AttributeError：“numpy.ndarray”对象没有属性“transform”

Question

我想创建一个包含两个步骤的sklearn 管道：

1. 自定义转换器功能
2. Keras 分类模型

这是我的数据集（当然，我提供了一个简化的子集来显示数据格式）：

x_train

array([[[0.45977011, 0.16666667, 0.18373494, ..., 0.33333333,
         0.71317829, 0.7246617 ],
        [0.6091954 , 0.25      , 0.28313253, ..., 0.33333333,
         0.66666667, 0.73101353],
        [0.25287356, 0.75      , 0.34337349, ..., 0.16666667,
         0.62790698, 0.62137531],
        ...,
        [0.6091954 , 0.58333333, 0.20481928, ..., 0.33333333,
         0.62015504, 0.65009666],
        [0.41954023, 0.91666667, 0.30722892, ..., 0.33333333,
         0.71317829, 0.76719138],
        [0.31609195, 0.41666667, 0.46987952, ..., 0.33333333,
         0.5503876 , 0.71306269]],

       [[0.6091954 , 0.25      , 0.28313253, ..., 0.33333333,
         0.66666667, 0.73101353],
        [0.25287356, 0.75      , 0.34337349, ..., 0.16666667,
         0.62790698, 0.62137531],
        [0.54022989, 0.5       , 0.34337349, ..., 0.33333333,
         0.57364341, 0.66238608],
        ...,
        [0.41954023, 0.91666667, 0.30722892, ..., 0.33333333,
         0.71317829, 0.76719138],
        [0.31609195, 0.41666667, 0.46987952, ..., 0.33333333,
         0.5503876 , 0.71306269],
        [0.44252874, 0.75      , 0.48192771, ..., 0.41666667,
         0.62015504, 0.65023474]],

       [[0.25287356, 0.75      , 0.34337349, ..., 0.16666667,
         0.62790698, 0.62137531],
        [0.54022989, 0.5       , 0.34337349, ..., 0.33333333,
         0.57364341, 0.66238608],
        [0.3908046 , 0.33333333, 0.34939759, ..., 0.41666667,
         0.58914729, 0.70450152],
        ...,
        [0.31609195, 0.41666667, 0.46987952, ..., 0.33333333,
         0.5503876 , 0.71306269],
        [0.44252874, 0.75      , 0.48192771, ..., 0.41666667,
         0.62015504, 0.65023474],
        [0.60344828, 0.41666667, 0.46686747, ..., 0.25      ,
         0.66666667, 0.61391881]]]

y_train

array([[1., 0., 0.],
       [1., 0., 0.],
       [1., 0., 0.]], dtype=float32)

这是我当前的代码：

import numpy as np
from keras.wrappers.scikit_learn import KerasClassifier
import tensorflow as tf
from tensorflow.keras.models import *
from tensorflow.keras.layers import *
from tensorflow.keras.optimizers import *
from tensorflow.keras.utils import *
from tensorflow.keras.callbacks import *
from sklearn.pipeline import Pipeline

# Custom transformer
class Transformer():

    def transform(self, x):
        x_img = np.apply_along_axis(self.rec_plot, 1, x).astype('float16')
        return x_img
    
    def rec_plot(s, eps=0.10, steps=10):
        d = pdist(s[:,None])
        d = np.floor(d/eps)
        d[d>steps] = steps
        Z = squareform(d)
        return Z
    
    def fit(self, x, y=None):
        return x

def create_model():
    model = Sequential()

    model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(50, 50, 17)))
    model.add(Conv2D(32, (3, 3), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))

    model.add(Conv2D(64, (3, 3), activation='relu'))
    model.add(Conv2D(64, (3, 3), activation='relu'))
    model.add(MaxPooling2D(pool_size=(2, 2)))
    model.add(Dropout(0.25))

    model.add(Flatten())
    model.add(Dense(256, activation='relu'))
    model.add(Dropout(0.5))
    model.add(Dense(3, activation='softmax'))

    #sgd = SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
    model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

    print(model.summary())
    
    return model

transformer = Transformer()
clf = KerasClassifier(build_fn=create_model, verbose=0)

blackbox_model = Pipeline([('transform', transformer),('clf',clf)])
blackbox_model.fit(x_train, y_train)

当我在我的数据集上运行此代码时，我收到以下错误：

AttributeError: 'numpy.ndarray' 对象没有属性 'transform'

好像和数据格式有关（所以上面分享了我的数据格式）。但我不确定如何解决这个问题。

Answer 1

方法Transformer().fit() 应该返回self。

因为您的Transformer 对象是无状态的，所以使用sklearn.preprocessing.FunctionTransformer 可能更容易。您可以使用您的转换函数实例化该类。类似于以下内容（未经测试）：

import sklearn.preprocessing

def _rec_plot(s, eps=0.10, steps=10):
    d = pdist(s[:,None])
    d = np.floor(d/eps)
    d[d>steps] = steps
    Z = squareform(d)
    return Z

def fun(x, y=None):
    return np.apply_along_axis(_rec_plot, 1, x).astype('float16')

transformer = sklearn.preprocessing.FunctionTransformer(func=fun)

我还建议不要使用语法from module import *，因为这会污染您的命名空间。当我第一次阅读您的问题时，我想知道问题是不是因为所有不必要的导入而导致对函数名称进行分类。