viirya commented on a change in pull request #28710:
URL: https://github.com/apache/spark/pull/28710#discussion_r442328666
##########
File path: python/pyspark/ml/classification.py
##########
@@ -990,241 +1218,26 @@ def featuresCol(self):
"""
return self._call_java("featuresCol")
- @property
- @since("3.1.0")
- def weightCol(self):
- """
- Field in "predictions" which gives the weight of each instance
- as a vector.
- """
- return self._call_java("weightCol")
-
- @property
- @since("2.3.0")
- def labels(self):
- """
- Returns the sequence of labels in ascending order. This order matches
the order used
- in metrics which are specified as arrays over labels, e.g.,
truePositiveRateByLabel.
-
- Note: In most cases, it will be values {0.0, 1.0, ..., numClasses-1},
However, if the
- training set is missing a label, then all of the arrays over labels
- (e.g., from truePositiveRateByLabel) will be of length numClasses-1
instead of the
- expected numClasses.
- """
- return self._call_java("labels")
-
- @property
- @since("2.3.0")
- def truePositiveRateByLabel(self):
- """
- Returns true positive rate for each label (category).
- """
- return self._call_java("truePositiveRateByLabel")
-
- @property
- @since("2.3.0")
- def falsePositiveRateByLabel(self):
- """
- Returns false positive rate for each label (category).
- """
- return self._call_java("falsePositiveRateByLabel")
-
- @property
- @since("2.3.0")
- def precisionByLabel(self):
- """
- Returns precision for each label (category).
- """
- return self._call_java("precisionByLabel")
-
- @property
- @since("2.3.0")
- def recallByLabel(self):
- """
- Returns recall for each label (category).
- """
- return self._call_java("recallByLabel")
-
- @since("2.3.0")
- def fMeasureByLabel(self, beta=1.0):
- """
- Returns f-measure for each label (category).
- """
- return self._call_java("fMeasureByLabel", beta)
-
- @property
- @since("2.3.0")
- def accuracy(self):
- """
- Returns accuracy.
- (equals to the total number of correctly classified instances
- out of the total number of instances.)
- """
- return self._call_java("accuracy")
-
- @property
- @since("2.3.0")
- def weightedTruePositiveRate(self):
- """
- Returns weighted true positive rate.
- (equals to precision, recall and f-measure)
- """
- return self._call_java("weightedTruePositiveRate")
-
- @property
- @since("2.3.0")
- def weightedFalsePositiveRate(self):
- """
- Returns weighted false positive rate.
- """
- return self._call_java("weightedFalsePositiveRate")
-
- @property
- @since("2.3.0")
- def weightedRecall(self):
- """
- Returns weighted averaged recall.
- (equals to precision, recall and f-measure)
- """
- return self._call_java("weightedRecall")
-
- @property
- @since("2.3.0")
- def weightedPrecision(self):
- """
- Returns weighted averaged precision.
- """
- return self._call_java("weightedPrecision")
-
- @since("2.3.0")
- def weightedFMeasure(self, beta=1.0):
- """
- Returns weighted averaged f-measure.
- """
- return self._call_java("weightedFMeasure", beta)
-
@inherit_doc
-class LogisticRegressionTrainingSummary(LogisticRegressionSummary):
+class LogisticRegressionTrainingSummary(LogisticRegressionSummary,
_TrainingSummary):
"""
Abstraction for multinomial Logistic Regression Training results.
- Currently, the training summary ignores the training weights except
- for the objective trace.
.. versionadded:: 2.0.0
"""
-
- @property
- @since("2.0.0")
- def objectiveHistory(self):
- """
- Objective function (scaled loss + regularization) at each
- iteration. It contains one more element, the initial state,
- than number of iterations.
- """
- return self._call_java("objectiveHistory")
-
- @property
- @since("2.0.0")
- def totalIterations(self):
- """
- Number of training iterations until termination.
- """
- return self._call_java("totalIterations")
+ pass
@inherit_doc
-class BinaryLogisticRegressionSummary(LogisticRegressionSummary):
+class BinaryLogisticRegressionSummary(_BinaryClassificationSummary,
+ LogisticRegressionSummary):
"""
Binary Logistic regression results for a given model.
.. versionadded:: 2.0.0
"""
-
- @property
- @since("2.0.0")
- def roc(self):
- """
- Returns the receiver operating characteristic (ROC) curve,
- which is a Dataframe having two fields (FPR, TPR) with
- (0.0, 0.0) prepended and (1.0, 1.0) appended to it.
-
- .. seealso:: `Wikipedia reference
- <http://en.wikipedia.org/wiki/Receiver_operating_characteristic>`_
-
- .. note:: This ignores instance weights (setting all to 1.0) from
- `LogisticRegression.weightCol`. This will change in later Spark
- versions.
- """
- return self._call_java("roc")
-
- @property
- @since("2.0.0")
- def areaUnderROC(self):
- """
- Computes the area under the receiver operating characteristic
- (ROC) curve.
-
- .. note:: This ignores instance weights (setting all to 1.0) from
- `LogisticRegression.weightCol`. This will change in later Spark
- versions.
- """
- return self._call_java("areaUnderROC")
-
- @property
- @since("2.0.0")
- def pr(self):
- """
- Returns the precision-recall curve, which is a Dataframe
- containing two fields recall, precision with (0.0, 1.0) prepended
- to it.
-
- .. note:: This ignores instance weights (setting all to 1.0) from
- `LogisticRegression.weightCol`. This will change in later Spark
- versions.
- """
- return self._call_java("pr")
-
- @property
- @since("2.0.0")
- def fMeasureByThreshold(self):
- """
- Returns a dataframe with two fields (threshold, F-Measure) curve
- with beta = 1.0.
-
- .. note:: This ignores instance weights (setting all to 1.0) from
- `LogisticRegression.weightCol`. This will change in later Spark
- versions.
- """
- return self._call_java("fMeasureByThreshold")
-
- @property
- @since("2.0.0")
- def precisionByThreshold(self):
- """
- Returns a dataframe with two fields (threshold, precision) curve.
- Every possible probability obtained in transforming the dataset
- are used as thresholds used in calculating the precision.
-
- .. note:: This ignores instance weights (setting all to 1.0) from
- `LogisticRegression.weightCol`. This will change in later Spark
- versions.
- """
- return self._call_java("precisionByThreshold")
-
- @property
- @since("2.0.0")
- def recallByThreshold(self):
- """
- Returns a dataframe with two fields (threshold, recall) curve.
- Every possible probability obtained in transforming the dataset
- are used as thresholds used in calculating the recall.
-
- .. note:: This ignores instance weights (setting all to 1.0) from
- `LogisticRegression.weightCol`. This will change in later Spark
- versions.
Review comment:
I saw you remove such note in latest commit. So now these methods use
weightCol?
----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact Infrastructure at:
[email protected]
---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]
