add lightgbm.booster support #270
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
|
|
@@ -31,7 +31,7 @@ following machine learning frameworks and packages: | |||||
| of XGBClassifier, XGBRegressor and xgboost.Booster. | ||||||
|
|
||||||
| * :ref:`library-lightgbm` - show feature importances and explain predictions | ||||||
| of LGBMClassifier , LGBMRegressor and lightgbm.Booster. | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
|
|
||||||
| * :ref:`library-lightning` - explain weights and predictions of lightning | ||||||
| classifiers and regressors. | ||||||
|
|
||||||
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change | ||||
|---|---|---|---|---|---|---|
| @@ -1,7 +1,7 @@ | ||||||
| # -*- coding: utf-8 -*- | ||||||
| from __future__ import absolute_import, division | ||||||
| from collections import defaultdict | ||||||
| from typing import DefaultDict, Any, Tuple | ||||||
|
|
||||||
| import numpy as np # type: ignore | ||||||
| import lightgbm # type: ignore | ||||||
|
|
@@ -17,7 +17,7 @@ | |||||
| all values sum to 1. | ||||||
| """ | ||||||
|
|
||||||
| @explain_weights.register(lightgbm.Booster) | ||||||
| @explain_weights.register(lightgbm.LGBMClassifier) | ||||||
| @explain_weights.register(lightgbm.LGBMRegressor) | ||||||
| def explain_weights_lightgbm(lgb, | ||||||
|
|
@@ -32,13 +32,15 @@ def explain_weights_lightgbm(lgb, | |||||
| ): | ||||||
| """ | ||||||
| Return an explanation of an LightGBM estimator (via scikit-learn wrapper | ||||||
| LGBMClassifier or LGBMRegressor, or via lightgbm.Booster) as feature importances. | ||||||
|
|
||||||
| See :func:`eli5.explain_weights` for description of | ||||||
| ``top``, ``feature_names``, | ||||||
| ``feature_re`` and ``feature_filter`` parameters. | ||||||
|
|
||||||
| ``target_names`` arguement is ignored for ``lightgbm.LGBMClassifer`` / ``lightgbm.LGBMRegressor``, | ||||||
| but used for ``lightgbm.Booster``. | ||||||
| ``target`` argument is ignored. | ||||||
|
There was a problem hiding this comment.
Suggested change
|
||||||
|
|
||||||
| Parameters | ||||||
| ---------- | ||||||
|
|
@@ -51,8 +53,9 @@ def explain_weights_lightgbm(lgb, | |||||
| across all trees | ||||||
| - 'weight' - the same as 'split', for compatibility with xgboost | ||||||
| """ | ||||||
| booster, is_regression = _check_booster_args(lgb) | ||||||
| coef = _get_lgb_feature_importances(booster, importance_type) | ||||||
| lgb_feature_names = booster.feature_name() | ||||||
| return get_feature_importance_explanation(lgb, vec, coef, | ||||||
| feature_names=feature_names, | ||||||
| estimator_feature_names=lgb_feature_names, | ||||||
|
|
@@ -64,7 +67,7 @@ def explain_weights_lightgbm(lgb, | |||||
| is_regression=isinstance(lgb, lightgbm.LGBMRegressor), | ||||||
| ) | ||||||
|
|
||||||
| @explain_prediction.register(lightgbm.Booster) | ||||||
| @explain_prediction.register(lightgbm.LGBMClassifier) | ||||||
| @explain_prediction.register(lightgbm.LGBMRegressor) | ||||||
| def explain_prediction_lightgbm( | ||||||
|
|
@@ -80,7 +83,7 @@ def explain_prediction_lightgbm( | |||||
| vectorized=False, | ||||||
| ): | ||||||
| """ Return an explanation of LightGBM prediction (via scikit-learn wrapper | ||||||
| LGBMClassifier or LGBMRegressor, or via lightgbm.Booster) as feature weights. | ||||||
|
|
||||||
| See :func:`eli5.explain_prediction` for description of | ||||||
| ``top``, ``top_targets``, ``target_names``, ``targets``, | ||||||
|
|
@@ -108,20 +111,49 @@ def explain_prediction_lightgbm( | |||||
| Weights of all features sum to the output score of the estimator. | ||||||
| """ | ||||||
|
|
||||||
| booster, is_regression = _check_booster_args(lgb) | ||||||
| lgb_feature_names = booster.feature_name() | ||||||
| vec, feature_names = handle_vec(lgb, doc, vec, vectorized, feature_names, | ||||||
| num_features=len(lgb_feature_names)) | ||||||
| if feature_names.bias_name is None: | ||||||
| # LightGBM estimators do not have an intercept, but here we interpret | ||||||
