AttributeError: 'numpy.ndarray' object has no attribute 'iloc'

Question

I am trying to combine two machine learning algorithm using stacking to achieve greater results but am failing in some of the aspects. Here's my code:

class Ensemble(threading.Thread): "Stacking with three Classification Models to improve the accuracy of Predictions" def init(self, X, Y, XT, YT, accLabel=None): threading.Thread.init(self) self.X = X self.Y = Y self.XT=XT self.YT=YT self.accLabel= accLabel

def Stacking(self,model,n_fold,train,test,y):

    folds=StratifiedKFold(n_splits=n_fold,random_state=1)
    test_pred=np.empty((test.shape[0],1),float)
    train_pred=np.empty((0,1),float)
    for train_indices,val_indices in folds.split(train,y):
        x_train,x_val=train.iloc[train_indices],train.iloc[val_indices]
        y_train,y_val=y.iloc[train_indices],y.iloc[val_indices]

        model.fit(X=x_train,y=y_train)
        train_pred=np.append(train_pred,model.predict(x_val))
        test_pred=np.append(test_pred,model.predict(test))
    return test_pred.reshape(-1,1),train_pred   

def run(self):
    X = np.zeros(self.X.shape)
    Y = np.zeros(self.Y.shape)
    XT = np.zeros(self.XT.shape)
    YT = np.zeros(self.YT.shape)
    np.copyto(X, self.X)
    np.copyto(Y, self.Y)
    np.copyto(XT, self.XT)
    np.copyto(YT, self.YT)

    model1 = tree.DecisionTreeClassifier(random_state=1)
    n_fold=4
    test_pred1 ,train_pred1=self.Stacking(model1, n_fold, X, XT, Y)
    train_pred1=pd.DataFrame(train_pred1)
    test_pred1=pd.DataFrame(test_pred1)

    model2 = KNeighborsClassifier()
    test_pred2 ,train_pred2=self.Stacking(model2, n_fold, X, XT, Y)
    train_pred2=pd.DataFrame(train_pred2)
    test_pred2=pd.DataFrame(test_pred2)

    df = pd.concat([train_pred1, train_pred2], axis=1)
    df_test = pd.concat([test_pred1, test_pred2], axis=1)
    model = LogisticRegression(random_state=1)
    model.fit(df,Y)
    sd = model.score(df_test, YT)
    acc = (sum(sd == YT) / len(YT) * 100)
    print("Accuracy of Ensemble Learning Model is : %.2f" % acc+' %')
    print('=' * 100)
    if self.accLabel: self.accLabel.set("Accuracy of Ensembelance Learning: %.2f" % (acc)+' %')

The error is in 'iloc' inside Stacking method.

I have been constantly getting the error of np.ndarray has no attribute 'iloc'. I tried to search but couldn't find any specific link though I think this has something to do with iloc belonging to np.ndarray. If someone could please help me with this!!

Answer 1

As the comments suggest, .iloc is a Pandas dataframe method.

To filter a numpy array you just need: array[indices]

In your case:

x_train,x_val=train[train_indices],train[val_indices]
y_train,y_val=y[train_indices],y[val_indices]