Comments (3)
After checking the source code, I found that the error was reported because featureIndex.FeatureIdx <= 0xffff.
It is exactly the opposite. The condition featureIndex.FeatureIdx <= 0xfff
is checked and if it is false then error is reported.
Finally, could you please help me explain what the featureIndex.FeatureIdx field means? Thank you.
You can see it in the code in model.cpp.
Basically all different binary splits in the trees in the trained model are grouped into "features". Features correspond to real features (including implicitly derived features from original categorical, text and embedding features) if the number of splits for a particular feature is less than MAX_VALUES_PER_BIN
(which is 254 ), otherwise original features are split into subfeatures with at most MAX_VALUES_PER_BIN
splits for each subfeature.
I suspect that the issue here is that too many derived features from categorical features are implicitly generated and used during the training.
Do you have categorical features, and if the answer is positive - how many? How many distinct values (categories) do they have?
from catboost.
After checking the source code, I found that the error was reported because featureIndex.FeatureIdx <= 0xffff.
It is exactly the opposite. The condition
featureIndex.FeatureIdx <= 0xfff
is checked and if it is false then error is reported.Finally, could you please help me explain what the featureIndex.FeatureIdx field means? Thank you.
You can see it in the code in model.cpp.
Basically all different binary splits in the trees in the trained model are grouped into "features". Features correspond to real features (including implicitly derived features from original categorical, text and embedding features) if the number of splits for a particular feature is less than
MAX_VALUES_PER_BIN
(which is 254 ), otherwise original features are split into subfeatures with at mostMAX_VALUES_PER_BIN
splits for each subfeature.I suspect that the issue here is that too many derived features from categorical features are implicitly generated and used during the training.
Do you have categorical features, and if the answer is positive - how many? How many distinct values (categories) do they have?
I have almost 900 categorical features,There are generally 2 to 30 different values ββfor each feature, and no more than 300 at most.I checked some previous issues and found that reducing max_ctr_complexity can solve this problem, but this will greatly affect the accuracy of the model.
What I want to know is whether this featureIndex.FeatureIdx is fixed before the model training starts, or will it continue to increase as the model is trained? Can I set it to stop training when it exceeds 0xffff during model training? Otherwise, it will waste a lot of time (because the error will not be reported until the model training is completed)
from catboost.
Hello!
or will it continue to increase as the model is trained
- yes. A new counter feature can be generated for each new split https://catboost.ai/en/docs/concepts/algorithm-main-stages_cat-to-numberic
You can you use model-size-reg option to decrease number of resulting features, it should solve your problem.
from catboost.
Related Issues (20)
- CatBoost for Apache Spark AUC eval metric not working as expected. HOT 3
- CatBoost throws an exception when dealing with a large dataset
- Catboost 1.2.5 broke text features on GPU "Can't find borders for feature #4138" HOT 12
- R: Failed to install 'unknown package' from GitHub HOT 2
- [Model dump: JSON] model.save_model does not warn when required "pool" argument is skipped
- tensor_search_helpers.cpp HOT 1
- quantize: Categorical features are not supported in block quantization
- MultiLogloss can not be used if 'class weight' is specified.
- InternalFeatureImportance is in documentation but not implemented HOT 1
- Internal CatBoost Error (contact developers for assistance): isRealTarget is false, but isClass is false HOT 3
- Can't set keyword arguments sample_weight and init_model while using a custom loss
- Numpy 2.0 support status? HOT 3
- Tests are failing for catboost python-package component. HOT 1
- I use optuna to select model params and "num_features_to_select" of select_features function. The result is bad.
- My text feature is Chinese and can't be tokenized by delimiter 'space'. How can I use a user-defined tokenizer?
- c++ Standalone evaluator not loading bias
- Unable to catch the TOutOfMemoryError using a try-catch block HOT 1
- Fix using logloss for early stopping when task_type=GPU and eval_metric is not implemented on GPU.
- CatBoostError: /src/catboost/catboost/libs/data/feature_names_converter.h:33: String '' is not a feature name
- Segmentation fault while using slice of the Pool. HOT 6
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
π 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. πππ
-
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 β€οΈ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from catboost.