import os

import numpy as np
import spacy
from keras.models import Sequential
from keras.layers import Dense, LSTM, Embedding
from keras.preprocessing.text import Tokenizer
from keras.preprocessing.sequence import pad_sequences
from keras.utils import to_categorical


BASEPATH = os.path.dirname(os.path.abspath(__file__))
MODEL_FILE = "rickroll.h5"


class NLPModel:
    
    def __init__(self):
        self.model = None
        self.NLP = spacy.load("en_core_web_sm", disable=["parser", "ner", "textcat"])
        self.NLP.max_length = 1198623
        self.tokenizer = Tokenizer()
        self.seq_len = 25
        self.sequences = None
        self.vocab_size = None
        
        
    def create_model(self, vocabulary_size):
        model: Sequential = Sequential()
        model.add(Embedding(vocabulary_size, 25, input_length=self.seq_len))
        model.add(LSTM(150, return_sequences=True))
        model.add(LSTM(150))
        model.add(Dense(150, activation="relu"))

        model.add(Dense(vocabulary_size, activation="softmax"))
        
        model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=["accuracy"])
    
        model.summary()
        
        return model


    def preprocess_text(self, texts):

        self.tokenizer.fit_on_texts(texts)
        sequences = self.tokenizer.texts_to_sequences(texts)
        sequences = np.array(sequences)
        
        return sequences
        

    def test_nlp(self, sample_text):

        doc = self.NLP(sample_text)
        
        print("Sample text:", sample_text)
        for token in doc:
            print(f"Token: {token.text}, POS: {token.pos_}, Lemma: {token.lemma_}, Dependency: {token.dep_}")
            
            
    def preload(self):
        with open(os.path.join(BASEPATH, "text.txt"), "r", encoding="utf-8") as file:
            data = file.read()
            filtered = '!"#$%&().*+,-/:;<=>?@[\\]^_`{|}~\t\n '
            tokens = [token.text.lower() for token in self.NLP(data) if token.text not in filtered]
        
        train_len = 26
        text_seq = []
        
        print("Total tokens:", len(tokens))
        
        for i in range(train_len, len(tokens)):
            seq = tokens[i-train_len:i]
            text_seq.append(seq)
        
        self.sequences = self.preprocess_text(text_seq)
        self.vocab_size = len(self.tokenizer.word_counts)+1
        self.model = self.create_model(self.vocab_size)
        
        print("Vocabulary size:", self.vocab_size)
        print("Total sequences:", len(self.sequences))
        
        
    def train(self, epochs=200, batch_size=64):
        
        x = self.sequences[:, :-1]
        y = self.sequences[:, -1]
        
        print("Input shape:", x.shape)
        print("Output shape:", y.shape)
        
        y = to_categorical(y, num_classes=self.vocab_size)
        self.model.fit(x, y, epochs=epochs, batch_size=batch_size, verbose=1)
        self.model.save_weights(os.path.join(BASEPATH, MODEL_FILE))
        
        
    def generate_text(self, seed_text, num_gen_words):

        output_text = []

        input_text = seed_text

        for i in range(self.seq_len, num_gen_words):
            
            encoded_text = self.tokenizer.texts_to_sequences([input_text])[0]
            pad_encoded = pad_sequences([encoded_text], maxlen=self.seq_len, truncating="pre")

            predict_x=self.model.predict(pad_encoded, verbose=0)[0]
            pred_word_ind=np.argmax(predict_x)
            
            pred_word = self.tokenizer.index_word[pred_word_ind] 
            
            input_text += " " + pred_word
            
            output_text.append(pred_word)

        return " ".join(output_text)


if __name__ == "__main__":
    
    nlp_model = NLPModel()
    nlp_model.preload()
    
    print("================================")
    nlp_model.test_nlp("Never gonna give you up")
    print("================================")
    
    if os.path.exists(os.path.join(BASEPATH, MODEL_FILE)):
        nlp_model.model.load_weights(os.path.join(BASEPATH, MODEL_FILE))
    else:
        nlp_model.train()
    
    while True:
        seed_text = input("Enter seed text (or 'exit' to quit): ")
        if seed_text.lower() == "exit": break
        
        num_gen_words = 50
        
        generated_text = nlp_model.generate_text(seed_text, num_gen_words)
        print("Generated Text:", generated_text.strip())

