#

# Licensed to the Apache Software Foundation (ASF) under one or more

# contributor license agreements. See the NOTICE file distributed with

# this work for additional information regarding copyright ownership.

# The ASF licenses this file to You under the Apache License, Version 2.0

# (the "License"); you may not use this file except in compliance with

# the License. You may obtain a copy of the License at

#

# http://www.apache.org/licenses/LICENSE-2.0

#

# Unless required by applicable law or agreed to in writing, software

# distributed under the License is distributed on an "AS IS" BASIS,

# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.

# See the License for the specific language governing permissions and

# limitations under the License.

#

"""

A collections of builtin functions

"""

import math

import sys

if sys.version < "3":

from itertools import imap as map

from pyspark import since, SparkContext

from pyspark.rdd import _prepare_for_python_RDD, ignore_unicode_prefix

from pyspark.serializers import PickleSerializer, AutoBatchedSerializer

from pyspark.sql.types import StringType

from pyspark.sql.column import Column, _to_java_column, _to_seq

from pyspark.sql.dataframe import DataFrame

def _create_function(name, doc=""):

""" Create a function for aggregator by name"""

def _(col):

sc = SparkContext._active_spark_context

jc = getattr(sc._jvm.functions, name)(col._jc if isinstance(col, Column) else col)

return Column(jc)

_.__name__ = name

_.__doc__ = doc

return _

def _create_binary_mathfunction(name, doc=""):

""" Create a binary mathfunction by name"""

def _(col1, col2):

sc = SparkContext._active_spark_context

# users might write ints for simplicity. This would throw an error on the JVM side.

jc = getattr(sc._jvm.functions, name)(col1._jc if isinstance(col1, Column) else float(col1),

col2._jc if isinstance(col2, Column) else float(col2))

return Column(jc)

_.__name__ = name

_.__doc__ = doc

return _

def _create_window_function(name, doc=''):

""" Create a window function by name """

def _():

sc = SparkContext._active_spark_context

jc = getattr(sc._jvm.functions, name)()

return Column(jc)

_.__name__ = name

_.__doc__ = 'Window function: ' + doc

return _

_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.',

}

# 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 denseRank is that denseRank leaves no gaps in ranking

sequence when there are ties. That is, if you were ranking a competition using denseRank

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':

"""returns the rank of rows within a window partition.

The difference between rank and denseRank is that denseRank leaves no gaps in ranking

sequence when there are ties. That is, if you were ranking a competition using denseRank

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.

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.""",

}

for _name, _doc in _functions.items():

globals()[_name] = since(1.3)(_create_function(_name, _doc))

for _name, _doc in _functions_1_4.items():

globals()[_name] = since(1.4)(_create_function(_name, _doc))

for _name, _doc in _binary_mathfunctions.items():

globals()[_name] = since(1.4)(_create_binary_mathfunction(_name, _doc))

for _name, _doc in _window_functions.items():

globals()[_name] = since(1.6)(_create_window_function(_name, _doc))

for _name, _doc in _functions_1_6.items():

globals()[_name] = since(1.6)(_create_function(_name, _doc))

for _name, _doc in _functions_2_1.items():

globals()[_name] = since(2.1)(_create_function(_name, _doc))

del _name, _doc

@since(1.3)

def approxCountDistinct(col, rsd=None):

"""

.. note:: Deprecated in 2.1, use approx_count_distinct instead.

"""

return approx_count_distinct(col, rsd)

@since(2.1)

def approx_count_distinct(col, rsd=None):

"""Returns a new :class:`Column` for approximate distinct count of ``col``.

>>> df.agg(approx_count_distinct(df.age).alias('c')).collect()

[Row(c=2)]

"""

sc = SparkContext._active_spark_context

if rsd is None:

jc = sc._jvm.functions.approx_count_distinct(_to_java_column(col))

else:

jc = sc._jvm.functions.approx_count_distinct(_to_java_column(col), rsd)

return Column(jc)

@since(1.6)

def broadcast(df):

"""Marks a DataFrame as small enough for use in broadcast joins."""

sc = SparkContext._active_spark_context

return DataFrame(sc._jvm.functions.broadcast(df._jdf), df.sql_ctx)

@since(1.4)

def coalesce(*cols):

"""Returns the first column that is not null.

