Well explained. Can you please make a tutorial on Multivariate (explanatory variables) Multistep (more than 1 step ahead) time series forecasting using LSTM?
I think you can write your custom training and test data generation functions for this, and then just plug it into an LSTM. Don't use the TimeSeriesGenerator provided by keras.
For the first time, I have found one that helps me follow the whole concept. Thank you. And that time series generator was new to me. It makes the work quite simple.
Thanks for the tutorial. Btw, can you provide the tutorials on multi-variate and multi-step method on time series prediction? It's also a popular and useful topics. Thanks!!!
How should I change the code for future predictions? If I am happy with the modell, how do I apply it to the whole dataset to truely predict values in the future?
Hi, "Cannot convert a symbolic Tensor (lstm_11/strided_slice:0) to a numpy array. This error may indicate that you're trying to pass a Tensor to a NumPy call, which is not supported" How to resolve this type of problem?????
Hey Nachiketa Hebbar, i tried the above time series with Oscilloscope data having 10,00,000 dataset. While trying to fit the model using('model.fit(gnerator, epoch=50)) code got stuck. please help me
Pls someone help me. A have dataset start from 2017-01-07, 2017-01-14, 2017-01-21, 2017-01-28, and repeat 2017-02-07...how do i make df.index.freq for that cuz when i use 'W' it dosen't work
Hi , i'm getting an error when i try to change the frequency to Day, the Alias im trying to use is "D" instead of "MS" but i'm getting an error and i'm still getting an error.
Thanks a lots Bro! But How to compute an accuracy measure based on RMSE? foreexample on your case RMSR is 26.04. so what is the accuracy of the model in %?? please help me ! please ! I am comfused!
Here is the answer: import numpy as np import pandas as pd from sklearn.metrics import mean_absolute_percentage_erro # Assuming you have the true test values in a 'TrueValues # test['TrueValues'] = true_values # Calculate the MAPE (Mean Absolute Percentage Error) bet mape = mean_absolute_percentage_error(test['Production'], # Convert MAPE to percentage format (0-100) percentage_accuracy = (1 - mape) * 100 # Display the percentage accuracy print(f"Percentage Accuracy: {percentage_accuracy:.2f}%")
Hello hoping this could get answered. But im getting an error with the input_shapes is that it is expecting (None, None, 1), found shape=(None, 3, 3). I have been following your discussion but can't seem to get pass this. I'm already at the epochs part but im stuck because of that. Please help :(
when i am running test prediction shell its continuously running its not stopping since 5 to 10 minut what is wrong with code if you could solve this i will be grateful thank you
Hello, great Tutorial! I tried to reconstruct your tutorial and ran into an error in this line: model.add(LSTM(100, activation='relu', input_shape=(n_input, n_features))) I get the Error: NotImplementedError: Cannot convert a symbolic Tensor (lstm/strided_slice:0) to a numpy array. This error may indicate that you're trying to pass a Tensor to a NumPy call, which is not supported Do you have an Idea whats the problem? Thanks in advance!
Can you recommend some references (videos or articles) on model that receive multiple input and also spit out (predict) multiple output? Like predict unit sales, how many customers, and such things.
in this RNN code how we can future forecast...for example if i want to forecast for year 2020-2030 and i have data set of past 20 years.. how we can do it??
Brother , in timeseriesGenerator ( ) , what does batch_size refer to, does it refer to number of columns or is it same as batch_size we apply in model. Fit() .
Thanks for the video. So let's say that i have 120 days in my training set and 20 days in my test set. What should be the n_input in this case? Thank you!
