python - 使用 Cloud Functions 和 Cloud Scheduler 创建到 BigQuery 的数据管道

Question

我正在尝试构建一个数据管道，该管道将从该网站下载数据并将其推送到 BigQuery 表。

def OH_Data_Pipeline(trigger='Yes'):
    if trigger=='Yes':
        import pandas as pd
        import pandas_gbq
        import datetime
        schema=[{'name': 'SOS_VOTERID', 'type': 'STRING'},{'name': 'COUNTY_NUMBER', 'type': 'STRING'}, {'name': 'COUNTY_ID', 'type': 'INT64'}, {'name': 'LAST_NAME', 'type': 'STRING'}, {'name': 'FIRST_NAME', 'type': 'STRING'}, {'name': 'MIDDLE_NAME', 'type': 'STRING'}, {'name': 'SUFFIX', 'type': 'STRING'}, {'name': 'DATE_OF_BIRTH', 'type': 'DATE'}, 
            {'name': 'REGISTRATION_DATE', 'type': 'DATE'}, {'name': 'VOTER_STATUS', 'type': 'STRING'}, 
            {'name': 'PARTY_AFFILIATION', 'type': 'STRING'}, {'name': 'RESIDENTIAL_ADDRESS1', 'type': 'STRING'}, 
            {'name': 'RESIDENTIAL_SECONDARY_ADDR', 'type': 'STRING'}, {'name': 'RESIDENTIAL_CITY', 'type': 'STRING'}, 
            {'name': 'RESIDENTIAL_STATE', 'type': 'STRING'}, {'name': 'RESIDENTIAL_ZIP', 'type': 'STRING'}, 
            {'name': 'RESIDENTIAL_ZIP_PLUS4', 'type': 'STRING'}, {'name': 'RESIDENTIAL_COUNTRY', 'type': 'STRING'}, 
            {'name': 'RESIDENTIAL_POSTALCODE', 'type': 'STRING'}, {'name': 'MAILING_ADDRESS1', 'type': 'STRING'}, 
            {'name': 'MAILING_SECONDARY_ADDRESS', 'type': 'STRING'}, {'name': 'MAILING_CITY', 'type': 'STRING'}, 
            {'name': 'MAILING_STATE', 'type': 'STRING'}, {'name': 'MAILING_ZIP', 'type': 'STRING'}, 
            {'name': 'MAILING_ZIP_PLUS4', 'type': 'STRING'}, {'name': 'MAILING_COUNTRY', 'type': 'STRING'}, 
            {'name': 'MAILING_POSTAL_CODE', 'type': 'STRING'}, {'name': 'CAREER_CENTER', 'type': 'STRING'}, 
            {'name': 'CITY', 'type': 'STRING'}, {'name': 'CITY_SCHOOL_DISTRICT', 'type': 'STRING'}, 
            {'name': 'COUNTY_COURT_DISTRICT', 'type': 'STRING'}, {'name': 'CONGRESSIONAL_DISTRICT', 'type': 'STRING'}, 
            {'name': 'COURT_OF_APPEALS', 'type': 'STRING'}, {'name': 'EDU_SERVICE_CENTER_DISTRICT', 'type': 'STRING'}, 
            {'name': 'EXEMPTED_VILL_SCHOOL_DISTRICT', 'type': 'STRING'}, {'name': 'LIBRARY', 'type': 'STRING'}, 
            {'name': 'LOCAL_SCHOOL_DISTRICT', 'type': 'STRING'}, {'name': 'MUNICIPAL_COURT_DISTRICT', 'type': 'STRING'}, 
            {'name': 'PRECINCT_NAME', 'type': 'STRING'}, {'name': 'PRECINCT_CODE', 'type': 'STRING'}, 
            {'name': 'STATE_BOARD_OF_EDUCATION', 'type': 'STRING'}, {'name': 'STATE_REPRESENTATIVE_DISTRICT', 'type': 'STRING'}, 
            {'name': 'STATE_SENATE_DISTRICT', 'type': 'STRING'}, {'name': 'TOWNSHIP', 'type': 'STRING'}, 
            {'name': 'VILLAGE', 'type': 'STRING'}, {'name': 'WARD', 'type': 'STRING'}, 
            {'name': 'PRIMARY_03_07_2000', 'type': 'STRING'}, {'name': 'GENERAL_11_07_2000', 'type': 'INT64'}, 
            {'name': 'SPECIAL_05_08_2001', 'type': 'STRING'}, {'name': 'GENERAL_11_06_2001', 'type': 'INT64'}, 
            {'name': 'PRIMARY_05_07_2002', 'type': 'STRING'}, {'name': 'GENERAL_11_05_2002', 'type': 'INT64'}, 
            {'name': 'SPECIAL_05_06_2003', 'type': 'STRING'}, {'name': 'GENERAL_11_04_2003', 'type': 'INT64'}, 
            {'name': 'PRIMARY_03_02_2004', 'type': 'STRING'}, {'name': 'GENERAL_11_02_2004', 'type': 'INT64'}, 
