Spark-PySpark sql各种内置函数

_functions = {
    'lit': 'Creates a :class:`Column` of literal value.',
    'col': 'Returns a :class:`Column` based on the given column name.',
    'column': 'Returns a :class:`Column` based on the given column name.',
    'asc': 'Returns a sort expression based on the ascending order of the given column name.',
    'desc': 'Returns a sort expression based on the descending order of the given column name.',

    'upper': 'Converts a string expression to upper case.',
    'lower': 'Converts a string expression to upper case.',
    'sqrt': 'Computes the square root of the specified float value.',
    'abs': 'Computes the absolute value.',

    'max': 'Aggregate function: returns the maximum value of the expression in a group.',
    'min': 'Aggregate function: returns the minimum value of the expression in a group.',
    'count': 'Aggregate function: returns the number of items in a group.',
    'sum': 'Aggregate function: returns the sum of all values in the expression.',
    'avg': 'Aggregate function: returns the average of the values in a group.',
    'mean': 'Aggregate function: returns the average of the values in a group.',
    'sumDistinct': 'Aggregate function: returns the sum of distinct values in the expression.',
}

_functions_1_4 = {
    # unary math functions
    'acos': 'Computes the cosine inverse of the given value; the returned angle is in the range' +
            '0.0 through pi.',
    'asin': 'Computes the sine inverse of the given value; the returned angle is in the range' +
            '-pi/2 through pi/2.',
    'atan': 'Computes the tangent inverse of the given value.',
    'cbrt': 'Computes the cube-root of the given value.',
    'ceil': 'Computes the ceiling of the given value.',
    'cos': 'Computes the cosine of the given value.',
    'cosh': 'Computes the hyperbolic cosine of the given value.',
    'exp': 'Computes the exponential of the given value.',
    'expm1': 'Computes the exponential of the given value minus one.',
    'floor': 'Computes the floor of the given value.',
    'log': 'Computes the natural logarithm of the given value.',
    'log10': 'Computes the logarithm of the given value in Base 10.',
    'log1p': 'Computes the natural logarithm of the given value plus one.',
    'rint': 'Returns the double value that is closest in value to the argument and' +
            ' is equal to a mathematical integer.',
    'signum': 'Computes the signum of the given value.',
    'sin': 'Computes the sine of the given value.',
    'sinh': 'Computes the hyperbolic sine of the given value.',
    'tan': 'Computes the tangent of the given value.',
    'tanh': 'Computes the hyperbolic tangent of the given value.',
    'toDegrees': '.. note:: Deprecated in 2.1, use degrees instead.',
    'toRadians': '.. note:: Deprecated in 2.1, use radians instead.',
    'bitwiseNOT': 'Computes bitwise not.',
}

_functions_1_6 = {
    # unary math functions
    'stddev': 'Aggregate function: returns the unbiased sample standard deviation of' +
              ' the expression in a group.',
    'stddev_samp': 'Aggregate function: returns the unbiased sample standard deviation of' +
                   ' the expression in a group.',
    'stddev_pop': 'Aggregate function: returns population standard deviation of' +
                  ' the expression in a group.',
    'variance': 'Aggregate function: returns the population variance of the values in a group.',
    'var_samp': 'Aggregate function: returns the unbiased variance of the values in a group.',
    'var_pop':  'Aggregate function: returns the population variance of the values in a group.',
    'skewness': 'Aggregate function: returns the skewness of the values in a group.',
    'kurtosis': 'Aggregate function: returns the kurtosis of the values in a group.',
    'collect_list': 'Aggregate function: returns a list of objects with duplicates.',
    'collect_set': 'Aggregate function: returns a set of objects with duplicate elements' +
                   ' eliminated.',
}

_functions_2_1 = {
    # unary math functions
    'degrees': 'Converts an angle measured in radians to an approximately equivalent angle ' +
               'measured in degrees.',
    'radians': 'Converts an angle measured in degrees to an approximately equivalent angle ' +
               'measured in radians.',
}

_functions_2_2 = {
    'to_date': 'Converts a string date into a DateType using the (optionally) specified format.',
    'to_timestamp': 'Converts a string timestamp into a timestamp type using the ' +
                    '(optionally) specified format.',
}

# math functions that take two arguments as input
_binary_mathfunctions = {
    'atan2': 'Returns the angle theta from the conversion of rectangular coordinates (x, y) to' +
             'polar coordinates (r, theta).',
    'hypot': 'Computes ``sqrt(a^2 + b^2)`` without intermediate overflow or underflow.',
    'pow': 'Returns the value of the first argument raised to the power of the second argument.',
}

_window_functions = {
    'row_number':
        """returns a sequential number starting at 1 within a window partition.""",
    'dense_rank':
        """returns the rank of rows within a window partition, without any gaps.

        The difference between rank and dense_rank is that dense_rank leaves no gaps in ranking
        sequence when there are ties. That is, if you were ranking a competition using dense_rank
        and had three people tie for second place, you would say that all three were in second
        place and that the next person came in third. Rank would give me sequential numbers, making
        the person that came in third place (after the ties) would register as coming in fifth.

        This is equivalent to the DENSE_RANK function in SQL.""",
    'rank':
        """returns the rank of rows within a window partition.

        The difference between rank and dense_rank is that dense_rank leaves no gaps in ranking
        sequence when there are ties. That is, if you were ranking a competition using dense_rank
        and had three people tie for second place, you would say that all three were in second
        place and that the next person came in third. Rank would give me sequential numbers, making
        the person that came in third place (after the ties) would register as coming in fifth.

