预处理数据 (TensorFlow)¶

Install the Transformers, Datasets, and Evaluate libraries to run this notebook.

In [ ]:

!pip install datasets evaluate transformers[sentencepiece]

In [ ]:

import tensorflow as tf
import numpy as np
from transformers import AutoTokenizer, TFAutoModelForSequenceClassification

# Same as before
checkpoint = "bert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
model = TFAutoModelForSequenceClassification.from_pretrained(checkpoint)
sequences = [
    "I've been waiting for a HuggingFace course my whole life.",
    "This course is amazing!",
]
batch = dict(tokenizer(sequences, padding=True, truncation=True, return_tensors="tf"))

# This is new
model.compile(optimizer="adam", loss="sparse_categorical_crossentropy")
labels = tf.convert_to_tensor([1, 1])
model.train_on_batch(batch, labels)

In [ ]:

from datasets import load_dataset

raw_datasets = load_dataset("glue", "mrpc")
raw_datasets

Out[ ]:

DatasetDict({
    train: Dataset({
        features: ['sentence1', 'sentence2', 'label', 'idx'],
        num_rows: 3668
    })
    validation: Dataset({
        features: ['sentence1', 'sentence2', 'label', 'idx'],
        num_rows: 408
    })
    test: Dataset({
        features: ['sentence1', 'sentence2', 'label', 'idx'],
        num_rows: 1725
    })
})

In [ ]:

raw_train_dataset = raw_datasets["train"]
raw_train_dataset[0]

Out[ ]:

{'idx': 0,
 'label': 1,
 'sentence1': 'Amrozi accused his brother , whom he called " the witness " , of deliberately distorting his evidence .',
 'sentence2': 'Referring to him as only " the witness " , Amrozi accused his brother of deliberately distorting his evidence .'}

In [ ]:

raw_train_dataset.features

Out[ ]:

{'sentence1': Value(dtype='string', id=None),
 'sentence2': Value(dtype='string', id=None),
 'label': ClassLabel(num_classes=2, names=['not_equivalent', 'equivalent'], names_file=None, id=None),
 'idx': Value(dtype='int32', id=None)}

In [ ]:

from transformers import AutoTokenizer

checkpoint = "bert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(checkpoint)
tokenized_sentences_1 = tokenizer(raw_datasets["train"]["sentence1"])
tokenized_sentences_2 = tokenizer(raw_datasets["train"]["sentence2"])

In [ ]:

inputs = tokenizer("This is the first sentence.", "This is the second one.")
inputs

Out[ ]:

{ 
  'input_ids': [101, 2023, 2003, 1996, 2034, 6251, 1012, 102, 2023, 2003, 1996, 2117, 2028, 1012, 102],
  'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1],
  'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
}

In [ ]:

tokenizer.convert_ids_to_tokens(inputs["input_ids"])

Out[ ]:

['[CLS]', 'this', 'is', 'the', 'first', 'sentence', '.', '[SEP]', 'this', 'is', 'the', 'second', 'one', '.', '[SEP]']

In [ ]:

tokenized_dataset = tokenizer(
    raw_datasets["train"]["sentence1"],
    raw_datasets["train"]["sentence2"],
    padding=True,
    truncation=True,
)

In [ ]:

def tokenize_function(example):
    return tokenizer(example["sentence1"], example["sentence2"], truncation=True)

In [ ]:

tokenized_datasets = raw_datasets.map(tokenize_function, batched=True)
tokenized_datasets

Out[ ]:

DatasetDict({
    train: Dataset({
        features: ['attention_mask', 'idx', 'input_ids', 'label', 'sentence1', 'sentence2', 'token_type_ids'],
        num_rows: 3668
    })
    validation: Dataset({
        features: ['attention_mask', 'idx', 'input_ids', 'label', 'sentence1', 'sentence2', 'token_type_ids'],
        num_rows: 408
    })
    test: Dataset({
        features: ['attention_mask', 'idx', 'input_ids', 'label', 'sentence1', 'sentence2', 'token_type_ids'],
        num_rows: 1725
    })
})

In [ ]:

from transformers import DataCollatorWithPadding

data_collator = DataCollatorWithPadding(tokenizer=tokenizer, return_tensors="tf")

In [ ]:

samples = tokenized_datasets["train"][:8]
samples = {k: v for k, v in samples.items() if k not in ["idx", "sentence1", "sentence2"]}
[len(x) for x in samples["input_ids"]]

Out[ ]:

[50, 59, 47, 67, 59, 50, 62, 32]

In [ ]:

batch = data_collator(samples)
{k: v.shape for k, v in batch.items()}

Out[ ]:

{'attention_mask': TensorShape([8, 67]),
 'input_ids': TensorShape([8, 67]),
 'token_type_ids': TensorShape([8, 67]),
 'labels': TensorShape([8])}

In [ ]:

tf_train_dataset = tokenized_datasets["train"].to_tf_dataset(
    columns=["attention_mask", "input_ids", "token_type_ids"],
    label_cols=["labels"],
    shuffle=True,
    collate_fn=data_collator,
    batch_size=8,
)

tf_validation_dataset = tokenized_datasets["validation"].to_tf_dataset(
    columns=["attention_mask", "input_ids", "token_type_ids"],
    label_cols=["labels"],
    shuffle=False,
    collate_fn=data_collator,
    batch_size=8,
)