from typing import Optional, Union, Tuple

import torch
from torch import nn
from transformers.modeling_outputs import SequenceClassifierOutput
from transformers import AutoTokenizer, DebertaV2Model, \
                         DebertaV2ForSequenceClassification

class ClassificationHead(nn.Module):
    """Head for sentence-level classification tasks."""

    def __init__(self, config, num_extra_dims):
        super().__init__()
        total_dims = config.hidden_size+num_extra_dims
        self.dense = nn.Linear(total_dims, total_dims)
        classifier_dropout = config.hidden_dropout_prob
        self.dropout = nn.Dropout(classifier_dropout)
        self.out_proj = nn.Linear(total_dims, config.num_labels)

    def forward(self, features, **kwargs):
        x = self.dropout(features)
        x = self.dense(x)
        x = torch.tanh(x)
        x = self.dropout(x)
        x = self.out_proj(x)
        return x

class CustomSequenceClassification(DebertaV2ForSequenceClassification):

    def __init__(self, config, num_extra_dims):
        super().__init__(config)
        self.num_labels = config.num_labels
        self.config = config

        # might need to rename this depending on the model
        self.deberta =  DebertaV2Model(config)
        self.classifier = ClassificationHead(config, num_extra_dims)

        # Initialize weights and apply final processing
        self.post_init()


    def forward(
        self,
        input_ids: Optional[torch.LongTensor] = None,
        attention_mask: Optional[torch.FloatTensor] = None,
        extra_data: Optional[torch.FloatTensor] = None,
        token_type_ids: Optional[torch.LongTensor] = None,
        position_ids: Optional[torch.LongTensor] = None,
        head_mask: Optional[torch.FloatTensor] = None,
        inputs_embeds: Optional[torch.FloatTensor] = None,
        labels: Optional[torch.LongTensor] = None,
        output_attentions: Optional[bool] = None,
        output_hidden_states: Optional[bool] = None,
        return_dict: Optional[bool] = None,
    ) -> Union[Tuple, SequenceClassifierOutput]:
        r"""
        labels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):
            Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,
            config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If
            `config.num_labels > 1` a classification loss is computed (Cross-Entropy).
        """
        return_dict = return_dict if return_dict is not None else self.config.use_return_dict

        outputs = self.deberta(
            input_ids,
            attention_mask=attention_mask,
            token_type_ids=token_type_ids,
            position_ids=position_ids,
            inputs_embeds=inputs_embeds,
            output_attentions=output_attentions,
            output_hidden_states=output_hidden_states,
            return_dict=return_dict,
        )

        # sequence_output will be (batch_size, seq_length, hidden_size)
        sequence_output = outputs[0]

        # additional data should be (batch_size, num_extra_dims)
        cls_embedding = sequence_output[:, 0, :]

        output = torch.cat((cls_embedding, extra_data), dim=-1)

        logits = self.classifier(output)

        loss = None
        if labels is not None:
            if self.config.problem_type is None:
                if self.num_labels == 1:
                    self.config.problem_type = "regression"
                elif self.num_labels > 1 and (labels.dtype == torch.long or labels.dtype == torch.int):
                    self.config.problem_type = "single_label_classification"
                else:
                    self.config.problem_type = "multi_label_classification"

            if self.config.problem_type == "regression":
                loss_fct = nn.MSELoss()
                if self.num_labels == 1:
                    loss = loss_fct(logits.squeeze(), labels.squeeze())
                else:
                    loss = loss_fct(logits, labels)
            elif self.config.problem_type == "single_label_classification":
                loss_fct = nn.CrossEntropyLoss()
                loss = loss_fct(logits.view(-1, self.num_labels), labels.view(-1))
            elif self.config.problem_type == "multi_label_classification":
                loss_fct = nn.BCEWithLogitsLoss()
                loss = loss_fct(logits, labels)

        if not return_dict:
            output = (logits,) + outputs[2:]
            return ((loss,) + output) if loss is not None else output

        return SequenceClassifierOutput(
            loss=loss,
            logits=logits,
            hidden_states=outputs.hidden_states,
            attentions=outputs.attentions,
        )