Skip to content

RKiding/Awesome-finance-skills / skills/alphaear-signal-tracker

alphaear-signal-tracker

Verified

Track finance investment signal evolution and update logic based on new finance market information. Use when monitoring finance signals and determining if they are strengthened, weakened, or falsified.

FileKindSize
SKILL.mdskill md1.8 KB
references/PROMPTS.mdmarkdown2.0 KB
scripts/__init__.pyscript0 B
scripts/fin_agent.pyscript3.8 KB
scripts/prompts/fin_agent.pyscript6.6 KB
scripts/prompts/forecast_analyst.pyscript1.9 KB
scripts/prompts/intent_agent.pyscript2.2 KB
scripts/prompts/isq_prompt_generator.pyscript1.8 KB
scripts/prompts/report_agent.pyscript18.1 KB
scripts/prompts/trend_agent.pyscript7.4 KB
scripts/prompts/visualizer.pyscript2.0 KB
scripts/schema/isq_template.pyscript13.6 KB
scripts/schema/models.pyscript6.1 KB
scripts/tools/__init__.pyscript448 B
scripts/tools/toolkits.pyscript18.7 KB
scripts/utils/__init__.pyscript25 B
scripts/utils/content_extractor.pyscript4.7 KB
scripts/utils/database_manager.pyscript21.3 KB
scripts/utils/hybrid_search.pyscript8.0 KB
scripts/utils/json_utils.pyscript6.2 KB
scripts/utils/llm/capability.pyscript2.8 KB
scripts/utils/llm/factory.pyscript3.6 KB
scripts/utils/llm/router.pyscript2.8 KB
scripts/utils/logging_setup.pyscript1.0 KB
scripts/utils/md_to_html.pyscript4.8 KB
scripts/utils/news_tools.pyscript9.9 KB
scripts/utils/predictor/evaluation.pyscript5.6 KB
scripts/utils/predictor/kline_generate.pyscript7.6 KB
scripts/utils/predictor/model/__init__.pyscript394 B
scripts/utils/predictor/model/kronos.pyscript30.4 KB
scripts/utils/predictor/model/module.pyscript22.3 KB
scripts/utils/predictor/training.pyscript18.3 KB
scripts/utils/search_tools.pyscript28.6 KB
scripts/utils/sentiment_tools.pyscript9.9 KB
scripts/utils/stock_tools.pyscript9.8 KB
tests/test_tracker.pyscript565 B

scripts/utils/predictor/model/kronos.py

View on GitHub
import numpy as np
import pandas as pd
import torch
from huggingface_hub import PyTorchModelHubMixin
import sys

from tqdm import trange

sys.path.append("../")
from model.module import *


class KronosTokenizer(nn.Module, PyTorchModelHubMixin):
    """
    KronosTokenizer module for tokenizing input data using a hybrid quantization approach.

    This tokenizer utilizes a combination of encoder and decoder Transformer blocks
    along with the Binary Spherical Quantization (BSQuantizer) to compress and decompress input data.

    Args:
           d_in (int): Input dimension.
           d_model (int): Model dimension.
           n_heads (int): Number of attention heads.
           ff_dim (int): Feed-forward dimension.
           n_enc_layers (int): Number of encoder layers.
           n_dec_layers (int): Number of decoder layers.
           ffn_dropout_p (float): Dropout probability for feed-forward networks.
           attn_dropout_p (float): Dropout probability for attention mechanisms.
           resid_dropout_p (float): Dropout probability for residual connections.
           s1_bits (int): Number of bits for the pre token in BSQuantizer.
           s2_bits (int): Number of bits for the post token in BSQuantizer.
           beta (float): Beta parameter for BSQuantizer.
           gamma0 (float): Gamma0 parameter for BSQuantizer.
           gamma (float): Gamma parameter for BSQuantizer.
           zeta (float): Zeta parameter for BSQuantizer.
           group_size (int): Group size parameter for BSQuantizer.

