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
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
|
import scipy as sp
from .base import _get_response
from .. import det_curve
from .._base import _check_pos_label_consistency
from ...utils import check_matplotlib_support
class DetCurveDisplay:
"""DET curve visualization.
It is recommend to use :func:`~sklearn.metrics.DetCurveDisplay.from_estimator`
or :func:`~sklearn.metrics.DetCurveDisplay.from_predictions` to create a
visualizer. All parameters are stored as attributes.
Read more in the :ref:`User Guide <visualizations>`.
.. versionadded:: 0.24
Parameters
----------
fpr : ndarray
False positive rate.
fnr : ndarray
False negative rate.
estimator_name : str, default=None
Name of estimator. If None, the estimator name is not shown.
pos_label : str or int, default=None
The label of the positive class.
Attributes
----------
line_ : matplotlib Artist
DET Curve.
ax_ : matplotlib Axes
Axes with DET Curve.
figure_ : matplotlib Figure
Figure containing the curve.
See Also
--------
det_curve : Compute error rates for different probability thresholds.
DetCurveDisplay.from_estimator : Plot DET curve given an estimator and
some data.
DetCurveDisplay.from_predictions : Plot DET curve given the true and
predicted labels.
Examples
--------
>>> import matplotlib.pyplot as plt
>>> from sklearn.datasets import make_classification
>>> from sklearn.metrics import det_curve, DetCurveDisplay
>>> from sklearn.model_selection import train_test_split
>>> from sklearn.svm import SVC
>>> X, y = make_classification(n_samples=1000, random_state=0)
>>> X_train, X_test, y_train, y_test = train_test_split(
... X, y, test_size=0.4, random_state=0)
>>> clf = SVC(random_state=0).fit(X_train, y_train)
>>> y_pred = clf.decision_function(X_test)
>>> fpr, fnr, _ = det_curve(y_test, y_pred)
>>> display = DetCurveDisplay(
... fpr=fpr, fnr=fnr, estimator_name="SVC"
... )
>>> display.plot()
<...>
>>> plt.show()
"""
def __init__(self, *, fpr, fnr, estimator_name=None, pos_label=None):
self.fpr = fpr
self.fnr = fnr
self.estimator_name = estimator_name
self.pos_label = pos_label
@classmethod
def from_estimator(
cls,
estimator,
X,
y,
*,
sample_weight=None,
response_method="auto",
pos_label=None,
name=None,
ax=None,
**kwargs,
):
"""Plot DET curve given an estimator and data.
Read more in the :ref:`User Guide <visualizations>`.
.. versionadded:: 1.0
Parameters
----------
estimator : estimator instance
Fitted classifier or a fitted :class:`~sklearn.pipeline.Pipeline`
in which the last estimator is a classifier.
X : {array-like, sparse matrix} of shape (n_samples, n_features)
Input values.
y : array-like of shape (n_samples,)
Target values.
sample_weight : array-like of shape (n_samples,), default=None
Sample weights.
response_method : {'predict_proba', 'decision_function', 'auto'} \
default='auto'
Specifies whether to use :term:`predict_proba` or
:term:`decision_function` as the predicted target response. If set
to 'auto', :term:`predict_proba` is tried first and if it does not
exist :term:`decision_function` is tried next.
pos_label : str or int, default=None
The label of the positive class. When `pos_label=None`, if `y_true`
is in {-1, 1} or {0, 1}, `pos_label` is set to 1, otherwise an
error will be raised.
name : str, default=None
Name of DET curve for labeling. If `None`, use the name of the
estimator.
ax : matplotlib axes, default=None
Axes object to plot on. If `None`, a new figure and axes is
created.
**kwargs : dict
Additional keywords arguments passed to matplotlib `plot` function.
Returns
-------
display : :class:`~sklearn.metrics.DetCurveDisplay`
Object that stores computed values.
See Also
--------
det_curve : Compute error rates for different probability thresholds.
DetCurveDisplay.from_predictions : Plot DET curve given the true and
predicted labels.
Examples
--------
>>> import matplotlib.pyplot as plt
>>> from sklearn.datasets import make_classification
>>> from sklearn.metrics import DetCurveDisplay
>>> from sklearn.model_selection import train_test_split
>>> from sklearn.svm import SVC
>>> X, y = make_classification(n_samples=1000, random_state=0)
>>> X_train, X_test, y_train, y_test = train_test_split(
... X, y, test_size=0.4, random_state=0)
>>> clf = SVC(random_state=0).fit(X_train, y_train)
>>> DetCurveDisplay.from_estimator(
... clf, X_test, y_test)
<...>
>>> plt.show()
"""
check_matplotlib_support(f"{cls.__name__}.from_estimator")
name = estimator.__class__.__name__ if name is None else name
y_pred, pos_label = _get_response(
X,
estimator,
response_method,
pos_label=pos_label,
)
return cls.from_predictions(
y_true=y,
y_pred=y_pred,
sample_weight=sample_weight,
name=name,
ax=ax,
pos_label=pos_label,
**kwargs,
)
@classmethod
def from_predictions(
cls,
y_true,
y_pred,
*,
sample_weight=None,
pos_label=None,
name=None,
ax=None,
**kwargs,
):
"""Plot the DET curve given the true and predicted labels.
