Time Series Data Preparation for Deep Learning (LSTM, RNN) models

Показать описание

#datascience #deeplearning #machinelearning

In this video I walk you through various time series concept and also we will see how we can prepare data for sequence models like LSTM, RNN or even auto encoders and other deep learning models. Next video we will see how to develop a LSTM model using prepared data here. We will also see concepts like Sliding window, Hopping or Tumbling window

Рекомендации по теме

Комментарии

Most of the time series videos I have seen are done by so called experts, but themselves don’t know what they are teaching. Here at AI Engineering Srinivasan is doing a really great job. He knows to explain it to us by covering each and every corner of the topic.

“If you can't explain it simply, you don't understand it well enough.”

Albert Einstein

story_teller_

Most of the people out there use a function to prepare the data for LSTM but here with the help of this generator it becomes really easy.
Thank You.

himanshuverma

If I need to learn some concept, I know "AI engineering" is the first place I search for. Thanks for the time and efforts you and your team put sir.

Induraj

This is very detailed explanation of windows, shifting and labeling in time series. I have came across Tensoflow Documentation, but I didn't understand at all. Thanks for sharing.

waqitshatasheel

Finally.... someone explained this stuff clearly. Thank you sooo much!!! 🙏🙏

arashchitgar

Unlike everyother idiot out there who predict single input LSTM's, you did a fantastic job in explaining how to create a samples for multiple inputs and multiple outputs.
Just subscribed to your video, thank you!

tejask

Great content sir . Hope you are doing well, kindly continue sharing your knowledge on ML DL as it greatly helps 🙂

shwetabhat

Thank you for the video, by far the best explanation I could find. Just one question, why do we add the column we are trying to predict in the data parameter of TimeseriesGenerator if we already have it in the target? I guess I'm having trouble understanding what those parameters are, but isn't data the set of features we want to use to predict the target?

leonandorfi

nice explanation ...thank you..it will be more beneficial for beginners like us if you can share a notebook for learning purposes for us...thanks again...

vijaychakole

Your video is very good. When is the next video we can watch? I want you to use an autoencoder. Thanks a lot!

slash

Another great video, really great job man, hope your videos reach more people <3

moustafa_shomer

Hi... This is really a great content, at 20.28 min you mentioned features. I think they are samples. because we have None values in the last 2 rows of target, we have to skip their corresponding input samples. That is why we are considering all the samples except last 2. could you please check and confirm whether I am right or not ?.

AMVSAGOs

Thanks for the video . It was very helpful . Still I have a doubt and a request . doubt :: When using lstm model at the time of prediction, to generate output of the second and subsequent timesteps, we will also need the other features at respective timesteps . So are you missing something in the video or is it my understanding that is wrong . Request :: when working with data of cryptocurrency price prediction, the range of values for price is very high . Using an ordinary scaler does not work and I suspect using log transform will induce a lot of error . Is there a way that can help . Can you make a video on it as it is on a related topic with a different set of problem . Thanks in Advance .

aninsignificantman

Thanks a lot for the video. I have a question. if we have daily data and want to predict the next 30 days so we shift the multi_target by -30?

anangsuwasto

Why do you give the appliance power also in the feature? Doesn't the LSTM then learn that the label is purely a copy of the appliance column?

MaximGehlmann

how can we get the code for this? its very helpful

matts.

Hi Srivatsan, thank you for the video. I have one question regarding Time Series using LSTM. I am working on a project where I have 3000 users, and corresponding to each user I have Time Series data. One naive thing would be to train a model for each user independently, but is there any other way I can train my LSTM to address this case?

I would appreciate any input you can provide. Thanks

soumitramehrotra

Normally, a model takes six consecutive time steps as input and predicts on 7th time step...now, I want the model to take six consecutive timesteps from t=0 to t=5 as input and t=12 as label, instead of t=7...what will be the arguments of TimeSeriesGenerator( ) in this case? Is it possible?

anirbanmukherjee

Thank you for sharing this data preprocessing technique. I have a question: what if I am dealing with a CNN-LSTM case?
In other words, my input features are in t*n*H*W shape. Can I still use this method?
Hope for your answer, thanks!

qiguosun

which version of tensorflow are you are using

nibinjoshy

Time Series Data Preparation for Deep Learning (LSTM, RNN) models

Time Series Data Preparation for Deep Learning (LSTM, RNN) models

What is Time Series Analysis?

Time Series Forecasting with XGBoost - Use python and machine learning to predict energy consumption

Prepare Time series Data for CNN and LSTM

How do you prepare your data for a time series forecast? (11 of 28)

Automated Data Prep for Time Series | Fix Common Issues with Time Series Data Automatically

Time-Series Data prep for ML & DL: Single and Multi-Output Forecasting! (forecasting market retu...

Preparing a Time Series Dataset for Supervised Learning Forecasting #shorts

MACHINE LEARNING SPECIALTY (MLS-C01) Exam Practice Questions - ANALYSIS P1

Time Series Prediction Process

LSTM Time Series Forecasting Tutorial in Python

How To Split Time Series Dataset | Machine Learning | Data Magic AI

Time Series Data in Stata

Multivariate Time Series Data Preprocessing with Pandas in Python | Machine Learning Tutorial

Profiling the Missing Value Structure of Your Timeseries Data

pandapower: Machine Learning Part 2 - Time Series Data Preparation

Amazon Stock Forecasting in PyTorch with LSTM Neural Network (Time Series Forecasting) | Tutorial 3

End to End Multivariate Time Series Modeling using LSTM

181 - Multivariate time series forecasting using LSTM

Time Series Analysis In Manufacturing | What is Time Series Analysis | Great Learning

Time Series Forecasting With RNN(LSTM)| Complete Python Tutorial|

Time Series Forecasting Using Machine Learning| Python

Deep Learning for Time Series | Dimitry Larko | Kaggle Days

Why do we split data into train test and validation sets?