File size: 29,112 Bytes
85653bc |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 |
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)
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):
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.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)
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):
"""
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.
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)
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):
"""
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.
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)
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):
with torch.no_grad():
batch_size = x.size(0)
initial_seq_len = x.size(1)
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)
def get_dynamic_stamp(x_stamp, y_stamp, current_seq_len, pred_step):
if current_seq_len <= max_context - pred_step:
return torch.cat([x_stamp, y_stamp[:, :pred_step, :]], dim=1)
else:
start_idx = max_context - pred_step
return torch.cat([x_stamp[:, -start_idx:, :], y_stamp[:, :pred_step, :]], dim=1)
if verbose:
ran = trange
else:
ran = range
for i in ran(pred_len):
current_seq_len = initial_seq_len + i
if current_seq_len <= max_context:
input_tokens = x_token
else:
input_tokens = [t[:, -max_context:].contiguous() for t in x_token]
current_stamp = get_dynamic_stamp(x_stamp, y_stamp, current_seq_len, i)
s1_logits, context = model.decode_s1(input_tokens[0], input_tokens[1], current_stamp)
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)
x_token[0] = torch.cat([x_token[0], sample_pre], dim=1)
x_token[1] = torch.cat([x_token[1], sample_post], dim=1)
torch.cuda.empty_cache()
input_tokens = [t[:, -max_context:].contiguous() for t in x_token]
z = tokenizer.decode(input_tokens, half=True)
z = z.reshape(batch_size, 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):
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)
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):
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, :]
preds = self.generate(x, x_stamp, y_stamp, pred_len, T, top_k, top_p, sample_count, verbose)
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
|