Inflation depreciates idle money. I'm in a privileged position to be able to save almost 65% of our net household income, as I placed it on safer investments. The key for us was not spending beyond our means. If you invest and have other sources of income outside of dividends then you will be able to live off dividends. Got north of $520K in my portfolio as I bought a lot of dividend stocks before, I'm buying more now, and I will buy more when it drops further.
The main problem is that most folks don’t care about anything other than football, Basketball and Music etc. They find it normal to take credit card debt which will cost them 20% per year but considers it risky to invest their money and make 10% or more per month. Learning to avoid high interest debt while also learning how to put your money to work for you by investing is a very powerful combo.
Starting out with a professional that knows the ropes of the choppy but profitable market is the best way to achieve getting a well structured portfolio. That’s why I have been working with 'MARGARET ANN WARNKEN" because in financial dealings one has to be prudent. Most traders enter and exit with a quick 10% profit which is not bad in general opinion but why not make more of the opportunities presented?.
She looks the part. MARGARET really seems to know her stuff. Out of curiosity i looked her up, found her web~page, and decided to read through her resume, educational background, qualifications and it was really impressive. She is a fiduciary who will act in my best interest. So, I booked a session with her.
The min max scaler is being fitted on the entire dataset. This means that you have essentially leaked information about the test data. The proper way to do this would be to first split your data into train and test set. Fit the scaler on train set only. Transform train and test set afterwards.
What If you had a machine learning algorithm. Which took like all common elements such as insider trading publicly available data or historical price points. And could predict with a higher certainty about the stock prices ? How effective is your model of prediction compared to linear regression or like standard deviation + avg
thanks. should not you make the time series stationary first? When you reshape X_train should not it be ( shape[0], shape[1],1) Great channel and tool by the way
Let me help you out, it is really simple, all you need to do is make sure your model input X_train (and X_test) are of shape (samples, timesteps, features), whereby you make your samples using a windowing algorithm. In his window algorithm all you need to do is remove the ' , 0' in line 25 (6 min 56 seconds). Of-course your y variable should not change and thus be of shape (samples, timesteps), which his is. The only other thing to keep in mind is that your scaler will now protest as it will try to unscale a dataframe when you want to pass it a series (only in numpy speak which becomes jargonny very quickly). I hacked my way around this by storing my y in a separate variable, scaling that, and using the associated scaler to inverse_transform my model's output. Good luck!
Why is this referred to as predictions, when it appears that the ML was able to learn the last 100 days (or however long the training + test set is) and effectively normalize the curve. I don't see how it predicted anything, which implies looking ahead
You are exactly right. That's why the predicted fit the actual so tightly in the graph, LOL. This model has no predictive power. If I had a nickel every time I saw this error in a Medium post, Github repo or YT vid...
Doesn't work. You will get a never ending loop of bugs to fix encoding, value errors, int()errors, etc. etc. etc. Unless you have the exact same file as he does, you're in for a Bug nightmare trying to fix Byte/UTF/ascii/latin-1 errors.
Inflation depreciates idle money. I'm in a privileged position to be able to save almost 65% of our net household income, as I placed it on safer investments. The key for us was not spending beyond our means. If you invest and have other sources of income outside of dividends then you will be able to live off dividends. Got north of $520K in my portfolio as I bought a lot of dividend stocks before, I'm buying more now, and I will buy more when it drops further.
The main problem is that most folks don’t care about anything other than football, Basketball and Music etc. They find it normal to take credit card debt which will cost them 20% per year but considers it risky to invest their money and make 10% or more per month. Learning to avoid high interest debt while also learning how to put your money to work for you by investing is a very powerful combo.
The one effective technique I'm confident nobody admits to using, is staying in touch with an Investment-Adviser.
Starting out with a professional that knows the ropes of the choppy but profitable market is the best way to achieve getting a well structured portfolio. That’s why I have been working with 'MARGARET ANN WARNKEN" because in financial dealings one has to be prudent. Most traders enter and exit with a quick 10% profit which is not bad in general opinion but why not make more of the opportunities presented?.