            {'name': 'SPECIAL_02_08_2005', 'type': 'STRING'}, {'name': 'PRIMARY_05_03_2005', 'type': 'STRING'}, 
            {'name': 'PRIMARY_09_13_2005', 'type': 'STRING'}, {'name': 'GENERAL_11_08_2005', 'type': 'INT64'}, 
            {'name': 'SPECIAL_02_07_2006', 'type': 'STRING'}, {'name': 'PRIMARY_05_02_2006', 'type': 'STRING'}, 
            {'name': 'GENERAL_11_07_2006', 'type': 'INT64'}, {'name': 'PRIMARY_05_08_2007', 'type': 'STRING'}, 
            {'name': 'PRIMARY_09_11_2007', 'type': 'STRING'}, {'name': 'GENERAL_11_06_2007', 'type': 'INT64'}, 
            {'name': 'PRIMARY_11_06_2007', 'type': 'STRING'}, {'name': 'GENERAL_12_11_2007', 'type': 'INT64'}, 
            {'name': 'PRIMARY_03_04_2008', 'type': 'STRING'}, {'name': 'PRIMARY_10_14_2008', 'type': 'STRING'}, 
            {'name': 'GENERAL_11_04_2008', 'type': 'INT64'}, {'name': 'GENERAL_11_18_2008', 'type': 'INT64'}, 
            {'name': 'PRIMARY_05_05_2009', 'type': 'STRING'}, {'name': 'PRIMARY_09_08_2009', 'type': 'STRING'}, 
            {'name': 'PRIMARY_09_15_2009', 'type': 'STRING'}, {'name': 'PRIMARY_09_29_2009', 'type': 'STRING'}, 
            {'name': 'GENERAL_11_03_2009', 'type': 'INT64'}, {'name': 'PRIMARY_05_04_2010', 'type': 'STRING'}, 
            {'name': 'PRIMARY_07_13_2010', 'type': 'STRING'}, {'name': 'PRIMARY_09_07_2010', 'type': 'STRING'}, 
            {'name': 'GENERAL_11_02_2010', 'type': 'INT64'}, {'name': 'PRIMARY_05_03_2011', 'type': 'STRING'}, 
            {'name': 'PRIMARY_09_13_2011', 'type': 'STRING'}, {'name': 'GENERAL_11_08_2011', 'type': 'INT64'}, 
            {'name': 'PRIMARY_03_06_2012', 'type': 'STRING'}, {'name': 'GENERAL_11_06_2012', 'type': 'INT64'}, 
            {'name': 'PRIMARY_05_07_2013', 'type': 'STRING'}, {'name': 'PRIMARY_09_10_2013', 'type': 'STRING'}, 
            {'name': 'PRIMARY_10_01_2013', 'type': 'STRING'}, {'name': 'GENERAL_11_05_2013', 'type': 'INT64'}, 
            {'name': 'PRIMARY_05_06_2014', 'type': 'STRING'}, {'name': 'GENERAL_11_04_2014', 'type': 'INT64'}, 
            {'name': 'PRIMARY_05_05_2015', 'type': 'STRING'}, {'name': 'PRIMARY_09_15_2015', 'type': 'STRING'}, 
            {'name': 'GENERAL_11_03_2015', 'type': 'INT64'}, {'name': 'PRIMARY_03_15_2016', 'type': 'STRING'}, 
            {'name': 'GENERAL_06_07_2016', 'type': 'INT64'}, {'name': 'PRIMARY_09_13_2016', 'type': 'STRING'}, 
            {'name': 'GENERAL_11_08_2016', 'type': 'INT64'}, {'name': 'PRIMARY_05_02_2017', 'type': 'STRING'}, 
            {'name': 'PRIMARY_09_12_2017', 'type': 'STRING'}, {'name': 'GENERAL_11_07_2017', 'type': 'INT64'}, 
            {'name': 'PRIMARY_05_08_2018', 'type': 'STRING'}, {'name': 'GENERAL_08_07_2018', 'type': 'INT64'}, 
            {'name': 'GENERAL_11_06_2018', 'type': 'INT64'}, {'name': 'PRIMARY_05_07_2019', 'type': 'STRING'}, 
            {'name': 'PRIMARY_09_10_2019', 'type': 'STRING'}, {'name': 'GENERAL_11_05_2019', 'type': 'INT64'}]
        prim_list = ['PRIMARY-03/07/2000', 'SPECIAL-05/08/2001', 'PRIMARY-05/07/2002', 'SPECIAL-05/06/2003', 'PRIMARY-03/02/2004', 
                'SPECIAL-02/08/2005', 'PRIMARY-05/03/2005', 'PRIMARY-09/13/2005', 'SPECIAL-02/07/2006', 'PRIMARY-05/02/2006', 
                'PRIMARY-05/08/2007', 'PRIMARY-09/11/2007', 'PRIMARY-11/06/2007', 'PRIMARY-03/04/2008', 'PRIMARY-10/14/2008', 
                'PRIMARY-05/05/2009', 'PRIMARY-09/08/2009', 'PRIMARY-09/15/2009', 'PRIMARY-09/29/2009', 'PRIMARY-05/04/2010', 
