def test_array_like(self):
ax = skplt.plot_ks_statistic([0, 1], [[0.8, 0.2], [0.2, 0.8]])
"""An example showing the plot_ks_statistic method used by a scikit-learn classifier""" from __future__ import absolute_import import matplotlib.pyplot as plt from scikitplot import classifier_factory from sklearn.linear_model import LogisticRegression from sklearn.datasets import load_breast_cancer as load_data X, y = load_data(return_X_y=True) lr = classifier_factory(LogisticRegression()) lr.plot_ks_statistic(X, y, random_state=1) plt.show() # Using the more flexible functions API from scikitplot import plotters as skplt lr = LogisticRegression() lr = lr.fit(X, y) probas = lr.predict_proba(X) skplt.plot_ks_statistic(y_true=y, y_probas=probas) plt.show()
def test_array_like(self):
ax = skplt.plot_ks_statistic([0, 1], [[0.8, 0.2], [0.2, 0.8]])
def plot_ks_statistic(clf, X, y, title='KS Statistic Plot', do_cv=True, cv=None,
shuffle=True, random_state=None, ax=None):
"""Generates the KS Statistic plot for a given classifier and dataset.
Args:
clf: Classifier instance that implements "fit" and "predict_proba" methods.
X (array-like, shape (n_samples, n_features)):
Training vector, where n_samples is the number of samples and
n_features is the number of features.
y (array-like, shape (n_samples) or (n_samples, n_features)):
Target relative to X for classification.
title (string, optional): Title of the generated plot. Defaults to "KS Statistic Plot".
do_cv (bool, optional): If True, the classifier is cross-validated on the dataset using the
cross-validation strategy in `cv` to generate the confusion matrix. If False, the
confusion matrix is generated without training or cross-validating the classifier.
This assumes that the classifier has already been called with its `fit` method beforehand.
cv (int, cross-validation generator, iterable, optional): Determines the
cross-validation strategy to be used for splitting.
Possible inputs for cv are:
- None, to use the default 3-fold cross-validation,
- integer, to specify the number of folds.
- An object to be used as a cross-validation generator.
- An iterable yielding train/test splits.
For integer/None inputs, if ``y`` is binary or multiclass,
:class:`StratifiedKFold` used. If the estimator is not a classifier
or if ``y`` is neither binary nor multiclass, :class:`KFold` is used.
shuffle (bool, optional): Used when do_cv is set to True. Determines whether to shuffle the
training data before splitting using cross-validation. Default set to True.
random_state (int :class:`RandomState`): Pseudo-random number generator state used
for random sampling.
ax (:class:`matplotlib.axes.Axes`, optional): The axes upon which to plot
the learning curve. If None, the plot is drawn on a new set of axes.
Returns:
ax (:class:`matplotlib.axes.Axes`): The axes on which the plot was drawn.
Example:
>>> lr = classifier_factory(LogisticRegression())
>>> lr.plot_ks_statistic(X, y, random_state=1)
<matplotlib.axes._subplots.AxesSubplot object at 0x7fe967d64490>
>>> plt.show()
.. image:: _static/examples/plot_ks_statistic.png
:align: center
:alt: KS Statistic
"""
y = np.array(y)
if not hasattr(clf, 'predict_proba'):
raise TypeError('"predict_proba" method not in classifier. Cannot calculate ROC Curve.')
if not do_cv:
probas = clf.predict_proba(X)
y_true = y
else:
if cv is None:
cv = StratifiedKFold(shuffle=shuffle, random_state=random_state)
elif isinstance(cv, int):
cv = StratifiedKFold(n_splits=cv, shuffle=shuffle, random_state=random_state)
else:
pass
clf_clone = clone(clf)
preds_list = []
trues_list = []
for train_index, test_index in cv.split(X, y):
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
clf_clone.fit(X_train, y_train)
preds = clf_clone.predict_proba(X_test)
preds_list.append(preds)
trues_list.append(y_test)
probas = np.concatenate(preds_list, axis=0)
y_true = np.concatenate(trues_list)
ax = plotters.plot_ks_statistic(y_true, probas, title=title, ax=ax)
return ax
def plot_ks_statistic(self):
# not working
skplt.plot_ks_statistic(self.y_test, self.y_prob)
plt.show()
def plot_ks_statistic_with_cv(clf, X, y, title='KS Statistic Plot',
do_cv=True, cv=None, shuffle=True,
random_state=None, ax=None, figsize=None,
title_fontsize="large", text_fontsize="medium"):
"""Generates the KS Statistic plot for a given classifier and dataset.
