test_df, performance
         
         X_test = pd.get_dummies(X_test, drop_first=True)
         X_test = X_test.reindex(columns=X_train.columns, fill_value=0)
@@ -86,12 +93,26 @@ if train_file and test_file:
 
         test_df.loc[test_df[column].isnull(), column] = predictions
 
-        return train_df, test_df
+        return train_df, test_df, performance
+
+    performances = []
 
     for column in numeric_columns:
-        train_df, test_df = fill_missing_values(train_df, test_df, column, "numeric")
+        train_df, test_df, performance = fill_missing_values(train_df, test_df, column, "numeric")
+        if performance is not None:
+            performances.append((column, "numeric", performance))
 
     for column in categorical_columns:
-        train_df, test_df = fill_missing_values(train_df, test_df, column, "categorical")
+        train_df, test_df, performance = fill_missing_values(train_df, test_df, column, "categorical")
+        if performance is not None:
+            performances.append((column, "categorical", performance))
 
     st.write("Test Data with Predictions", test_df)
+    
+    if performances:
+        st.write("Model Performance:")
+        for column, model_type, performance in performances:
+            if model_type == "numeric":
+                st.write(f"Column: {column}, Type: {model_type}, R^2 Score: {performance:.2f}")
+            else:
+                st.write(f"Column: {column}, Type: {model_type}, Accuracy Score: {performance:.2f}")