import torch
import numpy as np
import torch.nn as nn
import torch.nn.functional as F
from torch import Tensor
from typing import List, Tuple
import math
from functools import partial
from torch import nn, einsum, diagonal
from math import log2, ceil
import pdb
from sympy import Poly, legendre, Symbol, chebyshevt
from scipy.special import eval_legendre
def legendreDer(k, x):
def _legendre(k, x):
return (2 * k + 1) * eval_legendre(k, x)
out = 0
for i in np.arange(k - 1, -1, -2):
out += _legendre(i, x)
return out
def phi_(phi_c, x, lb=0, ub=1):
mask = np.logical_or(x < lb, x > ub) * 1.0
return np.polynomial.polynomial.Polynomial(phi_c)(x) * (1 - mask)
def get_phi_psi(k, base):
x = Symbol('x')
phi_coeff = np.zeros((k, k))
phi_2x_coeff = np.zeros((k, k))
if base == 'legendre':
for ki in range(k):
coeff_ = Poly(legendre(ki, 2 * x - 1), x).all_coeffs()
phi_coeff[ki, :ki + 1] = np.flip(np.sqrt(2 * ki + 1) * np.array(coeff_).astype(np.float64))
coeff_ = Poly(legendre(ki, 4 * x - 1), x).all_coeffs()
phi_2x_coeff[ki, :ki + 1] = np.flip(np.sqrt(2) * np.sqrt(2 * ki + 1) * np.array(coeff_).astype(np.float64))
psi1_coeff = np.zeros((k, k))
psi2_coeff = np.zeros((k, k))
for ki in range(k):
psi1_coeff[ki, :] = phi_2x_coeff[ki, :]
for i in range(k):
a = phi_2x_coeff[ki, :ki + 1]
b = phi_coeff[i, :i + 1]
prod_ = np.convolve(a, b)
prod_[np.abs(prod_) < 1e-8] = 0
proj_ = (prod_ * 1 / (np.arange(len(prod_)) + 1) * np.power(0.5, 1 + np.arange(len(prod_)))).sum()
psi1_coeff[ki, :] -= proj_ * phi_coeff[i, :]
psi2_coeff[ki, :] -= proj_ * phi_coeff[i, :]
for j in range(ki):
a = phi_2x_coeff[ki, :ki + 1]
b = psi1_coeff[j, :]
prod_ = np.convolve(a, b)
prod_[np.abs(prod_) < 1e-8] = 0
proj_ = (prod_ * 1 / (np.arange(len(prod_)) + 1) * np.power(0.5, 1 + np.arange(len(prod_)))).sum()
psi1_coeff[ki, :] -= proj_ * psi1_coeff[j, :]
psi2_coeff[ki, :] -= proj_ * psi2_coeff[j, :]
a = psi1_coeff[ki, :]
prod_ = np.convolve(a, a)
prod_[np.abs(prod_) < 1e-8] = 0
norm1 = (prod_ * 1 / (np.arange(len(prod_)) + 1) * np.power(0.5, 1 + np.arange(len(prod_)))).sum()
a = psi2_coeff[ki, :]
prod_ = np.convolve(a, a)
prod_[np.abs(prod_) < 1e-8] = 0
norm2 = (prod_ * 1 / (np.arange(len(prod_)) + 1) * (1 - np.power(0.5, 1 + np.arange(len(prod_))))).sum()
norm_ = np.sqrt(norm1 + norm2)
psi1_coeff[ki, :] /= norm_
psi2_coeff[ki, :] /= norm_
psi1_coeff[np.abs(psi1_coeff) < 1e-8] = 0
psi2_coeff[np.abs(psi2_coeff) < 1e-8] = 0
phi = [np.poly1d(np.flip(phi_coeff[i, :])) for i in range(k)]