| # them as having an intercept | ||||||
| feature_names.bias_name = '<BIAS>' | ||||||
| X = get_X(doc, vec, vectorized=vectorized) | ||||||
|
|
||||||
| if isinstance(lgb, lightgbm.Booster): | ||||||
| prediction = lgb.predict(X) | ||||||
| n_targets = prediction.shape[-1] | ||||||
| if is_regression is None and target_names is None: | ||||||
| # When n_targets is 1, this can be classification too. | ||||||
| # It's safer to assume regression in this case, | ||||||
| # unless users set it as a classification problem by assigning 'target_names' input [0,1] etc. | ||||||
| # If n_targets > 1, it must be classification. | ||||||
| is_regression = n_targets == 1 | ||||||
| elif is_regression is None: | ||||||
| is_regression = len(target_names) == 1 and n_targets == 1 | ||||||
|
|
||||||
| if is_regression: | ||||||
| proba = None | ||||||
| else: | ||||||
| if n_targets == 1: | ||||||
| p, = prediction | ||||||
| proba = np.array([1 - p, p]) | ||||||
| else: | ||||||
| proba, = prediction | ||||||
| else: | ||||||
| proba = predict_proba(lgb, X) | ||||||
| n_targets = _lgb_n_targets(lgb) | ||||||
|
|
||||||
| if is_regression: | ||||||
| names = ['y'] | ||||||
| elif isinstance(lgb, lightgbm.Booster): | ||||||
| names = np.arange(max(2, n_targets)) | ||||||
| else: | ||||||
| names = lgb.classes_ | ||||||
|
|
||||||
| weight_dicts = _get_prediction_feature_weights(booster, X, n_targets) | ||||||
| x = get_X0(add_intercept(X)) | ||||||
|
|
||||||
| def get_score_weights(_label_id): | ||||||
| _weights = _target_feature_weights( | ||||||
|
|
@@ -145,22 +177,38 @@ def get_score_weights(_label_id): | |||||
| targets=targets, | ||||||
| top_targets=top_targets, | ||||||
| is_regression=is_regression, | ||||||
| is_multiclass=n_targets > 1, | ||||||
| proba=proba, | ||||||
| get_score_weights=get_score_weights, | ||||||
| ) | ||||||
|
|
||||||
| def _check_booster_args(lgb, is_regression=None): | ||||||
| # type: (Any, bool) -> Tuple[lightgbm.Booster, bool] | ||||||
| if isinstance(lgb, lightgbm.Booster): | ||||||
| booster = lgb | ||||||
| else: | ||||||
| booster = lgb.booster_ | ||||||
| _is_regression = isinstance(lgb, lightgbm.LGBMRegressor) | ||||||
| if is_regression is not None and is_regression != _is_regression: | ||||||
| raise ValueError( | ||||||
| 'Inconsistent is_regression={} passed. ' | ||||||
| 'You don\'t have to pass it when using scikit-learn API' | ||||||
| .format(is_regression)) | ||||||
| is_regression = _is_regression | ||||||
| return booster, is_regression | ||||||
|
|
||||||
| def _lgb_n_targets(lgb): | ||||||
| if isinstance(lgb, lightgbm.LGBMClassifier): | ||||||
| return 1 if lgb.n_classes_ == 2 else lgb.n_classes_ | ||||||
| elif isinstance(lgb, lightgbm.LGBMRegressor): | ||||||
| return 1 | ||||||
| else: | ||||||
| raise TypeError | ||||||
|
|
||||||
|
|
||||||
| def _get_lgb_feature_importances(booster, importance_type): | ||||||
| aliases = {'weight': 'split'} | ||||||
| coef = booster.feature_importance( | ||||||
| importance_type=aliases.get(importance_type, importance_type) | ||||||
| ) | ||||||
| norm = coef.sum() | ||||||
|
|
@@ -237,17 +285,15 @@ def walk(tree, parent_id=-1): | |||||
| return leaf_index, split_index | ||||||
|
|
||||||
|
|
||||||
| def _get_prediction_feature_weights(booster, X, n_targets): | ||||||
| """ | ||||||
| Return a list of {feat_id: value} dicts with feature weights, | ||||||
| following ideas from http://blog.datadive.net/interpreting-random-forests/ | ||||||
| """ | ||||||
| dump = booster.dump_model() | ||||||
| tree_info = dump['tree_info'] | ||||||
| _compute_node_values(tree_info) | ||||||
| pred_leafs = booster.predict(X, pred_leaf=True).reshape(-1, n_targets) | ||||||
| tree_info = np.array(tree_info).reshape(-1, n_targets) | ||||||
| assert pred_leafs.shape == tree_info.shape | ||||||
|
|
||||||
|
|
||||||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
a nitpick: extra whitespace before comma