The problem is not about having multiple features and single features in this case. Think of univariate time series as a multi-feature problem where the scale within the time series has a large range. Hence, as we do scaling for traditional models, we also scale it down for time series data. You can try without doing so, and you will see a very large loss value
Hi i'm interested in deep learning . I fond this vidéo interesting but i've a l some confusions on predicting the wind speed using LSTM. Thé windowgenerator is a bit confusion on defining the parameters
Sir , I have a data set that has a columns DATE , TIME , AM/PM ,DATA So using This i created a new columns DateAndTime DateAndTime (e.g 2019-07-01 00:45:00 , 2019-07-01 01:00:00, etc) one month data time difference is 15 minutes there is total of 2976 rows. I am have used ARIMA and SARIMA to predict the next month DATA , but i am getting very bad result (only a straight line )(constant value) Please Sir help me as soon as you can. Thank You
How can we use multiple time series to make a prediction? You said that it would involve the n_features in the TimeSeriesGenerator, and I'm wondering how that works. I want to know how to predict by training the RNN with multiple other series that follow similar patterns.
Hi friend. Thank you so much for your tutorial, it's amazing. Please, help with this error: when I used the function scaler.transform I get TypeError: wrapped() missing 1 required positional argument: 'X'. I dont' khow how solved.
I have one doubt. [1,2,3] is used to predict [4]. Then [2,3,4] is used to predict [5]. In 2,3,4 shouldn't the 4 value be the actual instead of predicted? Why are we appending predicted value. Pls explain.
Yho! I am a new to RNN yet your Video was very informative. I enjoyed your approach and how simplified you made it look. When you get a chance, Could you please do Multivariate Forecasting. Thank you.
actually i am trying to forecast GW level with precipitation and temperature as input with RF model and i have precipitation and temperature upto 2050 how can i predict all data at once?
One quick question, I saw you remove the seasonality but you still used the original df in the model training. So can I understand that in this video you jut used the original dataset to train the RNN without removing the seasonality? TAHNKS!!
After spending hours reading documentation to understand everything... This short video was what I really needed!
Too good brother! The entire LSTM code explained line by line with the underlying concepts within 15 min! Much appreciated. You're a great teacher!
Thanks!
@@NachiketaHebbar Hai
Kindly make a video how to access GitHub programming file , alter the coding for our own dataset
@@NachiketaHebbar
What's the role of generators in time series?
Can u plz explain for LSTM model for exogenous variables
Man, you are already an scientist, keep the great work
The fact that you're making it so clear and simple 👏👏👏
You have become popular in my college, here in dublin..you are saving our life's here...simple and lucid videos...thanks a ton..
Thanks, this comment made my day!
You are the best Brother, Thanks for saving my life. Udemy couldn't explain it better than you
Glad to help, and thanks for such a kind comment!
This video was so helpful. You did a very nice job explaining how the batch training of predictions works. Thank you, Nachiketa!
it is the best video for LSTM on UA-cam.
Well explained. Can you please make a tutorial on Multivariate (explanatory variables) Multistep (more than 1 step ahead) time series forecasting using LSTM?
Did you find any good video for LSTM Multivariate Model?
@@SimplytheBest23 No.
I think you can write your custom training and test data generation functions for this, and then just plug it into an LSTM. Don't use the TimeSeriesGenerator provided by keras.
Yes you just have to increase features dimensions by number of features
how do we predict another three months production using this?
For the first time, I have found one that helps me follow the whole concept. Thank you.
And that time series generator was new to me. It makes the work quite simple.
Always love your content !!!keep making videos man
This is a very well presented and articulated walkthrough. Good work.
Get this man a trophy!
Beautifully explained!!! Thanks a lot.
This video was help me lot to do my research... thanx brother... please do more content like this. you are awesome
simple and precise bro! awesome!
Thanks for the tutorial. Btw, can you provide the tutorials on multi-variate and multi-step method on time series prediction? It's also a popular and useful topics. Thanks!!!
I have a problem. I do exacly the same what you did and my model predict the same values. What can i do?
How should I change the code for future predictions? If I am happy with the modell, how do I apply it to the whole dataset to truely predict values in the future?
short and to the point. thx a lot.
Hi,
"Cannot convert a symbolic Tensor (lstm_11/strided_slice:0) to a numpy array. This error may indicate that you're trying to pass a Tensor to a NumPy call, which is not supported"
How to resolve this type of problem?????
Same problem here with:
model.add(LSTM(100, activation='relu', input_shape=(n_input, n_features)))
Good job Boy!!! Well explained
Thanks Bhai. Got one SCI publication in Q2 based one your video❤❤❤❤❤
Really good video, well done, subscribed!