psi1 = [np.poly1d(np.flip(psi1_coeff[i, :])) for i in range(k)]
psi2 = [np.poly1d(np.flip(psi2_coeff[i, :])) for i in range(k)]
elif base == 'chebyshev':
for ki in range(k):
if ki == 0:
phi_coeff[ki, :ki + 1] = np.sqrt(2 / np.pi)
phi_2x_coeff[ki, :ki + 1] = np.sqrt(2 / np.pi) * np.sqrt(2)
else:
coeff_ = Poly(chebyshevt(ki, 2 * x - 1), x).all_coeffs()
phi_coeff[ki, :ki + 1] = np.flip(2 / np.sqrt(np.pi) * np.array(coeff_).astype(np.float64))
coeff_ = Poly(chebyshevt(ki, 4 * x - 1), x).all_coeffs()
phi_2x_coeff[ki, :ki + 1] = np.flip(
np.sqrt(2) * 2 / np.sqrt(np.pi) * np.array(coeff_).astype(np.float64))
phi = [partial(phi_, phi_coeff[i, :]) for i in range(k)]
x = Symbol('x')
kUse = 2 * k
roots = Poly(chebyshevt(kUse, 2 * x - 1)).all_roots()
x_m = np.array([rt.evalf(20) for rt in roots]).astype(np.float64)
# x_m[x_m==0.5] = 0.5 + 1e-8 # add small noise to avoid the case of 0.5 belonging to both phi(2x) and phi(2x-1)
# not needed for our purpose here, we use even k always to avoid
wm = np.pi / kUse / 2
psi1_coeff = np.zeros((k, k))
psi2_coeff = np.zeros((k, k))
psi1 = [[] for _ in range(k)]
psi2 = [[] for _ in range(k)]
for ki in range(k):
psi1_coeff[ki, :] = phi_2x_coeff[ki, :]
for i in range(k):
proj_ = (wm * phi[i](x_m) * np.sqrt(2) * phi[ki](2 * x_m)).sum()
psi1_coeff[ki, :] -= proj_ * phi_coeff[i, :]
psi2_coeff[ki, :] -= proj_ * phi_coeff[i, :]
for j in range(ki):
proj_ = (wm * psi1[j](x_m) * np.sqrt(2) * phi[ki](2 * x_m)).sum()
psi1_coeff[ki, :] -= proj_ * psi1_coeff[j, :]
psi2_coeff[ki, :] -= proj_ * psi2_coeff[j, :]
psi1[ki] = partial(phi_, psi1_coeff[ki, :], lb=0, ub=0.5)
psi2[ki] = partial(phi_, psi2_coeff[ki, :], lb=0.5, ub=1)
norm1 = (wm * psi1[ki](x_m) * psi1[ki](x_m)).sum()
norm2 = (wm * psi2[ki](x_m) * psi2[ki](x_m)).sum()
norm_ = np.sqrt(norm1 + norm2)
psi1_coeff[ki, :] /= norm_
psi2_coeff[ki, :] /= norm_
psi1_coeff[np.abs(psi1_coeff) < 1e-8] = 0
psi2_coeff[np.abs(psi2_coeff) < 1e-8] = 0
psi1[ki] = partial(phi_, psi1_coeff[ki, :], lb=0, ub=0.5 + 1e-16)
psi2[ki] = partial(phi_, psi2_coeff[ki, :], lb=0.5 + 1e-16, ub=1)
return phi, psi1, psi2
def get_filter(base, k):
def psi(psi1, psi2, i, inp):
mask = (inp <= 0.5) * 1.0
return psi1[i](inp) * mask + psi2[i](inp) * (1 - mask)
if base not in ['legendre', 'chebyshev']:
raise Exception('Base not supported')
x = Symbol('x')
H0 = np.zeros((k, k))
H1 = np.zeros((k, k))
G0 = np.zeros((k, k))
G1 = np.zeros((k, k))
PHI0 = np.zeros((k, k))
PHI1 = np.zeros((k, k))
phi, psi1, psi2 = get_phi_psi(k, base)