>>> cDf = spark.createDataFrame([(None, None), (1, None), (None, 2)], ("a", "b"))

>>> cDf.show()

+----+----+

| a| b|

+----+----+

|null|null|

| 1|null|

|null| 2|

+----+----+

>>> cDf.select(coalesce(cDf["a"], cDf["b"])).show()

+--------------+

|coalesce(a, b)|

+--------------+

| null|

| 1|

| 2|

+--------------+

>>> cDf.select('*', coalesce(cDf["a"], lit(0.0))).show()

+----+----+----------------+

| a| b|coalesce(a, 0.0)|

+----+----+----------------+

|null|null| 0.0|

| 1|null| 1.0|

|null| 2| 0.0|

+----+----+----------------+

"""

sc = SparkContext._active_spark_context

jc = sc._jvm.functions.coalesce(_to_seq(sc, cols, _to_java_column))

return Column(jc)

@since(1.6)

def corr(col1, col2):

"""Returns a new :class:`Column` for the Pearson Correlation Coefficient for ``col1``

and ``col2``.

>>> a = range(20)

>>> b = [2 * x for x in range(20)]

>>> df = spark.createDataFrame(zip(a, b), ["a", "b"])

>>> df.agg(corr("a", "b").alias('c')).collect()

[Row(c=1.0)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.corr(_to_java_column(col1), _to_java_column(col2)))

@since(2.0)

def covar_pop(col1, col2):

"""Returns a new :class:`Column` for the population covariance of ``col1``

and ``col2``.

>>> a = [1] * 10

>>> b = [1] * 10

>>> df = spark.createDataFrame(zip(a, b), ["a", "b"])

>>> df.agg(covar_pop("a", "b").alias('c')).collect()

[Row(c=0.0)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.covar_pop(_to_java_column(col1), _to_java_column(col2)))

@since(2.0)

def covar_samp(col1, col2):

"""Returns a new :class:`Column` for the sample covariance of ``col1``

and ``col2``.

>>> a = [1] * 10

>>> b = [1] * 10

>>> df = spark.createDataFrame(zip(a, b), ["a", "b"])

>>> df.agg(covar_samp("a", "b").alias('c')).collect()

[Row(c=0.0)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.covar_samp(_to_java_column(col1), _to_java_column(col2)))

@since(1.3)

def countDistinct(col, *cols):

"""Returns a new :class:`Column` for distinct count of ``col`` or ``cols``.

>>> df.agg(countDistinct(df.age, df.name).alias('c')).collect()

[Row(c=2)]

>>> df.agg(countDistinct("age", "name").alias('c')).collect()

[Row(c=2)]

"""

sc = SparkContext._active_spark_context

jc = sc._jvm.functions.countDistinct(_to_java_column(col), _to_seq(sc, cols, _to_java_column))

return Column(jc)

@since(1.3)

def first(col, ignorenulls=False):

"""Aggregate function: returns the first value in a group.

The function by default returns the first values it sees. It will return the first non-null

value it sees when ignoreNulls is set to true. If all values are null, then null is returned.

"""

sc = SparkContext._active_spark_context

jc = sc._jvm.functions.first(_to_java_column(col), ignorenulls)

return Column(jc)

@since(2.0)

def grouping(col):

"""

Aggregate function: indicates whether a specified column in a GROUP BY list is aggregated

or not, returns 1 for aggregated or 0 for not aggregated in the result set.

>>> df.cube("name").agg(grouping("name"), sum("age")).orderBy("name").show()

+-----+--------------+--------+

| name|grouping(name)|sum(age)|

+-----+--------------+--------+

| null| 1| 7|

|Alice| 0| 2|

| Bob| 0| 5|

+-----+--------------+--------+

"""

sc = SparkContext._active_spark_context

jc = sc._jvm.functions.grouping(_to_java_column(col))

return Column(jc)

@since(2.0)

def grouping_id(*cols):

"""

Aggregate function: returns the level of grouping, equals to

(grouping(c1) << (n-1)) + (grouping(c2) << (n-2)) + ... + grouping(cn)

.. note:: The list of columns should match with grouping columns exactly, or empty (means all

the grouping columns).

>>> df.cube("name").agg(grouping_id(), sum("age")).orderBy("name").show()

+-----+-------------+--------+

| name|grouping_id()|sum(age)|

+-----+-------------+--------+

| null| 1| 7|

|Alice| 0| 2|

| Bob| 0| 5|

+-----+-------------+--------+

"""

sc = SparkContext._active_spark_context

jc = sc._jvm.functions.grouping_id(_to_seq(sc, cols, _to_java_column))

return Column(jc)

@since(1.6)

def input_file_name():

"""Creates a string column for the file name of the current Spark task.

