google-cloud-dataflow - 谷歌数据流中的 Pardo 函数不产生任何输出
问题描述
我正在尝试在数据流中创建我的第一个管道,当我使用交互式光束运行器执行时,我有相同的代码运行,但是在数据流上我得到了各种各样的错误,这对我来说没有多大意义。
{"timestamp":1589992571906,"lastPageVisited":"https://kickassdataprojects.com/simple-and-complete-tutorial-on-simple-linear-regression/","pageUrl":"https://kickassdataprojects.com/","pageTitle":"Helping%20companies%20and%20developers%20create%20awesome%20data%20projects%20%7C%20Data%20Engineering/%20Data%20Science%20Blog","eventType":"Pageview","landingPage":0,"referrer":"direct","uiud":"31af5f22-4cc4-48e0-9478-49787dd5a19f","sessionId":322371}
这是我的代码
from __future__ import absolute_import
import apache_beam as beam
#from apache_beam.runners.interactive import interactive_runner
#import apache_beam.runners.interactive.interactive_beam as ib
import google.auth
from datetime import timedelta
import json
from datetime import datetime
from apache_beam import window
from apache_beam.transforms.trigger import AfterWatermark, AfterProcessingTime, AccumulationMode, AfterCount
from apache_beam.options.pipeline_options import GoogleCloudOptions
from apache_beam.options.pipeline_options import PipelineOptions
from apache_beam.options.pipeline_options import SetupOptions
from apache_beam.options.pipeline_options import StandardOptions
import argparse
import logging
from time import mktime
def setTimestamp(elem):
from apache_beam import window
return window.TimestampedValue(elem, elem['timestamp'])
def createTuples(elem):
return (elem["sessionId"], elem)
def checkOutput(elem):
print(elem)
return elem
class WriteToBigQuery(beam.PTransform):
"""Generate, format, and write BigQuery table row information."""
def __init__(self, table_name, dataset, schema, project):
"""Initializes the transform.
Args:
table_name: Name of the BigQuery table to use.
dataset: Name of the dataset to use.
schema: Dictionary in the format {'column_name': 'bigquery_type'}
project: Name of the Cloud project containing BigQuery table.
"""
# TODO(BEAM-6158): Revert the workaround once we can pickle super() on py3.
#super(WriteToBigQuery, self).__init__()
beam.PTransform.__init__(self)
self.table_name = table_name
self.dataset = dataset
self.schema = schema
self.project = project
def get_schema(self):
"""Build the output table schema."""
return ', '.join('%s:%s' % (col, self.schema[col]) for col in self.schema)
def expand(self, pcoll):
return (
pcoll
| 'ConvertToRow' >>
beam.Map(lambda elem: {col: elem[col]
for col in self.schema})
| beam.io.WriteToBigQuery(
self.table_name, self.dataset, self.project, self.get_schema()))
class ParseSessionEventFn(beam.DoFn):
"""Parses the raw game event info into a Python dictionary.
Each event line has the following format:
username,teamname,score,timestamp_in_ms,readable_time
e.g.:
user2_AsparagusPig,AsparagusPig,10,1445230923951,2015-11-02 09:09:28.224
The human-readable time string is not used here.
"""
def __init__(self):
# TODO(BEAM-6158): Revert the workaround once we can pickle super() on py3.
#super(ParseSessionEventFn, self).__init__()
beam.DoFn.__init__(self)
def process(self, elem):
#timestamp = mktime(datetime.strptime(elem["timestamp"], "%Y-%m-%d %H:%M:%S").utctimetuple())
elem['sessionId'] = int(elem['sessionId'])
elem['landingPage'] = int(elem['landingPage'])
yield elem
class AnalyzeSessions(beam.DoFn):
def __init__(self):
# TODO(BEAM-6158): Revert the workaround once we can pickle super() on py3.
#super(AnalyzeSessions, self).__init__()
from apache_beam import window
beam.DoFn.__init__(self)
def process(self, elem, window=beam.DoFn.WindowParam):
from apache_beam import window
sessionId = elem[0]
uiud = elem[1][0]["uiud"]
count_of_events = 0
pageUrl = []
window_end = window.end.to_utc_datetime()
window_start = window.start.to_utc_datetime()
session_duration = window_end - window_start
for rows in elem[1]:
if rows["landingPage"] == 1:
referrer = rows["refererr"]
pageUrl.append(rows["pageUrl"])
print({
"pageUrl":pageUrl,
"eventType":"pageview",
"uiud":uiud,
"sessionId":sessionId,
"session_duration": session_duration,
"window_start" : window_start
})
yield {
'pageUrl':pageUrl,
'eventType':"pageview",
'uiud':uiud,
'sessionId':sessionId,
'session_duration': session_duration,
'window_start' : window_start,
}
def run(argv=None, save_main_session=True):
parser = argparse.ArgumentParser()
parser.add_argument('--topic', type=str, help='Pub/Sub topic to read from')
parser.add_argument(
'--subscription', type=str, help='Pub/Sub subscription to read from')
parser.add_argument(
'--dataset',
type=str,
required=True,
help='BigQuery Dataset to write tables to. '
'Must already exist.')
