import paddle
import paddle.nn.functional as F
import re
import numpy as np

print(paddle.__version__)

# cpu/gpu环境选择，在 paddle.set_device() 输入对应运行设备。
# device = paddle.set_device('gpu')

 def prepare_train_features(examples):
        contexts = [examples[i]['context'] for i in range(len(examples))]
        questions = [examples[i]['question'] for i in range(len(examples))]

        tokenized_examples = tokenizer(
            questions,
            contexts,
            stride=doc_stride,
            max_seq_len=max_seq_length)

        # Let's label those examples!
        for i, tokenized_example in enumerate(tokenized_examples):
            # We will label impossible answers with the index of the CLS token.
            input_ids = tokenized_example["input_ids"]
            cls_index = input_ids.index(tokenizer.cls_token_id)

            # The offset mappings will give us a map from token to character position in the original context. This will
            # help us compute the start_positions and end_positions.
            offsets = tokenized_example['offset_mapping']

            # Grab the sequence corresponding to that example (to know what is the context and what is the question).
            sequence_ids = tokenized_example['token_type_ids']

            # One example can give several spans, this is the index of the example containing this span of text.
            sample_index = tokenized_example['overflow_to_sample']
            answers = examples[sample_index]['answers']
            answer_starts = examples[sample_index]['answer_starts']

            # Start/end character index of the answer in the text.
            start_char = answer_starts[0]
            end_char = start_char + len(answers[0])

            # Start token index of the current span in the text.
            token_start_index = 0
            while sequence_ids[token_start_index] != 1:
                token_start_index += 1

            # End token index of the current span in the text.
            token_end_index = len(input_ids) - 1
            while sequence_ids[token_end_index] != 1:
                token_end_index -= 1
            # Minus one more to reach actual text
            token_end_index -= 1

            # Detect if the answer is out of the span (in which case this feature is labeled with the CLS index).
            if not (offsets[token_start_index][0] <= start_char and
                    offsets[token_end_index][1] >= end_char):
                tokenized_examples[i]["start_positions"] = cls_index
                tokenized_examples[i]["end_positions"] = cls_index
            else:
                # Otherwise move the token_start_index and token_end_index to the two ends of the answer.
                # Note: we could go after the last offset if the answer is the last word (edge case).
                while token_start_index < len(offsets) and offsets[
                        token_start_index][0] <= start_char:
                    token_start_index += 1
                tokenized_examples[i]["start_positions"] = token_start_index - 1
                while offsets[token_end_index][1] >= end_char:
                    token_end_index -= 1
                tokenized_examples[i]["end_positions"] = token_end_index + 1

        return tokenized_examples

def prepare_validation_features(examples):
        # Tokenize our examples with truncation and maybe padding, but keep the overflows using a stride. This results
        # in one example possible giving several features when a context is long, each of those features having a
        # context that overlaps a bit the context of the previous feature.
        # NOTE: Almost the same functionality as HuggingFace's prepare_train_features function. The main difference is
        # that HugggingFace uses ArrowTable as basic data structure, while we use list of dictionary instead.
        contexts = [examples[i]['context'] for i in range(len(examples))]
        questions = [examples[i]['question'] for i in range(len(examples))]

        tokenized_examples = tokenizer(
            questions,
            contexts,
            stride=doc_stride,
            max_seq_len=max_seq_length)

        # For validation, there is no need to compute start and end positions
        for i, tokenized_example in enumerate(tokenized_examples):
            # Grab the sequence corresponding to that example (to know what is the context and what is the question).
            sequence_ids = tokenized_example['token_type_ids']

            # One example can give several spans, this is the index of the example containing this span of text.
            sample_index = tokenized_example['overflow_to_sample']
            tokenized_examples[i]["example_id"] = examples[sample_index]['id']

            # Set to None the offset_mapping that are not part of the context so it's easy to determine if a token
            # position is part of the context or not.
            tokenized_examples[i]["offset_mapping"] = [
                (o if sequence_ids[k] == 1 else None)
                for k, o in enumerate(tokenized_example["offset_mapping"])
            ]

        return tokenized_examples

 if train_file:
            train_ds = load_dataset(task_name, data_files=train_file)
        else:
            train_ds = load_dataset(task_name, splits='train')
        train_ds.map(prepare_train_features, batched=True)
        train_batch_sampler = paddle.io.DistributedBatchSampler(
            train_ds, batch_size=batch_size, shuffle=True)
        train_batchify_fn = lambda samples, fn=Dict({
            "input_ids": Pad(axis=0, pad_val=tokenizer.pad_token_id),
            "token_type_ids": Pad(axis=0, pad_val=tokenizer.pad_token_type_id),
            "start_positions": Stack(dtype="int64"),
            "end_positions": Stack(dtype="int64")
        }): fn(samples)

        train_data_loader = DataLoader(
            dataset=train_ds,
            batch_sampler=train_batch_sampler,
            collate_fn=train_batchify_fn,
            return_list=True)

        num_training_steps = max_steps if max_steps > 0 else len(
            train_data_loader) * num_train_epochs
        num_train_epochs = math.ceil(num_training_steps /
                                     len(train_data_loader))

        lr_scheduler = LinearDecayWithWarmup(
            learning_rate, num_training_steps, warmup_proportion)