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.input_file_name())

@since(1.6)

def isnan(col):

"""An expression that returns true iff the column is NaN.

>>> df = spark.createDataFrame([(1.0, float('nan')), (float('nan'), 2.0)], ("a", "b"))

>>> df.select(isnan("a").alias("r1"), isnan(df.a).alias("r2")).collect()

[Row(r1=False, r2=False), Row(r1=True, r2=True)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.isnan(_to_java_column(col)))

@since(1.6)

def isnull(col):

"""An expression that returns true iff the column is null.

>>> df = spark.createDataFrame([(1, None), (None, 2)], ("a", "b"))

>>> df.select(isnull("a").alias("r1"), isnull(df.a).alias("r2")).collect()

[Row(r1=False, r2=False), Row(r1=True, r2=True)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.isnull(_to_java_column(col)))

@since(1.3)

def last(col, ignorenulls=False):

"""Aggregate function: returns the last value in a group.

The function by default returns the last values it sees. It will return the last non-null

value it sees when ignoreNulls is set to true. If all values are null, then null is returned.

"""

sc = SparkContext._active_spark_context

jc = sc._jvm.functions.last(_to_java_column(col), ignorenulls)

return Column(jc)

@since(1.6)

def monotonically_increasing_id():

"""A column that generates monotonically increasing 64-bit integers.

The generated ID is guaranteed to be monotonically increasing and unique, but not consecutive.

The current implementation puts the partition ID in the upper 31 bits, and the record number

within each partition in the lower 33 bits. The assumption is that the data frame has

less than 1 billion partitions, and each partition has less than 8 billion records.

As an example, consider a :class:`DataFrame` with two partitions, each with 3 records.

This expression would return the following IDs:

0, 1, 2, 8589934592 (1L << 33), 8589934593, 8589934594.

>>> df0 = sc.parallelize(range(2), 2).mapPartitions(lambda x: [(1,), (2,), (3,)]).toDF(['col1'])

>>> df0.select(monotonically_increasing_id().alias('id')).collect()

[Row(id=0), Row(id=1), Row(id=2), Row(id=8589934592), Row(id=8589934593), Row(id=8589934594)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.monotonically_increasing_id())

@since(1.6)

def nanvl(col1, col2):

"""Returns col1 if it is not NaN, or col2 if col1 is NaN.

Both inputs should be floating point columns (DoubleType or FloatType).

>>> df = spark.createDataFrame([(1.0, float('nan')), (float('nan'), 2.0)], ("a", "b"))

>>> df.select(nanvl("a", "b").alias("r1"), nanvl(df.a, df.b).alias("r2")).collect()

[Row(r1=1.0, r2=1.0), Row(r1=2.0, r2=2.0)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.nanvl(_to_java_column(col1), _to_java_column(col2)))

@since(1.4)

def rand(seed=None):

"""Generates a random column with independent and identically distributed (i.i.d.) samples

from U[0.0, 1.0].

"""

sc = SparkContext._active_spark_context

if seed is not None:

jc = sc._jvm.functions.rand(seed)

else:

jc = sc._jvm.functions.rand()

return Column(jc)

@since(1.4)

def randn(seed=None):

"""Generates a column with independent and identically distributed (i.i.d.) samples from

the standard normal distribution.

"""

sc = SparkContext._active_spark_context

if seed is not None:

jc = sc._jvm.functions.randn(seed)

else:

jc = sc._jvm.functions.randn()

return Column(jc)

@since(1.5)

def round(col, scale=0):

"""

Round the given value to `scale` decimal places using HALF_UP rounding mode if `scale` >= 0

or at integral part when `scale` < 0.

>>> spark.createDataFrame([(2.5,)], ['a']).select(round('a', 0).alias('r')).collect()

[Row(r=3.0)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.round(_to_java_column(col), scale))

@since(2.0)

def bround(col, scale=0):

"""

Round the given value to `scale` decimal places using HALF_EVEN rounding mode if `scale` >= 0

or at integral part when `scale` < 0.

>>> spark.createDataFrame([(2.5,)], ['a']).select(bround('a', 0).alias('r')).collect()

[Row(r=2.0)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.bround(_to_java_column(col), scale))

@since(1.5)

def shiftLeft(col, numBits):

"""Shift the given value numBits left.

