group.py 文件源码

def _test():
    import doctest
    from pyspark.sql import Row, SparkSession
    import pyspark.sql.group
    globs = pyspark.sql.group.__dict__.copy()
    spark = SparkSession.builder\
        .master("local[4]")\
        .appName("sql.group tests")\
        .getOrCreate()
    sc = spark.sparkContext
    globs['sc'] = sc
    globs['df'] = sc.parallelize([(2, 'Alice'), (5, 'Bob')]) \
        .toDF(StructType([StructField('age', IntegerType()),
                          StructField('name', StringType())]))
    globs['df3'] = sc.parallelize([Row(name='Alice', age=2, height=80),
                                   Row(name='Bob', age=5, height=85)]).toDF()
    globs['df4'] = sc.parallelize([Row(course="dotNET", year=2012, earnings=10000),
                                   Row(course="Java",   year=2012, earnings=20000),
                                   Row(course="dotNET", year=2012, earnings=5000),
                                   Row(course="dotNET", year=2013, earnings=48000),
                                   Row(course="Java",   year=2013, earnings=30000)]).toDF()

    (failure_count, test_count) = doctest.testmod(
        pyspark.sql.group, globs=globs,
        optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE | doctest.REPORT_NDIFF)
    spark.stop()
    if failure_count:
        exit(-1)