2015-03-05 14:50:09 -05:00
|
|
|
#
|
|
|
|
# Licensed to the Apache Software Foundation (ASF) under one or more
|
|
|
|
# contributor license agreements. See the NOTICE file distributed with
|
|
|
|
# this work for additional information regarding copyright ownership.
|
|
|
|
# The ASF licenses this file to You under the Apache License, Version 2.0
|
|
|
|
# (the "License"); you may not use this file except in compliance with
|
|
|
|
# the License. You may obtain a copy of the License at
|
|
|
|
#
|
|
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
|
|
#
|
|
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
|
|
# See the License for the specific language governing permissions and
|
|
|
|
# limitations under the License.
|
|
|
|
#
|
|
|
|
|
2018-03-08 06:38:34 -05:00
|
|
|
import sys
|
2016-06-06 10:19:22 -04:00
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
from pyspark import since
|
2015-05-11 12:14:20 -04:00
|
|
|
from pyspark.mllib.common import JavaModelWrapper, callMLlibFunc
|
2015-03-05 14:50:09 -05:00
|
|
|
from pyspark.sql import SQLContext
|
2019-10-18 05:57:13 -04:00
|
|
|
from pyspark.sql.types import ArrayType, StructField, StructType, DoubleType
|
2015-05-11 12:14:20 -04:00
|
|
|
|
|
|
|
__all__ = ['BinaryClassificationMetrics', 'RegressionMetrics',
|
|
|
|
'MulticlassMetrics', 'RankingMetrics']
|
2015-03-05 14:50:09 -05:00
|
|
|
|
|
|
|
|
|
|
|
class BinaryClassificationMetrics(JavaModelWrapper):
|
|
|
|
"""
|
|
|
|
Evaluator for binary classification.
|
|
|
|
|
2020-11-24 20:24:41 -05:00
|
|
|
.. versionadded:: 1.4.0
|
|
|
|
|
|
|
|
Parameters
|
|
|
|
----------
|
|
|
|
scoreAndLabels : :py:class:`pyspark.RDD`
|
|
|
|
an RDD of score, label and optional weight.
|
2015-05-30 19:24:07 -04:00
|
|
|
|
2020-11-24 20:24:41 -05:00
|
|
|
Examples
|
|
|
|
--------
|
2015-03-05 14:50:09 -05:00
|
|
|
>>> scoreAndLabels = sc.parallelize([
|
|
|
|
... (0.1, 0.0), (0.1, 1.0), (0.4, 0.0), (0.6, 0.0), (0.6, 1.0), (0.6, 1.0), (0.8, 1.0)], 2)
|
|
|
|
>>> metrics = BinaryClassificationMetrics(scoreAndLabels)
|
2015-05-07 14:18:32 -04:00
|
|
|
>>> metrics.areaUnderROC
|
2015-03-05 14:50:09 -05:00
|
|
|
0.70...
|
2015-05-07 14:18:32 -04:00
|
|
|
>>> metrics.areaUnderPR
|
2015-03-05 14:50:09 -05:00
|
|
|
0.83...
|
|
|
|
>>> metrics.unpersist()
|
2019-02-25 18:16:51 -05:00
|
|
|
>>> scoreAndLabelsWithOptWeight = sc.parallelize([
|
|
|
|
... (0.1, 0.0, 1.0), (0.1, 1.0, 0.4), (0.4, 0.0, 0.2), (0.6, 0.0, 0.6), (0.6, 1.0, 0.9),
|
|
|
|
... (0.6, 1.0, 0.5), (0.8, 1.0, 0.7)], 2)
|
|
|
|
>>> metrics = BinaryClassificationMetrics(scoreAndLabelsWithOptWeight)
|
|
|
|
>>> metrics.areaUnderROC
|
|
|
|
0.79...
|
|
|
|
>>> metrics.areaUnderPR
|
|
|
|
0.88...
|
2015-03-05 14:50:09 -05:00
|
|
|
"""
|
|
|
|
|
|
|
|
def __init__(self, scoreAndLabels):
|
|
|
|
sc = scoreAndLabels.ctx
|
2015-12-16 18:48:11 -05:00
|
|
|
sql_ctx = SQLContext.getOrCreate(sc)
|
2019-02-25 18:16:51 -05:00
|
|
|
numCol = len(scoreAndLabels.first())
|
|
|
|
schema = StructType([
|
2015-03-05 14:50:09 -05:00
|
|
|
StructField("score", DoubleType(), nullable=False),
|
2019-02-25 18:16:51 -05:00
|
|
|
StructField("label", DoubleType(), nullable=False)])
|
|
|
|
if numCol == 3:
|
|
|
|
schema.add("weight", DoubleType(), False)
|
|
|
|
df = sql_ctx.createDataFrame(scoreAndLabels, schema=schema)
|
2015-03-05 14:50:09 -05:00
|
|
|
java_class = sc._jvm.org.apache.spark.mllib.evaluation.BinaryClassificationMetrics
|
|
|
|
java_model = java_class(df._jdf)
|
|
|
|
super(BinaryClassificationMetrics, self).__init__(java_model)
|
|
|
|
|
2015-05-07 14:18:32 -04:00
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-03-05 14:50:09 -05:00
|
|
|
def areaUnderROC(self):
|
|
|
|
"""
|
|
|
|
Computes the area under the receiver operating characteristic
|
|
|
|
(ROC) curve.
|
|
|
|
"""
|
|
|
|
return self.call("areaUnderROC")
|
|
|
|
|
2015-05-07 14:18:32 -04:00
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-03-05 14:50:09 -05:00
|
|
|
def areaUnderPR(self):
|
|
|
|
"""
|
|
|
|
Computes the area under the precision-recall curve.
|
|
|
|
"""
|
|
|
|
return self.call("areaUnderPR")
|
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-03-05 14:50:09 -05:00
|
|
|
def unpersist(self):
|
|
|
|
"""
|
|
|
|
Unpersists intermediate RDDs used in the computation.
|
|
|
|
"""
|
|
|
|
self.call("unpersist")
|
|
|
|
|
|
|
|
|
2015-05-07 14:18:32 -04:00
|
|
|
class RegressionMetrics(JavaModelWrapper):
|
|
|
|
"""
|
|
|
|
Evaluator for regression.
|
|
|
|
|
2020-11-24 20:24:41 -05:00
|
|
|
.. versionadded:: 1.4.0
|
|
|
|
|
|
|
|
Parameters
|
|
|
|
----------
|
|
|
|
predictionAndObservations : :py:class:`pyspark.RDD`
|
|
|
|
an RDD of prediction, observation and optional weight.
|
2015-05-30 19:24:07 -04:00
|
|
|
|
2020-11-24 20:24:41 -05:00
|
|
|
Examples
|
|
|
|
--------
|
2015-05-07 14:18:32 -04:00
|
|
|
>>> predictionAndObservations = sc.parallelize([
|
|
|
|
... (2.5, 3.0), (0.0, -0.5), (2.0, 2.0), (8.0, 7.0)])
|
|
|
|
>>> metrics = RegressionMetrics(predictionAndObservations)
|
|
|
|
>>> metrics.explainedVariance
|
2015-07-15 16:32:25 -04:00
|
|
|
8.859...