>>> spark.createDataFrame([(21,)], ['a']).select(shiftLeft('a', 1).alias('r')).collect()

[Row(r=42)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.shiftLeft(_to_java_column(col), numBits))

@since(1.5)

def shiftRight(col, numBits):

"""(Signed) shift the given value numBits right.

>>> spark.createDataFrame([(42,)], ['a']).select(shiftRight('a', 1).alias('r')).collect()

[Row(r=21)]

"""

sc = SparkContext._active_spark_context

jc = sc._jvm.functions.shiftRight(_to_java_column(col), numBits)

return Column(jc)

@since(1.5)

def shiftRightUnsigned(col, numBits):

"""Unsigned shift the given value numBits right.

>>> df = spark.createDataFrame([(-42,)], ['a'])

>>> df.select(shiftRightUnsigned('a', 1).alias('r')).collect()

[Row(r=9223372036854775787)]

"""

sc = SparkContext._active_spark_context

jc = sc._jvm.functions.shiftRightUnsigned(_to_java_column(col), numBits)

return Column(jc)

@since(1.6)

def spark_partition_id():

"""A column for partition ID.

.. note:: This is indeterministic because it depends on data partitioning and task scheduling.

>>> df.repartition(1).select(spark_partition_id().alias("pid")).collect()

[Row(pid=0), Row(pid=0)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.spark_partition_id())

@since(1.5)

def expr(str):

"""Parses the expression string into the column that it represents

>>> df.select(expr("length(name)")).collect()

[Row(length(name)=5), Row(length(name)=3)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.expr(str))

@ignore_unicode_prefix

@since(1.4)

def struct(*cols):

"""Creates a new struct column.

:param cols: list of column names (string) or list of :class:`Column` expressions

>>> df.select(struct('age', 'name').alias("struct")).collect()

[Row(struct=Row(age=2, name=u'Alice')), Row(struct=Row(age=5, name=u'Bob'))]

>>> df.select(struct([df.age, df.name]).alias("struct")).collect()

[Row(struct=Row(age=2, name=u'Alice')), Row(struct=Row(age=5, name=u'Bob'))]

"""

sc = SparkContext._active_spark_context

if len(cols) == 1 and isinstance(cols[0], (list, set)):

cols = cols[0]

jc = sc._jvm.functions.struct(_to_seq(sc, cols, _to_java_column))

return Column(jc)

@since(1.5)

def greatest(*cols):

"""

Returns the greatest value of the list of column names, skipping null values.

This function takes at least 2 parameters. It will return null iff all parameters are null.

>>> df = spark.createDataFrame([(1, 4, 3)], ['a', 'b', 'c'])

>>> df.select(greatest(df.a, df.b, df.c).alias("greatest")).collect()

[Row(greatest=4)]

"""

if len(cols) < 2:

raise ValueError("greatest should take at least two columns")

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.greatest(_to_seq(sc, cols, _to_java_column)))

@since(1.5)

def least(*cols):

"""

Returns the least value of the list of column names, skipping null values.

This function takes at least 2 parameters. It will return null iff all parameters are null.

>>> df = spark.createDataFrame([(1, 4, 3)], ['a', 'b', 'c'])

>>> df.select(least(df.a, df.b, df.c).alias("least")).collect()

[Row(least=1)]

"""

if len(cols) < 2:

raise ValueError("least should take at least two columns")

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.least(_to_seq(sc, cols, _to_java_column)))

@since(1.4)

def when(condition, value):

"""Evaluates a list of conditions and returns one of multiple possible result expressions.

If :func:`Column.otherwise` is not invoked, None is returned for unmatched conditions.

:param condition: a boolean :class:`Column` expression.

:param value: a literal value, or a :class:`Column` expression.

>>> df.select(when(df['age'] == 2, 3).otherwise(4).alias("age")).collect()

[Row(age=3), Row(age=4)]

>>> df.select(when(df.age == 2, df.age + 1).alias("age")).collect()

[Row(age=3), Row(age=None)]

"""

sc = SparkContext._active_spark_context

if not isinstance(condition, Column):

raise TypeError("condition should be a Column")

v = value._jc if isinstance(value, Column) else value

jc = sc._jvm.functions.when(condition._jc, v)

return Column(jc)

@since(1.5)

def log(arg1, arg2=None):

"""Returns the first argument-based logarithm of the second argument.

