diff options
Diffstat (limited to 'examples/src/main/python/mllib/binary_classification_metrics_example.py')
-rw-r--r-- | examples/src/main/python/mllib/binary_classification_metrics_example.py | 15 |
1 files changed, 10 insertions, 5 deletions
diff --git a/examples/src/main/python/mllib/binary_classification_metrics_example.py b/examples/src/main/python/mllib/binary_classification_metrics_example.py index 8f0fc9d45d..daf000e38d 100644 --- a/examples/src/main/python/mllib/binary_classification_metrics_example.py +++ b/examples/src/main/python/mllib/binary_classification_metrics_example.py @@ -18,20 +18,25 @@ Binary Classification Metrics Example. """ from __future__ import print_function -from pyspark import SparkContext +from pyspark.sql import SparkSession # $example on$ from pyspark.mllib.classification import LogisticRegressionWithLBFGS from pyspark.mllib.evaluation import BinaryClassificationMetrics -from pyspark.mllib.util import MLUtils +from pyspark.mllib.regression import LabeledPoint # $example off$ if __name__ == "__main__": - sc = SparkContext(appName="BinaryClassificationMetricsExample") + spark = SparkSession\ + .builder\ + .appName("BinaryClassificationMetricsExample")\ + .getOrCreate() # $example on$ # Several of the methods available in scala are currently missing from pyspark # Load training data in LIBSVM format - data = MLUtils.loadLibSVMFile(sc, "data/mllib/sample_binary_classification_data.txt") + data = spark\ + .read.format("libsvm").load("data/mllib/sample_binary_classification_data.txt")\ + .rdd.map(lambda row: LabeledPoint(row[0], row[1])) # Split data into training (60%) and test (40%) training, test = data.randomSplit([0.6, 0.4], seed=11L) @@ -53,4 +58,4 @@ if __name__ == "__main__": print("Area under ROC = %s" % metrics.areaUnderROC) # $example off$ - sc.stop() + spark.stop() |