如何逆转模型预测的一个热编码值

Question

我使用pandas傻瓜将类标签转换为一个热编码变量，并做出了模型预测。预测采用一种​​热编码形式，如何将预测转换为正常的类向量

    import numpy as np
    import pandas as pd
    from sklearn.model_selection import train_test_split
    import keras
    from keras import Sequential
    from keras.layers import Dense


    df = pd.read_csv('./datasets/train.csv', header=0)
    data = pd.read_csv('./datasets/test.csv', header=0)

    """
    ==============================================
    preparing the training set
    ==============================================
    """

    df = df.drop(['ID_code'], axis=1)
    data_labels = data['ID_code']
    data = data.drop(['ID_code'], axis=1)

    """
    ==============================================
    preparing the test set
    ==============================================
    """

    y = df['target'].values
    y = pd.get_dummies(y) # oneHotEncode y
    X = np.delete(df.values, 0, axis=1)

    data = data.values

    X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)

    model = Sequential()
    model.add(Dense(units=1000, activation='relu', input_dim=200))
    model.add(Dense(units=500, activation='relu'))
    model.add(Dense(units=200, activation='relu'))
    model.add(Dense(units=2, activation='softmax'))

    model.compile(
        loss="categorical_crossentropy",
        optimizer=keras.optimizers.Adam(lr=0.001),
        metrics=['accuracy']
    )
    n_epochs = 5

    history = model.fit(X_train, y_train, epochs=n_epochs, batch_size=1000, validation_data=(X_test, y_test))

    # now to predict the classes of the output
    predictions = model.predict(data)

我如何获得将预测更改回y的原始形式的信息。