regression

Hi I would like to propose a better implementation for 'test_indices':

We can remove the unneeded np.array casting:

Cleaner/New:
test_indices = list(set(range(len(texts))) - set(train_indices))

Old:
test_indices = np.array(list(set(range(len(texts))) - set(train_indices)))

Describe the bug
Unable to read data from a web location using address filed

To Reproduce

from pycaret.datasets import get_data
data = get_data(
    "economic_indicators_all_ex_3mo_china_inc_treas3mo", 
address="https://raw.githubusercontent.com/ngupta23/DS6373_TimeSeries/2b40f0071c3b7ec6a05dc0106f64e041f8cbaaef/Projects/gdp_prediction/data/",
)

Hi,

There are still parts of boost library that are used inside mlpack, more specifically in here

• mlpack/src/mlpack/core/tree/cosine_tree/cosine_tree.hpp boost::heap
• mlpack/src/mlpack/core/data/load_arff.hpp boost::tokenizer
• mlpack/tests/main_tests/emst_test.cpp boost::math::iround()
• mlpack/core/tree/cosine_tree/cosine_tree.cpp boost::m

That is a good suggestion. Another option is to have a keyword argument on fit which is a dictionary of estimator to kwargs to eliminate any potential for unnamed kwargs.

Originally posted by @camer314 in microsoft/FLAML#451 (comment)

Hi @JavierAntoran @stratisMarkou,

First of all, thanks for making all of this code available - it's been great to look through!

Im currently spending some time trying to work through the Weight Uncertainty in Neural Networks in order to implement Bayes-by-Backprop. I was struggling to understand the difference between your implementation of `Bayes-by-Bac