Update app.py

app.py

@@ -352,10 +352,12 @@ def calculate_topsis_score(df):
 
 #--------------------------------------------------- Nested Cross validation---------------------------------------------------------------------------
 
-def NestedKFoldCrossValidation(training_data, training_additive, testing_data, testing_additive, 
-                                training_dominance, testing_dominance, epochs,learning_rate,min_child_weight, batch_size=64,
-                                outer_n_splits=2, inner_n_splits=2, output_file='cross_validation_results.csv',
-                                predicted_phenotype_file='predicted_phenotype.csv', feature_selection=True):
+def NestedKFoldCrossValidation(
+    training_data, training_additive, testing_data, testing_additive, 
+    training_dominance, testing_dominance, epochs, learning_rate, min_child_weight, 
+    batch_size=64, outer_n_splits=2, output_file='cross_validation_results.csv', 
+    predicted_phenotype_file='predicted_phenotype.csv', feature_selection=True
+):
 
     if 'phenotypes' not in training_data.columns:
         raise ValueError("Training data does not contain the 'phenotypes' column.")
@@ -379,7 +381,7 @@ def NestedKFoldCrossValidation(training_data, training_additive, testing_data, t
 
     # Feature selection
     if feature_selection:
-        rf = RandomForestRegressor(n_estimators=100, random_state=42)
+        rf = RandomForestRegressor(n_estimators=100, random_state=65)
         rf.fit(training_genotypic_data_merged, phenotypic_info)
         selector = SelectFromModel(rf, threshold="mean", prefit=True)
         training_genotypic_data_merged = selector.transform(training_genotypic_data_merged)
@@ -424,8 +426,7 @@ def NestedKFoldCrossValidation(training_data, training_additive, testing_data, t
             elif model_name in ['RFModel']:
                 predicted_train, predicted_test, history = model_func(outer_trainX, outer_trainy, outer_testX, outer_testy)
             else:
-                predicted_train, predicted_test, history = model_func(outer_trainX, outer_trainy, outer_testX, outer_testy,learning_rate,min_child_weight)
-                
+                predicted_train, predicted_test, history = model_func(outer_trainX, outer_trainy, outer_testX, outer_testy, learning_rate, min_child_weight)
 
             # Calculate metrics
             mse_train, rmse_train, r2_train, corr_train = calculate_metrics(outer_trainy, predicted_train)
@@ -454,8 +455,6 @@ def NestedKFoldCrossValidation(training_data, training_additive, testing_data, t
 
     # Compile results
     results_df = pd.DataFrame(results)
-
-    # Calculate the average metrics for each model
     avg_results_df = results_df.groupby('Model').agg({
         'Train_MSE': 'mean',
         'Train_RMSE': 'mean',
@@ -500,6 +499,17 @@ def NestedKFoldCrossValidation(training_data, training_additive, testing_data, t
 
     return avg_results_df, predicted_all_df if all_predicted_phenotypes else None
 
+
+    # Save the results to the file
+    #results_df.to_csv(output_file, index=False)
+
+    # Save predicted phenotypes
+    #if all_predicted_phenotypes:
+       # predicted_all_df = pd.concat(all_predicted_phenotypes, axis=0, ignore_index=True)
+        #predicted_all_df.to_csv(predicted_phenotype_file, index=False)
+
+   # return results_df, predicted_all_df if all_predicted_phenotypes else None
+
 #--------------------------------------------------------------------Gradio interface---------------------------------------------------------------
 
 def run_cross_validation(training_file, training_additive_file, testing_file, testing_additive_file,