# Transformers installation
! pip install transformers datasets evaluate accelerate
# To install from source instead of the last release, comment the command above and uncomment the following one.
# ! pip install git+https://github.com/huggingface/transformers.git

#@title
from IPython.display import HTML

HTML('<iframe width="560" height="315" src="https://www.youtube.com/embed/wVHdVlPScxA?rel=0&amp;controls=0&amp;showinfo=0" frameborder="0" allowfullscreen></iframe>')

from huggingface_hub import notebook_login

notebook_login()

from datasets import load_dataset

wnut = load_dataset("wnut_17")

wnut["train"][0]

label_list = wnut["train"].features[f"ner_tags"].feature.names
label_list

#@title
from IPython.display import HTML

HTML('<iframe width="560" height="315" src="https://www.youtube.com/embed/iY2AZYdZAr0?rel=0&amp;controls=0&amp;showinfo=0" frameborder="0" allowfullscreen></iframe>')

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

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)  # تعيين الرموز إلى كلماتهم المقابلة.
        previous_word_idx = None
        label_ids = []
        for word_idx in word_ids:  # تعيين الرموز الخاصة إلى -100.
            if word_idx is None:
                label_ids.append(-100)
            elif word_idx != previous_word_idx:  # تسمية الرمز الأول فقط لكلمة معينة.
                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, return_tensors="tf")

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 create_optimizer

batch_size = 16
num_train_epochs = 3
num_train_steps = (len(tokenized_wnut["train"]) // batch_size) * num_train_epochs
optimizer, lr_schedule = create_optimizer(
    init_lr=2e-5,
    num_train_steps=num_train_steps,
    weight_decay_rate=0.01,
    num_warmup_steps=0,
)

from transformers import TFAutoModelForTokenClassification

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

tf_train_set = model.prepare_tf_dataset(
    tokenized_wnut["train"],
    shuffle=True,
    batch_size=16,
    collate_fn=data_collator,
)

tf_validation_set = model.prepare_tf_dataset(
    tokenized_wnut["validation"],
    shuffle=False,
    batch_size=16,
    collate_fn=data_collator,
)

import tensorflow as tf

model.compile(optimizer=optimizer)  # No loss argument!

from transformers.keras_callbacks import KerasMetricCallback

metric_callback = KerasMetricCallback(metric_fn=compute_metrics, eval_dataset=tf_validation_set)

from transformers.keras_callbacks import PushToHubCallback

push_to_hub_callback = PushToHubCallback(
    output_dir="my_awesome_wnut_model",
    tokenizer=tokenizer,
)

callbacks = [metric_callback, push_to_hub_callback]

model.fit(x=tf_train_set, validation_data=tf_validation_set, epochs=3, callbacks=callbacks)

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)

from transformers import AutoTokenizer

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

from transformers import TFAutoModelForTokenClassification

model = TFAutoModelForTokenClassification.from_pretrained("stevhliu/my_awesome_wnut_model")
logits = model(**inputs).logits

predicted_token_class_ids = tf.math.argmax(logits, axis=-1)
predicted_token_class = [model.config.id2label[t] for t in predicted_token_class_ids[0].numpy().tolist()]
predicted_token_class