将元组列表转换为 tensorflow 数据集 (tf.data.Dataset)

Question

来自 kaggle Natural Language Processing with Disaster Tweets 的数据

ds_train

>>>[("Already expecting to be inundated w/ articles about trad authors' pay plummeting by early next year but if this is true it'll be far worse",
  0)
 ('@blazerfan not everyone can see ignoranceshe is Latinoand that is All she can ever benothing morebut an attack dog 4 a hate group GOP',
  0),...]

`

像 [(X1, y1),...(X_n, y_n)]

或 dataframe

0                      Just happened a terrible car crash

1       Heard about #earthquake is different cities, s...

2       there is a forest fire at spot pond, geese are...

我想将它转换为 tensorflow 数据集。 我尝试tf.data.Dataset.from_tensor_slices(ds_train)但出现错误

ValueError：无法将混合类型的 Python 序列转换为 Tensor。

Answer 1

一种选择是拆分元组：

import tensorflow as tf

data = [("Already expecting to be inundated w/ articles about trad authors' pay plummeting by early next year but if this is true it'll be far worse", 0), ('@blazerfan not everyone can see ignoranceshe is Latinoand that is All she can ever benothing morebut an attack dog 4 a hate group GOP', 0)]
x, y = zip(*data)
dataset = tf.data.Dataset.from_tensor_slices((list(x), list(y)))

使用 dataframe：

dataset = tf.data.Dataset.from_tensor_slices((df['text'], df['target']))