    """

    def __init__(self, d_in, d_model, n_heads, ff_dim, n_enc_layers, n_dec_layers, ffn_dropout_p, attn_dropout_p, resid_dropout_p, s1_bits, s2_bits, beta, gamma0, gamma, zeta, group_size):

        super().__init__()
        self.d_in = d_in
        self.d_model = d_model
        self.n_heads = n_heads
        self.ff_dim = ff_dim
        self.enc_layers = n_enc_layers
        self.dec_layers = n_dec_layers
        self.ffn_dropout_p = ffn_dropout_p
        self.attn_dropout_p = attn_dropout_p
        self.resid_dropout_p = resid_dropout_p

        self.s1_bits = s1_bits
        self.s2_bits = s2_bits
        self.codebook_dim = s1_bits + s2_bits # Total dimension of the codebook after quantization
        self.embed = nn.Linear(self.d_in, self.d_model)
        self.head = nn.Linear(self.d_model, self.d_in)

        # Encoder Transformer Blocks
        self.encoder = nn.ModuleList([
            TransformerBlock(self.d_model, self.n_heads, self.ff_dim, self.ffn_dropout_p, self.attn_dropout_p, self.resid_dropout_p)
            for _ in range(self.enc_layers - 1)
        ])
        # Decoder Transformer Blocks
        self.decoder = nn.ModuleList([
            TransformerBlock(self.d_model, self.n_heads, self.ff_dim, self.ffn_dropout_p, self.attn_dropout_p, self.resid_dropout_p)
            for _ in range(self.dec_layers - 1)
        ])
        self.quant_embed = nn.Linear(in_features=self.d_model, out_features=self.codebook_dim) # Linear layer before quantization
        self.post_quant_embed_pre = nn.Linear(in_features=self.s1_bits, out_features=self.d_model) # Linear layer after quantization (pre part - s1 bits)
        self.post_quant_embed = nn.Linear(in_features=self.codebook_dim, out_features=self.d_model) # Linear layer after quantization (full codebook)
        self.tokenizer = BSQuantizer(self.s1_bits, self.s2_bits, beta, gamma0, gamma, zeta, group_size) # BSQuantizer module

    def forward(self, x):
        """
        Forward pass of the KronosTokenizer.

        Args:
            x (torch.Tensor): Input tensor of shape (batch_size, seq_len, d_in).

        Returns:
            tuple: A tuple containing:
                - tuple: (z_pre, z) - Reconstructed outputs from decoder with s1_bits and full codebook respectively,
                         both of shape (batch_size, seq_len, d_in).
                - torch.Tensor: bsq_loss - Loss from the BSQuantizer.
                - torch.Tensor: quantized - Quantized representation from BSQuantizer.
                - torch.Tensor: z_indices - Indices from the BSQuantizer.
        """
        z = self.embed(x)

        for layer in self.encoder:
            z = layer(z)

        z = self.quant_embed(z) # (B, T, codebook)

        bsq_loss, quantized, z_indices = self.tokenizer(z)

        quantized_pre = quantized[:, :, :self.s1_bits] # Extract the first part of quantized representation (s1_bits)
        z_pre = self.post_quant_embed_pre(quantized_pre)

        z = self.post_quant_embed(quantized)

        # Decoder layers (for pre part - s1 bits)
        for layer in self.decoder:
            z_pre = layer(z_pre)
        z_pre = self.head(z_pre)

        # Decoder layers (for full codebook)
        for layer in self.decoder:
            z = layer(z)
        z = self.head(z)

        return (z_pre, z), bsq_loss, quantized, z_indices

    def indices_to_bits(self, x, half=False):
        """
        Converts indices to bit representations and scales them.

        Args:
            x (torch.Tensor): Indices tensor.
            half (bool, optional): Whether to process only half of the codebook dimension. Defaults to False.

        Returns:
            torch.Tensor: Bit representation tensor.
        """
        if half:
            x1 = x[0] # Assuming x is a tuple of indices if half is True
            x2 = x[1]
            mask = 2 ** torch.arange(self.codebook_dim//2, device=x1.device, dtype=torch.long) # Create a mask for bit extraction
            x1 = (x1.unsqueeze(-1) & mask) != 0 # Extract bits for the first half
            x2 = (x2.unsqueeze(-1) & mask) != 0 # Extract bits for the second half
            x = torch.cat([x1, x2], dim=-1) # Concatenate the bit representations
        else:
            mask = 2 ** torch.arange(self.codebook_dim, device=x.device, dtype=torch.long) # Create a mask for bit extraction
            x = (x.unsqueeze(-1) & mask) != 0 # Extract bits

        x = x.float() * 2 - 1 # Convert boolean to bipolar (-1, 1)
        q_scale = 1. / (self.codebook_dim ** 0.5) # Scaling factor
        x = x * q_scale
        return x

    def encode(self, x, half=False):
        """
        Encodes the input data into quantized indices.

