def create_classification_report_chart(classifier, X_train, X_test, y_train,
y_test):
"""Create classification report chart.
Tip:
Check Sklearn-Neptune integration
`documentation <https://docs-beta.neptune.ai/essentials/integrations/machine-learning-frameworks/sklearn>`_
for the full example.
Args:
classifier (:obj:`classifier`):
| Fitted sklearn classifier object
X_train (:obj:`ndarray`):
| Training data matrix
X_test (:obj:`ndarray`):
| Testing data matrix
y_train (:obj:`ndarray`):
| The classification target for training
y_test (:obj:`ndarray`):
| The classification target for testing
Returns:
``neptune.types.File`` object that you can assign to run's ``base_namespace``.
Examples:
.. code:: python3
import neptune.new.integrations.sklearn as npt_utils
rfc = RandomForestClassifier()
rfc.fit(X_train, y_train)
run = neptune.init(project='my_workspace/my_project')
run['visuals/classification_report'] = \
npt_utils.create_classification_report_chart(rfc, X_train, X_test, y_train, y_test)
"""
assert is_classifier(
classifier), 'classifier should be sklearn classifier.'
chart = None
try:
fig, ax = plt.subplots()
visualizer = ClassificationReport(classifier,
support=True,
is_fitted=True,
ax=ax)
visualizer.fit(X_train, y_train)
visualizer.score(X_test, y_test)
visualizer.finalize()
chart = neptune.types.File.as_image(fig)
plt.close(fig)
except Exception as e:
print('Did not log Classification Report chart. Error: {}'.format(e))
return chart
def log_classification_report_chart(classifier, X_train, X_test, y_train, y_test, experiment=None):
"""Log classification report chart.
Make sure you created an experiment by using ``neptune.create_experiment()`` before you use this method.
Tip:
Check `Neptune documentation <https://docs.neptune.ai/integrations/scikit_learn.html>`_ for the full example.
Args:
classifier (:obj:`classifier`):
| Fitted sklearn classifier object
X_train (:obj:`ndarray`):
| Training data matrix
X_test (:obj:`ndarray`):
| Testing data matrix
y_train (:obj:`ndarray`):
| The classification target for training
y_test (:obj:`ndarray`):
| The classification target for testing
experiment (:obj:`neptune.experiments.Experiment`, optional, default is ``None``):
| Neptune ``Experiment`` object to control to which experiment you log the data.
| If ``None``, log to currently active, and most recent experiment.
Returns:
``None``
Examples:
.. code:: python3
rfc = RandomForestClassifier()
rfc.fit(X_train, y_train)
neptune.init('my_workspace/my_project')
exp = neptune.create_experiment()
log_classification_report_chart(rfc, X_train, X_test, y_train, y_test, experiment=exp)
"""
assert is_classifier(classifier), 'classifier should be sklearn classifier.'
exp = _validate_experiment(experiment)
try:
fig, ax = plt.subplots()
visualizer = ClassificationReport(classifier, support=True, is_fitted=True, ax=ax)
visualizer.fit(X_train, y_train)
visualizer.score(X_test, y_test)
visualizer.finalize()
exp.log_image('charts_sklearn', fig, image_name='Classification Report')
plt.close(fig)
except Exception as e:
print('Did not log Classification Report chart. Error: {}'.format(e))
def test_prepredict_classifier(self):
"""
Test the prepredict estimator with classification report
"""
# Make prepredictions
X, y = self.multiclass.X, self.multiclass.y
y_pred = GaussianNB().fit(X.train, y.train).predict(X.test)
# Create prepredict estimator with prior predictions
estimator = PrePredict(y_pred, CLASSIFIER)
assert estimator.fit(X.train, y.train) is estimator
assert estimator.predict(X.train) is y_pred
assert estimator.score(X.test, y.test) == pytest.approx(0.41, rel=1e-3)
# Test that a visualizer works with the pre-predictions.
viz = ClassificationReport(estimator)
viz.fit(None, y.train)
viz.score(None, y.test)
viz.finalize()
self.assert_images_similar(viz)
def classification(fname="classification.png"):
# Create side-by-side axes grid
_, axes = plt.subplots(ncols=2, figsize=(18,6))
# Add ClassificationReport to the reft
data = load_spam(split=True)
oz = ClassificationReport(MultinomialNB(), classes=["ham", "spam"], ax=axes[0])
oz.fit(data.X.train, data.y.train)
oz.score(data.X.test, data.y.test)
oz.finalize()
# Add DiscriminationThreshold to the right
data = load_spam(split=False)
oz = DiscriminationThreshold(LogisticRegression(), ax=axes[1])
oz.fit(data.X, data.y)
oz.finalize()
# Save figure
path = os.path.join(FIGURES, fname)
plt.tight_layout()
plt.savefig(path)
def classification(fname="classification.png"):
# Create side-by-side axes grid
_, axes = plt.subplots(ncols=2, figsize=(18, 6))
# Add ClassificationReport to the reft
data = load_spam(split=True)
oz = ClassificationReport(MultinomialNB(),
classes=["ham", "spam"],
ax=axes[0])
oz.fit(data.X.train, data.y.train)
oz.score(data.X.test, data.y.test)
oz.finalize()
# Add DiscriminationThreshold to the right
data = load_spam(split=False)
oz = DiscriminationThreshold(LogisticRegression(), ax=axes[1])
oz.fit(data.X, data.y)
oz.finalize()
# Save figure
path = os.path.join(FIGURES, fname)
plt.tight_layout()
plt.savefig(path)
