100 lines
3.4 KiB
Python
100 lines
3.4 KiB
Python
|
import numpy as np
|
||
|
|
|
||
|
|
from . import check_consistent_length
|
||
|
|
from ._optional_dependencies import check_matplotlib_support
|
||
|
|
from ._response import _get_response_values_binary
|
||
|
|
from .multiclass import type_of_target
|
||
|
|
from .validation import _check_pos_label_consistency
|
||
|
|
|
||
|
|
|
||
|
|
class _BinaryClassifierCurveDisplayMixin:
|
||
|
|
"""Mixin class to be used in Displays requiring a binary classifier.
|
||
|
|
|
||
|
|
The aim of this class is to centralize some validations regarding the estimator and
|
||
|
|
the target and gather the response of the estimator.
|
||
|
|
"""
|
||
|
|
|
||
|
|
def _validate_plot_params(self, *, ax=None, name=None):
|
||
|
|
check_matplotlib_support(f"{self.__class__.__name__}.plot")
|
||
|
|
import matplotlib.pyplot as plt
|
||
|
|
|
||
|
|
if ax is None:
|
||
|
|
_, ax = plt.subplots()
|
||
|
|
|
||
|
|
name = self.estimator_name if name is None else name
|
||
|
|
return ax, ax.figure, name
|
||
|
|
|
||
|
|
@classmethod
|
||
|
|
def _validate_and_get_response_values(
|
||
|
|
cls, estimator, X, y, *, response_method="auto", pos_label=None, name=None
|
||
|
|
):
|
||
|
|
check_matplotlib_support(f"{cls.__name__}.from_estimator")
|
||
|
|
|
||
|
|
name = estimator.__class__.__name__ if name is None else name
|
||
|
|
|
||
|
|
y_pred, pos_label = _get_response_values_binary(
|
||
|
|
estimator,
|
||
|
|
X,
|
||
|
|
response_method=response_method,
|
||
|
|
pos_label=pos_label,
|
||
|
|
)
|
||
|
|
|
||
|
|
return y_pred, pos_label, name
|
||
|
|
|
||
|
|
@classmethod
|
||
|
|
def _validate_from_predictions_params(
|
||
|
|
cls, y_true, y_pred, *, sample_weight=None, pos_label=None, name=None
|
||
|
|
):
|
||
|
|
check_matplotlib_support(f"{cls.__name__}.from_predictions")
|
||
|
|
|
||
|
|
if type_of_target(y_true) != "binary":
|
||
|
|
raise ValueError(
|
||
|
|
f"The target y is not binary. Got {type_of_target(y_true)} type of"
|
||
|
|
" target."
|
||
|
|
)
|
||
|
|
|
||
|
|
check_consistent_length(y_true, y_pred, sample_weight)
|
||
|
|
pos_label = _check_pos_label_consistency(pos_label, y_true)
|
||
|
|
|
||
|
|
name = name if name is not None else "Classifier"
|
||
|
|
|
||
|
|
return pos_label, name
|
||
|
|
|
||
|
|
|
||
|
|
def _validate_score_name(score_name, scoring, negate_score):
|
||
|
|
"""Validate the `score_name` parameter.
|
||
|
|
|
||
|
|
If `score_name` is provided, we just return it as-is.
|
||
|
|
If `score_name` is `None`, we use `Score` if `negate_score` is `False` and
|
||
|
|
`Negative score` otherwise.
|
||
|
|
If `score_name` is a string or a callable, we infer the name. We replace `_` by
|
||
|
|
spaces and capitalize the first letter. We remove `neg_` and replace it by
|
||
|
|
`"Negative"` if `negate_score` is `False` or just remove it otherwise.
|
||
|
|
"""
|
||
|
|
if score_name is not None:
|
||
|
|
return score_name
|
||
|
|
elif scoring is None:
|
||
|
|
return "Negative score" if negate_score else "Score"
|
||
|
|
else:
|
||
|
|
score_name = scoring.__name__ if callable(scoring) else scoring
|
||
|
|
if negate_score:
|
||
|
|
if score_name.startswith("neg_"):
|
||
|
|
score_name = score_name[4:]
|
||
|
|
else:
|
||
|
|
score_name = f"Negative {score_name}"
|
||
|
|
elif score_name.startswith("neg_"):
|
||
|
|
score_name = f"Negative {score_name[4:]}"
|
||
|
|
score_name = score_name.replace("_", " ")
|
||
|
|
return score_name.capitalize()
|
||
|
|
|
||
|
|
|
||
|
|
def _interval_max_min_ratio(data):
|
||
|
|
"""Compute the ratio between the largest and smallest inter-point distances.
|
||
|
|
|
||
|
|
A value larger than 5 typically indicates that the parameter range would
|
||
|
|
better be displayed with a log scale while a linear scale would be more
|
||
|
|
suitable otherwise.
|
||
|
|
"""
|
||
|
|
diff = np.diff(np.sort(data))
|
||
|
|
return diff.max() / diff.min()
|