Algorithm 1 Train_test_evaluate

Input: X_train, X_test, y_train, y_test, models Output: Score, Modelchoice Begin Writing a function to train, test, and evaluate models: Creating the dataframe and initializing variables: acc_M = 0 Modelchoice = ”” Score = DataFrame({“Classifier”: classifiers})   j = 0 For each model in the models list              model = i              Training Phase:              Train Model (X_train, y_train)              Testing Phase:              predictions = model.predict (X_test)              Performance Evaluation:              Metrics: Accuracy, Precision, Recall, F1-score, Matthews Correlation Coefficient,              Mean Squared Error: Acc, Preci, Re_Sc, F1_S,Mcc,Mse =              Classification_report(y_test, predictions).              Saving model performance metrics:              Score[j,”Accuracy”] = Acc; Score[j,”f1_score”] = F1_S; Score[j,”recall_score”] = re_sc              Score[j,”matthews_corrcoef”] = Mcc; Score[j, “precision_score”] = Preci;              Score[j, “Mse_score”] = Mse              Identifying the best model              if acc_M < acc then                      acc_M = acc                      Modelchoice = model              End            j = j + 1       Endfor       return Score, Modelchoice End Function