Args:
clf: Classifier instance that implements "fit" and "predict_proba"
methods.
X (array-like, shape (n_samples, n_features)):
Training vector, where n_samples is the number of samples and
n_features is the number of features.
y (array-like, shape (n_samples) or (n_samples, n_features)):
Target relative to X for classification.
title (string, optional): Title of the generated plot. Defaults to
"KS Statistic Plot".
do_cv (bool, optional): If True, the classifier is cross-validated on
the dataset using the cross-validation strategy in `cv` to generate
the confusion matrix. If False, the confusion matrix is generated
without training or cross-validating the classifier. This assumes
that the classifier has already been called with its `fit` method
beforehand.
cv (int, cross-validation generator, iterable, optional): Determines
the cross-validation strategy to be used for splitting.
Possible inputs for cv are:
- None, to use the default 3-fold cross-validation,
- integer, to specify the number of folds.
- An object to be used as a cross-validation generator.
- An iterable yielding train/test splits.
For integer/None inputs, if ``y`` is binary or multiclass,
:class:`StratifiedKFold` used. If the estimator is not a classifier
or if ``y`` is neither binary nor multiclass, :class:`KFold` is
used.
shuffle (bool, optional): Used when do_cv is set to True. Determines
whether to shuffle the training data before splitting using
cross-validation. Default set to True.
random_state (int :class:`RandomState`): Pseudo-random number generator
state used for random sampling.
ax (:class:`matplotlib.axes.Axes`, optional): The axes upon which to
plot the learning curve. If None, the plot is drawn on a new set of
axes.
figsize (2-tuple, optional): Tuple denoting figure size of the plot
e.g. (6, 6). Defaults to ``None``.
title_fontsize (string or int, optional): Matplotlib-style fontsizes.
Use e.g. "small", "medium", "large" or integer-values. Defaults to
"large".
text_fontsize (string or int, optional): Matplotlib-style fontsizes.
Use e.g. "small", "medium", "large" or integer-values. Defaults to
"medium".
Returns:
ax (:class:`matplotlib.axes.Axes`): The axes on which the plot was
drawn.
Example:
>>> lr = classifier_factory(LogisticRegression())
>>> lr.plot_ks_statistic(X, y, random_state=1)
<matplotlib.axes._subplots.AxesSubplot object at 0x7fe967d64490>
>>> plt.show()
.. image:: _static/examples/plot_ks_statistic.png
:align: center
:alt: KS Statistic
"""
y = np.array(y)
if not hasattr(clf, 'predict_proba'):
raise TypeError('"predict_proba" method not in classifier. '
'Cannot calculate ROC Curve.')
if not do_cv:
probas = clf.predict_proba(X)
y_true = y
else:
if cv is None:
cv = StratifiedKFold(shuffle=shuffle, random_state=random_state)
elif isinstance(cv, int):
cv = StratifiedKFold(n_splits=cv, shuffle=shuffle,
random_state=random_state)
else:
pass
clf_clone = clone(clf)
preds_list = []
trues_list = []
for train_index, test_index in cv.split(X, y):
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
clf_clone.fit(X_train, y_train)
preds = clf_clone.predict_proba(X_test)
preds_list.append(preds)
trues_list.append(y_test)
probas = np.concatenate(preds_list, axis=0)
y_true = np.concatenate(trues_list)
ax = plotters.plot_ks_statistic(y_true, probas, title=title,
ax=ax, figsize=figsize,
title_fontsize=title_fontsize,
text_fontsize=text_fontsize)
return ax