1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
|
#
# 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.
#
from pyspark import since
from pyspark.rdd import ignore_unicode_prefix
from pyspark.sql.column import Column, _to_seq, _to_java_column, _create_column_from_literal
from pyspark.sql.dataframe import DataFrame
from pyspark.sql.types import *
__all__ = ["GroupedData"]
def dfapi(f):
def _api(self):
name = f.__name__
jdf = getattr(self._jdf, name)()
return DataFrame(jdf, self.sql_ctx)
_api.__name__ = f.__name__
_api.__doc__ = f.__doc__
return _api
def df_varargs_api(f):
def _api(self, *args):
name = f.__name__
jdf = getattr(self._jdf, name)(_to_seq(self.sql_ctx._sc, args))
return DataFrame(jdf, self.sql_ctx)
_api.__name__ = f.__name__
_api.__doc__ = f.__doc__
return _api
class GroupedData(object):
"""
A set of methods for aggregations on a :class:`DataFrame`,
created by :func:`DataFrame.groupBy`.
.. note:: Experimental
.. versionadded:: 1.3
"""
def __init__(self, jdf, sql_ctx):
self._jdf = jdf
self.sql_ctx = sql_ctx
@ignore_unicode_prefix
@since(1.3)
def agg(self, *exprs):
"""Compute aggregates and returns the result as a :class:`DataFrame`.
The available aggregate functions are `avg`, `max`, `min`, `sum`, `count`.
If ``exprs`` is a single :class:`dict` mapping from string to string, then the key
is the column to perform aggregation on, and the value is the aggregate function.
Alternatively, ``exprs`` can also be a list of aggregate :class:`Column` expressions.
:param exprs: a dict mapping from column name (string) to aggregate functions (string),
or a list of :class:`Column`.
>>> gdf = df.groupBy(df.name)
>>> sorted(gdf.agg({"*": "count"}).collect())
[Row(name=u'Alice', count(1)=1), Row(name=u'Bob', count(1)=1)]
>>> from pyspark.sql import functions as F
>>> sorted(gdf.agg(F.min(df.age)).collect())
[Row(name=u'Alice', min(age)=2), Row(name=u'Bob', min(age)=5)]
"""
assert exprs, "exprs should not be empty"
if len(exprs) == 1 and isinstance(exprs[0], dict):
jdf = self._jdf.agg(exprs[0])
else:
# Columns
assert all(isinstance(c, Column) for c in exprs), "all exprs should be Column"
jdf = self._jdf.agg(exprs[0]._jc,
_to_seq(self.sql_ctx._sc, [c._jc for c in exprs[1:]]))
return DataFrame(jdf, self.sql_ctx)
@dfapi
@since(1.3)
def count(self):
"""Counts the number of records for each group.
>>> sorted(df.groupBy(df.age).count().collect())
[Row(age=2, count=1), Row(age=5, count=1)]
"""
@df_varargs_api
@since(1.3)
def mean(self, *cols):
"""Computes average values for each numeric columns for each group.
:func:`mean` is an alias for :func:`avg`.
:param cols: list of column names (string). Non-numeric columns are ignored.
>>> df.groupBy().mean('age').collect()
[Row(avg(age)=3.5)]
>>> df3.groupBy().mean('age', 'height').collect()
[Row(avg(age)=3.5, avg(height)=82.5)]
"""
@df_varargs_api
@since(1.3)
def avg(self, *cols):
"""Computes average values for each numeric columns for each group.
:func:`mean` is an alias for :func:`avg`.
:param cols: list of column names (string). Non-numeric columns are ignored.
>>> df.groupBy().avg('age').collect()
[Row(avg(age)=3.5)]
>>> df3.groupBy().avg('age', 'height').collect()
[Row(avg(age)=3.5, avg(height)=82.5)]
"""
@df_varargs_api
@since(1.3)
def max(self, *cols):
"""Computes the max value for each numeric columns for each group.
>>> df.groupBy().max('age').collect()
[Row(max(age)=5)]
>>> df3.groupBy().max('age', 'height').collect()
[Row(max(age)=5, max(height)=85)]
"""
@df_varargs_api
@since(1.3)
def min(self, *cols):
"""Computes the min value for each numeric column for each group.
:param cols: list of column names (string). Non-numeric columns are ignored.
>>> df.groupBy().min('age').collect()
[Row(min(age)=2)]
>>> df3.groupBy().min('age', 'height').collect()
[Row(min(age)=2, min(height)=80)]
"""
@df_varargs_api
@since(1.3)
def sum(self, *cols):
"""Compute the sum for each numeric columns for each group.
:param cols: list of column names (string). Non-numeric columns are ignored.
>>> df.groupBy().sum('age').collect()
[Row(sum(age)=7)]
>>> df3.groupBy().sum('age', 'height').collect()
[Row(sum(age)=7, sum(height)=165)]
"""
@since(1.6)
def pivot(self, pivot_col, values=None):
"""
Pivots a column of the current [[DataFrame]] and perform the specified aggregation.
There are two versions of pivot function: one that requires the caller to specify the list
of distinct values to pivot on, and one that does not. The latter is more concise but less
efficient, because Spark needs to first compute the list of distinct values internally.
:param pivot_col: Name of the column to pivot.
:param values: List of values that will be translated to columns in the output DataFrame.
// Compute the sum of earnings for each year by course with each course as a separate column
>>> df4.groupBy("year").pivot("course", ["dotNET", "Java"]).sum("earnings").collect()
[Row(year=2012, dotNET=15000, Java=20000), Row(year=2013, dotNET=48000, Java=30000)]
// Or without specifying column values (less efficient)
>>> df4.groupBy("year").pivot("course").sum("earnings").collect()
[Row(year=2012, Java=20000, dotNET=15000), Row(year=2013, Java=30000, dotNET=48000)]
"""
if values is None:
jgd = self._jdf.pivot(pivot_col)
else:
jgd = self._jdf.pivot(pivot_col, values)
return GroupedData(jgd, self.sql_ctx)
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)
if __name__ == "__main__":
_test()
|