        # Generate parameter names needed to perform weight decay.
        # All bias and LayerNorm parameters are excluded.
        decay_params = [
            p.name for n, p in model.named_parameters()
            if not any(nd in n for nd in ["bias", "norm"])
        ]
        optimizer = paddle.optimizer.AdamW(
            learning_rate=lr_scheduler,
            epsilon=adam_epsilon,
            parameters=model.parameters(),
            weight_decay=weight_decay,
            apply_decay_param_fun=lambda x: x in decay_params)
        criterion = CrossEntropyLossForSQuAD()

        global_step = 0
        tic_train = time.time()
        for epoch in range(num_train_epochs):
            for step, batch in enumerate(train_data_loader):
                global_step += 1
                input_ids, token_type_ids, start_positions, end_positions = batch
                logits = model(
                    input_ids=input_ids, token_type_ids=token_type_ids)
                loss = criterion(logits, (start_positions, end_positions))

                if global_step % logging_steps == 0:
                    print(
                        "global step %d, epoch: %d, batch: %d, loss: %f, speed: %.2f step/s"
                        % (global_step, epoch + 1, step + 1, loss,
                           logging_steps / (time.time() - tic_train)))
                    tic_train = time.time()
                loss.backward()
                optimizer.step()
                lr_scheduler.step()
                optimizer.clear_grad()

                if global_step % save_steps == 0 or global_step == num_training_steps:
                    if rank == 0:
                        output_dir_ = os.path.join(output_dir,
                                                  "model_%d" % global_step)
                        if not os.path.exists(output_dir_):
                            os.makedirs(output_dir_)
                        # need better way to get inner model of DataParallel
                        model_to_save = model._layers if isinstance(
                            model, paddle.DataParallel) else model
                        model_to_save.save_pretrained(output_dir_)
                        tokenizer.save_pretrained(output_dir_)
                        print('Saving checkpoint to:', output_dir_)
                    if global_step == num_training_steps:
                        break

 model_type='bert'
    model_name_or_path='bert-base-chinese'
    task_name = task_name.lower()
    model_type = model_type.lower()
    model_class, tokenizer_class = MODEL_CLASSES[model_type]
    tokenizer = tokenizer_class.from_pretrained(model_name_or_path)

@paddle.no_grad()
def eval（model, data_loader):
    model.eval（)

    all_start_logits = []
    all_end_logits = []
    tic_eval（)

    for batch in data_loader:
        input_ids, token_type_ids = batch
        start_logits_tensor, end_logits_tensor = model(input_ids,
                                                       token_type_ids)

        for idx in range(start_logits_tensor.shape[0]):
            if len(all_start_logits) % 1000 == 0 and len(all_start_logits):
                print("Processing example: %d" % len(all_start_logits))
                print('time per 1000:', time.time() - tic_eval)
                tic_eval（)

            all_start_logits.append(start_logits_tensor.numpy()[idx])
            all_end_logits.append(end_logits_tensor.numpy()[idx])

    all_predictions, _, _ = compute_prediction(
        data_loader.dataset.data, data_loader.dataset.new_data,
        (all_start_logits, all_end_logits), False, n_best_size,
        max_answer_length)

    # Can also write all_nbest_json and scores_diff_json files if needed
    with open('prediction.json', "w", encoding='utf-8') as writer:
        writer.write(
            json.dumps(
                all_predictions, ensure_ascii=False, indent=4) + "\n")

    squad_eval（
        examples=data_loader.dataset.data,
        preds=all_predictions,
        is_whitespace_splited=False)

    model.train()

class CrossEntropyLossForSQuAD(paddle.nn.Layer):
    def __init__(self):
        super(CrossEntropyLossForSQuAD, self).__init__()

    def forward(self, y, label):
        start_logits, end_logits = y
        start_position, end_position = label
        start_position = paddle.unsqueeze(start_position, axis=-1)
        end_position = paddle.unsqueeze(end_position, axis=-1)
        start_loss = paddle.nn.functional.cross_entropy(
            input=start_logits, label=start_position)
        end_loss = paddle.nn.functional.cross_entropy(
            input=end_logits, label=end_position)
        loss = (start_loss + end_loss) / 2
        return loss


