-
Notifications
You must be signed in to change notification settings - Fork 5
/
Copy pathInterpretableDecisionTreeRegression.py
233 lines (186 loc) · 9.21 KB
/
InterpretableDecisionTreeRegression.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
from sklearn.metrics import make_scorer, r2_score
from sklearn.tree import DecisionTreeRegressor
from treeutils import simplify_tree, tree_to_code
import re
class IDecisionTreeRegressor(DecisionTreeRegressor):
"""A decision tree regressor.
Read more in the :ref:`User Guide <tree>`.
Parameters
----------
criterion : string, optional (default="mse")
The function to measure the quality of a split. Supported criteria
are "mse" for the mean squared error, which is equal to variance
reduction as feature selection criterion, and "mae" for the mean
absolute error.
.. versionadded:: 0.18
Mean Absolute Error (MAE) criterion.
splitter : string, optional (default="best")
The strategy used to choose the split at each node. Supported
strategies are "best" to choose the best split and "random" to choose
the best random split.
max_features : int, float, string or None, optional (default=None)
The number of features to consider when looking for the best split:
- If int, then consider `max_features` features at each split.
- If float, then `max_features` is a percentage and
`int(max_features * n_features)` features are considered at each
split.
- If "auto", then `max_features=n_features`.
- If "sqrt", then `max_features=sqrt(n_features)`.
- If "log2", then `max_features=log2(n_features)`.
- If None, then `max_features=n_features`.
Note: the search for a split does not stop until at least one
valid partition of the node samples is found, even if it requires to
effectively inspect more than ``max_features`` features.
max_depth : int or None, optional (default=None)
The maximum depth of the tree. If None, then nodes are expanded until
all leaves are pure or until all leaves contain less than
min_samples_split samples.
min_samples_split : int, float, optional (default=2)
The minimum number of samples required to split an internal node:
- If int, then consider `min_samples_split` as the minimum number.
- If float, then `min_samples_split` is a percentage and
`ceil(min_samples_split * n_samples)` are the minimum
number of samples for each split.
.. versionchanged:: 0.18
Added float values for percentages.
min_samples_leaf : int, float, optional (default=1)
The minimum number of samples required to be at a leaf node:
- If int, then consider `min_samples_leaf` as the minimum number.
- If float, then `min_samples_leaf` is a percentage and
`ceil(min_samples_leaf * n_samples)` are the minimum
number of samples for each node.
.. versionchanged:: 0.18
Added float values for percentages.
min_weight_fraction_leaf : float, optional (default=0.)
The minimum weighted fraction of the sum total of weights (of all
the input samples) required to be at a leaf node. Samples have
equal weight when sample_weight is not provided.
max_leaf_nodes : int or None, optional (default=None)
Grow a tree with ``max_leaf_nodes`` in best-first fashion.
Best nodes are defined as relative reduction in impurity.
If None then unlimited number of leaf nodes.
random_state : int, RandomState instance or None, optional (default=None)
If int, random_state is the seed used by the random number generator;
If RandomState instance, random_state is the random number generator;
If None, the random number generator is the RandomState instance used
by `np.random`.
min_impurity_split : float, optional (default=1e-7)
Threshold for early stopping in tree growth. If the impurity
of a node is below the threshold, the node is a leaf.
.. versionadded:: 0.18
presort : bool, optional (default=False)
Whether to presort the data to speed up the finding of best splits in
fitting. For the default settings of a decision tree on large
datasets, setting this to true may slow down the training process.
When using either a smaller dataset or a restricted depth, this may
speed up the training.
Attributes
----------
feature_importances_ : array of shape = [n_features]
The feature importances.
The higher, the more important the feature.
The importance of a feature is computed as the
(normalized) total reduction of the criterion brought
by that feature. It is also known as the Gini importance [4]_.
max_features_ : int,
The inferred value of max_features.
n_features_ : int
The number of features when ``fit`` is performed.
n_outputs_ : int
The number of outputs when ``fit`` is performed.
tree_ : Tree object
The underlying Tree object.
