Informer模型实战案例(代码+数据集+参数讲解)

资源内容介绍

本篇博客带大家看的是Informer模型进行时间序列预测的实战案例，它是在2019年被提出并在ICLR 2020上被评为Best Paper，可以说Informer模型在当今的时间序列预测方面还是十分可靠的，Informer模型的实质是注意力机制+Transformer模型，Informer模型的核心思想是将输入序列进行自注意力机制的处理，以捕捉序列中的长期依赖关系，并利用Transformer的编码器-解码器结构进行预测，通过阅读本文你可以学会利用个人数据集训练模型。Informer是一种用于长序列时间序列预测的Transformer模型,但是它与传统的Transformer模型又有些不同点，与传统的Transformer模型相比，Informer具有以下几个独特的特点：1. ProbSparse自注意力机制：Informer引入了ProbSparse自注意力机制，该机制在时间复杂度和内存使用方面达到了O(Llog L)的水平，能够有效地捕捉序列之间的长期依赖关系。2. 自注意力蒸馏：通过减少级联层的输入，自注意力蒸馏技术可以有效处理极长的输入序列，提高了模型处理长序列的能力

import osimport numpy as npimport pandas as pdimport torchfrom torch.utils.data import Dataset, DataLoader# from sklearn.preprocessing import StandardScalerfrom utils.tools import StandardScalerfrom utils.timefeatures import time_featuresimport warningswarnings.filterwarnings('ignore')class Dataset_ETT_hour(Dataset): def __init__(self, root_path, flag='train', size=None, features='S', data_path='ETTh1.csv', target='OT', scale=True, inverse=False, timeenc=0, freq='h', cols=None): # size [seq_len, label_len, pred_len] # info if size == None: self.seq_len = 24*4*4 self.label_len = 24*4 self.pred_len = 24*4 else: self.seq_len = size[0] self.label_len = size[1] self.pred_len = size[2] # init assert flag in ['train', 'test', 'val'] type_map = {'train':0, 'val':1, 'test':2} self.set_type = type_map[flag] self.features = features self.target = target self.scale = scale self.inverse = inverse self.timeenc = timeenc self.freq = freq self.root_path = root_path self.data_path = data_path self.__read_data__() def __read_data__(self): self.scaler = StandardScaler() df_raw = pd.read_csv(os.path.join(self.root_path, self.data_path)) border1s = [0, 12*30*24 - self.seq_len, 12*30*24+4*30*24 - self.seq_len] border2s = [12*30*24, 12*30*24+4*30*24, 12*30*24+8*30*24] border1 = border1s[self.set_type] border2 = border2s[self.set_type] if self.features=='M' or self.features=='MS': cols_data = df_raw.columns[1:] df_data = df_raw[cols_data] elif self.features=='S': df_data = df_raw[[self.target]] if self.scale: train_data = df_data[border1s[0]:border2s[0]] self.scaler.fit(train_data.values) data = self.scaler.transform(df_data.values) else: data = df_data.values df_stamp = df_raw[['date']][border1:border2] df_stamp['date'] = pd.to_datetime(df_stamp.date) data_stamp = time_features(df_stamp, timeenc=self.timeenc, freq=self.freq) self.data_x = data[border1:border2] if self.inverse: self.data_y = df_data.values[border1:border2] else: self.data_y = data[border1:border2] self.data_stamp = data_stamp def __getitem__(self, index): s_begin = index s_end = s_begin + self.seq_len r_begin = s_end - self.label_len r_end = r_begin + self.label_len + self.pred_len seq_x = self.data_x[s_begin:s_end] if self.inverse: seq_y = np.concatenate([self.data_x[r_begin:r_begin+self.label_len], self.data_y[r_begin+self.label_len:r_end]], 0) else: seq_y = self.data_y[r_begin:r_end] seq_x_mark = self.data_stamp[s_begin:s_end] seq_y_mark = self.data_stamp[r_begin:r_end] return seq_x, seq_y, seq_x_mark, seq_y_mark def __len__(self): return len(self.data_x) - self.seq_len- self.pred_len + 1 def inverse_transform(self, data): return self.scaler.inverse_transform(data)class Dataset_ETT_minute(Dataset): def __init__(self, root_path, flag='train', size=None, features='S', data_path='sum.csv', target='OT', scale=True, inverse=False, timeenc=0, freq='t', cols=None): # size [seq_len, label_len, pred_len] # info if size == None: self.seq_len = 24*4*4 self.label_len = 24*4 self.pred_len = 24*4 else: self.seq_len = size[0] self.label_len = size[1] self.pred_len = size[2] # init assert flag in ['train', 'test', 'val'] type_map = {'train':0, 'val':1, 'test':2} self.set_type = type_map[flag] self.features = features self.target = target self.scale = scale self.inverse = inverse self.timeenc = timeenc self.freq = freq self.root_path = root_path self.data_path = data_path self.__read_data__() def __read_data__(self): self.scaler = StandardScaler() df_raw = pd.read_csv(os.path.join(self.root_path, self.data_path)) border1s = [0, 12*30*24*4 - self.seq_len, 12*30*24*4+4*30*24*4 - self.seq_len] border2s = [12*30*24*4, 12*30*24*4+4*30*24*4, 12*30*24*4+8*30*24*4] border1 = border1s[self.set_type] border2 = border2s[self.set_type] if self.features=='M' or self.features=='MS': cols_data = df_raw.columns[1:] df_data = df_raw[cols_data] elif self.features=='S': df_data = df_raw[[self.target]] if self.scale: train_data = df_data[border1s[0]:border2s[0]] self.scaler.fit(train_data.values) data = self.scaler.transform(df_data.values) else: data = df_data.values df_stamp = df_raw[['date']][border1:border2] df_stamp['date'] = pd.to_datetime(df_stamp.date) data_stamp = time_features(df_stamp, timeenc=self.timeenc, freq=self.freq) self.data_x = data[border1:border2] if self.inverse: self.data_y = df_data.values[border1:border2] else: self.data_y = data[border1:border2] self.data_stamp = data_stamp def __getitem__(self, index): s_begin = index s_end = s_begin + self.seq_len r_begin = s_end - self.label_len r_end = r_begin + self.label_len + self.pred_len seq_x = self.data_x[s_begin:s_end] if self.inverse: seq_y = np.concatenate([self.data_x[r_begin:r_begin+self.label_len], self.data_y[r_begin+self.label_len:r_end]], 0) else: seq_y = self.data_y[r_begin:r_end] seq_x_mark = self.data_stamp[s_begin:s_end] seq_y_mark = self.data_stamp[r_begin:r_end] return seq_x, seq_y, seq_x_mark, seq_y_mark def __len__(self): return len(self.data_x) - self.seq_len - self.pred_len + 1 def inverse_transform(self, data): return self.scaler.inverse_transform(data)class Dataset_Custom(Dataset): def __init__(self, root_path, flag='train', size=None, features='S', pre_data = None, data_path='ETTh1.csv', target='OT', scale=True, inverse=False, timeenc=0, freq='h', cols=None): # size [seq_len, label_len, pred_len] # info if size == None: self.seq_len = 24*4*4 self.label_len = 24*4 self.pred_len = 24*4 else: self.seq_len = size[0] self.label_len = size[1] self.pred_len = size[2] # init assert flag in ['train', 'test', 'val'] type_map = {'train':0, 'val':1, 'test':2} self.set_type = type_map[flag] self.features = features self.target = target self.scale = scale self.inverse = inverse self.timeenc = timeenc self.freq = freq self.cols = cols self.root_path = root_path self.data_path = data_path self.__read_data__() def __read_data__(self): self.scaler = StandardScaler() df_raw = pd.read_csv(os.path.join(self.root_path, self.data_path)) ''' df_raw.columns: ['date', ...(other features), target feature] ''' # cols = list(df_raw.columns); if self.cols: cols=self.cols.copy() cols.remove(self.target) else: cols = list