|
2015-05-07 14:18:32 -04:00
|
|
|
>>> metrics.meanAbsoluteError
|
|
|
|
0.5...
|
|
|
|
>>> metrics.meanSquaredError
|
|
|
|
0.37...
|
|
|
|
>>> metrics.rootMeanSquaredError
|
|
|
|
0.61...
|
|
|
|
>>> metrics.r2
|
|
|
|
0.94...
|
2019-03-26 10:06:04 -04:00
|
|
|
>>> predictionAndObservationsWithOptWeight = sc.parallelize([
|
|
|
|
... (2.5, 3.0, 0.5), (0.0, -0.5, 1.0), (2.0, 2.0, 0.3), (8.0, 7.0, 0.9)])
|
|
|
|
>>> metrics = RegressionMetrics(predictionAndObservationsWithOptWeight)
|
|
|
|
>>> metrics.rootMeanSquaredError
|
|
|
|
0.68...
|
2015-05-07 14:18:32 -04:00
|
|
|
"""
|
|
|
|
|
|
|
|
def __init__(self, predictionAndObservations):
|
|
|
|
sc = predictionAndObservations.ctx
|
2015-12-16 18:48:11 -05:00
|
|
|
sql_ctx = SQLContext.getOrCreate(sc)
|
2019-03-26 10:06:04 -04:00
|
|
|
numCol = len(predictionAndObservations.first())
|
|
|
|
schema = StructType([
|
2015-05-07 14:18:32 -04:00
|
|
|
StructField("prediction", DoubleType(), nullable=False),
|
2019-03-26 10:06:04 -04:00
|
|
|
StructField("observation", DoubleType(), nullable=False)])
|
|
|
|
if numCol == 3:
|
|
|
|
schema.add("weight", DoubleType(), False)
|
|
|
|
df = sql_ctx.createDataFrame(predictionAndObservations, schema=schema)
|
2015-05-07 14:18:32 -04:00
|
|
|
java_class = sc._jvm.org.apache.spark.mllib.evaluation.RegressionMetrics
|
|
|
|
java_model = java_class(df._jdf)
|
|
|
|
super(RegressionMetrics, self).__init__(java_model)
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-07 14:18:32 -04:00
|
|
|
def explainedVariance(self):
|
2018-09-12 23:19:43 -04:00
|
|
|
r"""
|
2015-05-07 14:18:32 -04:00
|
|
|
Returns the explained variance regression score.
|
2018-09-12 23:19:43 -04:00
|
|
|
explainedVariance = :math:`1 - \frac{variance(y - \hat{y})}{variance(y)}`
|
2015-05-07 14:18:32 -04:00
|
|
|
"""
|
|
|
|
return self.call("explainedVariance")
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-07 14:18:32 -04:00
|
|
|
def meanAbsoluteError(self):
|
|
|
|
"""
|
|
|
|
Returns the mean absolute error, which is a risk function corresponding to the
|
|
|
|
expected value of the absolute error loss or l1-norm loss.
|
|
|
|
"""
|
|
|
|
return self.call("meanAbsoluteError")
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-07 14:18:32 -04:00
|
|
|
def meanSquaredError(self):
|
|
|
|
"""
|
|
|
|
Returns the mean squared error, which is a risk function corresponding to the
|
|
|
|
expected value of the squared error loss or quadratic loss.
|
|
|
|
"""
|
|
|
|
return self.call("meanSquaredError")
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-07 14:18:32 -04:00
|
|
|
def rootMeanSquaredError(self):
|
|
|
|
"""
|
|
|
|
Returns the root mean squared error, which is defined as the square root of
|
|
|
|
the mean squared error.
|
|
|
|
"""
|
|
|
|
return self.call("rootMeanSquaredError")
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-07 14:18:32 -04:00
|
|
|
def r2(self):
|
|
|
|
"""
|
|
|
|
Returns R^2^, the coefficient of determination.
|
|
|
|
"""
|
|
|
|
return self.call("r2")
|
|
|
|
|
|
|
|
|
2015-05-10 03:57:14 -04:00
|
|
|
class MulticlassMetrics(JavaModelWrapper):
|
|
|
|
"""
|
|
|
|
Evaluator for multiclass classification.
|
|
|
|
|
2020-11-24 20:24:41 -05:00
|
|
|
.. versionadded:: 1.4.0
|
|
|
|
|
|
|
|
Parameters
|
|
|
|
----------
|
|
|
|
predictionAndLabels : :py:class:`pyspark.RDD`
|
|
|
|
an RDD of prediction, label, optional weight and optional probability.
|
2015-05-30 19:24:07 -04:00
|
|
|
|
2020-11-24 20:24:41 -05:00
|
|
|
Examples
|
|
|
|
--------
|
2015-05-10 03:57:14 -04:00
|
|
|
>>> predictionAndLabels = sc.parallelize([(0.0, 0.0), (0.0, 1.0), (0.0, 0.0),
|
|
|
|
... (1.0, 0.0), (1.0, 1.0), (1.0, 1.0), (1.0, 1.0), (2.0, 2.0), (2.0, 0.0)])
|
|
|
|
>>> metrics = MulticlassMetrics(predictionAndLabels)
|
2015-07-08 19:21:28 -04:00
|
|
|
>>> metrics.confusionMatrix().toArray()
|
|
|
|
array([[ 2., 1., 1.],
|
|
|
|
[ 1., 3., 0.],
|
|
|
|
[ 0., 0., 1.]])
|
2015-05-10 03:57:14 -04:00
|
|
|
>>> metrics.falsePositiveRate(0.0)
|
|
|
|
0.2...
|
|
|
|
>>> metrics.precision(1.0)
|
|
|
|
0.75...
|
|
|
|
>>> metrics.recall(2.0)
|
|
|
|
1.0...
|
|
|
|
>>> metrics.fMeasure(0.0, 2.0)
|
|
|
|
0.52...
|
2016-06-10 05:09:19 -04:00
|
|
|
>>> metrics.accuracy
|
2016-06-06 10:19:22 -04:00
|
|
|
0.66...
|
2015-05-10 03:57:14 -04:00
|
|
|
>>> metrics.weightedFalsePositiveRate
|
|
|
|
0.19...
|
|
|
|
>>> metrics.weightedPrecision
|
|
|
|
0.68...
|
|
|
|
>>> metrics.weightedRecall
|
|
|
|
0.66...
|
|
|
|
>>> metrics.weightedFMeasure()
|
|
|
|
0.66...
|
|
|
|
>>> metrics.weightedFMeasure(2.0)
|
|
|
|
0.65...