If there is only one argument, then this takes the natural logarithm of the argument.

>>> df.select(log(10.0, df.age).alias('ten')).rdd.map(lambda l: str(l.ten)[:7]).collect()

['0.30102', '0.69897']

>>> df.select(log(df.age).alias('e')).rdd.map(lambda l: str(l.e)[:7]).collect()

['0.69314', '1.60943']

"""

sc = SparkContext._active_spark_context

if arg2 is None:

jc = sc._jvm.functions.log(_to_java_column(arg1))

else:

jc = sc._jvm.functions.log(arg1, _to_java_column(arg2))

return Column(jc)

@since(1.5)

def log2(col):

"""Returns the base-2 logarithm of the argument.

>>> spark.createDataFrame([(4,)], ['a']).select(log2('a').alias('log2')).collect()

[Row(log2=2.0)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.log2(_to_java_column(col)))

@since(1.5)

@ignore_unicode_prefix

def conv(col, fromBase, toBase):

"""

Convert a number in a string column from one base to another.

>>> df = spark.createDataFrame([("010101",)], ['n'])

>>> df.select(conv(df.n, 2, 16).alias('hex')).collect()

[Row(hex=u'15')]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.conv(_to_java_column(col), fromBase, toBase))

@since(1.5)

def factorial(col):

"""

Computes the factorial of the given value.

>>> df = spark.createDataFrame([(5,)], ['n'])

>>> df.select(factorial(df.n).alias('f')).collect()

[Row(f=120)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.factorial(_to_java_column(col)))

# --------------- Window functions ------------------------

@since(1.4)

def lag(col, count=1, default=None):

"""

Window function: returns the value that is `offset` rows before the current row, and

`defaultValue` if there is less than `offset` rows before the current row. For example,

an `offset` of one will return the previous row at any given point in the window partition.

This is equivalent to the LAG function in SQL.

:param col: name of column or expression

:param count: number of row to extend

:param default: default value

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.lag(_to_java_column(col), count, default))

@since(1.4)

def lead(col, count=1, default=None):

"""

Window function: returns the value that is `offset` rows after the current row, and

`defaultValue` if there is less than `offset` rows after the current row. For example,

an `offset` of one will return the next row at any given point in the window partition.

This is equivalent to the LEAD function in SQL.

:param col: name of column or expression

:param count: number of row to extend

:param default: default value

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.lead(_to_java_column(col), count, default))

@since(1.4)

def ntile(n):

"""

Window function: returns the ntile group id (from 1 to `n` inclusive)

in an ordered window partition. For example, if `n` is 4, the first

quarter of the rows will get value 1, the second quarter will get 2,

the third quarter will get 3, and the last quarter will get 4.

This is equivalent to the NTILE function in SQL.

:param n: an integer

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.ntile(int(n)))

# ---------------------- Date/Timestamp functions ------------------------------

@since(1.5)

def current_date():

"""

Returns the current date as a date column.

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.current_date())

def current_timestamp():

"""

Returns the current timestamp as a timestamp column.

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.current_timestamp())

@ignore_unicode_prefix

@since(1.5)

def date_format(date, format):

"""

Converts a date/timestamp/string to a value of string in the format specified by the date

format given by the second argument.

A pattern could be for instance `dd.MM.yyyy` and could return a string like '18.03.1993'. All

pattern letters of the Java class `java.text.SimpleDateFormat` can be used.

.. note:: Use when ever possible specialized functions like `year`. These benefit from a

specialized implementation.

>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])

>>> df.select(date_format('a', 'MM/dd/yyy').alias('date')).collect()

[Row(date=u'04/08/2015')]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.date_format(_to_java_column(date), format))

@since(1.5)

def year(col):

"""

Extract the year of a given date as integer.

>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])

>>> df.select(year('a').alias('year')).collect()

[Row(year=2015)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.year(_to_java_column(col)))

@since(1.5)

def quarter(col):

"""

Extract the quarter of a given date as integer.

>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])

>>> df.select(quarter('a').alias('quarter')).collect()

[Row(quarter=2)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.quarter(_to_java_column(col)))

@since(1.5)

def month(col):

"""

Extract the month of a given date as integer.

>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])

>>> df.select(month('a').alias('month')).collect()

[Row(month=4)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.month(_to_java_column(col)))

@since(1.5)

def dayofmonth(col):

"""

Extract the day of the month of a given date as integer.