if base == 'legendre':
roots = Poly(legendre(k, 2 * x - 1)).all_roots()
x_m = np.array([rt.evalf(20) for rt in roots]).astype(np.float64)
wm = 1 / k / legendreDer(k, 2 * x_m - 1) / eval_legendre(k - 1, 2 * x_m - 1)
for ki in range(k):
for kpi in range(k):
H0[ki, kpi] = 1 / np.sqrt(2) * (wm * phi[ki](x_m / 2) * phi[kpi](x_m)).sum()
G0[ki, kpi] = 1 / np.sqrt(2) * (wm * psi(psi1, psi2, ki, x_m / 2) * phi[kpi](x_m)).sum()
H1[ki, kpi] = 1 / np.sqrt(2) * (wm * phi[ki]((x_m + 1) / 2) * phi[kpi](x_m)).sum()
G1[ki, kpi] = 1 / np.sqrt(2) * (wm * psi(psi1, psi2, ki, (x_m + 1) / 2) * phi[kpi](x_m)).sum()
PHI0 = np.eye(k)
PHI1 = np.eye(k)
elif base == 'chebyshev':
x = Symbol('x')
kUse = 2 * k
roots = Poly(chebyshevt(kUse, 2 * x - 1)).all_roots()
x_m = np.array([rt.evalf(20) for rt in roots]).astype(np.float64)
# x_m[x_m==0.5] = 0.5 + 1e-8 # add small noise to avoid the case of 0.5 belonging to both phi(2x) and phi(2x-1)
# not needed for our purpose here, we use even k always to avoid
wm = np.pi / kUse / 2
for ki in range(k):
for kpi in range(k):
H0[ki, kpi] = 1 / np.sqrt(2) * (wm * phi[ki](x_m / 2) * phi[kpi](x_m)).sum()
G0[ki, kpi] = 1 / np.sqrt(2) * (wm * psi(psi1, psi2, ki, x_m / 2) * phi[kpi](x_m)).sum()
H1[ki, kpi] = 1 / np.sqrt(2) * (wm * phi[ki]((x_m + 1) / 2) * phi[kpi](x_m)).sum()
G1[ki, kpi] = 1 / np.sqrt(2) * (wm * psi(psi1, psi2, ki, (x_m + 1) / 2) * phi[kpi](x_m)).sum()
PHI0[ki, kpi] = (wm * phi[ki](2 * x_m) * phi[kpi](2 * x_m)).sum() * 2
PHI1[ki, kpi] = (wm * phi[ki](2 * x_m - 1) * phi[kpi](2 * x_m - 1)).sum()
没有合适的资源?快使用搜索试试~ 我知道了~
温馨提示
在之前的文章中我们已经讲过Informer模型了,但是呢官方的预测功能开发的很简陋只能设定固定长度去预测未来固定范围的值,当我们想要发表论文的时候往往这个预测功能是并不能满足的,所以我在官方代码的基础上增添了一个滚动长期预测的功能,这个功能就是指我们可以第一次预测未来24个时间段的值然后我们像模型中填补 24个值再次去预测未来24个时间段的值(填补功能我设置成自动的了无需大家手动填补),这个功能可以说是很实用的,这样我们可以准确的评估固定时间段的值,当我们实际使用时可以设置自动爬取数据从而产生实际效用。本文修改内容完全为本人个人开发,创作不易所以如果能够帮助到大家希望大家给我的文章点点赞,同时可以关注本专栏(免费阅读),本专栏持续复现各种的顶会内容,无论你想发顶会还是其它水平的论文都能够对你有所帮助。 时间序列预测在许多领域都是关键要素,在这些场景中,我们可以利用大量的时间序列历史数据来进行长期预测,即长序列时间序列预测(LSTF)。然而,现有方法大多设计用于短期问题,如预测48点或更少的数据。随着序列长度的增加,模型的预测能力受到挑战。例如,当预测长度超过48点时,LSTM网络的预测
资源推荐
资源详情
资源评论
收起资源包目录
时间序列预测实战(十九)魔改Informer模型进行滚动长期预测(科研版本,结果可视化) (131个子文件)
ETTh1.csv 2.47MB
T1trainData-checkpoint.csv 561KB
MSST2trainData-checkpoint.csv 455KB
T1testData-checkpoint.csv 189KB
ETTh1-Test.csv 38KB
.gitignore 184B
model.iml 488B
myplot.png 59KB
MultiWaveletCorrelation.py 22KB
exp_informer-checkpoint.py 16KB
exp_informer (4)-checkpoint.py 16KB
exp_informer.py 15KB