        Args:
            x (torch.Tensor): Input tensor of shape (batch_size, seq_len, d_in).
            half (bool, optional): Whether to use half quantization in BSQuantizer. Defaults to False.

        Returns:
            torch.Tensor: Quantized indices from BSQuantizer.
        """
        z = self.embed(x)
        for layer in self.encoder:
            z = layer(z)
        z = self.quant_embed(z)

        bsq_loss, quantized, z_indices = self.tokenizer(z, half=half, collect_metrics=False)
        return z_indices

    def decode(self, x, half=False):
        """
        Decodes quantized indices back to the input data space.

        Args:
            x (torch.Tensor): Quantized indices tensor.
            half (bool, optional): Whether the indices were generated with half quantization. Defaults to False.

        Returns:
            torch.Tensor: Reconstructed output tensor of shape (batch_size, seq_len, d_in).
        """
        quantized = self.indices_to_bits(x, half)
        z = self.post_quant_embed(quantized)
        for layer in self.decoder:
            z = layer(z)
        z = self.head(z)
        return z


class Kronos(nn.Module, PyTorchModelHubMixin):
    """
    Kronos Model.

    Args:
        s1_bits (int): Number of bits for pre tokens.
        s2_bits (int): Number of bits for post tokens.
        n_layers (int): Number of Transformer blocks.
        d_model (int): Dimension of the model's embeddings and hidden states.
        n_heads (int): Number of attention heads in the MultiheadAttention layers.
        ff_dim (int): Dimension of the feedforward network in the Transformer blocks.
        ffn_dropout_p (float): Dropout probability for the feedforward network.
        attn_dropout_p (float): Dropout probability for the attention layers.
        resid_dropout_p (float): Dropout probability for residual connections.
        token_dropout_p (float): Dropout probability for token embeddings.
        learn_te (bool): Whether to use learnable temporal embeddings.
    """

    def __init__(self, s1_bits, s2_bits, n_layers, d_model, n_heads, ff_dim, ffn_dropout_p, attn_dropout_p, resid_dropout_p, token_dropout_p, learn_te, news_dim=None):
        super().__init__()
        self.s1_bits = s1_bits
        self.s2_bits = s2_bits
        self.n_layers = n_layers
        self.d_model = d_model
        self.n_heads = n_heads
        self.learn_te = learn_te
        self.ff_dim = ff_dim
        self.ffn_dropout_p = ffn_dropout_p
        self.attn_dropout_p = attn_dropout_p
        self.resid_dropout_p = resid_dropout_p
        self.token_dropout_p = token_dropout_p
        self.news_dim = news_dim

        self.s1_vocab_size = 2 ** self.s1_bits
        self.token_drop = nn.Dropout(self.token_dropout_p)
        self.embedding = HierarchicalEmbedding(self.s1_bits, self.s2_bits, self.d_model)
        self.time_emb = TemporalEmbedding(self.d_model, self.learn_te)
        self.transformer = nn.ModuleList([
            TransformerBlock(self.d_model, self.n_heads, self.ff_dim, self.ffn_dropout_p, self.attn_dropout_p, self.resid_dropout_p)
            for _ in range(self.n_layers)
        ])
        self.norm = RMSNorm(self.d_model)
        self.dep_layer = DependencyAwareLayer(self.d_model)
        self.head = DualHead(self.s1_bits, self.s2_bits, self.d_model)

        if self.news_dim is not None:
            self.news_proj = nn.Linear(self.news_dim, self.d_model)
        else:
            self.news_proj = None

        self.apply(self._init_weights)

    def _init_weights(self, module):

        if isinstance(module, nn.Linear):
            nn.init.xavier_normal_(module.weight)
            if module.bias is not None:
                nn.init.zeros_(module.bias)
        elif isinstance(module, nn.Embedding):
            nn.init.normal_(module.weight, mean=0, std=self.embedding.d_model ** -0.5)
        elif isinstance(module, nn.LayerNorm):
            nn.init.ones_(module.weight)
            nn.init.zeros_(module.bias)
        elif isinstance(module, RMSNorm):
            nn.init.ones_(module.weight)