Really helpful, keep making such videos
can this be used in a multivariable prediction? where we have more than one columns in a dataset but we want to only predict one column?
Amazing explanation! thank you
Very well explained. Thank you so much.!!!
Please do a Video on Multivariate Time Series modelling using LSTM. I like the your natural way of explanation..! keep it up!
Thanks for detailed explanation.
i found this really simple and handy
Hey Nachiketa Hebbar, i tried the above time series with Oscilloscope data having 10,00,000 dataset. While trying to fit the model using('model.fit(gnerator, epoch=50)) code got stuck.
please help me
Pls someone help me. A have dataset start from 2017-01-07, 2017-01-14, 2017-01-21, 2017-01-28, and repeat 2017-02-07...how do i make df.index.freq for that cuz when i use 'W' it dosen't work
Hi , i'm getting an error when i try to change the frequency to Day, the Alias im trying to use is "D" instead of "MS" but i'm getting an error and i'm still getting an error.
its monthly data so he explicitly defined it as MS . Its not daywise data so it wont convert to days for u
Thanks a lots Bro! But How to compute an accuracy measure based on RMSE? foreexample on your case RMSR is 26.04. so what is the accuracy of the model in %?? please help me ! please ! I am comfused!
Here is the answer:
import numpy as np
import pandas as pd
from sklearn.metrics import mean_absolute_percentage_erro
# Assuming you have the true test values in a 'TrueValues
# test['TrueValues'] = true_values
# Calculate the MAPE (Mean Absolute Percentage Error) bet
mape = mean_absolute_percentage_error(test['Production'],
# Convert MAPE to percentage format (0-100)
percentage_accuracy = (1 - mape) * 100
# Display the percentage accuracy
print(f"Percentage Accuracy: {percentage_accuracy:.2f}%")
thanks this video for make me easy to understanding and i will make reference for my thesis trial :) hehe
I have multiple variables.. does this help in multivariate forecasting?
Hello hoping this could get answered. But im getting an error with the input_shapes is that it is expecting (None, None, 1), found shape=(None, 3, 3). I have been following your discussion but can't seem to get pass this. I'm already at the epochs part but im stuck because of that. Please help :(
can you make another video for multi feature time series forecasting?i couldnt figure out what to do for that
Hi I've time duration column in mm ss format.. getting error can't assign to call function
My Data has hourly records for dates. It doesn't have all the hours. I can't view the Seasonal_Decompose because the freq can't be set.
when i am running test prediction shell its continuously running its not stopping since 5 to 10 minut what is wrong with code if you could solve this i will be grateful
thank you
What does basically mean of trend , seasonal and residual . How all of them is diffrent though?
Best tutorial EVER
Great explanation, thank you!
After training and testing the model how to use it for forecasting into the future?how to modify the code for that?
n_input = 3 How do I decide the value?
Hello, great Tutorial! I tried to reconstruct your tutorial and ran into an error in this line:
model.add(LSTM(100, activation='relu', input_shape=(n_input, n_features)))
I get the Error:
NotImplementedError: Cannot convert a symbolic Tensor (lstm/strided_slice:0) to a numpy array. This error may indicate that you're trying to pass a Tensor to a NumPy call, which is not supported
Do you have an Idea whats the problem?
Thanks in advance!
kindly update your numpy version'
Thanks !!!!!! i love uuuuuu for this hahaha i use this for my work :)
Haha glad to hear that
Hello. Do you know if the TimeSeriesGenerator class is a cross-validation method itself?
Hey
I'm currently working on data which contain 19 values how i can make a code to forecast next 10 years values
This is great video, thank you
Great Work Bro
Can you recommend some references (videos or articles) on model that receive multiple input and also spit out (predict) multiple output? Like predict unit sales, how many customers, and such things.
Thank you so much, just have one question why are you using the relu activation function and not the sigmoid or the tanh?
Awesome content 😊
Very good explanation, thanks
if you could have explained why you have taken as 100 neurons as input..i mean any logic behind of 100 only....please reply it.
