def log_test_preds_proba(classifier, X_test, y_pred_proba=None, nrows=1000, experiment=None):
"""Log test predictions probabilities.
Calculate and log test predictions probabilities and have them as csv file in the Neptune artifacts.
If you pass ``y_pred_proba``, then predictions probabilities are logged without computing from ``X_test`` data.
Estimator should be fitted before calling this function.
Path to predictions probabilities in the Neptune artifacts is 'csv/test_preds_proba.csv'.
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`):
| Scikit-learn classifier to compute predictions probabilities.
X_test (:obj:`ndarray`):
| Testing data matrix.
y_pred_proba (:obj:`ndarray`, optional, default is ``None``):
| Classifier predictions probabilities on test data.
nrows (`int`, optional, default is 1000):
| Number of rows to log.
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')
neptune.create_experiment()
log_test_preds_proba(rfc, X_test, y_test)
"""
assert is_classifier(classifier), 'Classifier should be sklearn classifier.'
assert isinstance(nrows, int), 'nrows should be integer, {} was passed'.format(type(nrows))
exp = _validate_experiment(experiment)
if y_pred_proba is None:
try:
y_pred_proba = classifier.predict_proba(X_test)
except Exception as e:
print('This classifier does not provide predictions probabilities. Error: {}'.format(e))
return
df = pd.DataFrame(data=y_pred_proba, columns=classifier.classes_)
log_csv('test_preds_proba', df.head(nrows), exp)
def log_cluster_labels(model, X, nrows=1000, experiment=None, **kwargs):
"""Log index of the cluster label each sample belongs to.
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:
model (:obj:`KMeans`):
| KMeans object.
X (:obj:`ndarray`):
| Training instances to cluster.
nrows (`int`, optional, default is 1000):
| Number of rows to log.
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.
kwargs:
KMeans parameters.
Returns:
``None``
Examples:
.. code:: python3
km = KMeans(n_init=11, max_iter=270)
X, y = make_blobs(n_samples=579, n_features=17, centers=7, random_state=28743)
neptune.init('my_workspace/my_project')
neptune.create_experiment()
log_cluster_labels(km, X=X)
"""
assert isinstance(model,
KMeans), 'Model should be sklearn KMeans instance.'
assert isinstance(nrows,
int), 'nrows should be integer, {} was passed'.format(
type(nrows))
exp = _validate_experiment(experiment)
model.set_params(**kwargs)
labels = model.fit_predict(X)
df = pd.DataFrame(data={'cluster_labels': labels})
log_csv('cluster_labels', df.head(nrows), exp)
def log_test_predictions(estimator,
X_test,
y_test,
y_pred=None,
nrows=1000,
experiment=None):
"""Log test predictions.
Calculate and log test predictions and have them as csv file in the Neptune artifacts.
If you pass ``y_pred``, then predictions are logged without computing from ``X_test`` data.
Estimator should be fitted before calling this function.
Path to predictions in the Neptune artifacts is 'csv/test_predictions.csv'.
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:
estimator (:obj:`estimator`):
| Scikit-learn estimator to compute predictions.
X_test (:obj:`ndarray`):
| Testing data matrix.
y_test (:obj:`ndarray`):
| Target for testing.
y_pred (:obj:`ndarray`, optional, default is ``None``):
| Estimator predictions on test data.
nrows (`int`, optional, default is 1000):
| Number of rows to log.
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
rfr = RandomForestRegressor()
rfr.fit(X_train, y_train)
neptune.init('my_workspace/my_project')
neptune.create_experiment()
log_test_predictions(rfr, X_test, y_test)
"""
assert is_regressor(estimator) or is_classifier(estimator),\
'Estimator should be sklearn regressor or classifier.'
assert isinstance(nrows,
int), 'nrows should be integer, {} was passed'.format(
type(nrows))
exp = _validate_experiment(experiment)
if y_pred is None:
y_pred = estimator.predict(X_test)
# single output
if len(y_pred.shape) == 1:
df = pd.DataFrame(data={'y_true': y_test, 'y_pred': y_pred})
log_csv('test_predictions', df.head(nrows), exp)
# multi output
if len(y_pred.shape) == 2:
df = pd.DataFrame()
for j in range(y_pred.shape[1]):
df['y_test_output_{}'.format(j)] = y_test[:, j]
df['y_pred_output_{}'.format(j)] = y_pred[:, j]
log_csv('test_predictions', df.head(nrows), exp)