                'PRIMARY-07/13/2010', 'PRIMARY-09/07/2010', 'PRIMARY-05/03/2011', 'PRIMARY-09/13/2011', 'PRIMARY-03/06/2012', 
                'PRIMARY-05/07/2013', 'PRIMARY-09/10/2013', 'PRIMARY-10/01/2013', 'PRIMARY-05/06/2014', 'PRIMARY-05/05/2015', 
                'PRIMARY-09/15/2015', 'PRIMARY-03/15/2016', 'PRIMARY-09/13/2016', 'PRIMARY-05/02/2017', 'PRIMARY-09/12/2017', 
                'PRIMARY-05/08/2018', 'PRIMARY-05/07/2019', 'PRIMARY-09/10/2019']
        prim_list = [f.replace('-', '_').replace('/', '_') for f in prim_list]
        gen_list = ['GENERAL-11/07/2000', 'GENERAL-11/06/2001', 'GENERAL-11/05/2002', 'GENERAL-11/04/2003', 'GENERAL-11/02/2004', 
               'GENERAL-11/08/2005', 'GENERAL-11/07/2006', 'GENERAL-11/06/2007', 'GENERAL-12/11/2007', 'GENERAL-11/04/2008', 
               'GENERAL-11/18/2008', 'GENERAL-11/03/2009', 'GENERAL-11/02/2010', 'GENERAL-11/08/2011', 'GENERAL-11/06/2012', 
               'GENERAL-11/05/2013', 'GENERAL-11/04/2014', 'GENERAL-11/03/2015', 'GENERAL-06/07/2016', 'GENERAL-11/08/2016', 
               'GENERAL-11/07/2017', 'GENERAL-08/07/2018', 'GENERAL-11/06/2018', 'GENERAL-11/05/2019']
        gen_list = [f.replace('-', '_').replace('/', '_') for f in gen_list]
        party_list = ['PARTY_AFFILIATION']
        df=[pd.read_csv('https://www6.sos.state.oh.us/ords/f?p=VOTERFTP:DOWNLOAD::FILE:NO:2:P2_PRODUCT_NUMBER:{}'.format(88+f), encoding='Latin1', low_memory=False) for f in range(1, 17)]
        df=pd.concat(df)
        df.columns = [f.replace('-', '_').replace('/', '_') for f in df.columns]
        df['birth_year'] = df['DATE_OF_BIRTH'].map(lambda x: str(x)[:-6]).astype(int)
        df['Age'] = now.year - df['birth_year']
        for f in prim_list:
            df.loc[df[f]=='D', f]='Democrat'
            df.loc[df[f]=='R', f]='Republican'
            df.loc[df[f]=='G', f]='Green'
            df.loc[df[f]=='E', f]='Reform'
            df.loc[df[f]=='L', f]='Libertarian'
            df.loc[df[f]=='C', f]='Constitution'
            df.loc[df[f]=='N', f]='Natural Law'
            df.loc[df[f]=='S', f]='Socialist'
            df.loc[df[f]=='X', f]='Without Affiliation'
            df.loc[(df[f]=='') | (df[f].isnull()==True) | (df[f]==0), f]='Not Voted'
        for f in party_list:
            df.loc[df[f]=='D', f]='Democrat'
            df.loc[df[f]=='R', f]='Republican'
            df.loc[df[f]=='G', f]='Green'
            df.loc[df[f]=='E', f]='Reform'
            df.loc[df[f]=='L', f]='Libertarian'
            df.loc[df[f]=='C', f]='Constitution'
            df.loc[df[f]=='N', f]='Natural Law'
            df.loc[df[f]=='S', f]='Socialist'
            df.loc[df[f]=='X', f]='Unaffiliated'
            df.loc[(df[f]=='') | (df[f].isnull()==True) | (df[f]==0), f]='Unaffiliated'
        for g in gen_list:  
            df.loc[(df[g]!='') & (df[g].isnull()!=True) & (df[g]!=0) & (df[g]!='NaN'), g]=1
            df.loc[(df[g]=='') | (df[g].isnull()==True) | (df[g]==0) | (df[g]=='NaN'), g]=0
        df[gen_list]=df[gen_list].astype(int)
        df[prim_list]=df[prim_list].astype(str)
        df[party_list]=df[party_list].astype(str)
        df.to_gbq(destination_table='Voterfile.OH_Voterfile', project_id='oh-data-pipeline', if_exists='replace', table_schema=schema, reauth=False)
    else:
        pass