import math

import torch
import torch.nn as nn
import torch.optim as optim


class MultiHeadAttention(nn.Module):
    def __init__(self, d_model, num_heads):
        super(MultiHeadAttention, self).__init__()
        assert d_model % num_heads == 0, "d_model must be divisible by num_heads"
        
        self.d_model = d_model
        self.num_heads = num_heads
        self.d_k = d_model // num_heads
        
        self.W_q = nn.Linear(d_model, d_model)
        self.W_k = nn.Linear(d_model, d_model)
        self.W_v = nn.Linear(d_model, d_model)
        self.W_o = nn.Linear(d_model, d_model)
        
    def scaled_dot_product_attention(self, Q, K, V, mask=None):
        attn_scores = torch.matmul(Q, K.transpose(-2, -1)) / math.sqrt(self.d_k)
        if mask is not None:
            attn_scores = attn_scores.masked_fill(mask == 0, -1e9)
        attn_probs = torch.softmax(attn_scores, dim=-1)
        output = torch.matmul(attn_probs, V)
        return output
        
    def split_heads(self, x):
        batch_size, seq_length, d_model = x.size()
        return x.view(batch_size, seq_length, self.num_heads, self.d_k).transpose(1, 2)
        
    def combine_heads(self, x):
        batch_size, _, seq_length, d_k = x.size()
        return x.transpose(1, 2).contiguous().view(batch_size, seq_length, self.d_model)
        
    def forward(self, Q, K, V, mask=None):
        Q = self.split_heads(self.W_q(Q))
        K = self.split_heads(self.W_k(K))
        V = self.split_heads(self.W_v(V))
        
        attn_output = self.scaled_dot_product_attention(Q, K, V, mask)
        output = self.W_o(self.combine_heads(attn_output))
        return output
    
    
class PositionWiseFeedForward(nn.Module):
    def __init__(self, d_model, d_ff):
        super(PositionWiseFeedForward, self).__init__()
        self.fc1 = nn.Linear(d_model, d_ff)
        self.fc2 = nn.Linear(d_ff, d_model)
        self.relu = nn.ReLU()

    def forward(self, x):
        return self.fc2(self.relu(self.fc1(x)))
    
    
class PositionalEncoding(nn.Module):
    def __init__(self, d_model, max_seq_length):
        super(PositionalEncoding, self).__init__()
        
        pe = torch.zeros(max_seq_length, d_model)
        position = torch.arange(0, max_seq_length, dtype=torch.float).unsqueeze(1)
        div_term = torch.exp(torch.arange(0, d_model, 2).float() * -(math.log(10000.0) / d_model))
        
        pe[:, 0::2] = torch.sin(position * div_term)
        pe[:, 1::2] = torch.cos(position * div_term)
        
        self.register_buffer('pe', pe.unsqueeze(0))
        
    def forward(self, x):
        return x + self.pe[:, :x.size(1)]
    
    
class EncoderLayer(nn.Module):
    def __init__(self, d_model, num_heads, d_ff, dropout):
        super(EncoderLayer, self).__init__()
        self.self_attn = MultiHeadAttention(d_model, num_heads)
        self.feed_forward = PositionWiseFeedForward(d_model, d_ff)
        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, x, mask):
        attn_output = self.self_attn(x, x, x, mask)
        x = self.norm1(x + self.dropout(attn_output))
        ff_output = self.feed_forward(x)
        x = self.norm2(x + self.dropout(ff_output))
        return x
    
    
class DecoderLayer(nn.Module):
    def __init__(self, d_model, num_heads, d_ff, dropout):
        super(DecoderLayer, self).__init__()
        self.self_attn = MultiHeadAttention(d_model, num_heads)
        self.cross_attn = MultiHeadAttention(d_model, num_heads)
        self.feed_forward = PositionWiseFeedForward(d_model, d_ff)
        self.norm1 = nn.LayerNorm(d_model)
        self.norm2 = nn.LayerNorm(d_model)
        self.norm3 = nn.LayerNorm(d_model)
        self.dropout = nn.Dropout(dropout)
        
    def forward(self, x, enc_output, src_mask, tgt_mask):
        attn_output = self.self_attn(x, x, x, tgt_mask)
        x = self.norm1(x + self.dropout(attn_output))
        attn_output = self.cross_attn(x, enc_output, enc_output, src_mask)
        x = self.norm2(x + self.dropout(attn_output))
        ff_output = self.feed_forward(x)
        x = self.norm3(x + self.dropout(ff_output))
        return x
    
