- 最简单的注册UDF ---- 直接将lambda表达式注册成UDF
下面是一个简单的清洗函数
from pyspark.sql.types import StringType
spark.udf.register('sex_distinct', lambda x: 'M' if x == u'男' else 'F', StringType())
spark.sql("""
select sex_distinct('男')
""").show()
结果
+---------------+
|sex_distinct(男)|
+---------------+
| M|
+---------------+
- 很多时候逻辑比较复杂，匿名函数不能完成工作，可以自己
def一个函数，将def的函数名填入上面lambda函数所在位置就行
from pyspark.sql.types import StringType
def sex_distinct(sex_chinese):
if sex_chinese == u'男':
return u'M'
else:
return u'F'
spark.udf.register('sex_distinct_rename', sex_distinct, StringType())
spark.sql("""
select sex_distinct_rename('女')
""").show()
源码分析
def register(self, name, f, returnType=None):
"""注册python的函数或自定义的函数为udf
:param name: sql语句中的函数名
:param f: 函数，可以python的，也可以是自定义的
:param returnType:
["DataType", "NullType", "StringType", "BinaryType", "BooleanType", "DateType",
"TimestampType", "DecimalType", "DoubleType", "FloatType", "ByteType", "IntegerType",
"LongType", "ShortType", "ArrayType", "MapType", "StructField", "StructType"]
可以看出规律了吧，和sql中的一一对应
:return: a user-defined function.
To register a nondeterministic Python function, users need to first build
a nondeterministic user-defined function for the Python function and then register it
as a SQL function.
`returnType` can be optionally specified when `f` is a Python function but not
when `f` is a user-defined function. Please see below.
1. 当f是python内部的函数（所谓python内部的函数就是python自带的函数）
`returnType` 默认是 string type 并且可以按需指定. 返回类型必须匹配指定类型.
这种情况约等于
`register(name, f, returnType=StringType())`.
>>> strlen = spark.udf.register("stringLengthString", lambda x: len(x))
>>> spark.sql("SELECT stringLengthString('test')").collect()
[Row(stringLengthString(test)=u'4')]
>>> spark.sql("SELECT 'foo' AS text").select(strlen("text")).collect()
[Row(stringLengthString(text)=u'3')]
>>> from pyspark.sql.types import IntegerType
>>> _ = spark.udf.register("stringLengthInt", lambda x: len(x), IntegerType())
>>> spark.sql("SELECT stringLengthInt('test')").collect()
[Row(stringLengthInt(test)=4)]
2. 当f是用户自定义的函数
Spark uses the return type of the given user-defined function as the return type of
the registered user-defined function. `returnType` should not be specified.
In this case, this API works as if `register(name, f)`.
>>> from pyspark.sql.types import IntegerType
>>> from pyspark.sql.functions import udf
>>> slen = udf(lambda s: len(s), IntegerType())
>>> _ = spark.udf.register("slen", slen)
>>> spark.sql("SELECT slen('test')").collect()
[Row(slen(test)=4)]
>>> import random
>>> from pyspark.sql.functions import udf
>>> from pyspark.sql.types import IntegerType
>>> random_udf = udf(lambda: random.randint(0, 100), IntegerType()).asNondeterministic()
>>> new_random_udf = spark.udf.register("random_udf", random_udf)
>>> spark.sql("SELECT random_udf()").collect() # doctest: +SKIP
[Row(random_udf()=82)]
>>> from pyspark.sql.functions import pandas_udf, PandasUDFType
>>> @pandas_udf("integer", PandasUDFType.SCALAR) # doctest: +SKIP
... def add_one(x):
... return x + 1
...
>>> _ = spark.udf.register("add_one", add_one) # doctest: +SKIP
>>> spark.sql("SELECT add_one(id) FROM range(3)").collect() # doctest: +SKIP
[Row(add_one(id)=1), Row(add_one(id)=2), Row(add_one(id)=3)]
>>> @pandas_udf("integer", PandasUDFType.GROUPED_AGG) # doctest: +SKIP
... def sum_udf(v):
... return v.sum()
...
