I have a 1k rows and 14 columns dataframe containing numpy arrays like shown below.
我有一个1k行和14列数据帧包含numpy数组，如下所示。
Here a subset of 2 rows and 3 columns :
这里是2行3列的子集：
[5,4,74,-12] [ 78,1,2,-9] [5 ,1,1,2]
[10,4,4,-1] [ 8,15,21,-19] [1,1,0,0]
where each cell is a numpy array of shape (4,1).
其中每个单元格是一个numpy形状的阵列（4,1）。
I couldn't find the right placeholder to input my whole dataframe as it needs to be processed by row batches.
我找不到合适的占位符来输入我的整个数据帧，因为它需要按行批处理。
Could anyone have an idea ?
谁能有想法？
I tried this to find the proper placeholder for my dataframe but its not correct:
我试过这个找到我的数据帧的正确占位符，但它不正确：
x = tf.placeholder(tf.int32,[None,14],name='x')
with tf.Session() as sess:
print(sess.run(x,feed_dict={x:Data}))
It gives ValueError: setting an array element with a sequence.
Does anyone have an idea please ?
有人有想法吗？
1 个解决方案
#1
0
You did not specify in which format your data is available, so I assume it is a numpy array. In this case, you can do it like this:
您没有指定数据的可用格式，因此我假设它是一个numpy数组。在这种情况下，您可以这样做：
n_columns = 14
n_elements_per_column = 4
x = tf.placeholder(tf.int32, [None, n_columns, n_elements_per_column], name='x')
with tf.Session() as sess:
print(sess.run(x,feed_dict={x:Data}))
#1
0
You did not specify in which format your data is available, so I assume it is a numpy array. In this case, you can do it like this:
您没有指定数据的可用格式，因此我假设它是一个numpy数组。在这种情况下，您可以这样做：
n_columns = 14
n_elements_per_column = 4
x = tf.placeholder(tf.int32, [None, n_columns, n_elements_per_column], name='x')
with tf.Session() as sess:
print(sess.run(x,feed_dict={x:Data}))