parser.add_argument(
'--table_name',
type=str,
default='game_stats',
help='The BigQuery table name. Should not already exist.')
parser.add_argument(
'--fixed_window_duration',
type=int,
default=60,
help='Numeric value of fixed window duration for user '
'analysis, in minutes')
parser.add_argument(
'--session_gap',
type=int,
default=5,
help='Numeric value of gap between user sessions, '
'in minutes')
parser.add_argument(
'--user_activity_window_duration',
type=int,
default=30,
help='Numeric value of fixed window for finding mean of '
'user session duration, in minutes')
args, pipeline_args = parser.parse_known_args(argv)
session_gap = args.session_gap * 60
options = PipelineOptions(pipeline_args)
# Set the pipeline mode to stream the data from Pub/Sub.
options.view_as(StandardOptions).streaming = True
options.view_as( StandardOptions).runner= 'DataflowRunner'
options.view_as(SetupOptions).save_main_session = save_main_session
p = beam.Pipeline(options=options)
lines = (p
| beam.io.ReadFromPubSub(
subscription="projects/phrasal-bond-274216/subscriptions/rrrr")
| 'decode' >> beam.Map(lambda x: x.decode('utf-8'))
| beam.Map(lambda x: json.loads(x))
| beam.ParDo(ParseSessionEventFn())
)
next = ( lines
| 'AddEventTimestamps' >> beam.Map(setTimestamp)
| 'Create Tuples' >> beam.Map(createTuples)
| 'Window' >> beam.WindowInto(window.Sessions(15))
| 'group by key' >> beam.GroupByKey()
| 'analyze sessions' >> beam.ParDo(AnalyzeSessions())
| beam.Map(print)
| 'WriteTeamScoreSums' >> WriteToBigQuery(
args.table_name, args.dataset,
{
"uiud":'STRING',
"session_duration": 'INTEGER',
"window_start" : 'TIMESTAMP'
},
options.view_as(GoogleCloudOptions).project)
)
result = p.run()
# result.wait_till_termination()
if __name__ == '__main__':
logging.getLogger().setLevel(logging.INFO)
run()
我面临的问题是AnalyzeSessions Pardo 函数不会产生任何输出或任何错误。我已经在交互式光束运行器中尝试过这段代码,它已经奏效了。
任何想法为什么管道不工作?
包括分析会话步骤在内的所有其他步骤都有输入
这是输出部分。
在此之后的步骤不起作用,我也没有在日志中看到任何内容,也不是打印语句在那里添加了一些东西。
编辑:如果有帮助的话,我的数据如何进入 WindoInto 和 GroupBy 关键步骤。
解决方案
我只使用了带有 Java SDK 的 Beam,但处理函数通常不会返回。它调用 Beam 提供的回调来输出结果。这样您就可以获取一个输入并返回任意数量的输出。
在您的示例中,AnalyzeSessions#process
有一个return
声明。查看 Beam 示例,我看到了 DoFn 函数中的一个语句yield
。process
试试yield
?那是 Python 版本的输出回调吗?
https://beam.apache.org/get-started/wordcount-example/#specifying-explicit-dofns
推荐阅读
- python - Google Domains API“HttpAccessTokenRefreshError:未授权客户端:客户端未经授权无法使用此方法检索访问令牌。”
- excel - “HomeKey Unit:=wdStory”上的 Excel 错误“对象不支持此属性或方法”
- javascript - 我无法正确使用 setState 来更改值
- java - 为什么 String.equals() 在底层不使用 hashCode() 相等检查?
- python - Wagtail:搜索结果页面上的页面内容?
- sql - 是否可以在 FOREIGN KEY 的子表中插入行?
- r - 将来自多个回归模型的输出和测试结果合并到一个 csv 文件中
- c++ - 获取 C2760 语法错误:意外标记“int”,std::max 的预期“表达式”
(...) - python-3.x - 加入后如何使不和谐机器人离开服务器
- html - 移除水平滚动条