pip install transformers datasets evaluate seqeval

>>> from huggingface_hub import notebook_login

>>> notebook_login()

>>> from datasets import load_dataset

>>> wnut = load_dataset("flaitenberger/wnut_17")

>>> wnut["train"][0]
{'id': '0',
 'ner_tags': [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 7, 8, 8, 0, 7, 0, 0, 0, 0, 0, 0, 0, 0],
 'tokens': ['@paulwalk', 'It', "'s", 'the', 'view', 'from', 'where', 'I', "'m", 'living', 'for', 'two', 'weeks', '.', 'Empire', 'State', 'Building', '=', 'ESB', '.', 'Pretty', 'bad', 'storm', 'here', 'last', 'evening', '.']
}

>>> label_list = wnut["train"].features[f"ner_tags"].feature.names
>>> label_list
[
    "O",
    "B-corporation",
    "I-corporation",
    "B-creative-work",
    "I-creative-work",
    "B-group",
    "I-group",
    "B-location",
    "I-location",
    "B-person",
    "I-person",
    "B-product",
    "I-product",
]

>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("distilbert/distilbert-base-uncased")

>>> example = wnut["train"][0]
>>> tokenized_input = tokenizer(example["tokens"], is_split_into_words=True)
>>> tokens = tokenizer.convert_ids_to_tokens(tokenized_input["input_ids"])
>>> tokens
['[CLS]', '@', 'paul', '##walk', 'it', "'", 's', 'the', 'view', 'from', 'where', 'i', "'", 'm', 'living', 'for', 'two', 'weeks', '.', 'empire', 'state', 'building', '=', 'es', '##b', '.', 'pretty', 'bad', 'storm', 'here', 'last', 'evening', '.', '[SEP]']

>>> def tokenize_and_align_labels(examples):
...     tokenized_inputs = tokenizer(examples["tokens"], truncation=True, is_split_into_words=True)

...     labels = []
...     for i, label in enumerate(examples[f"ner_tags"]):
...         word_ids = tokenized_inputs.word_ids(batch_index=i)  # Map tokens to their respective word.
...         previous_word_idx = None
...         label_ids = []
...         for word_idx in word_ids:  # Set the special tokens to -100.
...             if word_idx is None:
...                 label_ids.append(-100)
...             elif word_idx != previous_word_idx:  # Only label the first token of a given word.
...                 label_ids.append(label[word_idx])
...             else:
...                 label_ids.append(-100)
...             previous_word_idx = word_idx
...         labels.append(label_ids)

...     tokenized_inputs["labels"] = labels
...     return tokenized_inputs

>>> tokenized_wnut = wnut.map(tokenize_and_align_labels, batched=True)

>>> from transformers import DataCollatorForTokenClassification

>>> data_collator = DataCollatorForTokenClassification(tokenizer=tokenizer)

>>> import evaluate

>>> seqeval = evaluate.load("seqeval")

>>> import numpy as np

>>> labels = [label_list[i] for i in example[f"ner_tags"]]


>>> def compute_metrics(p):
...     predictions, labels = p
...     predictions = np.argmax(predictions, axis=2)

...     true_predictions = [
...         [label_list[p] for (p, l) in zip(prediction, label) if l != -100]
...         for prediction, label in zip(predictions, labels)
...     ]
...     true_labels = [
...         [label_list[l] for (p, l) in zip(prediction, label) if l != -100]
...         for prediction, label in zip(predictions, labels)
...     ]

...     results = seqeval.compute(predictions=true_predictions, references=true_labels)
...     return {
...         "precision": results["overall_precision"],
...         "recall": results["overall_recall"],
...         "f1": results["overall_f1"],
...         "accuracy": results["overall_accuracy"],
...     }

>>> id2label = {
...     0: "O",
...     1: "B-corporation",
...     2: "I-corporation",
...     3: "B-creative-work",
...     4: "I-creative-work",
...     5: "B-group",
...     6: "I-group",
...     7: "B-location",
...     8: "I-location",
...     9: "B-person",
...     10: "I-person",
...     11: "B-product",
...     12: "I-product",
... }
>>> label2id = {
...     "O": 0,
...     "B-corporation": 1,
...     "I-corporation": 2,
...     "B-creative-work": 3,
...     "I-creative-work": 4,
...     "B-group": 5,
...     "I-group": 6,
...     "B-location": 7,
...     "I-location": 8,
...     "B-person": 9,
...     "I-person": 10,
...     "B-product": 11,
...     "I-product": 12,
... }

>>> from transformers import AutoModelForTokenClassification, TrainingArguments, Trainer

>>> model = AutoModelForTokenClassification.from_pretrained(
...     "distilbert/distilbert-base-uncased", num_labels=13, id2label=id2label, label2id=label2id
... )

>>> training_args = TrainingArguments(
...     output_dir="my_awesome_wnut_model",
...     learning_rate=2e-5,
...     per_device_train_batch_size=16,
...     per_device_eval_batch_size=16,
...     num_train_epochs=2,
...     weight_decay=0.01,
...     eval_strategy="epoch",
...     save_strategy="epoch",
...     load_best_model_at_end=True,
...     push_to_hub=True,
... )

>>> trainer = Trainer(
...     model=model,
...     args=training_args,
...     train_dataset=tokenized_wnut["train"],
...     eval_dataset=tokenized_wnut["test"],
...     processing_class=tokenizer,
...     data_collator=data_collator,
...     compute_metrics=compute_metrics,
... )

>>> trainer.train()

>>> trainer.push_to_hub()

>>> text = "The Golden State Warriors are an American professional basketball team based in San Francisco."

>>> from transformers import pipeline

>>> classifier = pipeline("ner", model="stevhliu/my_awesome_wnut_model")
>>> classifier(text)
[{'entity': 'B-location',
  'score': 0.42658573,
  'index': 2,
  'word': 'golden',
  'start': 4,
  'end': 10},
 {'entity': 'I-location',
  'score': 0.35856336,
  'index': 3,
  'word': 'state',
  'start': 11,
  'end': 16},
 {'entity': 'B-group',
  'score': 0.3064001,
  'index': 4,
  'word': 'warriors',
  'start': 17,
  'end': 25},
 {'entity': 'B-location',
  'score': 0.65523505,
  'index': 13,
  'word': 'san',
  'start': 80,
  'end': 83},
 {'entity': 'B-location',
  'score': 0.4668663,
  'index': 14,
  'word': 'francisco',
  'start': 84,
  'end': 93}]

>>> from transformers import AutoTokenizer

>>> tokenizer = AutoTokenizer.from_pretrained("stevhliu/my_awesome_wnut_model")
>>> inputs = tokenizer(text, return_tensors="pt")

>>> from transformers import AutoModelForTokenClassification

>>> model = AutoModelForTokenClassification.from_pretrained("stevhliu/my_awesome_wnut_model")
>>> with torch.no_grad():
...     logits = model(**inputs).logits

>>> predictions = torch.argmax(logits, dim=2)
>>> predicted_token_class = [model.config.id2label[t.item()] for t in predictions[0]]
>>> predicted_token_class
['O',
 'O',
 'B-location',
 'I-location',
 'B-group',
 'O',
 'O',
 'O',
 'O',
 'O',
 'O',
 'O',
 'O',
 'B-location',
 'B-location',
 'O',
 'O']