将 pandas 数据帧中的 numpy 数组加载到 tensorflow 数据集中

Question

我正在尝试使用以下命令将我的 pandas 数据帧 (df) 加载到 Tensorflow 数据集中：

target = df['label']
features = df['encoded_sentence']

dataset = tf.data.Dataset.from_tensor_slices((features.values, target.values))

这是我的 pandas 数据框的摘录：

+-------+-----------------------+------------------+
| label | sentence              | encoded_sentence |
+-------+-----------------------+------------------+
| 0     | Hello world           | [5, 7]           |
+-------+-----------------------+------------------+
| 1     | my name is john smith | [1, 9, 10, 2, 6] |
+-------+-----------------------+------------------+
| 1     | Hello! My name is     | [5, 3, 9, 10]    |
+-------+-----------------------+------------------+
| 0     | foo baar              | [8, 4]           |
+-------+-----------------------+------------------+

# df.dtypes gives me:
label                int8
sentence             object
encoded_sentencee    object

但它总是给我一个值错误：

ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type list).

谁能告诉我如何在我的 Tensorflow 数据集中使用编码句子？非常感谢您的帮助！

Answer 1

你可以先把你的 Pandas 值变成一个参差不齐的张量，然后用它制作数据集：

import tensorflow as tf
import pandas as pd

df = pd.DataFrame({'label': [0, 1, 1, 0],
                   'sentence': ['Hello world', 'my name is john smith',
                                'Hello! My name is', 'foo baar'],
                   'encoded_sentence': [[5, 7], [1, 9, 10, 2, 6],
                                        [5, 3, 9, 10], [8, 4]]})
features = tf.ragged.stack(list(df['encoded_sentence']))
target = tf.convert_to_tensor(df['label'].values)
dataset = tf.data.Dataset.from_tensor_slices((features, target))
for f, t in dataset:
    print(f.numpy(), t.numpy())

输出：

[5 7] 0
[ 1  9 10  2  6] 1
[ 5  3  9 10] 1
[8 4] 0

请注意，您可能希望使用 padded_batch 从数据集中获取批量示例。

编辑：由于填充批处理目前似乎不适用于由不规则张量制成的数据集，因此您也可以先将不规则张量转换为常规张量：

import tensorflow as tf
import pandas as pd

df = pd.DataFrame({'label': [0, 1, 1, 0],
                   'sentence': ['Hello world', 'my name is john smith',
                                'Hello! My name is', 'foo baar'],
                   'encoded_sentence': [[5, 7], [1, 9, 10, 2, 6],
                                        [5, 3, 9, 10], [8, 4]]})
features_ragged = tf.ragged.stack(list(df['encoded_sentence']))
features = features_ragged.to_tensor(default_value=-1)
target = tf.convert_to_tensor(df['label'].values)
dataset = tf.data.Dataset.from_tensor_slices((features, target))
batches = dataset.batch(2)
for f, t in batches:
    print(f.numpy(), t.numpy())

输出：

[[ 5  7 -1 -1 -1]
 [ 1  9 10  2  6]] [0 1]
[[ 5  3  9 10 -1]
 [ 8  4 -1 -1 -1]] [1 0]