问题是在云函数中定义函数后，我将在云调度程序中运行脚本，它会说函数已运行，但 BigQuery 中不会显示任何数据。

以下是日志：[ { "insertId": "1idtfdbg5drzu63", "jsonPayload": { "targetType": "HTTP", "url": "https://us-central1-oh-data-pipeline.cloudfunctions.net/OH_Data_Pipeline", "@type": "type.googleapis.com/google.cloud.scheduler.logging.AttemptFinished", "jobName": "projects/oh-data-pipeline/locations/us-east4/jobs/OH_Voterfile_Data_Loader" }, "httpRequest": { "status": 200 }, "resource": { "type": "cloud_scheduler_job", "labels": { "project_id": "oh-data-pipeline", "location": "us-east4", "job_id": "OH_Voterfile_Data_Loader" } }, "timestamp": "2020-01-01T21:12:39.949108697Z", "severity": "INFO", "logName": "projects/oh-data-pipeline/logs/cloudscheduler.googleapis.com%2Fexecutions", "receiveTimestamp": "2020-01-01T21:12:39.949108697Z" }, { "insertId": "k9f9cjg5ds4bft", "jsonPayload": { "jobName": "projects/oh-data-pipeline/locations/us-east4/jobs/OH_Voterfile_Data_Loader", "targetType": "HTTP", "url": "https://us-central1-oh-data-pipeline.cloudfunctions.net/OH_Data_Pipeline", "@type": "type.googleapis.com/google.cloud.scheduler.logging.AttemptStarted", "scheduledTime": "2020-01-06T05:00:00.271618Z" }, "resource": { "type": "cloud_scheduler_job", "labels": { "job_id": "OH_Voterfile_Data_Loader", "project_id": "oh-data-pipeline", "location": "us-east4" } }, "timestamp": "2020-01-01T21:12:39.823311702Z", "severity": "INFO", "logName": "projects/oh-data-pipeline/logs/cloudscheduler.googleapis.com%2Fexecutions", "receiveTimestamp": "2020-01-01T21:12:39.823311702Z" }, { "insertId": "1xnnrrug5g0c2qj", "jsonPayload": { "targetType": "HTTP", "url": "https://us-central1-oh-data-pipeline.cloudfunctions.net/OH_Data_Pipeline", "@type": "type.googleapis.com/google.cloud.scheduler.logging.AttemptFinished", "jobName": "projects/oh-data-pipeline/locations/us-east4/jobs/OH_Voterfile_Data_Loader" }, "httpRequest": { "status": 200 }, "resource": { "type": "cloud_scheduler_job", "labels": { "job_id": "OH_Voterfile_Data_Loader", "project_id": "oh-data-pipeline", "location": "us-east4" } }, "timestamp": "2020-01-01T21:12:37.290359769Z", "severity": "INFO", "logName": "projects/oh-data-pipeline/logs/cloudscheduler.googleapis.com%2Fexecutions", "receiveTimestamp": "2020-01-01T21:12:37.290359769Z" }, { "insertId": "sv8ssdg5e3blni", "jsonPayload": { "targetType": "HTTP", "url": "https://us-central1-oh-data-pipeline.cloudfunctions.net/OH_Data_Pipeline", "@type": "type.googleapis.com/google.cloud.scheduler.logging.AttemptStarted", "scheduledTime": "2020-01-06T05:00:00.183767Z", "jobName": "projects/oh-data-pipeline/locations/us-east4/jobs/OH_Voterfile_Data_Loader" }, "resource": { "type": "cloud_scheduler_job", "labels": { "job_id": "OH_Voterfile_Data_Loader", "project_id": "oh-data-pipeline", "location": "us-east4" } }, "timestamp": "2020-01-01T21:12:36.916739031Z", "severity": "INFO", "logName": "projects/oh-data-pipeline/logs/cloudscheduler.googleapis.com%2Fexecutions", "receiveTimestamp": "2020-01-01T21:12:36.916739031Z" }, { "insertId": "7i1kgtfutdv2s", "jsonPayload": { "jobName": "projects/oh-data-pipeline/locations/us-east4/jobs/OH_Voterfile_Data_Loader", "targetType": "HTTP", "url": "https://us-central1-oh-data-pipeline.cloudfunctions.net/OH_Data_Pipeline", "@type": "type.googleapis.com/google.cloud.scheduler.logging.AttemptFinished" }, "httpRequest": { "status": 