Polynomial Regression in Python - sklearn
Вставка
- Опубліковано 11 чер 2023
- Please feel free to download the dataset from this link:
github.com/rashida048/Machine...
The complete notebook is available here:
github.com/rashida048/Machine...
As mentioned in the video, here is the link to the simple linear regression explanation:
• Simple Linear Regressi...
Please feel free to check out my Data Science blog where you will find a lot of data visualization, exploratory data analysis, statistical analysis, machine learning, natural language processing, and computer vision tutorials and projects:
regenerativetoday.com/
Twitter page:
/ rashida048
Facebook Page:
regenerativetoday.com/
#polynomialregression #machinelearning #datascience #artificialintelligence #dataAnalytics #python #sklearn #jupyternotebook
You are an excellent teacher. Thank you for your videos.
Amazing explanation! Thank you very much
wonderful way to simplify a diffcult topic to beginners. keep it up!
Recommend her for beginer. well structured explanation
Will you please upload a tutorial for random forest?
Thanks for the video. A question: is poly.fit(X_poly_train, y_train) necessary?
how do input new input values and predict a value for them
Thank you for the excellent post; what about other statistics like R-squared and correlation coefficient?
Have you thought about the multivariate polynomial equation model? As you mentioned, training is overfitting but validation is very poor. Any suggestions are welcome.
If you are using this for a real world project, first try with different polynomial first and if you still do not get good results try other models. Usually for real world projects we try several different models with different parameters and finalize the best one.
@@regenerativetoday4244 Yes, I am using a real-world problem and trying to start with it before trying others.
@@regenerativetoday4244 Actually, I want to establish an empirical equation, as most of the other models are black boxes without equations.
Why we used fit_transform for trained data, but just use transform for test data?
Because you want to get mean and standard deviation for scaling from training data only and then use that information to transform test data. You don't want to fit in the test data because you want the test data to be totally unknown to the model
why using degree = 6, please ?
degree is a hyperparameter. You need try different degrees to find out the best fit for you. Thank you for the question. May be someone will benefit from it.
why did u choose degree 6?
That's just an estimate. degree is a hyperparameter here that you need to try different values to find the right one for you. Look at this video where you will find a method to tune the hyperparameter faster: ua-cam.com/video/km71sruT9jE/v-deo.html