She looks the part. MARGARET really seems to know her stuff. Out of curiosity i looked her up, found her web~page, and decided to read through her resume, educational background, qualifications and it was really impressive. She is a fiduciary who will act in my best interest. So, I booked a session with her.
Identifying lucrative investments can get you ahead in no time, in years of Investing, my portfolio has experience immense growth, because i did so.
The min max scaler is being fitted on the entire dataset. This means that you have essentially leaked information about the test data.
The proper way to do this would be to first split your data into train and test set. Fit the scaler on train set only. Transform train and test set afterwards.
💯 agree
This is basic coding (only) and has nothing todo with stock predictions guys!
where did that "T.astype" come from on line 10? Undefined variable? cant figure it out
Trust me everyone, you can learn more here
instead of other tutorials on internet
Thank u Kite for making learning Fun and Easy
We need more tutorials like this.
Super cool, thanks for sharing!
line 10 - where is T come from?
What If you had a machine learning algorithm. Which took like all common elements such as insider trading publicly available data or historical price points. And could predict with a higher certainty about the stock prices ?
How effective is your model of prediction compared to linear regression or like standard deviation + avg
The repo link points to a voice-recognizer?!
Great Content
6:25
window_size = 20
to_split = df['price'].rolling(window_size).mean()
what do you mean by this?
as bad as the presenter, posting code with 0 explaination
@@willjohnson4579 ha ha.. cool observation..
thx it helped me a-lot u deserver a sub and like and pls do more videos can't wait to see them
Thank you
Game-changing!
I'm sorry what T mean in code what is the defend for her ?
Can we predict te NASDAQ with Python?
thanks. should not you make the time series stationary first? When you reshape X_train should not it be ( shape[0], shape[1],1)
Great channel and tool by the way
Why is he in pain though
Hey man is it possible that you show us a tutorial for multivariate rnn to predict stock prices?
Thank you.
Let me help you out, it is really simple, all you need to do is make sure your model input X_train (and X_test) are of shape (samples, timesteps, features), whereby you make your samples using a windowing algorithm. In his window algorithm all you need to do is remove the ' , 0' in line 25 (6 min 56 seconds). Of-course your y variable should not change and thus be of shape (samples, timesteps), which his is. The only other thing to keep in mind is that your scaler will now protest as it will try to unscale a dataframe when you want to pass it a series (only in numpy speak which becomes jargonny very quickly). I hacked my way around this by storing my y in a separate variable, scaling that, and using the associated scaler to inverse_transform my model's output. Good luck!
@@isaacgroen3692 can you please provide a short pyton code for it? would really appreciate
He never defined T. What is T, his train data?
I took it to mean the Tesla close data without the time series data.
So basically, you can just declare the following?
T = tesla['Close'].to_numpy()
instead of dropping the date column and all that?
Why is this referred to as predictions, when it appears that the ML was able to learn the last 100 days (or however long the training + test set is) and effectively normalize the curve.
I don't see how it predicted anything, which implies looking ahead
You are exactly right. That's why the predicted fit the actual so tightly in the graph, LOL. This model has no predictive power.
If I had a nickel every time I saw this error in a Medium post, Github repo or YT vid...
awsome wow😀
Have you stopped uploading?
8.45 batch_size=???? i cant see if its 2 or not
Quality Content!
Didn't understand a sh1t but like it anyways
Doesn't work. You will get a never ending loop of bugs to fix encoding, value errors, int()errors, etc. etc. etc. Unless you have the exact same file as he does, you're in for a Bug nightmare trying to fix Byte/UTF/ascii/latin-1 errors.
How do I add you on LinkedIn?
line 10 is incorrect
you linked the wrong github repo
also, you didnt fit the zoom ins properly to the screen so it cuts off some of the code so it's not readable
I watch this because this is small
Super fast .Go bit slow. Hope it's knowledge sharing not website publicity
What a thrash..
What?
NameError: name 'T' is not defined
got the same error
You open your mouth so wide when you talk
You make weird observations in your comments
is this what you got from the tutorial?
this guy talking is so obnoxious lol