TensorFlow 2.0 Tutorial for Beginners 16 – Google Stock Price Prediction Using RNN – LSTM




[ad_1]

In this video, we are going to predict the opening price of the Google stock given the highest, lowest, and closing price for that particular day by using Deep Learning, RNN-LSTM. The prediction of the Google stock market with RNN-LSTM is really gonna help you build the concept of time series data analysis using RNN and LSTM.

What is RNN?
Recurrent Neural Networks are the first of its kind State of the Art algorithms that can memorize/remember previous inputs in memory when a huge set of Sequential data is given to it.
Recurrent Neural Network is a generalization of a feedforward neural network that has internal memory.
RNN is recurrent in nature as it performs the same function for every input of data while the output of the current input depends on the past one computation.
After producing the output, it is copied and sent back into the recurrent network. For making a decision, it considers the current input and the output that it has learned from the previous input.
In other neural networks, all the inputs are independent of each other. But in RNN, all the inputs are related to each other.

What is LSTM?
Long Short Term Memory networks – usually just called “LSTMs” – are a special kind of RNN, capable of learning long-term dependencies.
Generally, LSTM is composed of a cell (the memory part of the LSTM unit) and three “regulators”, usually called gates, of the flow of information inside the LSTM unit: an input gate, an output gate and a forget gate.

Steps to build a stock prediction model
Data Preprocessing
Building the RNN
Making the prediction and visualization

#GoogleStockPrice #Prediction #RNN_LSTM
🔊 Watch till last for a detailed description
02:30 What is RNN
04:18 Types of RNN
06:05 Vanishing and Exploding Gradient
08:38 LSTM Networks
15:18 Start Preparation for LSTM
25:28 Build LSTM Model
33:55 Prepare Test Dataset
42:00 Visualize Predicted Stock Price

👇👇👇👇👇👇👇👇👇👇👇👇👇👇
✨ Kite is a free AI-powered coding assistant that will help you code faster and smarter. The Kite plugin integrates with all the top editors and IDEs to give you smart completions and documentation while you’re typing. I’ve been using Kite for 6 months and I love it! Get your FREE coding assistant today!!
https://www.kite.com/get-kite/?utm_medium=referral&utm_source=youtube&utm_campaign=kgptalkie&utm_content=description-only
—————————————————————