See also
--------
DecisionTreeClassifier
References
----------
.. [1] https://en.wikipedia.org/wiki/Decision_tree_learning
.. [2] L. Breiman, J. Friedman, R. Olshen, and C. Stone, "Classification
and Regression Trees", Wadsworth, Belmont, CA, 1984.
.. [3] T. Hastie, R. Tibshirani and J. Friedman. "Elements of Statistical
Learning", Springer, 2009.
.. [4] L. Breiman, and A. Cutler, "Random Forests",
http://www.stat.berkeley.edu/~breiman/RandomForests/cc_home.htm
Examples
--------
>>> from sklearn.datasets import load_boston
>>> from sklearn.model_selection import cross_val_score
>>> from sklearn.tree import DecisionTreeRegressor
>>> boston = load_boston()
>>> regressor = DecisionTreeRegressor(random_state=0)
>>> cross_val_score(regressor, boston.data, boston.target, cv=10)
... # doctest: +SKIP
...
array([ 0.61..., 0.57..., -0.34..., 0.41..., 0.75...,
0.07..., 0.29..., 0.33..., -1.42..., -1.77...])
"""
def __init__(self,
criterion="mse",
splitter="best",
max_depth=None,
min_samples_split=2,
min_samples_leaf=1,
min_weight_fraction_leaf=0.,
max_features=None,
random_state=None,
max_leaf_nodes=None,
min_impurity_split=1e-7,
presort=False,
verbose=False,
acceptable_score_drop=0.01):
super(IDecisionTreeRegressor, self).__init__(
criterion=criterion,
splitter=splitter,
max_depth=max_depth,
min_samples_split=min_samples_split,
min_samples_leaf=min_samples_leaf,
min_weight_fraction_leaf=min_weight_fraction_leaf,
max_features=max_features,
max_leaf_nodes=max_leaf_nodes,
random_state=random_state,
min_impurity_split=min_impurity_split,
presort=presort)
self.acceptable_score_drop = acceptable_score_drop
self.verbose = verbose
def fit(self, X, y, sample_weight=None, check_input=True,
X_idx_sorted=None, scorer=make_scorer(r2_score, greater_is_better=True)):
"""Build a decision tree regressor from the training set (X, y).
Parameters
----------
X : array-like or sparse matrix, shape = [n_samples, n_features]
The training input samples. Internally, it will be converted to
``dtype=np.float32`` and if a sparse matrix is provided
to a sparse ``csc_matrix``.
y : array-like, shape = [n_samples] or [n_samples, n_outputs]
The target values (real numbers). Use ``dtype=np.float64`` and
``order='C'`` for maximum efficiency.
sample_weight : array-like, shape = [n_samples] or None
Sample weights. If None, then samples are equally weighted. Splits
that would create child nodes with net zero or negative weight are
ignored while searching for a split in each node.
check_input : boolean, (default=True)
Allow to bypass several input checking.
Don't use this parameter unless you know what you do.
X_idx_sorted : array-like, shape = [n_samples, n_features], optional
The indexes of the sorted training input samples. If many tree
are grown on the same dataset, this allows the ordering to be
cached between trees. If None, the data will be sorted here.
Don't use this parameter unless you know what to do.
Returns
-------
self : object
Returns self.
"""
super(IDecisionTreeRegressor, self).fit(
X, y,
sample_weight=sample_weight,
check_input=check_input,
X_idx_sorted=X_idx_sorted)
simplify_tree(self, X, y, scorer, self.acceptable_score_drop, verbose=self.verbose)
return self
def __str__(self):
feature_names = ["ft"+str(i) for i in range(len(self.feature_importances_))]
return self.tostring(feature_names)
def tostring(self, feature_names, decimals=4):
return re.sub('\n\s+return', ' return', tree_to_code(self, feature_names, transform_to_probabilities=False, decimals=decimals))