|
2019-02-08 12:46:54 -05:00
|
|
|
>>> predAndLabelsWithOptWeight = sc.parallelize([(0.0, 0.0, 1.0), (0.0, 1.0, 1.0),
|
|
|
|
... (0.0, 0.0, 1.0), (1.0, 0.0, 1.0), (1.0, 1.0, 1.0), (1.0, 1.0, 1.0), (1.0, 1.0, 1.0),
|
|
|
|
... (2.0, 2.0, 1.0), (2.0, 0.0, 1.0)])
|
|
|
|
>>> metrics = MulticlassMetrics(predAndLabelsWithOptWeight)
|
|
|
|
>>> metrics.confusionMatrix().toArray()
|
|
|
|
array([[ 2., 1., 1.],
|
|
|
|
[ 1., 3., 0.],
|
|
|
|
[ 0., 0., 1.]])
|
|
|
|
>>> metrics.falsePositiveRate(0.0)
|
|
|
|
0.2...
|
|
|
|
>>> metrics.precision(1.0)
|
|
|
|
0.75...
|
|
|
|
>>> metrics.recall(2.0)
|
|
|
|
1.0...
|
|
|
|
>>> metrics.fMeasure(0.0, 2.0)
|
|
|
|
0.52...
|
|
|
|
>>> metrics.accuracy
|
|
|
|
0.66...
|
|
|
|
>>> metrics.weightedFalsePositiveRate
|
|
|
|
0.19...
|
|
|
|
>>> metrics.weightedPrecision
|
|
|
|
0.68...
|
|
|
|
>>> metrics.weightedRecall
|
|
|
|
0.66...
|
|
|
|
>>> metrics.weightedFMeasure()
|
|
|
|
0.66...
|
|
|
|
>>> metrics.weightedFMeasure(2.0)
|
|
|
|
0.65...
|
2019-10-18 05:57:13 -04:00
|
|
|
>>> predictionAndLabelsWithProbabilities = sc.parallelize([
|
|
|
|
... (1.0, 1.0, 1.0, [0.1, 0.8, 0.1]), (0.0, 2.0, 1.0, [0.9, 0.05, 0.05]),
|
|
|
|
... (0.0, 0.0, 1.0, [0.8, 0.2, 0.0]), (1.0, 1.0, 1.0, [0.3, 0.65, 0.05])])
|
|
|
|
>>> metrics = MulticlassMetrics(predictionAndLabelsWithProbabilities)
|
|
|
|
>>> metrics.logLoss()
|
|
|
|
0.9682...
|
2015-05-10 03:57:14 -04:00
|
|
|
"""
|
|
|
|
|
2019-02-25 18:16:51 -05:00
|
|
|
def __init__(self, predictionAndLabels):
|
|
|
|
sc = predictionAndLabels.ctx
|
2015-12-16 18:48:11 -05:00
|
|
|
sql_ctx = SQLContext.getOrCreate(sc)
|
2019-02-25 18:16:51 -05:00
|
|
|
numCol = len(predictionAndLabels.first())
|
2019-02-08 12:46:54 -05:00
|
|
|
schema = StructType([
|
2015-05-10 03:57:14 -04:00
|
|
|
StructField("prediction", DoubleType(), nullable=False),
|
2019-02-08 12:46:54 -05:00
|
|
|
StructField("label", DoubleType(), nullable=False)])
|
2019-10-18 05:57:13 -04:00
|
|
|
if numCol >= 3:
|
2019-02-08 12:46:54 -05:00
|
|
|
schema.add("weight", DoubleType(), False)
|
2019-10-18 05:57:13 -04:00
|
|
|
if numCol == 4:
|
|
|
|
schema.add("probability", ArrayType(DoubleType(), False), False)
|
2019-02-25 18:16:51 -05:00
|
|
|
df = sql_ctx.createDataFrame(predictionAndLabels, schema)
|
2015-05-10 03:57:14 -04:00
|
|
|
java_class = sc._jvm.org.apache.spark.mllib.evaluation.MulticlassMetrics
|
|
|
|
java_model = java_class(df._jdf)
|
|
|
|
super(MulticlassMetrics, self).__init__(java_model)
|
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-07-08 19:21:28 -04:00
|
|
|
def confusionMatrix(self):
|
|
|
|
"""
|
|
|
|
Returns confusion matrix: predicted classes are in columns,
|
|
|
|
they are ordered by class label ascending, as in "labels".
|
|
|
|
"""
|
|
|
|
return self.call("confusionMatrix")
|
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-10 03:57:14 -04:00
|
|
|
def truePositiveRate(self, label):
|
|
|
|
"""
|
|
|
|
Returns true positive rate for a given label (category).
|
|
|
|
"""
|
|
|
|
return self.call("truePositiveRate", label)
|
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-10 03:57:14 -04:00
|
|
|
def falsePositiveRate(self, label):
|
|
|
|
"""
|
|
|
|
Returns false positive rate for a given label (category).
|
|
|
|
"""
|
|
|
|
return self.call("falsePositiveRate", label)
|
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2018-11-07 23:48:50 -05:00
|
|
|
def precision(self, label):
|
2015-05-10 03:57:14 -04:00
|
|
|
"""
|
2018-11-07 23:48:50 -05:00
|
|
|
Returns precision.
|
2015-05-10 03:57:14 -04:00
|
|
|
"""
|
2018-11-07 23:48:50 -05:00
|
|
|
return self.call("precision", float(label))
|
2015-05-10 03:57:14 -04:00
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2018-11-07 23:48:50 -05:00
|
|
|
def recall(self, label):
|
2015-05-10 03:57:14 -04:00
|
|
|
"""
|
2018-11-07 23:48:50 -05:00
|
|
|
Returns recall.
|
2015-05-10 03:57:14 -04:00
|
|
|
"""
|
2018-11-07 23:48:50 -05:00
|
|
|
return self.call("recall", float(label))
|
2015-05-10 03:57:14 -04:00
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2018-11-07 23:48:50 -05:00
|
|
|
def fMeasure(self, label, beta=None):
|
2015-05-10 03:57:14 -04:00
|
|
|
"""
|
2018-11-07 23:48:50 -05:00
|
|
|
Returns f-measure.
|
2015-05-10 03:57:14 -04:00
|
|
|
"""
|
|
|
|
if beta is None:
|
2018-11-07 23:48:50 -05:00
|
|
|
return self.call("fMeasure", label)
|
2015-05-10 03:57:14 -04:00
|
|
|
else:
|
2018-11-07 23:48:50 -05:00
|
|
|
return self.call("fMeasure", label, beta)
|
2015-05-10 03:57:14 -04:00
|
|
|
|
2016-06-10 05:09:19 -04:00
|
|
|
@property
|
2016-06-06 10:19:22 -04:00
|
|
|
@since('2.0.0')
|
|
|
|
def accuracy(self):
|
|
|
|
"""
|
|
|
|
Returns accuracy (equals to the total number of correctly classified instances
|
|
|
|
out of the total number of instances).
