Very useful video, well explained and really easy to follow along the entire thing for someone like myself that is still a beginner to python for data science, and was fun to follow along the machine learning even though the majority of it went over my head for the time being! One question i have is what is the reason that the 3 federal reserve data sets could be combined using .concat and then .ffill, however the 2 zillow files require the loop to_datetime, creating a new month column and then merging based on this column? is this simply because of the fact the data from the original csv was not in the correct format initially?
How to predict future values for rows that have NaN values at 22:20 after building the model sir :( I don't know how to do the predictions phase after I build my model
I am getting an error, at the program step : price_data.index = dfs[0].index ........and the error in shows "ValueError: Length mismatch: Expected axis has 748 elements, new values have 754 elements" kindly help
@@Dataquestio my dfs[0] has 754 rows, and my dfs[1] has 319 rows exactly the way shown in your video, thanks again for your reply. regards, rajesh manjrekar
i am also getting a warning at the following step : for df in dfs: df.index = pd.to_datetime(df.index) df["month"] = df.index.to_period("M") the warning is as follows: C:\Users\HP\AppData\Local\Temp\ipykernel_12456\3620532488.py:2: UserWarning: Parsing '16-02-2008' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.
![Predict Bitcoin Prices With Machine Learning And Python [W/Full Code]](http://i.ytimg.com/vi/TF2Nx_ifmrU/mqdefault.jpg)
![Predict Bitcoin Prices With Machine Learning And Python [W/Full Code]](/img/tr.png)
![Build Your First Machine Learning Project [Full Beginner Walkthrough]](/img/n.gif)
You speak so concise and clear !! So well organized ! Even better than our professor at the university!
Vik, these tutorials are amazing. I'm a Dataquest member and absolutely love the platform and learning with your team. Incredible stuff! Thanks.
Thanks, we need more similar videos
Thanks Vikas you always give us a real user friendly experience
Vik this is amazing, man. I really appreciate you having this free material. high quality stuff
Very useful video, well explained and really easy to follow along the entire thing for someone like myself that is still a beginner to python for data science, and was fun to follow along the machine learning even though the majority of it went over my head for the time being!
One question i have is what is the reason that the 3 federal reserve data sets could be combined using .concat and then .ffill, however the 2 zillow files require the loop to_datetime, creating a new month column and then merging based on this column? is this simply because of the fact the data from the original csv was not in the correct format initially?
Thank you very much
But I have a question
What is the method you did use of this project? ANN or RNN?
This was awesome. Thank you for being so clear and thorough.
Bravo Dataquest 👏 I hope in another video, you will teach how to calculate each algorithm manually.
Thank you
Where is the predicted data?
Hi Vik, Incredible stuff! Thanks.
would you consider doing a video on predicting sales forecasts of different products
what is prerequiste before doing project?
Thank you! This was great! Would love to see on the same topic using LSTM :D
How to predict future values for rows that have NaN values at 22:20 after building the model sir :( I don't know how to do the predictions phase after I build my model
please anyone can help me with this one :'(
Very fine job, Sir!
Thank you.
Very valuable channel. Just love it! Subscribed..
شكرا ❤️
Very informative. Thanks for sharing. (I am sure this can be done using JS, too.)
Yes, you can do this in JS, but it would be harder. JS doesn't have the same data libraries (pandas, scikit-learn, etc) that Python does.
Just asking how to deploy this model?? I mean to make a website for prediction
Thanks very much especially for the data
Thanks! This video was very usefull!
What other machine learning algorithms can we use with this data?
Pretty much any regression algorithm - SVM, random forests, xgboost, etc.
Thanks a lot for this very helpful video!!
Can this be done using R? Thanks
Hi James - you can definitely do this using R. R has packages that work similarly to pandas and scikit-learn.
I am getting an error, at the program step : price_data.index = dfs[0].index ........and the error in shows "ValueError: Length mismatch: Expected axis has 748 elements, new values have 754 elements" kindly help
It looks like price_data has a different number of rows from dfs[0]. This would happen if the data wasn't loaded/cleaned properly.
@@Dataquestio your video also the exact number of records that i have ....kindly request you to please check, thanks a lot for replying
@@Dataquestio my dfs[0] has 754 rows, and my dfs[1] has 319 rows exactly the way shown in your video, thanks again for your reply. regards, rajesh manjrekar
This one is very complicated project
Hi Vik, thank you for sharing the video it helped a lot. also would you mid sharing your email I have some questions to ask ?
i am also getting a warning at the following step :
for df in dfs:
df.index = pd.to_datetime(df.index)
df["month"] = df.index.to_period("M")
the warning is as follows: C:\Users\HP\AppData\Local\Temp\ipykernel_12456\3620532488.py:2: UserWarning: Parsing '16-02-2008' in DD/MM/YYYY format. Provide format or specify infer_datetime_format=True for consistent parsing.
This warning is fine, this is related to how dates are written in the US vs some other countries.