如何将numpy数组的字典输出到文件[重复]

Question

from os import listdir
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array
from keras.applications.vgg19 import preprocess_input
from keras.applications.vgg19 import decode_predictions
from keras.applications.vgg19 import VGG19
from keras.preprocessing import image
from keras.models import Model
from PIL import Image
from PIL import ImageFile
ImageFile.LOAD_TRUNCATED_IMAGES = True
import numpy as np
import os
import time
import matplotlib.pyplot as plt
import csv
from pickle import dump
import xlsxwriter
from sklearn.feature_extraction import DictVectorizer
import pandas as pd   
import os
from openpyxl import load_workbook
import xlsxwriter
import pickle
# load an image from file
path1 = '/home/mclab/Desktop/Test'    #path of folder of images

# extract features from each photo in the directory
def extract_features(directory):
   # load the model
   model = VGG16()
   # re-structure the model
   model.layers.pop()
   model = Model(inputs=model.inputs, outputs=model.layers[-1].output)
   # summarize
   print(model.summary())
   # extract features from each photo
   features = dict()
   for name in listdir(directory):
      # load an image from file
      filename = directory + '/' + name
      image = load_img(filename, target_size=(224, 224))
      # convert the image pixels to a numpy array
      image = img_to_array(image)
      # reshape data for the model
      image = image.reshape((1, image.shape[0], image.shape[1], image.shape[2]))
      # prepare the image for the VGG model
      image = preprocess_input(image)
      # get features
      feature = model.predict(image, verbose=0)
      # get image id
      image_id = name.split('.')[0]
      # store feature
      features[image_id] = feature
      print('>%s' % name)
return features
# extract features from all images
directory = path1
features = extract_features(directory)
print('Extracted Features: %d' % len(features))
print (features)

我从给定目录中的数据中为 4 个输入图像运行此代码。我的字典是这种形式的
特征 = {'1': array([[0. , 4.845782 , 0. , ..., 2.6509986, 0. , 0. ]], dtype=float32), '3': 数组([[0. , 0.5562537, 0. , ..., 1.1013255, 0. , 0. ]], dtype=float32), '2': 数组([[0.11465299, 0., 3.7899919, ..., 0., 0., 0. ]], dtype=float32), '4': 数组([[0. , 0. , 0. , ..., 0. , 2.6636925, 0.]], dtype=float32)}

我注意到字典中的每个值都由关键图像的特征数组表示。我的问题是：如何将输入图像的特征数组保存在 excel 文件中，以便将这些特征用于回归问题。

Answer 1

这是仅使用 numpy 功能保存到 CSV 的一种方法。 CSV 文件可以在 Excel 中打开。

该解决方案假定您要事先按键排序。请注意，字典不被认为是有序的。如果订购很重要，请考虑使用collections.OrderedDict。

我提供了一个最小的示例，可以应用于任意大小的字典。

import numpy as np

# example dictionary input
d = {0: np.array([1, 2, 3, 4, 5]),
     1: np.array([6, 7, 8, 9, 10]),
     2: np.array([11, 12, 13, 14, 15])}

# build array from dictionary
arr = np.array([v for _, v in sorted(d.items())])

# array([[ 1,  2,  3,  4,  5],
#        [ 6,  7,  8,  9, 10],
#        [11, 12, 13, 14, 15]])

# save to array
np.savetxt('out.csv', arr, delimiter=',')

如果您真的需要保存为.xlsx 格式，可以通过 Pandas 进行：

pd.DataFrame(arr).to_excel('file.xlsx', index=False)