200 }, "resource": { "type": "cloud_scheduler_job", "labels": { "project_id": "oh-data-pipeline", "location": "us-east4", "job_id": "OH_Voterfile_Data_Loader" } }, "timestamp": "2020-01-01T19:37:07.201347795Z", "severity": "INFO", "logName": "projects/oh-data-pipeline/logs/cloudscheduler.googleapis.com%2Fexecutions", "receiveTimestamp": "2020-01-01T19:37:07.201347795Z" }, { "insertId": "19io9oog5fvqy42", "jsonPayload": { "@type": "type.googleapis.com/google.cloud.scheduler.logging.AttemptStarted", "scheduledTime": "2020-01-06T05:00:00Z", "jobName": "projects/oh-data-pipeline/locations/us-east4/jobs/OH_Voterfile_Data_Loader", "targetType": "HTTP", "url": "https://us-central1-oh-data-pipeline.cloudfunctions.net/OH_Data_Pipeline" }, "resource": { "type": "cloud_scheduler_job", "labels": { "location": "us-east4", "job_id": "OH_Voterfile_Data_Loader", "project_id": "oh-data-pipeline" } }, "timestamp": "2020-01-01T19:37:07.092810676Z", "severity": "INFO", "logName": "projects/oh-data-pipeline/logs/cloudscheduler.googleapis.com%2Fexecutions", "receiveTimestamp": "2020-01-01T19:37:07.092810676Z" }, { "insertId": "1t7pz9vg5e70eo5", "jsonPayload": { "jobName": "projects/oh-data-pipeline/locations/us-east4/jobs/OH_Voterfile_Data_Loader", "targetType": "HTTP", "url": "https://us-central1-oh-data-pipeline.cloudfunctions.net/OH_Data_Pipeline", "@type": "type.googleapis.com/google.cloud.scheduler.logging.AttemptFinished" }, "httpRequest": { "status": 200 }, "resource": { "type": "cloud_scheduler_job", "labels": { "job_id": "OH_Voterfile_Data_Loader", "project_id": "oh-data-pipeline", "location": "us-east4" } }, "timestamp": "2020-01-01T17:30:00.396767720Z", "severity": "INFO", "logName": "projects/oh-data-pipeline/logs/cloudscheduler.googleapis.com%2Fexecutions", "receiveTimestamp": "2020-01-01T17:30:00.396767720Z" }, { "insertId": "1p23vr0g59sba7d", "jsonPayload": { "targetType": "HTTP", "url": "https://us-central1-oh-data-pipeline.cloudfunctions.net/OH_Data_Pipeline", "@type": "type.googleapis.com/google.cloud.scheduler.logging.AttemptStarted", "scheduledTime": "2020-01-01T17:30:00.250018Z", "jobName": "projects/oh-data-pipeline/locations/us-east4/jobs/OH_Voterfile_Data_Loader" }, "resource": { "type": "cloud_scheduler_job", "labels": { "location": "us-east4", "job_id": "OH_Voterfile_Data_Loader", "project_id": "oh-data-pipeline" } }, "timestamp": "2020-01-01T17:30:00.267802278Z", "severity": "INFO", "logName": "projects/oh-data-pipeline/logs/cloudscheduler.googleapis.com%2Fexecutions", "receiveTimestamp": "2020-01-01T17:30:00.267802278Z" }, { "insertId": "1yi5eng4p1lgiq", "jsonPayload": { "@type": "type.googleapis.com/google.cloud.scheduler.logging.AttemptFinished", "jobName": "projects/oh-data-pipeline/locations/us-east4/jobs/OH_Voterfile_Data_Loader", "targetType": "HTTP", "url": "https://us-central1-oh-data-pipeline.cloudfunctions.net/OH_Data_Pipeline" }, "httpRequest": { "status": 