Unit test pyspark code using python

Question

I have a script in pysparkas below. I want unit test a functionin this script.

def rename_chars(column_name):
    chars = ((' ', '_&'), ('.', '_$'))
    new_cols = reduce(lambda a, kv: a.replace(*kv), chars, column_name)
    return new_cols


def column_names(df):
    changed_col_names = df.schema.names
    for cols in changed_col_names:
        df = df.withColumnRenamed(cols, rename_chars(cols))
    return df   

I wrote unittestas below to test the function.

But I do not know how to send unittest. I did spark-submitthat does nothing.

import unittest
from my_script import column_names

from pyspark import SparkContext, SparkConf
from pyspark.sql import HiveContext
conf = SparkConf()
sc = SparkContext(conf=conf)
sqlContext = HiveContext(sc)

cols = ['ID', 'NAME', 'last.name', 'abc test']
val = [(1, 'Sam', 'SMITH', 'eng'), (2, 'RAM', 'Reddy', 'turbine')]
df = sqlContext.createDataFrame(val, cols)


class RenameColumnNames(unittest.TestCase):
    def test_column_names(self):
        df1 = column_names(df)
        result = df1.schema.names
        expected = ['ID', 'NAME', 'last_$name', 'abc_&test']
        self.assertEqual(result, expected)

How can I integrate this script to work as unittest

what can i run on node where i have it installed pyspark?

Answer 1

Pyspark Unittests Team Guide

1. You need to download Unzip spark from the site and unzip it. Or if you already have a working Spark and Python distribution, just install pyspark :pip install pyspark

2. :

export SPARK_HOME="/home/eugene/spark-1.6.0-bin-hadoop2.6"
export PYTHONPATH="$SPARK_HOME/python/:$SPARK_HOME/python/lib/py4j-0.9-src.zip:$PYTHONPATH"
export PATH="SPARK_HOME/bin:$PATH"

.profile . Spark, .

3. , :

PYSPARK_SUBMIT_ARGS="--jars path/to/hive/jars/jar.jar,path/to/other/jars/jar.jar --conf spark.driver.userClassPathFirst=true --master local[*] pyspark-shell"
PYSPARK_PYTHON="/home/eugene/anaconda3/envs/ste/bin/python3"

? . Pyspark py4j java- Spark. , Kafka Python TestHiveContext Scala, , . "".

4. pyspark/tests.py, pyspark/streaming/tests.py, pyspark/sql/tests.py, pyspark/ml/tests.py, pyspark/mllib/tests.py, TestCase pyspark. ( pyspark/sql/tests.py):

class HiveContextSQLTests(ReusedPySparkTestCase):

    @classmethod
    def setUpClass(cls):
        ReusedPySparkTestCase.setUpClass()
        cls.tempdir = tempfile.NamedTemporaryFile(delete=False)
        try:
            cls.sc._jvm.org.apache.hadoop.hive.conf.HiveConf()
        except py4j.protocol.Py4JError:
            cls.tearDownClass()
            raise unittest.SkipTest("Hive is not available")
        except TypeError:
            cls.tearDownClass()
            raise unittest.SkipTest("Hive is not available")
        os.unlink(cls.tempdir.name)
        _scala_HiveContext =\
            cls.sc._jvm.org.apache.spark.sql.hive.test.TestHiveContext(cls.sc._jsc.sc())
        cls.sqlCtx = HiveContext(cls.sc, _scala_HiveContext)
        cls.testData = [Row(key=i, value=str(i)) for i in range(100)]
        cls.df = cls.sc.parallelize(cls.testData).toDF()

    @classmethod
    def tearDownClass(cls):
        ReusedPySparkTestCase.tearDownClass()
        shutil.rmtree(cls.tempdir.name, ignore_errors=True)

-jars Hive PYSPARK_SUBMIT_ARGS,

:

class SQLContextTests(ReusedPySparkTestCase):
    def test_get_or_create(self):
        sqlCtx = SQLContext.getOrCreate(self.sc)
        self.assertTrue(SQLContext.getOrCreate(self.sc) is sqlCtx)

, pyspark pip, test.py, . Spark .

TestCase : python -m unittest test.py

Answer 2

. CLI:

python -m unittest my_unit_test_script.py

import functools
import unittest

from pyspark import SparkContext, SparkConf
from pyspark.sql import HiveContext


def rename_chars(column_name):
    chars = ((' ', '_&'), ('.', '_$'))
    new_cols = functools.reduce(lambda a, kv: a.replace(*kv), chars, column_name)
    return new_cols


def column_names(df):
    changed_col_names = df.schema.names
    for cols in changed_col_names:
        df = df.withColumnRenamed(cols, rename_chars(cols))
    return df


class RenameColumnNames(unittest.TestCase):
    def setUp(self):
        conf = SparkConf()
        sc = SparkContext(conf=conf)
        self.sqlContext = HiveContext(sc)

    def test_column_names(self):
        cols = ['ID', 'NAME', 'last.name', 'abc test']
        val = [(1, 'Sam', 'SMITH', 'eng'), (2, 'RAM', 'Reddy', 'turbine')]
        df = self.sqlContext.createDataFrame(val, cols)
        result = df.schema.names
        expected = ['ID', 'NAME', 'last_$name', 'abc_&test']
        self.assertEqual(result, expected)