    def forward(self, s1_ids, s2_ids, stamp=None, padding_mask=None, use_teacher_forcing=False, s1_targets=None, news_emb=None):
        """
        Args:
            s1_ids (torch.Tensor): Input tensor of s1 token IDs. Shape: [batch_size, seq_len]
            s2_ids (torch.Tensor): Input tensor of s2 token IDs. Shape: [batch_size, seq_len]
            stamp (torch.Tensor, optional): Temporal stamp tensor. Shape: [batch_size, seq_len]. Defaults to None.
            padding_mask (torch.Tensor, optional): Mask for padding tokens. Shape: [batch_size, seq_len]. Defaults to None.
            use_teacher_forcing (bool, optional): Whether to use teacher forcing for s1 decoding. Defaults to False.
            s1_targets (torch.Tensor, optional): Target s1 token IDs for teacher forcing. Shape: [batch_size, seq_len]. Defaults to None.
            news_emb (torch.Tensor, optional): News embedding tensor. Shape: [batch_size, news_dim]. Defaults to None.

        Returns:
            Tuple[torch.Tensor, torch.Tensor]:
                - s1 logits: Logits for s1 token predictions. Shape: [batch_size, seq_len, s1_vocab_size]
                - s2_logits: Logits for s2 token predictions, conditioned on s1. Shape: [batch_size, seq_len, s2_vocab_size]
        """
        x = self.embedding([s1_ids, s2_ids])
        if stamp is not None:
            time_embedding = self.time_emb(stamp)
            x = x + time_embedding
        x = self.token_drop(x)

        for layer in self.transformer:
            x = layer(x, key_padding_mask=padding_mask)

        x = self.norm(x)

        if news_emb is not None and self.news_proj is not None:
            news_bias = self.news_proj(news_emb).unsqueeze(1) # [B, 1, d_model]
            x = x + news_bias

        s1_logits = self.head(x)

        if use_teacher_forcing:
            sibling_embed = self.embedding.emb_s1(s1_targets)
        else:
            s1_probs = F.softmax(s1_logits.detach(), dim=-1)
            sample_s1_ids = torch.multinomial(s1_probs.view(-1, self.s1_vocab_size), 1).view(s1_ids.shape)
            sibling_embed = self.embedding.emb_s1(sample_s1_ids)

        x2 = self.dep_layer(x, sibling_embed, key_padding_mask=padding_mask) # Dependency Aware Layer: Condition on s1 embeddings
        s2_logits = self.head.cond_forward(x2)
        return s1_logits, s2_logits

    def decode_s1(self, s1_ids, s2_ids, stamp=None, padding_mask=None, news_emb=None):
        """
        Decodes only the s1 tokens.

        This method performs a forward pass to predict only s1 tokens. It returns the s1 logits
        and the context representation from the Transformer, which can be used for subsequent s2 decoding.

        Args:
            s1_ids (torch.Tensor): Input tensor of s1 token IDs. Shape: [batch_size, seq_len]
            s2_ids (torch.Tensor): Input tensor of s2 token IDs. Shape: [batch_size, seq_len]
            stamp (torch.Tensor, optional): Temporal stamp tensor. Shape: [batch_size, seq_len]. Defaults to None.
            padding_mask (torch.Tensor, optional): Mask for padding tokens. Shape: [batch_size, seq_len]. Defaults to None.
            news_emb (torch.Tensor, optional): News embedding tensor. Shape: [batch_size, news_dim]. Defaults to None.

        Returns:
            Tuple[torch.Tensor, torch.Tensor]:
                - s1 logits: Logits for s1 token predictions. Shape: [batch_size, seq_len, s1_vocab_size]
                - context: Context representation from the Transformer. Shape: [batch_size, seq_len, d_model]
        """
        x = self.embedding([s1_ids, s2_ids])
        if stamp is not None:
            time_embedding = self.time_emb(stamp)
            x = x + time_embedding
        x = self.token_drop(x)

        for layer in self.transformer:
            x = layer(x, key_padding_mask=padding_mask)

        x = self.norm(x)

        if news_emb is not None and self.news_proj is not None:
            news_bias = self.news_proj(news_emb).unsqueeze(1) # [B, 1, d_model]
            x = x + news_bias

        s1_logits = self.head(x)
        return s1_logits, x

    def decode_s2(self, context, s1_ids, padding_mask=None):
        """
        Decodes the s2 tokens, conditioned on the context and s1 tokens.

