dataframe.py 文件源码

def _test():
    import doctest
    from pyspark.context import SparkContext
    from pyspark.sql import Row, SQLContext
    import pyspark.sql.dataframe
    globs = pyspark.sql.dataframe.__dict__.copy()
    sc = SparkContext('local[4]', 'PythonTest')
    globs['sc'] = sc
    globs['sqlContext'] = SQLContext(sc)
    globs['df'] = sc.parallelize([(2, 'Alice'), (5, 'Bob')])\
        .toDF(StructType([StructField('age', IntegerType()),
                          StructField('name', StringType())]))
    globs['df2'] = sc.parallelize([Row(name='Tom', height=80), Row(name='Bob', height=85)]).toDF()
    globs['df3'] = sc.parallelize([Row(name='Alice', age=2),
                                   Row(name='Bob', age=5)]).toDF()
    globs['df4'] = sc.parallelize([Row(name='Alice', age=10, height=80),
                                  Row(name='Bob', age=5, height=None),
                                  Row(name='Tom', age=None, height=None),
                                  Row(name=None, age=None, height=None)]).toDF()

    (failure_count, test_count) = doctest.testmod(
        pyspark.sql.dataframe, globs=globs,
        optionflags=doctest.ELLIPSIS | doctest.NORMALIZE_WHITESPACE | doctest.REPORT_NDIFF)
    globs['sc'].stop()
    if failure_count:
        exit(-1)