200 }, "resource": { "type": "cloud_scheduler_job", "labels": { "job_id": "OH_Voterfile_Data_Loader", "project_id": "oh-data-pipeline", "location": "us-east4" } }, "timestamp": "2020-01-01T17:26:15.268636308Z", "severity": "INFO", "logName": "projects/oh-data-pipeline/logs/cloudscheduler.googleapis.com%2Fexecutions", "receiveTimestamp": "2020-01-01T17:26:15.268636308Z" }, { "insertId": "1u1dz02g41np17v", "jsonPayload": { "jobName": "projects/oh-data-pipeline/locations/us-east4/jobs/OH_Voterfile_Data_Loader", "targetType": "HTTP", "url": "https://us-central1-oh-data-pipeline.cloudfunctions.net/OH_Data_Pipeline", "@type": "type.googleapis.com/google.cloud.scheduler.logging.AttemptStarted", "scheduledTime": "2020-01-01T17:30:00.369545Z" }, "resource": { "type": "cloud_scheduler_job", "labels": { "job_id": "OH_Voterfile_Data_Loader", "project_id": "oh-data-pipeline", "location": "us-east4" } }, "timestamp": "2020-01-01T17:26:15.133041426Z", "severity": "INFO", "logName": "projects/oh-data-pipeline/logs/cloudscheduler.googleapis.com%2Fexecutions", "receiveTimestamp": "2020-01-01T17:26:15.133041426Z" }, { "insertId": "1gzxg1lg4qi1i28", "jsonPayload": { "@type": "type.googleapis.com/google.cloud.scheduler.logging.AttemptFinished", "jobName": "projects/oh-data-pipeline/locations/us-east4/jobs/OH_Voterfile_Data_Loader", "targetType": "HTTP", "url": "https://us-central1-oh-data-pipeline.cloudfunctions.net/OH_Data_Pipeline" }, "httpRequest": { "status": 200 }, "resource": { "type": "cloud_scheduler_job", "labels": { "job_id": "OH_Voterfile_Data_Loader", "project_id": "oh-data-pipeline", "location": "us-east4" } }, "timestamp": "2020-01-01T17:22:41.388248918Z", "severity": "INFO", "logName": "projects/oh-data-pipeline/logs/cloudscheduler.googleapis.com%2Fexecutions", "receiveTimestamp": "2020-01-01T17:22:41.388248918Z" }, { "insertId": "1es7ag9g5bdguh5", "jsonPayload": { "targetType": "HTTP", "url": "https://us-central1-oh-data-pipeline.cloudfunctions.net/OH_Data_Pipeline", "@type": "type.googleapis.com/google.cloud.scheduler.logging.AttemptStarted", "scheduledTime": "2020-01-01T17:30:00.257483Z", "jobName": "projects/oh-data-pipeline/locations/us-east4/jobs/OH_Voterfile_Data_Loader" }, "resource": { "type": "cloud_scheduler_job", "labels": { "project_id": "oh-data-pipeline", "location": "us-east4", "job_id": "OH_Voterfile_Data_Loader" } }, "timestamp": "2020-01-01T17:22:41.268121872Z", "severity": "INFO", "logName": "projects/oh-data-pipeline/logs/cloudscheduler.googleapis.com%2Fexecutions", "receiveTimestamp": "2020-01-01T17:22:41.268121872Z" } ]