    
class Transformer(nn.Module):
    def __init__(self, src_vocab_size, tgt_vocab_size, d_model, num_heads, num_layers, d_ff, max_seq_length, dropout):
        super(Transformer, self).__init__()
        self.encoder_embedding = nn.Embedding(src_vocab_size, d_model)
        self.decoder_embedding = nn.Embedding(tgt_vocab_size, d_model)
        self.positional_encoding = PositionalEncoding(d_model, max_seq_length)

        self.encoder_layers = nn.ModuleList([EncoderLayer(d_model, num_heads, d_ff, dropout) for _ in range(num_layers)])
        self.decoder_layers = nn.ModuleList([DecoderLayer(d_model, num_heads, d_ff, dropout) for _ in range(num_layers)])

        self.fc = nn.Linear(d_model, tgt_vocab_size)
        self.dropout = nn.Dropout(dropout)

    def generate_mask(self, src, tgt):
        src_mask = (src != 0).unsqueeze(1).unsqueeze(2)
        tgt_mask = (tgt != 0).unsqueeze(1).unsqueeze(3)
        seq_length = tgt.size(1)
        nopeak_mask = (1 - torch.triu(torch.ones(1, seq_length, seq_length), diagonal=1)).bool()
        tgt_mask = tgt_mask & nopeak_mask
        return src_mask, tgt_mask

    def forward(self, src, tgt):
        src_mask, tgt_mask = self.generate_mask(src, tgt)
        src_embedded = self.dropout(self.positional_encoding(self.encoder_embedding(src)))
        tgt_embedded = self.dropout(self.positional_encoding(self.decoder_embedding(tgt)))

        enc_output = src_embedded
        for enc_layer in self.encoder_layers:
            enc_output = enc_layer(enc_output, src_mask)

        dec_output = tgt_embedded
        for dec_layer in self.decoder_layers:
            dec_output = dec_layer(dec_output, enc_output, src_mask, tgt_mask)

        output = self.fc(dec_output)
        return output
    
    

src_vocab_size = 5000
tgt_vocab_size = 5000
d_model = 512
num_heads = 8
num_layers = 6
d_ff = 2048
max_seq_length = 100
dropout = 0.1

transformer = Transformer(src_vocab_size, tgt_vocab_size, d_model, num_heads, num_layers, d_ff, max_seq_length, dropout)

# Generate random sample data
src_data = torch.randint(1, src_vocab_size, (64, max_seq_length))  # (batch_size, seq_length)
tgt_data = torch.randint(1, tgt_vocab_size, (64, max_seq_length))  # (batch_size, seq_length)

criterion = nn.CrossEntropyLoss(ignore_index=0)
optimizer = optim.Adam(transformer.parameters(), lr=0.0001, betas=(0.9, 0.98), eps=1e-9)

transformer.train()

for epoch in range(100):
    optimizer.zero_grad()
    output = transformer(src_data, tgt_data[:, :-1])
    loss = criterion(output.contiguous().view(-1, tgt_vocab_size), tgt_data[:, 1:].contiguous().view(-1))
    loss.backward()
    optimizer.step()
    print(f"Epoch: {epoch+1}, Loss: {loss.item()}")

from datasets import load_dataset
from trl import DPOConfig, DPOTrainer
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline


dataset = load_dataset("trl-lib/ultrafeedback_binarized", split="train")

model_name = "gpt2"
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto")
ref_model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto")

tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer.pad_token = tokenizer.eos_token
tokenizer.chat_template = "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}"

dpo_config = DPOConfig(
    beta=0.1,
    learning_rate=5e-6,
    per_device_train_batch_size=2,
    num_train_epochs=1,
    logging_steps=1,
    max_prompt_length=64,
    max_length=128,
    remove_unused_columns=False
)

dpo_trainer = DPOTrainer(
    model=model,
    ref_model=ref_model,
    args=dpo_config,
    processing_class=tokenizer,
    train_dataset=dataset,
)

dpo_trainer.train()
dpo_trainer.save_model(model_name)

text_generator = pipeline("text-generation", model=model_name, tokenizer=tokenizer)

while True:
    user_input = input("Enter your prompt: ")
    if user_input.lower() == "exit":
        break
    generated_text = text_generator(user_input, max_length=50, num_return_sequences=1)
    print("Generated text:", generated_text[0]['generated_text'])