def run():
    task_name='dureader_robust'
    train_file=None
    predict_file=None
    model_type='bert'
    model_name_or_path='bert-base-chinese'
    output_dir='models'
    max_seq_length=128
    batch_size=8
    learning_rate=5e-5
    weight_decay=0.0
    adam_epsilon=1e-8
    ax_grad_norm=1.0
    num_train_epochs=3
    max_steps=-1
    warmup_proportion=0.0
    logging_steps=200
    save_steps=200
    seed=42
    device='gpu'
    doc_stride =128
    n_best_size =20
    max_query_length=64
    max_answer_length=30
    do_lower_case=True
    verbose=True
    do_train=True
    do_predict=True
    paddle.set_device(device)
    if paddle.distributed.get_world_size() > 1:
        paddle.distributed.init_parallel_env()
    rank = paddle.distributed.get_rank()
    task_name='dureader_robust'
    model_type='bert'
    model_name_or_path='bert-base-chinese'
    task_name = task_name.lower()
    model_type = model_type.lower()
    model_class, tokenizer_class = MODEL_CLASSES[model_type]
    tokenizer = tokenizer_class.from_pretrained(model_name_or_path)
    set_seed(1024)
    if rank == 0:
        if os.path.exists(model_name_or_path):
            print("init checkpoint from %s" % model_name_or_path)

    model = model_class.from_pretrained(model_name_or_path)

    if paddle.distributed.get_world_size() > 1:
        model = paddle.DataParallel(model)

    def prepare_train_features(examples):
        contexts = [examples[i]['context'] for i in range(len(examples))]
        questions = [examples[i]['question'] for i in range(len(examples))]

        tokenized_examples = tokenizer(
            questions,
            contexts,
            stride=doc_stride,
            max_seq_len=max_seq_length)

        # Let's label those examples!
        for i, tokenized_example in enumerate(tokenized_examples):
            # We will label impossible answers with the index of the CLS token.
            input_ids = tokenized_example["input_ids"]
            cls_index = input_ids.index(tokenizer.cls_token_id)

            # The offset mappings will give us a map from token to character position in the original context. This will
            # help us compute the start_positions and end_positions.
            offsets = tokenized_example['offset_mapping']

            # Grab the sequence corresponding to that example (to know what is the context and what is the question).
            sequence_ids = tokenized_example['token_type_ids']

            # One example can give several spans, this is the index of the example containing this span of text.
            sample_index = tokenized_example['overflow_to_sample']
            answers = examples[sample_index]['answers']
            answer_starts = examples[sample_index]['answer_starts']

            # Start/end character index of the answer in the text.
            start_char = answer_starts[0]
            end_char = start_char + len(answers[0])

            # Start token index of the current span in the text.
            token_start_index = 0
            while sequence_ids[token_start_index] != 1:
                token_start_index += 1

            # End token index of the current span in the text.
            token_end_index = len(input_ids) - 1
            while sequence_ids[token_end_index] != 1:
                token_end_index -= 1
            # Minus one more to reach actual text
            token_end_index -= 1

            # Detect if the answer is out of the span (in which case this feature is labeled with the CLS index).
            if not (offsets[token_start_index][0] <= start_char and
                    offsets[token_end_index][1] >= end_char):
                tokenized_examples[i]["start_positions"] = cls_index
                tokenized_examples[i]["end_positions"] = cls_index
            else:
                # Otherwise move the token_start_index and token_end_index to the two ends of the answer.
                # Note: we could go after the last offset if the answer is the last word (edge case).
                while token_start_index < len(offsets) and offsets[
                        token_start_index][0] <= start_char:
                    token_start_index += 1
                tokenized_examples[i]["start_positions"] = token_start_index - 1
                while offsets[token_end_index][1] >= end_char:
                    token_end_index -= 1
                tokenized_examples[i]["end_positions"] = token_end_index + 1

        return tokenized_examples

    if do_train:
        
        if train_file:
            train_ds = load_dataset(task_name, data_files=train_file)
        else:
            train_ds = load_dataset(task_name, splits='train')
        train_ds.map(prepare_train_features, batched=True)
        train_batch_sampler = paddle.io.DistributedBatchSampler(
            train_ds, batch_size=batch_size, shuffle=True)
        train_batchify_fn = lambda samples, fn=Dict({
            "input_ids": Pad(axis=0, pad_val=tokenizer.pad_token_id),
            "token_type_ids": Pad(axis=0, pad_val=tokenizer.pad_token_type_id),
            "start_positions": Stack(dtype="int64"),
            "end_positions": Stack(dtype="int64")
        }): fn(samples)

        train_data_loader = DataLoader(
            dataset=train_ds,
            batch_sampler=train_batch_sampler,
            collate_fn=train_batchify_fn,
            return_list=True)

        num_training_steps = max_steps if max_steps > 0 else len(
            train_data_loader) * num_train_epochs
        num_train_epochs = math.ceil(num_training_steps /
                                     len(train_data_loader))

        lr_scheduler = LinearDecayWithWarmup(
            learning_rate, num_training_steps, warmup_proportion)