|
|
|
|
"""
|
|
|
|
return self.call("accuracy")
|
|
|
|
|
2015-05-10 03:57:14 -04:00
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-10 03:57:14 -04:00
|
|
|
def weightedTruePositiveRate(self):
|
|
|
|
"""
|
|
|
|
Returns weighted true positive rate.
|
|
|
|
(equals to precision, recall and f-measure)
|
|
|
|
"""
|
|
|
|
return self.call("weightedTruePositiveRate")
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-10 03:57:14 -04:00
|
|
|
def weightedFalsePositiveRate(self):
|
|
|
|
"""
|
|
|
|
Returns weighted false positive rate.
|
|
|
|
"""
|
|
|
|
return self.call("weightedFalsePositiveRate")
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-10 03:57:14 -04:00
|
|
|
def weightedRecall(self):
|
|
|
|
"""
|
|
|
|
Returns weighted averaged recall.
|
|
|
|
(equals to precision, recall and f-measure)
|
|
|
|
"""
|
|
|
|
return self.call("weightedRecall")
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-10 03:57:14 -04:00
|
|
|
def weightedPrecision(self):
|
|
|
|
"""
|
|
|
|
Returns weighted averaged precision.
|
|
|
|
"""
|
|
|
|
return self.call("weightedPrecision")
|
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-10 03:57:14 -04:00
|
|
|
def weightedFMeasure(self, beta=None):
|
|
|
|
"""
|
|
|
|
Returns weighted averaged f-measure.
|
|
|
|
"""
|
|
|
|
if beta is None:
|
|
|
|
return self.call("weightedFMeasure")
|
|
|
|
else:
|
|
|
|
return self.call("weightedFMeasure", beta)
|
|
|
|
|
2019-10-18 05:57:13 -04:00
|
|
|
@since('3.0.0')
|
|
|
|
def logLoss(self, eps=1e-15):
|
|
|
|
"""
|
|
|
|
Returns weighted logLoss.
|
|
|
|
"""
|
|
|
|
return self.call("logLoss", eps)
|
|
|
|
|
2015-05-10 03:57:14 -04:00
|
|
|
|
2015-05-11 12:14:20 -04:00
|
|
|
class RankingMetrics(JavaModelWrapper):
|
|
|
|
"""
|
|
|
|
Evaluator for ranking algorithms.
|
|
|
|
|
2020-11-24 20:24:41 -05:00
|
|
|
.. versionadded:: 1.4.0
|
2015-05-30 19:24:07 -04:00
|
|
|
|
2020-11-24 20:24:41 -05:00
|
|
|
Parameters
|
|
|
|
----------
|
|
|
|
predictionAndLabels : :py:class:`pyspark.RDD`
|
|
|
|
an RDD of (predicted ranking, ground truth set) pairs.
|
|
|
|
|
|
|
|
Examples
|
|
|
|
--------
|
2015-05-11 12:14:20 -04:00
|
|
|
>>> predictionAndLabels = sc.parallelize([
|
|
|
|
... ([1, 6, 2, 7, 8, 3, 9, 10, 4, 5], [1, 2, 3, 4, 5]),
|
|
|
|
... ([4, 1, 5, 6, 2, 7, 3, 8, 9, 10], [1, 2, 3]),
|
|
|
|
... ([1, 2, 3, 4, 5], [])])
|
|
|
|
>>> metrics = RankingMetrics(predictionAndLabels)
|
|
|
|
>>> metrics.precisionAt(1)
|
|
|
|
0.33...
|
|
|
|
>>> metrics.precisionAt(5)
|
|
|
|
0.26...
|
|
|
|
>>> metrics.precisionAt(15)
|
|
|
|
0.17...
|
|
|
|
>>> metrics.meanAveragePrecision
|
|
|
|
0.35...
|
2019-05-09 09:47:05 -04:00
|
|
|
>>> metrics.meanAveragePrecisionAt(1)
|
|
|
|
0.3333333333333333...
|
|
|
|
>>> metrics.meanAveragePrecisionAt(2)
|
|
|
|
0.25...
|
2015-05-11 12:14:20 -04:00
|
|
|
>>> metrics.ndcgAt(3)
|
|
|
|
0.33...
|
|
|
|
>>> metrics.ndcgAt(10)
|
|
|
|
0.48...
|
2019-03-06 09:28:53 -05:00
|
|
|
>>> metrics.recallAt(1)
|
|
|
|
0.06...
|
|
|
|
>>> metrics.recallAt(5)
|
|
|
|
0.35...
|
|
|
|
>>> metrics.recallAt(15)
|
|
|
|
0.66...
|
2015-05-11 12:14:20 -04:00
|
|
|
"""
|
|
|
|
|
|
|
|
def __init__(self, predictionAndLabels):
|
|
|
|
sc = predictionAndLabels.ctx
|
2015-12-16 18:48:11 -05:00
|
|
|
sql_ctx = SQLContext.getOrCreate(sc)
|
2015-05-11 12:14:20 -04:00
|
|
|
df = sql_ctx.createDataFrame(predictionAndLabels,
|
|
|
|
schema=sql_ctx._inferSchema(predictionAndLabels))
|
|
|
|
java_model = callMLlibFunc("newRankingMetrics", df._jdf)
|
|
|
|
super(RankingMetrics, self).__init__(java_model)
|
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-11 12:14:20 -04:00
|
|
|
def precisionAt(self, k):
|
|
|
|
"""
|
|
|
|
Compute the average precision of all the queries, truncated at ranking position k.
|
|
|
|
|
|
|
|
If for a query, the ranking algorithm returns n (n < k) results, the precision value
|
|
|
|
will be computed as #(relevant items retrieved) / k. This formula also applies when
|
|
|
|
the size of the ground truth set is less than k.
|
|
|
|
|
|
|
|
If a query has an empty ground truth set, zero will be used as precision together
|
|
|
|
with a log warning.
|
|
|
|
"""
|
|
|
|
return self.call("precisionAt", int(k))
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-11 12:14:20 -04:00
|
|
|
def meanAveragePrecision(self):
|
|
|
|
"""
|
|
|
|
Returns the mean average precision (MAP) of all the queries.
|
|
|
|
If a query has an empty ground truth set, the average precision will be zero and
|
2020-11-27 11:22:45 -05:00
|
|
|
a log warning is generated.
|
2015-05-11 12:14:20 -04:00
|
|
|
"""
|
|
|
|
return self.call("meanAveragePrecision")
|
|
|
|
|
2019-05-09 09:47:05 -04:00
|
|
|
@since('3.0.0')
|
|
|
|
def meanAveragePrecisionAt(self, k):
|
|
|
|
"""
|
|
|
|
Returns the mean average precision (MAP) at first k ranking of all the queries.
|
|
|
|
If a query has an empty ground truth set, the average precision will be zero and
|
2020-11-27 11:22:45 -05:00
|
|
|
a log warning is generated.
|
2019-05-09 09:47:05 -04:00
|
|
|
"""
|
|
|
|
return self.call("meanAveragePrecisionAt", int(k))
|
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-11 12:14:20 -04:00
|
|
|
def ndcgAt(self, k):
|
|
|
|
"""
|
|
|
|
Compute the average NDCG value of all the queries, truncated at ranking position k.