data_loader-checkpoint.py 14KB
data_loader.py 13KB
SelfAttention_Family.py 12KB
FiLM.py 11KB
ETSformer_EncDec.py 11KB
MICN.py 10KB
Nonstationary_Transformer.py 10KB
PatchTST.py 9KB
TimesNet.py 8KB
FEDformer.py 8KB
main_informer.py 8KB
Informer.py 7KB
Pyraformer_EncDec.py 7KB
FourierCorrelation.py 7KB
model.py 7KB
TiDE.py 7KB
Embed.py 7KB
Autoformer.py 7KB
Autoformer_EncDec.py 7KB
AutoCorrelation.py 6KB
Crossformer.py 6KB
attn.py 6KB
iTransformer.py 6KB
Transformer.py 6KB
timefeatures.py 5KB
LightTS.py 5KB
TransformerBlocks.py 5KB
Reformer.py 5KB
Embedding.py 5KB
Transformer_EncDec.py 5KB
ETSformer.py 4KB
DLinear.py 4KB
Crossformer_EncDec.py 4KB
Pyraformer.py 4KB
embed.py 4KB
encoder.py 3KB
Invertible.py 3KB
tools.py 3KB
Conv_Blocks.py 2KB
decoder.py 2KB
exp_basic.py 875B
masking.py 851B
metrics.py 826B
Projection.py 745B
__init__.py 1B
__init__.py 0B
__init__.py 0B
__init__.py 0B
__init__.py 0B
MultiWaveletCorrelation.cpython-39.pyc 18KB
ETSformer_EncDec.cpython-39.pyc 12KB
exp_informer.cpython-39.pyc 10KB
FiLM.cpython-39.pyc 9KB
SelfAttention_Family.cpython-39.pyc 9KB
data_loader.cpython-38.pyc 9KB
data_loader.cpython-39.pyc 9KB
exp_informer.cpython-38.pyc 9KB
Embed.cpython-39.pyc 7KB
timefeatures.cpython-39.pyc 7KB
timefeatures.cpython-38.pyc 7KB
MICN.cpython-39.pyc 7KB
Autoformer_EncDec.cpython-39.pyc 7KB
Pyraformer_EncDec.cpython-39.pyc 7KB
Embedding.cpython-39.pyc 6KB
Nonstationary_Transformer.cpython-39.pyc 6KB
Informer.cpython-39.pyc 6KB
TimesNet.cpython-39.pyc 6KB
TiDE.cpython-39.pyc 5KB
AutoCorrelation.cpython-39.pyc 5KB
TransformerBlocks.cpython-39.pyc 5KB
PatchTST.cpython-39.pyc 5KB
FEDformer.cpython-39.pyc 5KB
embed.cpython-39.pyc 5KB
attn.cpython-39.pyc 5KB
embed.cpython-38.pyc 5KB
attn.cpython-38.pyc 5KB
FourierCorrelation.cpython-39.pyc 5KB
model.cpython-38.pyc 5KB
model.cpython-39.pyc 5KB
Transformer_EncDec.cpython-39.pyc 4KB
Crossformer.cpython-39.pyc 4KB
Crossformer_EncDec.cpython-39.pyc 4KB
Autoformer.cpython-39.pyc 4KB
LightTS.cpython-39.pyc 4KB
iTransformer.cpython-39.pyc 4KB
Transformer.cpython-39.pyc 4KB
Reformer.cpython-39.pyc 4KB
Invertible.cpython-39.pyc 4KB
共 131 条
- 1
- 2
资源评论
- sasdk2023-12-27如果我想要多目标预测多目标(预测两个目标比如说预测A和B),那么在主代码main中的target是不是要改成default=['A','B'],在data_parser中的T是不是改成['A','B'],还有其中的M':要不要将[7,7,7]改成【7,7,2】,还有data_loader与exp中也要改?
Snu77
- 粉丝: 4w+
- 资源: 18
上传资源 快速赚钱
- 我的内容管理 展开
- 我的资源 快来上传第一个资源
- 我的收益 登录查看自己的收益
- 我的积分 登录查看自己的积分
- 我的C币 登录后查看C币余额
- 我的收藏
- 我的下载
- 下载帮助
安全验证
文档复制为VIP权益,开通VIP直接复制
信息提交成功