Read more in the :ref:`User Guide <visualizations>`.
.. versionadded:: 1.0
Parameters
----------
y_true : array-like of shape (n_samples,)
True labels.
y_pred : array-like of shape (n_samples,)
Target scores, can either be probability estimates of the positive
class, confidence values, or non-thresholded measure of decisions
(as returned by `decision_function` on some classifiers).
sample_weight : array-like of shape (n_samples,), default=None
Sample weights.
pos_label : str or int, default=None
The label of the positive class. When `pos_label=None`, if `y_true`
is in {-1, 1} or {0, 1}, `pos_label` is set to 1, otherwise an
error will be raised.
name : str, default=None
Name of DET curve for labeling. If `None`, name will be set to
`"Classifier"`.
ax : matplotlib axes, default=None
Axes object to plot on. If `None`, a new figure and axes is
created.
**kwargs : dict
Additional keywords arguments passed to matplotlib `plot` function.
Returns
-------
display : :class:`~sklearn.metrics.DetCurveDisplay`
Object that stores computed values.
See Also
--------
det_curve : Compute error rates for different probability thresholds.
DetCurveDisplay.from_estimator : Plot DET curve given an estimator and
some data.
Examples
--------
>>> import matplotlib.pyplot as plt
>>> from sklearn.datasets import make_classification
>>> from sklearn.metrics import DetCurveDisplay
>>> from sklearn.model_selection import train_test_split
>>> from sklearn.svm import SVC
>>> X, y = make_classification(n_samples=1000, random_state=0)
>>> X_train, X_test, y_train, y_test = train_test_split(
... X, y, test_size=0.4, random_state=0)
>>> clf = SVC(random_state=0).fit(X_train, y_train)
>>> y_pred = clf.decision_function(X_test)
>>> DetCurveDisplay.from_predictions(
... y_test, y_pred)
<...>
>>> plt.show()
"""
check_matplotlib_support(f"{cls.__name__}.from_predictions")
fpr, fnr, _ = det_curve(
y_true,
y_pred,
pos_label=pos_label,
sample_weight=sample_weight,
)
pos_label = _check_pos_label_consistency(pos_label, y_true)
name = "Classifier" if name is None else name
viz = DetCurveDisplay(
fpr=fpr,
fnr=fnr,
estimator_name=name,
pos_label=pos_label,
)
return viz.plot(ax=ax, name=name, **kwargs)
def plot(self, ax=None, *, name=None, **kwargs):
"""Plot visualization.
Parameters
----------
ax : matplotlib axes, default=None
Axes object to plot on. If `None`, a new figure and axes is
created.
name : str, default=None
Name of DET curve for labeling. If `None`, use `estimator_name` if
it is not `None`, otherwise no labeling is shown.
**kwargs : dict
Additional keywords arguments passed to matplotlib `plot` function.
Returns
-------
display : :class:`~sklearn.metrics.plot.DetCurveDisplay`
Object that stores computed values.
"""
check_matplotlib_support("DetCurveDisplay.plot")
name = self.estimator_name if name is None else name
line_kwargs = {} if name is None else {"label": name}
line_kwargs.update(**kwargs)
import matplotlib.pyplot as plt
if ax is None:
_, ax = plt.subplots()
(self.line_,) = ax.plot(
sp.stats.norm.ppf(self.fpr),
sp.stats.norm.ppf(self.fnr),
**line_kwargs,
)
info_pos_label = (
f" (Positive label: {self.pos_label})" if self.pos_label is not None else ""
)
xlabel = "False Positive Rate" + info_pos_label
ylabel = "False Negative Rate" + info_pos_label
ax.set(xlabel=xlabel, ylabel=ylabel)
if "label" in line_kwargs:
ax.legend(loc="lower right")
ticks = [0.001, 0.01, 0.05, 0.20, 0.5, 0.80, 0.95, 0.99, 0.999]
tick_locations = sp.stats.norm.ppf(ticks)
tick_labels = [
"{:.0%}".format(s) if (100 * s).is_integer() else "{:.1%}".format(s)
for s in ticks
]
ax.set_xticks(tick_locations)
ax.set_xticklabels(tick_labels)
ax.set_xlim(-3, 3)
ax.set_yticks(tick_locations)
ax.set_yticklabels(tick_labels)
ax.set_ylim(-3, 3)
self.ax_ = ax
self.figure_ = ax.figure
return self
|