|
|
|
|
The discounted cumulative gain at position k is computed as:
|
2015-05-18 11:35:14 -04:00
|
|
|
sum,,i=1,,^k^ (2^{relevance of ''i''th item}^ - 1) / log(i + 1),
|
2015-05-11 12:14:20 -04:00
|
|
|
and the NDCG is obtained by dividing the DCG value on the ground truth set.
|
|
|
|
In the current implementation, the relevance value is binary.
|
2015-05-18 11:35:14 -04:00
|
|
|
If a query has an empty ground truth set, zero will be used as NDCG together with
|
2015-05-11 12:14:20 -04:00
|
|
|
a log warning.
|
|
|
|
"""
|
|
|
|
return self.call("ndcgAt", int(k))
|
|
|
|
|
2019-03-06 09:28:53 -05:00
|
|
|
@since('3.0.0')
|
|
|
|
def recallAt(self, k):
|
|
|
|
"""
|
|
|
|
Compute the average recall of all the queries, truncated at ranking position k.
|
|
|
|
|
|
|
|
If for a query, the ranking algorithm returns n results, the recall value
|
|
|
|
will be computed as #(relevant items retrieved) / #(ground truth set).
|
|
|
|
This formula also applies when the size of the ground truth set is less than k.
|
|
|
|
|
|
|
|
If a query has an empty ground truth set, zero will be used as recall together
|
|
|
|
with a log warning.
|
|
|
|
"""
|
|
|
|
return self.call("recallAt", int(k))
|
|
|
|
|
2015-05-11 12:14:20 -04:00
|
|
|
|
2015-05-20 10:55:51 -04:00
|
|
|
class MultilabelMetrics(JavaModelWrapper):
|
|
|
|
"""
|
|
|
|
Evaluator for multilabel classification.
|
|
|
|
|
2020-11-24 20:24:41 -05:00
|
|
|
.. versionadded:: 1.4.0
|
|
|
|
|
|
|
|
Parameters
|
|
|
|
----------
|
|
|
|
predictionAndLabels : :py:class:`pyspark.RDD`
|
|
|
|
an RDD of (predictions, labels) pairs,
|
|
|
|
both are non-null Arrays, each with unique elements.
|
2015-05-30 19:24:07 -04:00
|
|
|
|
2020-11-24 20:24:41 -05:00
|
|
|
Examples
|
|
|
|
--------
|
2015-05-20 10:55:51 -04:00
|
|
|
>>> predictionAndLabels = sc.parallelize([([0.0, 1.0], [0.0, 2.0]), ([0.0, 2.0], [0.0, 1.0]),
|
|
|
|
... ([], [0.0]), ([2.0], [2.0]), ([2.0, 0.0], [2.0, 0.0]),
|
|
|
|
... ([0.0, 1.0, 2.0], [0.0, 1.0]), ([1.0], [1.0, 2.0])])
|
|
|
|
>>> metrics = MultilabelMetrics(predictionAndLabels)
|
|
|
|
>>> metrics.precision(0.0)
|
|
|
|
1.0
|
|
|
|
>>> metrics.recall(1.0)
|
|
|
|
0.66...
|
|
|
|
>>> metrics.f1Measure(2.0)
|
|
|
|
0.5
|
|
|
|
>>> metrics.precision()
|
|
|
|
0.66...
|
|
|
|
>>> metrics.recall()
|
|
|
|
0.64...
|
|
|
|
>>> metrics.f1Measure()
|
|
|
|
0.63...
|
|
|
|
>>> metrics.microPrecision
|
|
|
|
0.72...
|
|
|
|
>>> metrics.microRecall
|
|
|
|
0.66...
|
|
|
|
>>> metrics.microF1Measure
|
|
|
|
0.69...
|
|
|
|
>>> metrics.hammingLoss
|
|
|
|
0.33...
|
|
|
|
>>> metrics.subsetAccuracy
|
|
|
|
0.28...
|
|
|
|
>>> metrics.accuracy
|
|
|
|
0.54...
|
|
|
|
"""
|
|
|
|
|
|
|
|
def __init__(self, predictionAndLabels):
|
|
|
|
sc = predictionAndLabels.ctx
|
2015-12-16 18:48:11 -05:00
|
|
|
sql_ctx = SQLContext.getOrCreate(sc)
|
2015-05-20 10:55:51 -04:00
|
|
|
df = sql_ctx.createDataFrame(predictionAndLabels,
|
|
|
|
schema=sql_ctx._inferSchema(predictionAndLabels))
|
|
|
|
java_class = sc._jvm.org.apache.spark.mllib.evaluation.MultilabelMetrics
|
|
|
|
java_model = java_class(df._jdf)
|
|
|
|
super(MultilabelMetrics, self).__init__(java_model)
|
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-20 10:55:51 -04:00
|
|
|
def precision(self, label=None):
|
|
|
|
"""
|
|
|
|
Returns precision or precision for a given label (category) if specified.
|
|
|
|
"""
|
|
|
|
if label is None:
|
|
|
|
return self.call("precision")
|
|
|
|
else:
|
|
|
|
return self.call("precision", float(label))
|
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-20 10:55:51 -04:00
|
|
|
def recall(self, label=None):
|
|
|
|
"""
|
|
|
|
Returns recall or recall for a given label (category) if specified.
|
|
|
|
"""
|
|
|
|
if label is None:
|
|
|
|
return self.call("recall")
|
|
|
|
else:
|
|
|
|
return self.call("recall", float(label))
|
|
|
|
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-20 10:55:51 -04:00
|
|
|
def f1Measure(self, label=None):
|
|
|
|
"""
|
|
|
|
Returns f1Measure or f1Measure for a given label (category) if specified.
|
|
|
|
"""
|
|
|
|
if label is None:
|
|
|
|
return self.call("f1Measure")
|
|
|
|
else:
|
|
|
|
return self.call("f1Measure", float(label))
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-20 10:55:51 -04:00
|
|
|
def microPrecision(self):
|
|
|
|
"""
|
|
|
|
Returns micro-averaged label-based precision.
|
|
|
|
(equals to micro-averaged document-based precision)
|
|
|
|
"""
|
|
|
|
return self.call("microPrecision")
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-20 10:55:51 -04:00
|
|
|
def microRecall(self):
|
|
|
|
"""
|
|
|
|
Returns micro-averaged label-based recall.
|
|
|
|
(equals to micro-averaged document-based recall)
|
|
|
|
"""
|
|
|
|
return self.call("microRecall")
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-20 10:55:51 -04:00
|
|
|
def microF1Measure(self):
|
|
|
|
"""
|
|
|
|
Returns micro-averaged label-based f1-measure.
|
|
|
|
(equals to micro-averaged document-based f1-measure)
|
|
|
|
"""
|
|
|
|
return self.call("microF1Measure")
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-20 10:55:51 -04:00
|
|
|
def hammingLoss(self):
|
|
|
|
"""
|
|
|
|
Returns Hamming-loss.