>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])

>>> df.select(dayofmonth('a').alias('day')).collect()

[Row(day=8)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.dayofmonth(_to_java_column(col)))

@since(1.5)

def dayofyear(col):

"""

Extract the day of the year of a given date as integer.

>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])

>>> df.select(dayofyear('a').alias('day')).collect()

[Row(day=98)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.dayofyear(_to_java_column(col)))

@since(1.5)

def hour(col):

"""

Extract the hours of a given date as integer.

>>> df = spark.createDataFrame([('2015-04-08 13:08:15',)], ['a'])

>>> df.select(hour('a').alias('hour')).collect()

[Row(hour=13)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.hour(_to_java_column(col)))

@since(1.5)

def minute(col):

"""

Extract the minutes of a given date as integer.

>>> df = spark.createDataFrame([('2015-04-08 13:08:15',)], ['a'])

>>> df.select(minute('a').alias('minute')).collect()

[Row(minute=8)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.minute(_to_java_column(col)))

@since(1.5)

def second(col):

"""

Extract the seconds of a given date as integer.

>>> df = spark.createDataFrame([('2015-04-08 13:08:15',)], ['a'])

>>> df.select(second('a').alias('second')).collect()

[Row(second=15)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.second(_to_java_column(col)))

@since(1.5)

def weekofyear(col):

"""

Extract the week number of a given date as integer.

>>> df = spark.createDataFrame([('2015-04-08',)], ['a'])

>>> df.select(weekofyear(df.a).alias('week')).collect()

[Row(week=15)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.weekofyear(_to_java_column(col)))

@since(1.5)

def date_add(start, days):

"""

Returns the date that is `days` days after `start`

>>> df = spark.createDataFrame([('2015-04-08',)], ['d'])

>>> df.select(date_add(df.d, 1).alias('d')).collect()

[Row(d=datetime.date(2015, 4, 9))]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.date_add(_to_java_column(start), days))

@since(1.5)

def date_sub(start, days):

"""

Returns the date that is `days` days before `start`

>>> df = spark.createDataFrame([('2015-04-08',)], ['d'])

>>> df.select(date_sub(df.d, 1).alias('d')).collect()

[Row(d=datetime.date(2015, 4, 7))]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.date_sub(_to_java_column(start), days))

@since(1.5)

def datediff(end, start):

"""

Returns the number of days from `start` to `end`.

>>> df = spark.createDataFrame([('2015-04-08','2015-05-10')], ['d1', 'd2'])

>>> df.select(datediff(df.d2, df.d1).alias('diff')).collect()

[Row(diff=32)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.datediff(_to_java_column(end), _to_java_column(start)))

@since(1.5)

def add_months(start, months):

"""

Returns the date that is `months` months after `start`

>>> df = spark.createDataFrame([('2015-04-08',)], ['d'])

>>> df.select(add_months(df.d, 1).alias('d')).collect()

[Row(d=datetime.date(2015, 5, 8))]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.add_months(_to_java_column(start), months))

@since(1.5)

def months_between(date1, date2):

"""

Returns the number of months between date1 and date2.

>>> df = spark.createDataFrame([('1997-02-28 10:30:00', '1996-10-30')], ['t', 'd'])

>>> df.select(months_between(df.t, df.d).alias('months')).collect()

[Row(months=3.9495967...)]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.months_between(_to_java_column(date1), _to_java_column(date2)))

@since(1.5)

def to_date(col):

"""

Converts the column of :class:`pyspark.sql.types.StringType` or

:class:`pyspark.sql.types.TimestampType` into :class:`pyspark.sql.types.DateType`.

>>> df = spark.createDataFrame([('1997-02-28 10:30:00',)], ['t'])

>>> df.select(to_date(df.t).alias('date')).collect()

[Row(date=datetime.date(1997, 2, 28))]

"""

sc = SparkContext._active_spark_context

return Column(sc._jvm.functions.to_date(_to_java_column(col)))

@since(1.5)

def trunc(date, format):

"""

Returns date truncated to the unit specified by the format.

:param format: 'year', 'YYYY', 'yy' or 'month', 'mon', 'mm'

>>> df = spark.createDataFrame([('1997-02-28',)], ['d'])

>>> df.select(trunc(df.d, 'year').alias('year')).collect()

[Row(year=datetime.date(1997, 1, 1))]

>>> df.select(trunc(df.d, 'mon').alias('month')).collect()

[Row(month=datetime.date(1997, 2, 1))]