python (65.2k questions)

javascript (44.3k questions)

reactjs (22.7k questions)

java (20.8k questions)

c# (17.4k questions)

html (16.3k questions)

r (13.7k questions)

android (13k questions)

Questions - feature-selection

How to automatically choose meaning num_features_to_select with best result in select_features from CatBoostClassifier?

I'm writting a class on Python, where I'm trying to automatically pick up a value of num_features_to_select in CatBoostClassifier().select_features(). Right now, function uses enumeration of num_fea...
test-img

curly_arti

python

feature-selection

catboost

Votes: 0

Answers: 2

Latest Answer

Use the summary dictionary output to find your best point. If you want an interactive plot to define it, you can use the following: import matplotlib.pyplot as plt line = plt.plot(summary["loss_...
test-img

Darwin

Feature selection for Negative binomial regression

I am trying to fit a negative binomial regression to count data, with 90 variables. Tried feature selection with GBM, LASSO and random forest. But when I fit the model using glm.nb from MASS, the coef...
test-img

SravyaK

r

glm

feature-selection

Votes: 0

Answers: 0

How to use sklearn.feature_selection with 3D numpy array data

I have a 3D data like this (150, 1040, 82) = (frame, feature, num_data) . It is like 3D tensor. This data is X_data and Y_data is (82,) whole code is under the code. The labeling_load() function consi...
test-img

WONJUN LEE

scikit-learn

feature-selection

Votes: 0

Answers: 0

n_jobs=-1 not using 100% of CPU

I am using Sequential Feature Selection on ~200 features. I have 8 physical cores (+8 virtual), number of jobs is set to -1, but it still doesnt use 100% of CPU power, instead it uses 8%. How can I ma...
test-img

Tomward Matthias

scikit-learn

feature-selection

Votes: 0

Answers: 0

Posts

Questions

Blogs

Jobs