💯 Read Full Blog with Code
https://kgptalkie.com/google-stock-price-prediction-using-rnn-lstm/
💬 Leave your comments and doubts in the comment section
📌 Save this channel and video for watch later
👍 Like this video to show your support and love ❤️

~~~~~~~~
🆓 Watch My Top Free Data Science Videos
👉🏻 Python for Data Scientist
https://bit.ly/3dETtFb
👉🏻 Machine Learning for Beginners
https://bit.ly/2WOVh7N
👉🏻 Feature Selection in Machine Learning
https://bit.ly/2YW6ZQH
👉🏻 Text Preprocessing and Mining for NLP
https://bit.ly/31sYMUN
👉🏻 Natural Language Processing (NLP)
Tutorials https://bit.ly/3dF1cTL
👉🏻 Deep Learning with TensorFlow 2.0
and Keras https://bit.ly/3dFl09G
👉🏻 COVID 19 Data Analysis and Visualization
Masterclass https://bit.ly/31vNC1U
👉🏻 Machine Learning Model Deployment Using
Flask at AWS https://bit.ly/3b1svaD
👉🏻 Make Your Own Automated Email Marketing
Software in Python https://bit.ly/2QqLaDy

***********
🤝 BE MY FRIEND
🌍 Check Out ML Blogs: https://kgptalkie.com
🐦Add me on Twitter: https://twitter.com/laxmimerit
📄 Follow me on GitHub: https://github.com/laxmimerit
📕 Add me on Facebook: https://facebook.com/kgptalkie
💼 Add me on LinkedIn: https://linkedin.com/in/laxmimerit
👉🏻 Complete Udemy Courses: https://bit.ly/32taBK2
⚡ Check out my Recent Videos: https://bit.ly/3ldnbWm
🔔 Subscribe me for Free Videos: https://bit.ly/34wN6T6
🤑 Get in touch for Promotion: info@kgptalkie.com

✍️🏆🏅🎁🎊🎉✌️👌⭐⭐⭐⭐⭐
ENROLL in My Highest Rated Udemy Courses
to 🔑 Unlock Data Science Interviews 🔎 and Tests

📚 📗 NLP: Natural Language Processing ML Model Deployment at AWS
Build & Deploy ML NLP Models with Real-world use Cases.
Multi-Label & Multi-Class Text Classification using BERT.
Course Link: https://bit.ly/bert_nlp

📊 📈 Data Visualization in Python Masterclass: Beginners to Pro
Visualization in matplotlib, Seaborn, Plotly & Cufflinks,
EDA on Boston Housing, Titanic, IPL, FIFA, Covid-19 Data.
Course Link: https://bit.ly/udemy95off_kgptalkie

📘 📙 Natural Language Processing (NLP) in Python for Beginners
NLP: Complete Text Processing with Spacy, NLTK, Scikit-Learn,
Deep Learning, word2vec, GloVe, BERT, RoBERTa, DistilBERT
Course Link: https://bit.ly/intro_nlp

Source


[ad_2]

Comment List

  • KGP Talkie
    December 20, 2020

    The scaling is acting weird for me when I scale test and predicted set the prices do not scale up to 1800 but rather to just 800, I followed the same process can some help me out?

  • KGP Talkie
    December 20, 2020

    You save me … thank you!

  • KGP Talkie
    December 20, 2020

    I want to classify anomaly detection using RNN keras.tf but I have a problem where the accuracy value increases but the val_accuracy value does not change and just remains constant at 50%. this is my complete code available on google colab https://colab.research.google.com/drive/1saoNuCxj08JCxZ_7taIjhp8sJEIV-T5U?usp=sharing

  • KGP Talkie
    December 20, 2020

    Hi can you help on only time wise rate predictions..

  • KGP Talkie
    December 20, 2020

    Can please do one video over the lstm time series anomly detection.

  • KGP Talkie
    December 20, 2020

    Thanks for great video. I have few questions:
    1. What is we are using only one column, do we need to scale? I didn't however prediction seems way off…

    2. Whenver I restart and re-run all code, even if no change has been made predictions are different every time, why is it so?

  • KGP Talkie
    December 20, 2020

    Really good tutorial thank you for taking the time to share it. I was skeptical at first but really liked how you train it was very easy to follow. Thank you for explaining things so well. I'm now trying to find how to save the trained model to load rather than having to re-run optimize each time.

  • KGP Talkie
    December 20, 2020

    i think inverse transform for past 60 days is missing, can anyone help me?

  • KGP Talkie
    December 20, 2020

    Aren't you using the test values in the iteration in the final part? Thus corrupting the results.
    Shouldn't you calculate a 60days prediction, then use THAT result for the next batch of 60 days?

    If you do it this way no wonder it fits so nicely in the end.

  • KGP Talkie
    December 20, 2020

    How can I deploy this to a web based application? I am a beginner any kind of help would be appreciated.

  • KGP Talkie
    December 20, 2020

    scaler.scale_ gives me array([1., 1., 1., 1., 1.])..Can someone enlighten me here???

  • KGP Talkie
    December 20, 2020

    Best explanation of the concepts and code as well…

  • KGP Talkie
    December 20, 2020

    What do I do if I want to see the future prediction not now

  • KGP Talkie
    December 20, 2020

    Many thanks for this wonderful lecture. I really appreciate you.

  • KGP Talkie
    December 20, 2020

    sir, can u explain me why did you increase the order of dropping out neurons in this code section?

  • KGP Talkie
    December 20, 2020

    + за старания. Но слишком сложная сеть для такого мелкого набора данных, вот она и получается переобученной

  • KGP Talkie
    December 20, 2020

    thx for the video, give huge help for begginers like me, best wishes for you

  • KGP Talkie
    December 20, 2020

    bro make a videos on inception module, resnets, yolo algorithm and gan's….

  • KGP Talkie
    December 20, 2020

    In X_test variable you put real data from that csv file. You should predict those data, what am I missing?

  • KGP Talkie
    December 20, 2020

    Could you please send me The theory jupyter file?

  • KGP Talkie
    December 20, 2020

    many many many thanks!!

  • KGP Talkie
    December 20, 2020

    Almost ridiculous, gopher turns his head = 50 million views, tutorial on machines learning to think 20k

  • KGP Talkie
    December 20, 2020

    While training the model I am getting loss as NAN and all my predicted values are also NAN, can anyone help me on this plz?

  • KGP Talkie
    December 20, 2020

    Hello when i do regressior.fit(x_train, y_train, epochs=10, batch_size=32)
    I have "TypeError:'NonType' Object is not callable"

  • KGP Talkie
    December 20, 2020

    How to add the confusion matrix after this?

  • KGP Talkie
    December 20, 2020

    Amazing channel

  • KGP Talkie
    December 20, 2020

    Sorry, maybe I didn’t understand something, but: if you have an X_test for 2019, then you don’t need predict Y for 2019? -> y_pred = regressior.predict(X_test)

  • KGP Talkie
    December 20, 2020

    Where can I find the code?

  • KGP Talkie
    December 20, 2020

    Dude at least provide GitHub link for the code.

  • KGP Talkie
    December 20, 2020

    as for the 60 window, is that for cross validation ? sliding window cross validation ?

  • KGP Talkie
    December 20, 2020

    Can I ask where is the full code please ?

  • KGP Talkie
    December 20, 2020

    Great explanation, is there any way i could connect with you?

  • KGP Talkie
    December 20, 2020

    why cant we use the scaler.inverse_transform ?

  • KGP Talkie
    December 20, 2020

    Nice video and excellent explanation. I try to follow the video but I got an error converting X_train to a numpy array: at 23:25 of the video the statement:
    X_train, y_train = np.array(X_train), np.array(y_train)
    I got an error: PandasArray must be 1-dimensional.
    I wonder if this would be a Numpy version issue.

  • KGP Talkie
    December 20, 2020

    Hi KGP ,

    i have used different data set for this code and i am facing the below issue :

    While plotting a graph at the end i am getting an error on y_pred – which says — "x and y can be no greater than 2-D, but have shapes (332,) and (332, 60, 1)" — hence it only plots y_train and not y_pred. Kindly suggest

  • KGP Talkie
    December 20, 2020

    The shape of training data is 3617, but the shape of xtrain and ytrain is only 3557. Where is the data missing ??

  • KGP Talkie
    December 20, 2020

    An excellent and detailed tutorial to understand the RNN- LSTM. Huge respect to the presenter.

  • KGP Talkie
    December 20, 2020

    Hey, I had a question as to how you can predict future stocks with this data.

  • KGP Talkie
    December 20, 2020

    can i use batch normalization, and standard scaler?

  • KGP Talkie
    December 20, 2020

    Hello, can you please link working directories to your notebooks. Thank you soo much for all you do for us beginners

Write a comment