import torch
import torch.nn as nn

import numpy as np
import numpy as np
import pandas as pd

import torch.nn.functional as F

from transformers import PretrainedConfig
import torch.optim as optim

class BertCustomConfig(PretrainedConfig):
    model_type = "bert"

    def __init__(
            self,
            vocab_size=30873,
            hidden_size=768,
            num_hidden_layers=12,
            num_attention_heads=12,
            intermediate_size=3072,
            hidden_act="gelu",
            hidden_dropout_prob=0.1,
            attention_probs_dropout_prob=0.1,
            max_position_embeddings=512,
            type_vocab_size=2,
            initializer_range=0.02,
            layer_norm_eps=1e-12,
            pad_token_id=0,
            position_embedding_type="absolute",
            use_cache=True,
            classifier_dropout=None,
            max_length=512,
            id2label={"0": "Neutral", "1": "Hawkish", "2": "Dovish"},
            label2id={"positive": 1, "negative": 2, "neutral": 0},
            hyperparams=None,
            **kwargs
    ):
        super().__init__(pad_token_id=pad_token_id, **kwargs)
        self.vocab_size = vocab_size
        self.hidden_size = hidden_size
        self.num_hidden_layers = num_hidden_layers
        self.num_attention_heads = num_attention_heads
        self.hidden_act = hidden_act
        self.intermediate_size = intermediate_size
        self.hidden_dropout_prob = hidden_dropout_prob
        self.attention_probs_dropout_prob = attention_probs_dropout_prob
        self.max_position_embeddings = max_position_embeddings
        self.type_vocab_size = type_vocab_size
        self.initializer_range = initializer_range
        self.layer_norm_eps = layer_norm_eps
        self.position_embedding_type = position_embedding_type
        self.use_cache = use_cache
        self.classifier_dropout = classifier_dropout
        self.max_length = max_length
        self.id2label = id2label
        self.label2id = label2id
        self.hyperparams = hyperparams