        This method decodes s2 tokens based on a pre-computed context representation (typically from `decode_s1`)
        and the s1 token IDs. It uses the dependency-aware layer and the conditional s2 head to predict s2 tokens.

        Args:
            context (torch.Tensor): Context representation from the transformer (output of decode_s1).
                                     Shape: [batch_size, seq_len, d_model]
            s1_ids (torch.torch.Tensor): Input tensor of s1 token IDs. Shape: [batch_size, seq_len]
            padding_mask (torch.Tensor, optional): Mask for padding tokens. Shape: [batch_size, seq_len]. Defaults to None.

        Returns:
            torch.Tensor: s2 logits. Shape: [batch_size, seq_len, s2_vocab_size]
        """
        sibling_embed = self.embedding.emb_s1(s1_ids)
        x2 = self.dep_layer(context, sibling_embed, key_padding_mask=padding_mask)
        return self.head.cond_forward(x2)


def top_k_top_p_filtering(
        logits,
        top_k: int = 0,
        top_p: float = 1.0,
        filter_value: float = -float("Inf"),
        min_tokens_to_keep: int = 1,
):
    """Filter a distribution of logits using top-k and/or nucleus (top-p) filtering
    Args:
        logits: logits distribution shape (batch size, vocabulary size)
        if top_k > 0: keep only top k tokens with highest probability (top-k filtering).
        if top_p < 1.0: keep the top tokens with cumulative probability >= top_p (nucleus filtering).
            Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751)
        Make sure we keep at least min_tokens_to_keep per batch example in the output
    From: https://gist.github.com/thomwolf/1a5a29f6962089e871b94cbd09daf317
    """
    if top_k > 0:
        top_k = min(max(top_k, min_tokens_to_keep), logits.size(-1))  # Safety check
        # Remove all tokens with a probability less than the last token of the top-k
        indices_to_remove = logits < torch.topk(logits, top_k)[0][..., -1, None]
        logits[indices_to_remove] = filter_value
        return logits

    if top_p < 1.0:
        sorted_logits, sorted_indices = torch.sort(logits, descending=True)
        cumulative_probs = torch.cumsum(F.softmax(sorted_logits, dim=-1), dim=-1)

        # Remove tokens with cumulative probability above the threshold (token with 0 are kept)
        sorted_indices_to_remove = cumulative_probs > top_p
        if min_tokens_to_keep > 1:
            # Keep at least min_tokens_to_keep (set to min_tokens_to_keep-1 because we add the first one below)
            sorted_indices_to_remove[..., :min_tokens_to_keep] = 0
        # Shift the indices to the right to keep also the first token above the threshold
        sorted_indices_to_remove[..., 1:] = sorted_indices_to_remove[..., :-1].clone()
        sorted_indices_to_remove[..., 0] = 0

        # scatter sorted tensors to original indexing
        indices_to_remove = sorted_indices_to_remove.scatter(1, sorted_indices, sorted_indices_to_remove)
        logits[indices_to_remove] = filter_value
        return logits


def sample_from_logits(logits, temperature=1.0, top_k=None, top_p=None, sample_logits=True):
    logits = logits / temperature
    if top_k is not None or top_p is not None:
        if top_k > 0 or top_p < 1.0:
            logits = top_k_top_p_filtering(logits, top_k=top_k, top_p=top_p)

    probs = F.softmax(logits, dim=-1)

    if not sample_logits:
        _, x = top_k(probs, k=1, dim=-1)
    else:
        x = torch.multinomial(probs, num_samples=1)

    return x


def auto_regressive_inference(tokenizer, model, x, x_stamp, y_stamp, max_context, pred_len, clip=5, T=1.0, top_k=0, top_p=0.99, sample_count=5, verbose=False, news_emb=None):
    with torch.no_grad():
        x = torch.clip(x, -clip, clip)

        device = x.device
        x = x.unsqueeze(1).repeat(1, sample_count, 1, 1).reshape(-1, x.size(1), x.size(2)).to(device)
        x_stamp = x_stamp.unsqueeze(1).repeat(1, sample_count, 1, 1).reshape(-1, x_stamp.size(1), x_stamp.size(2)).to(device)
        y_stamp = y_stamp.unsqueeze(1).repeat(1, sample_count, 1, 1).reshape(-1, y_stamp.size(1), y_stamp.size(2)).to(device)

