Comments (3)
@dePuff, thank you for opening this issue!
I'm sorry, but I don't think I'm completely understanding what functionality you're looking for.
It sounds like you're familiar with HH's feature_engineer
, so you may have already seen this Medium article. If you haven't seen it, would you mind checking that out and letting me know if that's at all what you're talking about?
My other thought is that you might be looking for the feature_selector
kwarg of CVExperiment
. Both feature_engineer
and feature_selector
are also kwargs in the forge_experiment
method of all the OptPros for optimization, which is when you would be using Integer
to define a search space.
I'm sorry if I'm completely missing your point. Would you mind providing a minimal code snippet of what you're trying to accomplish?
from hyperparameter_hunter.
First of all. Thank you for your time and for your response.
Yes, I started with Medium article but probably missing something because never use libs like this one before.
For example, if I run something like code below then hyperparameter_hunter will looking for good learning rate by checking learning rates closest to good one.
I found this possibility to be amazing.
opt_1 = BayesianOptPro(iterations=100, random_state=32)
opt_1.forge_experiment(
AdaBoostRegressor,
model_init_params=dict(
n_estimators=40,
learning_rate=Real(0.01, 1.0),
loss='linear',
),
)
opt_1.go()
From now I wanna use same approaches for feature selection but fail with it.
My expectation was to have something like rasbt.github.io/mlxtend/user_guide/feature_selection/SequentialFeatureSelector/
Let's forget for moment about question in the title because probably it's totally wrong idea how to get what I want.
Could you provide any snippet of code how to make any kind of feature selection with hyperparameter_hunter it will really help to understand the technics?
I tried feature_selector kwargs in this way:
possible_features = [['col_1', 'col_2', 'col_3', 'col_4', ], ['col_1', 'col_2', 'col_4', ]]
...
feature_selector=Categorical(possible_features)
And it did't work anyhow.
But here I had ideas of features combinations which should work.
I really want to know how to make hyperparameter_hunter found them if we don't have them.
Any sample of any technics please.
from hyperparameter_hunter.
Hahaha thank you so much for bringing this up, because I forgot to add that when I was working on the rest of Feature Engineering! I had always intended to add optimization of feature_selector
, so thank you for reminding me it's not actually in there yet.
I'll get started on this and update you with any developments!
from hyperparameter_hunter.
Related Issues (20)
- Support for various advanced functionality? HOT 9
- Unable to access docs HOT 2
- How to do predict_proba in catboost classifier? HOT 3
- Support for nested parameters/parameterizing objects that can't be called by name. HOT 2
- How to handle variable number of layers?
- How can I set class weights in a multiclass classification with imbalance dataset? HOT 1
- How to use the Experiments? HOT 6
- OSError: could not get source code HOT 9
- Q: what is RandomForestOptPro exactly? HOT 3
- Doc improvement suggestion HOT 4
- logloss issue with multiclass task HOT 4
- Metaclass conflict with Keras 2.3.0 HOT 1
- Timeseries Cross Validation HOT 6
- pd.DataFrame.sparse supported in environment?
- Interface with pytorch or tensorflow models HOT 2
- Problem with library scikit-optimize in Python 3.6 HOT 9
- ROC AUC scores don't match to those of sklearn HOT 1
- Failed to import packages from hyperparameter_hunter HOT 3
- ImportError: cannot import name 'Log10' HOT 1
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from hyperparameter_hunter.