def test_tree2dict():
X = [[1, 1], [0, 2], [0, 3], [1, 3], [2, 3], [0, 4]]
y = [0, 0, 0, 1, 1, 1]
clf = DecisionTreeClassifier(random_state=42).fit(X, y)
text = tree2text(get_tree_info(clf))
print(text)
expected = """
x1 <= 2.500 (33.3%) ---> [1.000, 0.000]
x1 > 2.500 (66.7%)
x0 <= 0.500 (33.3%)
x1 <= 3.500 (16.7%) ---> [1.000, 0.000]
x1 > 3.500 (16.7%) ---> [0.000, 1.000]
x0 > 0.500 (33.3%) ---> [0.000, 1.000]
""".strip()
assert text == expected
# check it with feature_names
text = tree2text(get_tree_info(clf, feature_names=['x', 'y']))
print(text)
expected = """
y <= 2.500 (33.3%) ---> [1.000, 0.000]
y > 2.500 (66.7%)
x <= 0.500 (33.3%)
y <= 3.500 (16.7%) ---> [1.000, 0.000]
y > 3.500 (16.7%) ---> [0.000, 1.000]
x > 0.500 (33.3%) ---> [0.000, 1.000]
""".strip()
assert text == expected
def explain_decision_tree(
estimator,
vec=None,
top=_TOP,
target_names=None,
targets=None, # ignored
feature_names=None,
feature_re=None,
feature_filter=None,
**export_graphviz_kwargs):
"""
Return an explanation of a decision tree.
See :func:`eli5.explain_weights` for description of
``top``, ``target_names``, ``feature_names``,
``feature_re`` and ``feature_filter`` parameters.
``targets`` parameter is ignored.
``vec`` is a vectorizer instance used to transform
raw features to the input of the estimator (e.g. a fitted
CountVectorizer instance); you can pass it instead of ``feature_names``.
All other keyword arguments are passed to
`sklearn.tree.export_graphviz`_ function.
.. _sklearn.tree.export_graphviz: http://scikit-learn.org/stable/modules/generated/sklearn.tree.export_graphviz.html
"""
feature_names = get_feature_names(estimator,
vec,
feature_names=feature_names)
coef = estimator.feature_importances_
tree_feature_names = feature_names
feature_names, flt_indices = feature_names.handle_filter(
feature_filter, feature_re)
if flt_indices is not None:
coef = coef[flt_indices]
indices = argsort_k_largest_positive(coef, top)
names, values = feature_names[indices], coef[indices]
export_graphviz_kwargs.setdefault("proportion", True)
tree_info = get_tree_info(estimator,
feature_names=tree_feature_names,
class_names=target_names,
**export_graphviz_kwargs)
return Explanation(
feature_importances=FeatureImportances(
[FeatureWeight(*x) for x in zip(names, values)],
remaining=np.count_nonzero(coef) - len(indices),
),
decision_tree=tree_info,
description=DESCRIPTION_DECISION_TREE,
estimator=repr(estimator),
method='decision tree',
)
def explain_decision_tree(
estimator,
vec=None,
top=_TOP,
target_names=None,
targets=None, # ignored
feature_names=None,
feature_re=None,
feature_filter=None,
**export_graphviz_kwargs):
"""
Return an explanation of a decision tree.
See :func:`eli5.explain_weights` for description of
``top``, ``target_names``, ``feature_names``,
``feature_re`` and ``feature_filter`` parameters.
``targets`` parameter is ignored.
``vec`` is a vectorizer instance used to transform
raw features to the input of the estimator (e.g. a fitted
CountVectorizer instance); you can pass it instead of ``feature_names``.
All other keyword arguments are passed to
`sklearn.tree.export_graphviz`_ function.
.. _sklearn.tree.export_graphviz: http://scikit-learn.org/stable/modules/generated/sklearn.tree.export_graphviz.html
"""
feature_names = get_feature_names(estimator,
vec,
feature_names=feature_names)
tree_feature_names = feature_names
feature_names, flt_indices = feature_names.handle_filter(
feature_filter, feature_re)
feature_importances = get_feature_importances_filtered(
estimator.feature_importances_, feature_names, flt_indices, top)
export_graphviz_kwargs.setdefault("proportion", True)
tree_info = get_tree_info(estimator,
feature_names=tree_feature_names,
class_names=target_names,
**export_graphviz_kwargs)
return Explanation(
feature_importances=feature_importances,
decision_tree=tree_info,
description=DESCRIPTION_DECISION_TREE,
estimator=repr(estimator),
method='decision tree',
)
def explain_decision_tree(
clf,
vec=None,
top=_TOP,
target_names=None,
targets=None, # ignored
feature_names=None,
feature_re=None,
**export_graphviz_kwargs):
"""
Return an explanation of a decision tree classifier in the
following format (compatible with random forest explanations)::
Explanation(
estimator="<classifier repr>",
method="<interpretation method>",
description="<human readable description>",
decision_tree={...tree information},
feature_importances=[
FeatureWeight(feature_name, importance, std_deviation),
...
]
)
"""
feature_names = get_feature_names(clf, vec, feature_names=feature_names)
coef = clf.feature_importances_
tree_feature_names = feature_names
if feature_re is not None:
feature_names, flt_indices = feature_names.filtered_by_re(feature_re)
coef = coef[flt_indices]
indices = argsort_k_largest(coef, top)
names, values = feature_names[indices], coef[indices]
std = np.zeros_like(values)
export_graphviz_kwargs.setdefault("proportion", True)
tree_info = get_tree_info(clf,
feature_names=tree_feature_names,
class_names=target_names,
**export_graphviz_kwargs)
return Explanation(
feature_importances=[
FeatureWeight(*x) for x in zip(names, values, std)
],
decision_tree=tree_info,
description=DESCRIPTION_DECISION_TREE,
estimator=repr(clf),
method='decision tree',
)