        x_token = tokenizer.encode(x, half=True)
        
        initial_seq_len = x.size(1)
        batch_size = x_token[0].size(0)
        total_seq_len = initial_seq_len + pred_len
        full_stamp = torch.cat([x_stamp, y_stamp], dim=1)

        generated_pre = x_token[0].new_empty(batch_size, pred_len)
        generated_post = x_token[1].new_empty(batch_size, pred_len)

        pre_buffer = x_token[0].new_zeros(batch_size, max_context)
        post_buffer = x_token[1].new_zeros(batch_size, max_context)
        buffer_len = min(initial_seq_len, max_context)
        if buffer_len > 0:
            start_idx = max(0, initial_seq_len - max_context)
            pre_buffer[:, :buffer_len] = x_token[0][:, start_idx:start_idx + buffer_len]
            post_buffer[:, :buffer_len] = x_token[1][:, start_idx:start_idx + buffer_len]

        if verbose:
            ran = trange
        else:
            ran = range
        for i in ran(pred_len):
            current_seq_len = initial_seq_len + i
            window_len = min(current_seq_len, max_context)

            if current_seq_len <= max_context:
                input_tokens = [
                    pre_buffer[:, :window_len],
                    post_buffer[:, :window_len]
                ]
            else:
                input_tokens = [pre_buffer, post_buffer]

            context_end = current_seq_len
            context_start = max(0, context_end - max_context)
            current_stamp = full_stamp[:, context_start:context_end, :].contiguous()

            s1_logits, context = model.decode_s1(input_tokens[0], input_tokens[1], current_stamp, news_emb=news_emb)
            s1_logits = s1_logits[:, -1, :]
            sample_pre = sample_from_logits(s1_logits, temperature=T, top_k=top_k, top_p=top_p, sample_logits=True)

            s2_logits = model.decode_s2(context, sample_pre)
            s2_logits = s2_logits[:, -1, :]
            sample_post = sample_from_logits(s2_logits, temperature=T, top_k=top_k, top_p=top_p, sample_logits=True)

            generated_pre[:, i] = sample_pre.squeeze(-1)
            generated_post[:, i] = sample_post.squeeze(-1)

            if current_seq_len < max_context:
                pre_buffer[:, current_seq_len] = sample_pre.squeeze(-1)
                post_buffer[:, current_seq_len] = sample_post.squeeze(-1)
            else:
                pre_buffer.copy_(torch.roll(pre_buffer, shifts=-1, dims=1))
                post_buffer.copy_(torch.roll(post_buffer, shifts=-1, dims=1))
                pre_buffer[:, -1] = sample_pre.squeeze(-1)
                post_buffer[:, -1] = sample_post.squeeze(-1)

        full_pre = torch.cat([x_token[0], generated_pre], dim=1)
        full_post = torch.cat([x_token[1], generated_post], dim=1)

        context_start = max(0, total_seq_len - max_context)
        input_tokens = [
            full_pre[:, context_start:total_seq_len].contiguous(),
            full_post[:, context_start:total_seq_len].contiguous()
        ]
        z = tokenizer.decode(input_tokens, half=True)
        z = z.reshape(-1, sample_count, z.size(1), z.size(2))
        preds = z.cpu().numpy()
        preds = np.mean(preds, axis=1)

        return preds


def calc_time_stamps(x_timestamp):
    time_df = pd.DataFrame()
    time_df['minute'] = x_timestamp.dt.minute
    time_df['hour'] = x_timestamp.dt.hour
    time_df['weekday'] = x_timestamp.dt.weekday
    time_df['day'] = x_timestamp.dt.day
    time_df['month'] = x_timestamp.dt.month
    return time_df


class KronosPredictor:

    def __init__(self, model, tokenizer, device="cuda:0", max_context=512, clip=5):
        self.tokenizer = tokenizer
        self.model = model
        self.max_context = max_context
        self.clip = clip
        self.price_cols = ['open', 'high', 'low', 'close']
        self.vol_col = 'volume'
        self.amt_vol = 'amount'
        self.time_cols = ['minute', 'hour', 'weekday', 'day', 'month']
        self.device = device

        self.tokenizer = self.tokenizer.to(self.device)
        self.model = self.model.to(self.device)