>>> _ = spark.udf.register("sum_udf", sum_udf) # doctest: +SKIP
>>> q = "SELECT sum_udf(v1) FROM VALUES (3, 0), (2, 0), (1, 1) tbl(v1, v2) GROUP BY v2"
>>> spark.sql(q).collect() # doctest: +SKIP
[Row(sum_udf(v1)=1), Row(sum_udf(v1)=5)]
.. note:: Registration for a user-defined function (case 2.) was added from
Spark 2.3.0.
"""
# This is to check whether the input function is from a user-defined function or
# Python function.
if hasattr(f, 'asNondeterministic'):
if returnType is not None:
raise TypeError(
"Invalid returnType: data type can not be specified when f is"
"a user-defined function, but got %s." % returnType)
if f.evalType not in [PythonEvalType.SQL_BATCHED_UDF,
PythonEvalType.SQL_SCALAR_PANDAS_UDF,
PythonEvalType.SQL_GROUPED_AGG_PANDAS_UDF]:
raise ValueError(
"Invalid f: f must be SQL_BATCHED_UDF, SQL_SCALAR_PANDAS_UDF or "
"SQL_GROUPED_AGG_PANDAS_UDF")
register_udf = UserDefinedFunction(f.func, returnType=f.returnType, name=name,
evalType=f.evalType,
deterministic=f.deterministic)
return_udf = f
else:
if returnType is None: #这里指定了返回类型默认为StringType()
returnType = StringType()
register_udf = UserDefinedFunction(f, returnType=returnType, name=name,
evalType=PythonEvalType.SQL_BATCHED_UDF)
return_udf = register_udf._wrapped()
self.sparkSession._jsparkSession.udf().registerPython(name, register_udf._judf)
return return_udf
-
复杂数据类型，
ArrayType、MapType、StructType-
ArrayTypeDemo
-
from pyspark.sql.types import *
def split_to_array(input_string):
word_list = input_string.split('|')
return word_list
spark.udf.register('split_to_array', split_to_array, ArrayType(StringType()))
spark.sql("""
select split_to_array('我| shi|真的')
""").show()
结果
+-------------------------+
|split_to_array(我| shi|真的)|
+-------------------------+
| [我, shi, 真的]|
+-------------------------+
-
MapTypeDemo
from pyspark.sql.types import *
def word_count(input_string):
word_dict = {}
word_list = input_string.split(' ')
for word in word_list:
word_dict[word] = 0
for word in word_list:
word_dict[word] += 1
return word_dict
spark.udf.register('word_count', word_count, MapType(StringType(), IntegerType()))
spark.sql("""
select word_count('this apple belong to big apple')
""").show(truncate=False)
结果
+----------------------------------------------------------+
|word_count(this apple belong to big apple) |
+----------------------------------------------------------+
|Map(this -> 1, big -> 1, belong -> 1, to -> 1, apple -> 2)|
+----------------------------------------------------------+
-
StructTypeDemo
from pyspark.sql.types import *
import hashlib
def string_to_struct(input_string):
my_dict={}
m = hashlib.md5()
m.update(input_string.encode('utf-8'))
my_dict['id'] = m.hexdigest()
my_dict['content'] = input_string
return my_dict
schema = StructType([
StructField("id", StringType(), True),
StructField("content", StringType(), True)
])
spark.udf.register('string_to_struct', string_to_struct, schema)
df = spark.sql("""
select string_to_struct('my name is hello world')
""")
df.show(truncate=False)
df.printSchema()
结果
+---------------------------------------------------------+
|string_to_struct(my name is hello world) |
+---------------------------------------------------------+
|[1e030e259e2c7759fb24572ac4d62d3f,my name is hello world]|
+---------------------------------------------------------+
root
|-- string_to_struct(my name is hello world): struct (nullable = true)
| |-- id: string (nullable = true)
| |-- content: string (nullable = true)
可以看出规律了吧，python中的类型要和自己定义的复杂类型对应起来。
此外，复杂数据类型支持嵌套，array中可以嵌套struct、map、array，其他同理。
