Train Mnist Получить набор данных с Anaconda - PullRequest
Новая
       15

Train Mnist Получить набор данных с Anaconda

0 голосов
/ 12 марта 2019

ОК, так как мне не удалось использовать функцию mnist с более новой версией Anaconda (устаревшая ошибка с предупреждением об ошибке), я преобразовал файлы в csv, используя этот код для загрузки и обучения: 

        import csv with `open('C:\\Users\\User\\datasets\\mldata\\fetch\\mnist_train.csv') as sample, open('randomized.csv', "w", newline='') as out:`
        csv1=csv.reader(sample)
        #header = next(csv1, None)
        csv_writer = csv.writer(out)
        #if header:
        #    csv_writer.writerow(header)
        csv_writer.writerows(sorted(csv1, key=lambda x:int(x[0])))

    import csv
    fname_in = 'randomized.csv'
    fname_out = 'new_randomized.csv'
    with open(fname_in, 'r') as fin, open(fname_out, 'w', newline='') as fout:
        reader = csv.reader(fin)
        writer = csv.writer(fout)
        for row in reader:
            writer.writerow(row[1:])

    with open ("randomized.csv", "r") as csvfile:
        reader = csv.reader(csvfile)
        collected = []
        for row in reader:
            collected.append(row[0])

    with open("extracted_randomized_column.csv", "w", newline='') as csv_file:
        writer = csv.writer(csv_file, delimiter=',')
        for line in collected:
            writer.writerow(line)

    with open('new_randomized.csv') as sample:
        csv1=csv.reader(sample)
        c = list(csv1)
        collected = []

    for i in range(len(c)):
        s = ''
        for j in range(len(c[i])):
            if int(c[i][j]) > 128:
                s = s + '1'
            else:
                s = s + '0'
        collected.append(s)

    with open("bw_output.csv", "w", newline='') as csv_file:
        writer = csv.writer(csv_file, delimiter=',')
        for line in collected:
            writer.writerow(line)

    from PIL import Image

    A = np.array([0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0])
    B = np.reshape(A, (-1, 28))

    img = Image.fromarray(B)
    img.show()

But I think I am missing some steps because I have errors with the train test split function.

Я хотел бы знать, как использовать разделенную модель поезда и теста: 

from sklearn.model_selection import train_test_split
train_img, test_img, train_lbl, test_lbl = train_test_split(
    data, data.target, test_size=1/7.0, random_state=0)

, поскольку я получил следующее сообщение об ошибке: 

AttributeError                            Traceback (most recent call last)
<ipython-input-43-4744a5acdbfa> in <module>
      1 from sklearn.model_selection import train_test_split
      2 train_img, test_img, train_lbl, test_lbl = train_test_split(
----> 3     data, data.target, test_size=1/7.0, random_state=0)

~\Anaconda3\lib\site-packages\pandas\core\generic.py in __getattr__(self, name)
   4374             if self._info_axis._can_hold_identifiers_and_holds_name(name):
   4375                 return self[name]
-> 4376             return object.__getattribute__(self, name)
   4377 
   4378     def __setattr__(self, name, value):

AttributeError: 'DataFrame' object has no attribute 'target'

Любой совет?

...