python - numpy ndarray 到 Pandas 数据框

Question

使用假数据作为我输入的形状，在下面的最小工作示例中，我说明了如何创建我的自动编码器网络，以及我面临的问题 numpy ndarray 进行预测。

import numpy as np
import pandas as pd
import random
import keras
from keras.models import Sequential
from keras.layers import Dense
from keras.callbacks import ModelCheckpoint
from sklearn.metrics import mean_squared_error
class SingleEncoder:

    def __init__(self, train, test):
        self.x_train = train
        self.x_test = test
        self.first_dim = 1
        self.second_dim = 100
        self.channels = 4
        self.input_dim = (self.first_dim, self.second_dim, 
               self.channels) #(1, 100, 4)

    def buildModel(self):
        input_layer = self.input_dim
        autoencoder = Sequential()
        activ='relu'

        # encoder
        autoencoder.add(Dense(200,  activation='relu', input_shape=input_layer)) 
        autoencoder.add(Dense(100,  activation='relu')) 
        autoencoder.add(Dense(80,  activation='linear'))   

        #decoder
        autoencoder.add(Dense(80, activation='linear'))  
        autoencoder.add(Dense(100, activation='relu')) 
        autoencoder.add(Dense(200, activation='relu'))
        autoencoder.add(Dense(self.channels, activation='relu'))

        autoencoder.compile(optimizer='adam', loss='mae',  
metrics=['mean_squared_error'])
        autoencoder.summary()

        filepath = "weights.hdf5"
        checkpoint = ModelCheckpoint(filepath, monitor='loss',
 verbose=1, save_best_only=True, mode='max')
        callbacks_list = [checkpoint]

        autoencoder.fit(self.x_train, self.x_train, epochs=10, batch_size=32, 
          shuffle=True,callbacks=callbacks_list)

        return autoencoder

#

网络损耗:

def LosScore2(x_pred, x_test):
    mse = []
    for i in range(len(x_test)):
        mse.append(mean_squared_error(pd.DataFrame(x_pred[i]), pd.DataFrame(x_test[i])))
    return mse

生成假数据:

#Generate sample data, the shape of expected input
# X: ND-Array containing fixed-length segments of shape (1,100,4)
X = np.random.randn(2000, 1, 100, 4)
a,b,c = np.repeat(0, 700), np.repeat(1, 700), np.repeat(2, 600)
y = np.hstack((a,b,c))

from sklearn.model_selection import  train_test_split

x_train, x_test, y_train, y_test = train_test_split(X, y, test_size=0.20, random_state=7)
LABELS= list(set(np.ndarray.flatten(y_train)))

训练网络:

models = []
for i in range(len(LABELS)):
  print(LABELS[i])
  sub_train = x_train[y_train == i]
  sub_test = x_test[y_test == i]
  
  autoencoder = SingleEncoder(sub_train, sub_test)
  autoencoder = autoencoder.buildModel()
  models.append(autoencoder)

此 MWE工作完美，但是当我尝试在测试集上进行评估时，由于输入形状，我遇到了一个错误，如下所示:

print("Evaluating on test set -> ")
x_pred = []
# for each model
 # predition
for e in range(len(models)):
    x_pred.append(models[e].predict(x_test))

scored0 = (LosScore2(x_pred[0], x_test))
scored1 = (LosScore2(x_pred[1], x_test))
scored2 = (LosScore2(x_pred[2], x_test))

这是错误:

Evaluating on test set -> 

---------------------------------------------------------------------------

ValueError                                Traceback (most recent call last)

<ipython-input-11-989c507cfd63> in <module>()
      9 #scored0 = (LosScore2(x_pred[0][np.newaxis], x_test))
     10 
---> 11 scored0 = (LosScore2(x_pred[0], x_test))
     12 scored1 = (LosScore2(x_pred[1], x_test))
     13 scored2 = (LosScore2(x_pred[2], x_test))

3 frames

<ipython-input-9-356737ea1f97> in LosScore2(x_pred, x_test)
      2     mse = []
      3     for i in range(len(x_test)):
----> 4         mse.append(mean_squared_error(pd.DataFrame(x_pred[i]), pd.DataFrame(x_test[i])))
      5     return mse

/usr/local/lib/python3.6/dist-packages/pandas/core/frame.py in __init__(self, data, index, columns, dtype, copy)
    462                 mgr = init_dict({data.name: data}, index, columns, dtype=dtype)
    463             else:
--> 464                 mgr = init_ndarray(data, index, columns, dtype=dtype, copy=copy)
    465 
    466         # For data is list-like, or Iterable (will consume into list)

/usr/local/lib/python3.6/dist-packages/pandas/core/internals/construction.py in init_ndarray(values, index, columns, dtype, copy)
    167     # by definition an array here
    168     # the dtypes will be coerced to a single dtype
--> 169     values = prep_ndarray(values, copy=copy)
    170 
    171     if dtype is not None:

/usr/local/lib/python3.6/dist-packages/pandas/core/internals/construction.py in prep_ndarray(values, copy)
    293         values = values.reshape((values.shape[0], 1))
    294     elif values.ndim != 2:
--> 295         raise ValueError("Must pass 2-d input")
    296 
    297     return values

ValueError: Must pass 2-d input

我知道这与测试数据形状有关，但我不知道如何修复它。

Answer 1

您正在使用带有 4D 输入的 sklearn mse 将它们转换为 Pandas 数据帧，这将产生一系列错误。我建议你保持简单的 numpy 格式来计算每个样本的 mse:

def LosScore2(x_pred, x_test):
    mse = []
    for i in range(len(x_test)):
        mse.append(np.mean(np.square(x_test[i]-x_pred[i])))
    return mse

这里是运行笔记本: https://colab.research.google.com/drive/1OWdTYuIVeIWyMp477DoNNNKJ3ZXSoDji?usp=sharing