    def generate(self, x, x_stamp, y_stamp, pred_len, T, top_k, top_p, sample_count, verbose, news_emb=None):

        x_tensor = torch.from_numpy(np.array(x).astype(np.float32)).to(self.device)
        x_stamp_tensor = torch.from_numpy(np.array(x_stamp).astype(np.float32)).to(self.device)
        y_stamp_tensor = torch.from_numpy(np.array(y_stamp).astype(np.float32)).to(self.device)

        preds = auto_regressive_inference(self.tokenizer, self.model, x_tensor, x_stamp_tensor, y_stamp_tensor, self.max_context, pred_len,
                                          self.clip, T, top_k, top_p, sample_count, verbose, news_emb=news_emb)
        preds = preds[:, -pred_len:, :]
        return preds

    def predict(self, df, x_timestamp, y_timestamp, pred_len, T=1.0, top_k=0, top_p=0.9, sample_count=1, verbose=True, news_emb=None):

        if not isinstance(df, pd.DataFrame):
            raise ValueError("Input must be a pandas DataFrame.")

        if not all(col in df.columns for col in self.price_cols):
            raise ValueError(f"Price columns {self.price_cols} not found in DataFrame.")

        df = df.copy()
        if self.vol_col not in df.columns:
            df[self.vol_col] = 0.0  # Fill missing volume with zeros
            df[self.amt_vol] = 0.0  # Fill missing amount with zeros
        if self.amt_vol not in df.columns and self.vol_col in df.columns:
            df[self.amt_vol] = df[self.vol_col] * df[self.price_cols].mean(axis=1)

        if df[self.price_cols + [self.vol_col, self.amt_vol]].isnull().values.any():
            raise ValueError("Input DataFrame contains NaN values in price or volume columns.")

        x_time_df = calc_time_stamps(x_timestamp)
        y_time_df = calc_time_stamps(y_timestamp)

        x = df[self.price_cols + [self.vol_col, self.amt_vol]].values.astype(np.float32)
        x_stamp = x_time_df.values.astype(np.float32)
        y_stamp = y_time_df.values.astype(np.float32)

        x_mean, x_std = np.mean(x, axis=0), np.std(x, axis=0)

        x = (x - x_mean) / (x_std + 1e-5)
        x = np.clip(x, -self.clip, self.clip)

        x = x[np.newaxis, :]
        x_stamp = x_stamp[np.newaxis, :]
        y_stamp = y_stamp[np.newaxis, :]

        if news_emb is not None:
            news_emb_tensor = torch.from_numpy(np.array(news_emb).astype(np.float32)).to(self.device)
            # Ensure batch dimension for news_emb if only one sample
            if news_emb_tensor.ndim == 1:
                news_emb_tensor = news_emb_tensor.unsqueeze(0)
        else:
            news_emb_tensor = None

        preds = self.generate(x, x_stamp, y_stamp, pred_len, T, top_k, top_p, sample_count, verbose, news_emb=news_emb_tensor)

        preds = preds.squeeze(0)
        preds = preds * (x_std + 1e-5) + x_mean

        pred_df = pd.DataFrame(preds, columns=self.price_cols + [self.vol_col, self.amt_vol], index=y_timestamp)
        return pred_df


    def predict_batch(self, df_list, x_timestamp_list, y_timestamp_list, pred_len, T=1.0, top_k=0, top_p=0.9, sample_count=1, verbose=True):
        """
        Perform parallel (batch) prediction on multiple time series. All series must have the same historical length and prediction length (pred_len).

        Args:
            df_list (List[pd.DataFrame]): List of input DataFrames, each containing price columns and optional volume/amount columns.
            x_timestamp_list (List[pd.DatetimeIndex or Series]): List of timestamps corresponding to historical data, length should match the number of rows in each DataFrame.
            y_timestamp_list (List[pd.DatetimeIndex or Series]): List of future prediction timestamps, length should equal pred_len.
            pred_len (int): Number of prediction steps.
            T (float): Sampling temperature.
            top_k (int): Top-k filtering threshold.
            top_p (float): Top-p (nucleus sampling) threshold.
            sample_count (int): Number of parallel samples per series, automatically averaged internally.
            verbose (bool): Whether to display autoregressive progress.