|
|
|
|
"""
|
|
|
|
return self.call("hammingLoss")
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-20 10:55:51 -04:00
|
|
|
def subsetAccuracy(self):
|
|
|
|
"""
|
|
|
|
Returns subset accuracy.
|
|
|
|
(for equal sets of labels)
|
|
|
|
"""
|
|
|
|
return self.call("subsetAccuracy")
|
|
|
|
|
|
|
|
@property
|
2015-10-20 18:05:02 -04:00
|
|
|
@since('1.4.0')
|
2015-05-20 10:55:51 -04:00
|
|
|
def accuracy(self):
|
|
|
|
"""
|
|
|
|
Returns accuracy.
|
|
|
|
"""
|
|
|
|
return self.call("accuracy")
|
|
|
|
|
|
|
|
|
2015-03-05 14:50:09 -05:00
|
|
|
def _test():
|
|
|
|
import doctest
|
[SPARK-24740][PYTHON][ML] Make PySpark's tests compatible with NumPy 1.14+
## What changes were proposed in this pull request?
This PR proposes to make PySpark's tests compatible with NumPy 0.14+
NumPy 0.14.x introduced rather radical changes about its string representation.
For example, the tests below are failed:
```
**********************************************************************
File "/.../spark/python/pyspark/ml/linalg/__init__.py", line 895, in __main__.DenseMatrix.__str__
Failed example:
print(dm)
Expected:
DenseMatrix([[ 0., 2.],
[ 1., 3.]])
Got:
DenseMatrix([[0., 2.],
[1., 3.]])
**********************************************************************
File "/.../spark/python/pyspark/ml/linalg/__init__.py", line 899, in __main__.DenseMatrix.__str__
Failed example:
print(dm)
Expected:
DenseMatrix([[ 0., 1.],
[ 2., 3.]])
Got:
DenseMatrix([[0., 1.],
[2., 3.]])
**********************************************************************
File "/.../spark/python/pyspark/ml/linalg/__init__.py", line 939, in __main__.DenseMatrix.toArray
Failed example:
m.toArray()
Expected:
array([[ 0., 2.],
[ 1., 3.]])
Got:
array([[0., 2.],
[1., 3.]])
**********************************************************************
File "/.../spark/python/pyspark/ml/linalg/__init__.py", line 324, in __main__.DenseVector.dot
Failed example:
dense.dot(np.reshape([1., 2., 3., 4.], (2, 2), order='F'))
Expected:
array([ 5., 11.])
Got:
array([ 5., 11.])
**********************************************************************
File "/.../spark/python/pyspark/ml/linalg/__init__.py", line 567, in __main__.SparseVector.dot
Failed example:
a.dot(np.array([[1, 1], [2, 2], [3, 3], [4, 4]]))
Expected:
array([ 22., 22.])
Got:
array([22., 22.])
```
See [release note](https://docs.scipy.org/doc/numpy-1.14.0/release.html#compatibility-notes).
## How was this patch tested?
Manually tested:
```
$ ./run-tests --python-executables=python3.6,python2.7 --modules=pyspark-ml,pyspark-mllib
Running PySpark tests. Output is in /.../spark/python/unit-tests.log
Will test against the following Python executables: ['python3.6', 'python2.7']
Will test the following Python modules: ['pyspark-ml', 'pyspark-mllib']
Starting test(python2.7): pyspark.mllib.tests
Starting test(python2.7): pyspark.ml.classification
Starting test(python3.6): pyspark.mllib.tests
Starting test(python2.7): pyspark.ml.clustering
Finished test(python2.7): pyspark.ml.clustering (54s)
Starting test(python2.7): pyspark.ml.evaluation
Finished test(python2.7): pyspark.ml.classification (74s)
Starting test(python2.7): pyspark.ml.feature
Finished test(python2.7): pyspark.ml.evaluation (27s)
Starting test(python2.7): pyspark.ml.fpm
Finished test(python2.7): pyspark.ml.fpm (0s)
Starting test(python2.7): pyspark.ml.image
Finished test(python2.7): pyspark.ml.image (17s)
Starting test(python2.7): pyspark.ml.linalg.__init__
Finished test(python2.7): pyspark.ml.linalg.__init__ (1s)
Starting test(python2.7): pyspark.ml.recommendation
Finished test(python2.7): pyspark.ml.feature (76s)
Starting test(python2.7): pyspark.ml.regression
Finished test(python2.7): pyspark.ml.recommendation (69s)
Starting test(python2.7): pyspark.ml.stat
Finished test(python2.7): pyspark.ml.regression (45s)
Starting test(python2.7): pyspark.ml.tests
Finished test(python2.7): pyspark.ml.stat (28s)
Starting test(python2.7): pyspark.ml.tuning
Finished test(python2.7): pyspark.ml.tuning (20s)
Starting test(python2.7): pyspark.mllib.classification
Finished test(python2.7): pyspark.mllib.classification (31s)
Starting test(python2.7): pyspark.mllib.clustering
Finished test(python2.7): pyspark.mllib.tests (260s)
Starting test(python2.7): pyspark.mllib.evaluation
Finished test(python3.6): pyspark.mllib.tests (266s)
Starting test(python2.7): pyspark.mllib.feature
Finished test(python2.7): pyspark.mllib.evaluation (21s)
Starting test(python2.7): pyspark.mllib.fpm
Finished test(python2.7): pyspark.mllib.feature (38s)
Starting test(python2.7): pyspark.mllib.linalg.__init__
Finished test(python2.7): pyspark.mllib.linalg.__init__ (1s)
Starting test(python2.7): pyspark.mllib.linalg.distributed
Finished test(python2.7): pyspark.mllib.fpm (34s)
Starting test(python2.7): pyspark.mllib.random
Finished test(python2.7): pyspark.mllib.clustering (64s)
Starting test(python2.7): pyspark.mllib.recommendation
Finished test(python2.7): pyspark.mllib.random (15s)
Starting test(python2.7): pyspark.mllib.regression
Finished test(python2.7): pyspark.mllib.linalg.distributed (47s)
Starting test(python2.7): pyspark.mllib.stat.KernelDensity
Finished test(python2.7): pyspark.mllib.stat.KernelDensity (0s)
Starting test(python2.7): pyspark.mllib.stat._statistics
