Github user thunterdb commented on a diff in the pull request:
https://github.com/apache/spark/pull/11621#discussion_r56587642
--- Diff: python/pyspark/ml/classification.py ---
@@ -231,6 +232,210 @@ def intercept(self):
"""
return self._call_java("intercept")
+ @property
+ @since("2.0.0")
+ def summary(self):
+ """
+ Gets summary (e.g. residuals, mse, r-squared ) of model on
+ training set. An exception is thrown if
+ `trainingSummary == None`.
+ """
+ java_blrt_summary = self._call_java("summary")
+ return BinaryLogisticRegressionTrainingSummary(java_blrt_summary)
+
+ @property
+ @since("2.0.0")
+ def hasSummary(self):
+ """
+ Indicates whether a training summary exists for this model
+ instance.
+ """
+ return self._call_java("hasSummary")
+
+ """
+ TODO: enable once Scala API is made public
+ def evaluate(self, df):
+ ""
+ Evaluates the model on a testset.
+ @param dataset Test dataset to evaluate model on.
+ ""
+ java_blr_summary = self._call_java("evaluate", df)
+ return BinaryLogisticRegressionSummary(java_blr_summary)
+ """
+
+
+class LogisticRegressionSummary(JavaCallable):
+ """
+ Abstraction for Logistic Regression Results for a given model.
+
+ .. versionadded:: 2.0.0
+ """
+
+ @property
+ @since("2.0.0")
+ def predictions(self):
+ """
+ Dataframe outputted by the model's `transform` method.
--- End diff --
nit: technically, `outputted` is not in the dictionary.
---
If your project is set up for it, you can reply to this email and have your
reply appear on GitHub as well. If your project does not have this feature
enabled and wishes so, or if the feature is enabled but not working, please
contact infrastructure at [email protected] or file a JIRA ticket
with INFRA.
---
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