        Returns:
            List[pd.DataFrame]: List of prediction results in the same order as input, each DataFrame contains
                                `open, high, low, close, volume, amount` columns, indexed by corresponding `y_timestamp`.
        """
        # Basic validation
        if not isinstance(df_list, (list, tuple)) or not isinstance(x_timestamp_list, (list, tuple)) or not isinstance(y_timestamp_list, (list, tuple)):
            raise ValueError("df_list, x_timestamp_list, y_timestamp_list must be list or tuple types.")
        if not (len(df_list) == len(x_timestamp_list) == len(y_timestamp_list)):
            raise ValueError("df_list, x_timestamp_list, y_timestamp_list must have consistent lengths.")

        num_series = len(df_list)

        x_list = []
        x_stamp_list = []
        y_stamp_list = []
        means = []
        stds = []
        seq_lens = []
        y_lens = []

        for i in range(num_series):
            df = df_list[i]
            if not isinstance(df, pd.DataFrame):
                raise ValueError(f"Input at index {i} is not a pandas DataFrame.")
            if not all(col in df.columns for col in self.price_cols):
                raise ValueError(f"DataFrame at index {i} is missing price columns {self.price_cols}.")

            df = df.copy()
            if self.vol_col not in df.columns:
                df[self.vol_col] = 0.0
                df[self.amt_vol] = 0.0
            if self.amt_vol not in df.columns and self.vol_col in df.columns:
                df[self.amt_vol] = df[self.vol_col] * df[self.price_cols].mean(axis=1)

            if df[self.price_cols + [self.vol_col, self.amt_vol]].isnull().values.any():
                raise ValueError(f"DataFrame at index {i} contains NaN values in price or volume columns.")

            x_timestamp = x_timestamp_list[i]
            y_timestamp = y_timestamp_list[i]

            x_time_df = calc_time_stamps(x_timestamp)
            y_time_df = calc_time_stamps(y_timestamp)

            x = df[self.price_cols + [self.vol_col, self.amt_vol]].values.astype(np.float32)
            x_stamp = x_time_df.values.astype(np.float32)
            y_stamp = y_time_df.values.astype(np.float32)

            if x.shape[0] != x_stamp.shape[0]:
                raise ValueError(f"Inconsistent lengths at index {i}: x has {x.shape[0]} vs x_stamp has {x_stamp.shape[0]}.")
            if y_stamp.shape[0] != pred_len:
                raise ValueError(f"y_timestamp length at index {i} should equal pred_len={pred_len}, got {y_stamp.shape[0]}.")

            x_mean, x_std = np.mean(x, axis=0), np.std(x, axis=0)
            x_norm = (x - x_mean) / (x_std + 1e-5)
            x_norm = np.clip(x_norm, -self.clip, self.clip)

            x_list.append(x_norm)
            x_stamp_list.append(x_stamp)
            y_stamp_list.append(y_stamp)
            means.append(x_mean)
            stds.append(x_std)

            seq_lens.append(x_norm.shape[0])
            y_lens.append(y_stamp.shape[0])

        # Require all series to have consistent historical and prediction lengths for batch processing
        if len(set(seq_lens)) != 1:
            raise ValueError(f"Parallel prediction requires all series to have consistent historical lengths, got: {seq_lens}")
        if len(set(y_lens)) != 1:
            raise ValueError(f"Parallel prediction requires all series to have consistent prediction lengths, got: {y_lens}")

        x_batch = np.stack(x_list, axis=0).astype(np.float32)           # (B, seq_len, feat)
        x_stamp_batch = np.stack(x_stamp_list, axis=0).astype(np.float32) # (B, seq_len, time_feat)
        y_stamp_batch = np.stack(y_stamp_list, axis=0).astype(np.float32) # (B, pred_len, time_feat)

        preds = self.generate(x_batch, x_stamp_batch, y_stamp_batch, pred_len, T, top_k, top_p, sample_count, verbose)
        # preds: (B, pred_len, feat)

        pred_dfs = []
        for i in range(num_series):
            preds_i = preds[i] * (stds[i] + 1e-5) + means[i]
            pred_df = pd.DataFrame(preds_i, columns=self.price_cols + [self.vol_col, self.amt_vol], index=y_timestamp_list[i])
            pred_dfs.append(pred_df)

        return pred_dfs
slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 194kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 194kUpdated Claude CodeCodexVerifiedInstall