Finished test(python2.7): pyspark.mllib.recommendation (40s)
Starting test(python2.7): pyspark.mllib.tree
Finished test(python2.7): pyspark.mllib.regression (38s)
Starting test(python2.7): pyspark.mllib.util
Finished test(python2.7): pyspark.mllib.stat._statistics (19s)
Starting test(python3.6): pyspark.ml.classification
Finished test(python2.7): pyspark.mllib.tree (26s)
Starting test(python3.6): pyspark.ml.clustering
Finished test(python2.7): pyspark.mllib.util (27s)
Starting test(python3.6): pyspark.ml.evaluation
Finished test(python3.6): pyspark.ml.evaluation (30s)
Starting test(python3.6): pyspark.ml.feature
Finished test(python2.7): pyspark.ml.tests (234s)
Starting test(python3.6): pyspark.ml.fpm
Finished test(python3.6): pyspark.ml.fpm (1s)
Starting test(python3.6): pyspark.ml.image
Finished test(python3.6): pyspark.ml.clustering (55s)
Starting test(python3.6): pyspark.ml.linalg.__init__
Finished test(python3.6): pyspark.ml.linalg.__init__ (0s)
Starting test(python3.6): pyspark.ml.recommendation
Finished test(python3.6): pyspark.ml.classification (71s)
Starting test(python3.6): pyspark.ml.regression
Finished test(python3.6): pyspark.ml.image (18s)
Starting test(python3.6): pyspark.ml.stat
Finished test(python3.6): pyspark.ml.stat (37s)
Starting test(python3.6): pyspark.ml.tests
Finished test(python3.6): pyspark.ml.regression (59s)
Starting test(python3.6): pyspark.ml.tuning
Finished test(python3.6): pyspark.ml.feature (93s)
Starting test(python3.6): pyspark.mllib.classification
Finished test(python3.6): pyspark.ml.recommendation (83s)
Starting test(python3.6): pyspark.mllib.clustering
Finished test(python3.6): pyspark.ml.tuning (29s)
Starting test(python3.6): pyspark.mllib.evaluation
Finished test(python3.6): pyspark.mllib.evaluation (26s)
Starting test(python3.6): pyspark.mllib.feature
Finished test(python3.6): pyspark.mllib.classification (43s)
Starting test(python3.6): pyspark.mllib.fpm
Finished test(python3.6): pyspark.mllib.clustering (81s)
Starting test(python3.6): pyspark.mllib.linalg.__init__
Finished test(python3.6): pyspark.mllib.linalg.__init__ (2s)
Starting test(python3.6): pyspark.mllib.linalg.distributed
Finished test(python3.6): pyspark.mllib.fpm (48s)
Starting test(python3.6): pyspark.mllib.random
Finished test(python3.6): pyspark.mllib.feature (54s)
Starting test(python3.6): pyspark.mllib.recommendation
Finished test(python3.6): pyspark.mllib.random (18s)
Starting test(python3.6): pyspark.mllib.regression
Finished test(python3.6): pyspark.mllib.linalg.distributed (55s)
Starting test(python3.6): pyspark.mllib.stat.KernelDensity
Finished test(python3.6): pyspark.mllib.stat.KernelDensity (1s)
Starting test(python3.6): pyspark.mllib.stat._statistics
Finished test(python3.6): pyspark.mllib.recommendation (51s)
Starting test(python3.6): pyspark.mllib.tree
Finished test(python3.6): pyspark.mllib.regression (45s)
Starting test(python3.6): pyspark.mllib.util
Finished test(python3.6): pyspark.mllib.stat._statistics (21s)
Finished test(python3.6): pyspark.mllib.tree (27s)
Finished test(python3.6): pyspark.mllib.util (27s)
Finished test(python3.6): pyspark.ml.tests (264s)
```
Author: hyukjinkwon <gurwls223@apache.org>
Closes #21715 from HyukjinKwon/SPARK-24740.
2018-07-06 23:39:29 -04:00
|
|
|
import numpy
|
2016-05-23 21:14:48 -04:00
|
|
|
from pyspark.sql import SparkSession
|
2015-03-05 14:50:09 -05:00
|
|
|
import pyspark.mllib.evaluation
|
[SPARK-24740][PYTHON][ML] Make PySpark's tests compatible with NumPy 1.14+
## What changes were proposed in this pull request?
This PR proposes to make PySpark's tests compatible with NumPy 0.14+
NumPy 0.14.x introduced rather radical changes about its string representation.
For example, the tests below are failed:
```
**********************************************************************
File "/.../spark/python/pyspark/ml/linalg/__init__.py", line 895, in __main__.DenseMatrix.__str__
Failed example:
print(dm)
Expected:
DenseMatrix([[ 0., 2.],
[ 1., 3.]])
Got:
DenseMatrix([[0., 2.],
[1., 3.]])
**********************************************************************
File "/.../spark/python/pyspark/ml/linalg/__init__.py", line 899, in __main__.DenseMatrix.__str__
Failed example:
print(dm)
Expected:
DenseMatrix([[ 0., 1.],
[ 2., 3.]])
Got:
DenseMatrix([[0., 1.],
[2., 3.]])
**********************************************************************
File "/.../spark/python/pyspark/ml/linalg/__init__.py", line 939, in __main__.DenseMatrix.toArray
Failed example:
m.toArray()
Expected:
array([[ 0., 2.],
[ 1., 3.]])
Got:
array([[0., 2.],
[1., 3.]])
**********************************************************************
File "/.../spark/python/pyspark/ml/linalg/__init__.py", line 324, in __main__.DenseVector.dot
Failed example:
dense.dot(np.reshape([1., 2., 3., 4.], (2, 2), order='F'))
Expected:
array([ 5., 11.])
Got:
array([ 5., 11.])
**********************************************************************
File "/.../spark/python/pyspark/ml/linalg/__init__.py", line 567, in __main__.SparseVector.dot
Failed example:
a.dot(np.array([[1, 1], [2, 2], [3, 3], [4, 4]]))
Expected:
array([ 22., 22.])
Got:
array([22., 22.])
```
See [release note](https://docs.scipy.org/doc/numpy-1.14.0/release.html#compatibility-notes).
