---
metadata:
- name: generator
content: Diplodoc Platform v5.50.3
alternate:
- https://catboost.ai/docs/en/concepts/python-reference_catboostclassifier_get_feature_importance.md
---
> **Documentation Index:** Fetch the complete configuration index at https://catboost.ai/docs/en/llms.txt
# get_feature_importance
Calculate and return the [feature importances](https://catboost.ai/docs/en/concepts/fstr.md).
## Method call format {#call-format}
```python
get_feature_importance(data=None,
reference_data=None,
type=EFstrType.FeatureImportance,
prettified=False,
thread_count=-1,
verbose=False,
log_cout=sys.stdout,
log_cerr=sys.stderr)
```
## Parameters {#parameters}
### data
#### Description
The dataset for feature importance calculation.
The required dataset depends on the selected feature importance calculation type (specified in the `type` parameter):
- PredictionValuesChange — Either None or the same dataset that was used for training if the model does not contain information regarding the weight of leaves. All models trained with CatBoost version 0.9 or higher contain leaf weight information by default.
- LossFunctionChange — Any dataset. Feature importances are calculated on a subset for large datasets.
- PredictionDiff — A list of object pairs.
**Possible types**
catboost.Pool
**Default value**
Required parameter for the LossFunctionChange and ShapValues type of feature importances and in case the model does not contain information regarding the weight of leaves.
None otherwise.
### reference_data
#### Description
Reference data for Independent Tree SHAP values from [Explainable AI for Trees: From Local Explanations to Global Understanding](https://arxiv.org/abs/1905.04610v1). If `type` is [`ShapValues`](https://catboost.ai/docs/en/concepts/shap-values.md) and `reference_data` is not `None`, then Independent Tree SHAP values are calculated.
**Possible types**
catboost.Pool
**Default value**
None
### type
_Alias:_`fstr_type` (deprecated, use `type` instead)
#### Description
The type of feature importance to calculate.
Possible values:
- FeatureImportance: Equal to [PredictionValuesChange](https://catboost.ai/docs/en/concepts/fstr.md#regular-feature-importance) for non-ranking metrics and [LossFunctionChange](https://catboost.ai/docs/en/concepts/fstr.md#regular-feature-importances__lossfunctionchange) for ranking metrics (the value is determined automatically).
- [ShapValues](https://catboost.ai/docs/en/concepts/shap-values.md): A vector $v$ with contributions of each feature to the prediction for every input object and the expected value of the model prediction for the object (average prediction given no knowledge about the object).
- [Interaction](https://catboost.ai/docs/en/concepts/feature-interaction.md#feature-interaction-strength): The value of the feature interaction strength for each pair of features.
- PredictionDiff: A vector with contributions of each feature to the RawFormulaVal difference for each pair of objects.
**Possible types**
- string
- [EFStrType](https://catboost.ai/docs/en/concepts/python-efstr-type__desc.md)
{% note info %}
It is recommended to use EFStrType for this parameter.
{% endnote %}
**Default value**
FeatureImportance
### prettified
#### Description
Return the feature importances as a list of the following pairs sorted by feature importance:
```
(feature_id, feature importance)
```
Should be used if one of the following values of the `type`parameter is selected:
- PredictionValuesChange
- PredictionValuesChange
**Possible types**
bool
**Default value**
False
### thread_count
#### Description
The number of threads to use for operation.
Optimizes the speed of execution. This parameter doesn't affect results.
**Possible types**
int
**Default value**
-1 (the number of threads is equal to the number of processor cores)
### verbose
#### Description
The purpose of this parameter depends on the type of the given value:
- bool — Output progress to stdout.
Works with the [ShapValues](https://catboost.ai/docs/en/concepts/shap-values.md) type of feature importance calculation.
- int — The logging period.
**Possible types**
- bool
- int
**Default value**
False
### log_cout
Output stream or callback for logging.
**Possible types**
- callable Python object
- python object providing the `write()` method
**Default value**
sys.stdout
### log_cerr
Error stream or callback for logging.
**Possible types**
- callable Python object
- python object providing the `write()` method
**Default value**
sys.stderr
## Type of return value {#output-format}
Depends on the selected feature strength calculation method:
- PredictionValuesChange, LossFunctionChange or PredictionValuesChange with the `prettified` parameter set to False
: a list of length `[n_features]` with float feature importances values for each feature
- PredictionValuesChange or LossFunctionChange with the `prettified` parameter set to True
: a list of length `[n_features]` with `(feature_id (string), feature_importance (float))` pairs, sorted by feature importance values in descending order
- ShapValues: np.array of shape `(n_objects, n_features + 1)` with float ShapValues for each `(object, feature)`
- Interaction: list of length [ n_features] of three element lists of `(first_feature_index, second_feature_index, interaction_score (float))`