Can it be used for stock price prediction? What is the accuracy
in this RNN code how we can future forecast...for example if i want to forecast for year 2020-2030 and i have data set of past 20 years..
how we can do it??
thank you so much.this is very help full video
Whicj video that show you did make a data stationery??
Does this forecast into the future though? How is that done?
Hi. I have a doubt. I exactly followed the same code but my predictions are straight pls could you help as where I had gone wrong.?
Wonderful Bro!
Brother , in timeseriesGenerator ( ) , what does batch_size refer to, does it refer to number of columns or is it same as batch_size we apply in model. Fit() .
Great explanation bro.
Can you pls explain how to forecast for next few months
Superb🎉
Thanks for the video. So let's say that i have 120 days in my training set and 20 days in my test set. What should be the n_input in this case? Thank you!
Thank you for the great video! Just one question, why do we need to scale our series (if we are using only one series)?
some models work better with numbers from 0 to 1, i think
The problem is not about having multiple features and single features in this case. Think of univariate time series as a multi-feature problem where the scale within the time series has a large range. Hence, as we do scaling for traditional models, we also scale it down for time series data. You can try without doing so, and you will see a very large loss value
why the predictions column does not display in my code 😭😭
Thanks, very good explanation
why scaled_train used 2 times in TimeseriesGenerator ? please help
So helpful ! brother thanks!
How to decide the number of neurons in the input layer like you have taken 100
Hi i'm interested in deep learning . I fond this vidéo interesting but i've a l some confusions on predicting the wind speed using LSTM. Thé windowgenerator is a bit confusion on defining the parameters
Sir , I have a data set that has a columns
DATE , TIME , AM/PM ,DATA
So using This i created a new columns DateAndTime
DateAndTime (e.g 2019-07-01 00:45:00 , 2019-07-01 01:00:00, etc) one month data
time difference is 15 minutes there is total of 2976 rows.
I am have used ARIMA and SARIMA to predict the next month DATA , but i am getting very bad result (only a straight line )(constant value)
Please Sir help me as soon as you can.
Thank You
Cool! But how we generate a IC for the forecast and test set?
How can we use multiple time series to make a prediction?
You said that it would involve the n_features in the TimeSeriesGenerator, and I'm wondering how that works. I want to know how to predict by training the RNN with multiple other series that follow similar patterns.
Please, is this prediction for one year ahead on a monthly basis or is it for one month ahead?
Great explanation man.thank you very much ❤️❤️❤️
You're welcome!
How to predict the data for future dates? I mean to say after the test data..?
How can I use multiple dependent and independent variables in this?
Hi friend. Thank you so much for your tutorial, it's amazing. Please, help with this error: when I used the function scaler.transform I get TypeError: wrapped() missing 1 required positional argument: 'X'. I dont' khow how solved.
can we do rainfall prediction using LSTM?
Please help if u can.
It is possible to predict 30-50 years temperature prediction by using LSTM model
how to tune the above model by grid search cv
Multivariate time series...
thank you for this vidéo . iI have a qst , please how should we prepare our data if we have a lot of products ( we will have redondant date )
Thank you so much. This is very help.
I have one doubt. [1,2,3] is used to predict [4]. Then [2,3,4] is used to predict [5]. In 2,3,4 shouldn't the 4 value be the actual instead of predicted? Why are we appending predicted value. Pls explain.
Yho! I am a new to RNN yet your Video was very informative. I enjoyed your approach and how simplified you made it look.
When you get a chance, Could you please do Multivariate Forecasting. Thank you.
actually i am trying to forecast GW level with precipitation and temperature as input with RF model and i have precipitation and temperature upto 2050 how can i predict all data at once?
If I have daily data can I forecast the tomorrow outcome ?
can any one give the code for forcasting.i dont know how to forcast the the future values
One quick question, I saw you remove the seasonality but you still used the original df in the model training. So can I understand that in this video you jut used the original dataset to train the RNN without removing the seasonality? TAHNKS!!
Super video, thank you,
How to get forecasted values after building LSTM modelling