## How was this patch tested?
Manually tested:
```
$ ./run-tests --python-executables=python3.6,python2.7 --modules=pyspark-ml,pyspark-mllib
Running PySpark tests. Output is in /.../spark/python/unit-tests.log
Will test against the following Python executables: ['python3.6', 'python2.7']
Will test the following Python modules: ['pyspark-ml', 'pyspark-mllib']
Starting test(python2.7): pyspark.mllib.tests
Starting test(python2.7): pyspark.ml.classification
Starting test(python3.6): pyspark.mllib.tests
Starting test(python2.7): pyspark.ml.clustering
Finished test(python2.7): pyspark.ml.clustering (54s)
Starting test(python2.7): pyspark.ml.evaluation
Finished test(python2.7): pyspark.ml.classification (74s)
Starting test(python2.7): pyspark.ml.feature
Finished test(python2.7): pyspark.ml.evaluation (27s)
Starting test(python2.7): pyspark.ml.fpm
Finished test(python2.7): pyspark.ml.fpm (0s)
Starting test(python2.7): pyspark.ml.image
Finished test(python2.7): pyspark.ml.image (17s)
Starting test(python2.7): pyspark.ml.linalg.__init__
Finished test(python2.7): pyspark.ml.linalg.__init__ (1s)
Starting test(python2.7): pyspark.ml.recommendation
Finished test(python2.7): pyspark.ml.feature (76s)
Starting test(python2.7): pyspark.ml.regression
Finished test(python2.7): pyspark.ml.recommendation (69s)
Starting test(python2.7): pyspark.ml.stat
Finished test(python2.7): pyspark.ml.regression (45s)
Starting test(python2.7): pyspark.ml.tests
Finished test(python2.7): pyspark.ml.stat (28s)
Starting test(python2.7): pyspark.ml.tuning
Finished test(python2.7): pyspark.ml.tuning (20s)
Starting test(python2.7): pyspark.mllib.classification
Finished test(python2.7): pyspark.mllib.classification (31s)
Starting test(python2.7): pyspark.mllib.clustering
Finished test(python2.7): pyspark.mllib.tests (260s)
Starting test(python2.7): pyspark.mllib.evaluation
Finished test(python3.6): pyspark.mllib.tests (266s)
Starting test(python2.7): pyspark.mllib.feature
Finished test(python2.7): pyspark.mllib.evaluation (21s)
Starting test(python2.7): pyspark.mllib.fpm
Finished test(python2.7): pyspark.mllib.feature (38s)
Starting test(python2.7): pyspark.mllib.linalg.__init__
Finished test(python2.7): pyspark.mllib.linalg.__init__ (1s)
Starting test(python2.7): pyspark.mllib.linalg.distributed
Finished test(python2.7): pyspark.mllib.fpm (34s)
Starting test(python2.7): pyspark.mllib.random
Finished test(python2.7): pyspark.mllib.clustering (64s)
Starting test(python2.7): pyspark.mllib.recommendation
Finished test(python2.7): pyspark.mllib.random (15s)
Starting test(python2.7): pyspark.mllib.regression
Finished test(python2.7): pyspark.mllib.linalg.distributed (47s)
Starting test(python2.7): pyspark.mllib.stat.KernelDensity
Finished test(python2.7): pyspark.mllib.stat.KernelDensity (0s)
Starting test(python2.7): pyspark.mllib.stat._statistics
Finished test(python2.7): pyspark.mllib.recommendation (40s)
Starting test(python2.7): pyspark.mllib.tree
Finished test(python2.7): pyspark.mllib.regression (38s)
Starting test(python2.7): pyspark.mllib.util
Finished test(python2.7): pyspark.mllib.stat._statistics (19s)
Starting test(python3.6): pyspark.ml.classification
Finished test(python2.7): pyspark.mllib.tree (26s)
Starting test(python3.6): pyspark.ml.clustering
Finished test(python2.7): pyspark.mllib.util (27s)
Starting test(python3.6): pyspark.ml.evaluation
Finished test(python3.6): pyspark.ml.evaluation (30s)
Starting test(python3.6): pyspark.ml.feature
Finished test(python2.7): pyspark.ml.tests (234s)
Starting test(python3.6): pyspark.ml.fpm
Finished test(python3.6): pyspark.ml.fpm (1s)
Starting test(python3.6): pyspark.ml.image
Finished test(python3.6): pyspark.ml.clustering (55s)
Starting test(python3.6): pyspark.ml.linalg.__init__
Finished test(python3.6): pyspark.ml.linalg.__init__ (0s)
Starting test(python3.6): pyspark.ml.recommendation
Finished test(python3.6): pyspark.ml.classification (71s)
Starting test(python3.6): pyspark.ml.regression
Finished test(python3.6): pyspark.ml.image (18s)
Starting test(python3.6): pyspark.ml.stat
Finished test(python3.6): pyspark.ml.stat (37s)
Starting test(python3.6): pyspark.ml.tests
Finished test(python3.6): pyspark.ml.regression (59s)
Starting test(python3.6): pyspark.ml.tuning
Finished test(python3.6): pyspark.ml.feature (93s)
Starting test(python3.6): pyspark.mllib.classification
Finished test(python3.6): pyspark.ml.recommendation (83s)
Starting test(python3.6): pyspark.mllib.clustering
Finished test(python3.6): pyspark.ml.tuning (29s)
Starting test(python3.6): pyspark.mllib.evaluation
Finished test(python3.6): pyspark.mllib.evaluation (26s)
Starting test(python3.6): pyspark.mllib.feature
Finished test(python3.6): pyspark.mllib.classification (43s)
Starting test(python3.6): pyspark.mllib.fpm
Finished test(python3.6): pyspark.mllib.clustering (81s)
Starting test(python3.6): pyspark.mllib.linalg.__init__
Finished test(python3.6): pyspark.mllib.linalg.__init__ (2s)
Starting test(python3.6): pyspark.mllib.linalg.distributed
Finished test(python3.6): pyspark.mllib.fpm (48s)
Starting test(python3.6): pyspark.mllib.random
Finished test(python3.6): pyspark.mllib.feature (54s)
Starting test(python3.6): pyspark.mllib.recommendation
Finished test(python3.6): pyspark.mllib.random (18s)
Starting test(python3.6): pyspark.mllib.regression
Finished test(python3.6): pyspark.mllib.linalg.distributed (55s)
Starting test(python3.6): pyspark.mllib.stat.KernelDensity
Finished test(python3.6): pyspark.mllib.stat.KernelDensity (1s)
Starting test(python3.6): pyspark.mllib.stat._statistics
Finished test(python3.6): pyspark.mllib.recommendation (51s)
Starting test(python3.6): pyspark.mllib.tree
Finished test(python3.6): pyspark.mllib.regression (45s)
Starting test(python3.6): pyspark.mllib.util
Finished test(python3.6): pyspark.mllib.stat._statistics (21s)
Finished test(python3.6): pyspark.mllib.tree (27s)
Finished test(python3.6): pyspark.mllib.util (27s)
Finished test(python3.6): pyspark.ml.tests (264s)
```
Author: hyukjinkwon <gurwls223@apache.org>
Closes #21715 from HyukjinKwon/SPARK-24740.
2018-07-06 23:39:29 -04:00
|
|
|
try:
|
|
|
|
# Numpy 1.14+ changed it's string format.
|
|
|
|
numpy.set_printoptions(legacy='1.13')
|
|
|
|
except TypeError:
|
|
|
|
pass
|
2015-03-05 14:50:09 -05:00
|
|
|
globs = pyspark.mllib.evaluation.__dict__.copy()
|
2016-05-23 21:14:48 -04:00
|
|
|
spark = SparkSession.builder\
|
|
|
|
.master("local[4]")\
|
|
|
|
.appName("mllib.evaluation tests")\
|
|
|
|
.getOrCreate()
|
|
|
|
globs['sc'] = spark.sparkContext
|
2015-03-05 14:50:09 -05:00
|
|
|
(failure_count, test_count) = doctest.testmod(globs=globs, optionflags=doctest.ELLIPSIS)
|
2016-05-23 21:14:48 -04:00
|
|
|
spark.stop()
|
2015-03-05 14:50:09 -05:00
|
|
|
if failure_count:
|
2018-03-08 06:38:34 -05:00
|
|
|
sys.exit(-1)
|
2015-03-05 14:50:09 -05:00
|
|
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
|
_test()
|