        # Generate parameter names needed to perform weight decay.
        # All bias and LayerNorm parameters are excluded.
        decay_params = [
            p.name for n, p in model.named_parameters()
            if not any(nd in n for nd in ["bias", "norm"])
        ]
        optimizer = paddle.optimizer.AdamW(
            learning_rate=lr_scheduler,
            epsilon=adam_epsilon,
            parameters=model.parameters(),
            weight_decay=weight_decay,
            apply_decay_param_fun=lambda x: x in decay_params)
        criterion = CrossEntropyLossForSQuAD()

        global_step = 0
        tic_train = time.time()
        for epoch in range(num_train_epochs):
            for step, batch in enumerate(train_data_loader):
                global_step += 1
                input_ids, token_type_ids, start_positions, end_positions = batch
                logits = model(
                    input_ids=input_ids, token_type_ids=token_type_ids)
                loss = criterion(logits, (start_positions, end_positions))

                if global_step % logging_steps == 0:
                    print(
                        "global step %d, epoch: %d, batch: %d, loss: %f, speed: %.2f step/s"
                        % (global_step, epoch + 1, step + 1, loss,
                           logging_steps / (time.time() - tic_train)))
                    tic_train = time.time()
                loss.backward()
                optimizer.step()
                lr_scheduler.step()
                optimizer.clear_grad()

                if global_step % save_steps == 0 or global_step == num_training_steps:
                    if rank == 0:
                        output_dir_ = os.path.join(output_dir,
                                                  "model_%d" % global_step)
                        if not os.path.exists(output_dir_):
                            os.makedirs(output_dir_)
                        # need better way to get inner model of DataParallel
                        model_to_save = model._layers if isinstance(
                            model, paddle.DataParallel) else model
                        model_to_save.save_pretrained(output_dir_)
                        tokenizer.save_pretrained(output_dir_)
                        print('Saving checkpoint to:', output_dir_)
                    if global_step == num_training_steps:
                        break

    def prepare_validation_features(examples):
        # Tokenize our examples with truncation and maybe padding, but keep the overflows using a stride. This results
        # in one example possible giving several features when a context is long, each of those features having a
        # context that overlaps a bit the context of the previous feature.
        # NOTE: Almost the same functionality as HuggingFace's prepare_train_features function. The main difference is
        # that HugggingFace uses ArrowTable as basic data structure, while we use list of dictionary instead.
        contexts = [examples[i]['context'] for i in range(len(examples))]
        questions = [examples[i]['question'] for i in range(len(examples))]

        tokenized_examples = tokenizer(
            questions,
            contexts,
            stride=doc_stride,
            max_seq_len=max_seq_length)

        # For validation, there is no need to compute start and end positions
        for i, tokenized_example in enumerate(tokenized_examples):
            # Grab the sequence corresponding to that example (to know what is the context and what is the question).
            sequence_ids = tokenized_example['token_type_ids']

            # One example can give several spans, this is the index of the example containing this span of text.
            sample_index = tokenized_example['overflow_to_sample']
            tokenized_examples[i]["example_id"] = examples[sample_index]['id']

            # Set to None the offset_mapping that are not part of the context so it's easy to determine if a token
            # position is part of the context or not.
            tokenized_examples[i]["offset_mapping"] = [
                (o if sequence_ids[k] == 1 else None)
                for k, o in enumerate(tokenized_example["offset_mapping"])
            ]

        return tokenized_examples

    if do_predict and rank == 0:

        if predict_file:
            dev_ds = load_dataset(task_name, data_files=predict_file)
        else:
            dev_ds = load_dataset(task_name, splits='dev')

        dev_ds.map(prepare_validation_features, batched=True)
        dev_batch_sampler = paddle.io.BatchSampler(
            dev_ds, batch_size=batch_size, shuffle=False)

        dev_batchify_fn = lambda samples, fn=Dict({
            "input_ids": Pad(axis=0, pad_val=tokenizer.pad_token_id),
            "token_type_ids": Pad(axis=0, pad_val=tokenizer.pad_token_type_id)
        }): fn(samples)

        dev_data_loader = DataLoader(
            dataset=dev_ds,
            batch_sampler=dev_batch_sampler,
            collate_fn=dev_batchify_fn,
            return_list=True)

        eval（model, dev_data_loader)