XGBoost Regression Algorithm in Machine Learning | Python | XGBoost Algorithm

[@MuhammadKamran-ii4rh]

Is it ok if after applying cross validation, we train the model on all X and Y???

[@StatsWire]

No, because if your model will see all the data then how you will come to know how your model is going to perform on new unseen data? To check the performance of the model on unseen data we keep the test data aside. So you cannot use the data of all X and Y. I hope you are understanding what I am trying to say

[@MuhammadKamran-ii4rh]

Thank you very much for your kind response. Sorry sir I think I did not write my question much clear. Basically I wanna ask is it ok if we fit a model on all dataset and then test it on testing dataset.

[@StatsWire]

@@MuhammadKamran-ii4rh Yes you can do that

[@v1hana350]

I have a question about the Xgboost algorithm. The question is how parallelization works in the Xgboost algorithm and explain me with an example.

[@StatsWire]

As per a blog, "The parallel computation takes place in the operation where the model scans through all features on each internal node and set a threshold. Say we have a 4-core CPU for the training computation, then XGBoost separate the features into 4 groups. For the splitting operation on a node, XGBoost distributes the operation on each feature to their corresponding core. The training data is stored in a piece of shared memory, each core only needs to access one group of features, and perform the computation individually."

[@v1hana350]

@@StatsWire thanks for your information

[@StatsWire]

@@v1hana350 You're welcome

[@anmol_seth_xx]

Can you please tell the use of objective?

[@StatsWire]

Hello, may I know which objective are you talking about?

[@anmol_seth_xx]

“reg: squared error "

[@anmol_seth_xx]

& and I also wanted to know why you have used whole X, y dataset in cross_val_score function?

[@StatsWire]

@@anmol_seth_xx We want to check whether the mean squared error is low or high

[@StatsWire]

@@anmol_seth_xx We can just use training dataset also.

[@Izzworld_]

I followed these steps and now I just want to know the accuracy of the model please can you tell me?

[@StatsWire]

You can try this: # Calculate accuracy accuracy = accuracy_score(y_test, y_pred) # Print the accuracy print("Accuracy:", accuracy)

[@dhruv6433]

Why all my hyper parameters are none

[@StatsWire]

Please change it manually

[@goutamidas7427]

Sir, it is showing, in the line 28 {from xgboost import XGBRegressor} AttributeError: partially initialized module 'xgboost' has no attribute 'DMatrix' (most likely due to a circular import) ​Please help me out. 🙏thank you in advance.

[@StatsWire]

Please check if you were able to import the xgboost module or not.