        This is equivalent to the RANK function in SQL.""",
    'cume_dist':
        """returns the cumulative distribution of values within a window partition,
        i.e. the fraction of rows that are below the current row.""",
    'percent_rank':
        """returns the relative rank (i.e. percentile) of rows within a window partition.""",
}

©著作权归作者所有,转载或内容合作请联系作者
  • 序言:七十年代末,一起剥皮案震惊了整个滨河市,随后出现的几起案子,更是在滨河造成了极大的恐慌,老刑警刘岩,带你破解...
    沈念sama阅读 212,222评论 6 493
  • 序言:滨河连续发生了三起死亡事件,死亡现场离奇诡异,居然都是意外死亡,警方通过查阅死者的电脑和手机,发现死者居然都...
    沈念sama阅读 90,455评论 3 385
  • 文/潘晓璐 我一进店门,熙熙楼的掌柜王于贵愁眉苦脸地迎上来,“玉大人,你说我怎么就摊上这事。” “怎么了?”我有些...
    开封第一讲书人阅读 157,720评论 0 348
  • 文/不坏的土叔 我叫张陵,是天一观的道长。 经常有香客问我,道长,这世上最难降的妖魔是什么? 我笑而不...
    开封第一讲书人阅读 56,568评论 1 284
  • 正文 为了忘掉前任,我火速办了婚礼,结果婚礼上,老公的妹妹穿的比我还像新娘。我一直安慰自己,他们只是感情好,可当我...
    茶点故事阅读 65,696评论 6 386
  • 文/花漫 我一把揭开白布。 她就那样静静地躺着,像睡着了一般。 火红的嫁衣衬着肌肤如雪。 梳的纹丝不乱的头发上,一...
    开封第一讲书人阅读 49,879评论 1 290
  • 那天,我揣着相机与录音,去河边找鬼。 笑死,一个胖子当着我的面吹牛,可吹牛的内容都是我干的。 我是一名探鬼主播,决...
    沈念sama阅读 39,028评论 3 409
  • 文/苍兰香墨 我猛地睁开眼,长吁一口气:“原来是场噩梦啊……” “哼!你这毒妇竟也来了?” 一声冷哼从身侧响起,我...
    开封第一讲书人阅读 37,773评论 0 268
  • 序言:老挝万荣一对情侣失踪,失踪者是张志新(化名)和其女友刘颖,没想到半个月后,有当地人在树林里发现了一具尸体,经...
    沈念sama阅读 44,220评论 1 303
  • 正文 独居荒郊野岭守林人离奇死亡,尸身上长有42处带血的脓包…… 初始之章·张勋 以下内容为张勋视角 年9月15日...
    茶点故事阅读 36,550评论 2 327
  • 正文 我和宋清朗相恋三年,在试婚纱的时候发现自己被绿了。 大学时的朋友给我发了我未婚夫和他白月光在一起吃饭的照片。...
    茶点故事阅读 38,697评论 1 341
  • 序言:一个原本活蹦乱跳的男人离奇死亡,死状恐怖,灵堂内的尸体忽然破棺而出,到底是诈尸还是另有隐情,我是刑警宁泽,带...
    沈念sama阅读 34,360评论 4 332
  • 正文 年R本政府宣布,位于F岛的核电站,受9级特大地震影响,放射性物质发生泄漏。R本人自食恶果不足惜,却给世界环境...
    茶点故事阅读 40,002评论 3 315
  • 文/蒙蒙 一、第九天 我趴在偏房一处隐蔽的房顶上张望。 院中可真热闹,春花似锦、人声如沸。这庄子的主人今日做“春日...
    开封第一讲书人阅读 30,782评论 0 21
  • 文/苍兰香墨 我抬头看了看天上的太阳。三九已至,却和暖如春,着一层夹袄步出监牢的瞬间,已是汗流浃背。 一阵脚步声响...
    开封第一讲书人阅读 32,010评论 1 266
  • 我被黑心中介骗来泰国打工, 没想到刚下飞机就差点儿被人妖公主榨干…… 1. 我叫王不留,地道东北人。 一个月前我还...
    沈念sama阅读 46,433评论 2 360
  • 正文 我出身青楼,却偏偏与公主长得像,于是被迫代替她去往敌国和亲。 传闻我的和亲对象是个残疾皇子,可洞房花烛夜当晚...
    茶点故事阅读 43,587评论 2 350

推荐阅读更多精彩内容

  • spark sql 调试技巧--内置udf查看 Spark SQL内置了许多常用的udf,我们该如何拿到用户的ud...
    cda766963c7e阅读 2,714评论 0 0
  • 1、在hive中注册udf函数 add jar hdfs://hdp-hdfs01/apps/udf.jar; -...
    赵简书阅读 4,107评论 0 4
  • 1,不把自己当成图书馆,而是践行出自己的原则 这是听学霸猫播客讲到的一个理论,是说我们不应该只是追求看了多少本书,...
    雀岛札记阅读 104评论 0 0
  • 花草之勃勃生机,是春光之明媚,夏云之蔽日;而于你注视这一刻,是有心之呵护,处世之坦然;懂得在寻常中的遇见、不经意的...
    妙喜文人紫砂阅读 79评论 0 0
  • 人有的时候真的很奇怪,你明明知道自己很喜欢一个人,可是偏偏却不能放过自己,偏偏堆满了情绪要发在那个喜欢的人身上,你...
    081045eb431c阅读 279评论 0 1