你能帮我弄清楚为什么这不起作用吗？

score 0 · Accepted Answer

当我测试您的代码时，我收到以下错误消息：OH_Data_Pipeline() takes from 0 to 1 positional arguments but 2 were given

您应该修改您的函数定义以遵循示例代码（我不确定trigger它的用途，所以现在我只是将它硬编码为'Yes'）：

def OH_Data_Pipeline(event, context):
    trigger='Yes'
    ...

此外，请确保您有一个requirements.txt文件并且它指定了正确的库：

pandas
pandas_gbq
datetime

在所有这些更改之后，我收到此错误：

Error: function terminated. Recommended action: inspect logs for termination reason. Details:
<urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed: unable to get local issuer certificate (_ssl.c:1051)>

您尝试访问的域的 SSL 证书似乎存在问题。尽管存在证书方面的问题，您仍需要尝试read_csv()使用该域以允许使用该域。

score 0 · Accepted Answer

我稍微更改了您的代码以在我的机器和 Cloud Functions 中运行。

def main(arg):
    import pandas as pd
    import pandas_gbq
    import datetime, io, requests
    from google.oauth2 import service_account
    schema=[{'name': 'SOS_VOTERID', 'type': 'STRING'},{'name': 'COUNTY_NUMBER', 'type': 'STRING'}, {'name': 'COUNTY_ID', 'type': 'INT64'}, {'name': 'LAST_NAME', 'type': 'STRING'}, {'name': 'FIRST_NAME', 'type': 'STRING'}, {'name': 'MIDDLE_NAME', 'type': 'STRING'}, {'name': 'SUFFIX', 'type': 'STRING'}, {'name': 'DATE_OF_BIRTH', 'type': 'DATE'}, 
        {'name': 'REGISTRATION_DATE', 'type': 'DATE'}, {'name': 'VOTER_STATUS', 'type': 'STRING'}, 
        {'name': 'PARTY_AFFILIATION', 'type': 'STRING'}, {'name': 'RESIDENTIAL_ADDRESS1', 'type': 'STRING'}, 
        {'name': 'RESIDENTIAL_SECONDARY_ADDR', 'type': 'STRING'}, {'name': 'RESIDENTIAL_CITY', 'type': 'STRING'}, 
        {'name': 'RESIDENTIAL_STATE', 'type': 'STRING'}, {'name': 'RESIDENTIAL_ZIP', 'type': 'STRING'}, 
        {'name': 'RESIDENTIAL_ZIP_PLUS4', 'type': 'STRING'}, {'name': 'RESIDENTIAL_COUNTRY', 'type': 'STRING'}, 
        {'name': 'RESIDENTIAL_POSTALCODE', 'type': 'STRING'}, {'name': 'MAILING_ADDRESS1', 'type': 'STRING'}, 
        {'name': 'MAILING_SECONDARY_ADDRESS', 'type': 'STRING'}, {'name': 'MAILING_CITY', 'type': 'STRING'}, 
        {'name': 'MAILING_STATE', 'type': 'STRING'}, {'name': 'MAILING_ZIP', 'type': 'STRING'}, 
        {'name': 'MAILING_ZIP_PLUS4', 'type': 'STRING'}, {'name': 'MAILING_COUNTRY', 'type': 'STRING'}, 
        {'name': 'MAILING_POSTAL_CODE', 'type': 'STRING'}, {'name': 'CAREER_CENTER', 'type': 'STRING'}, 
        {'name': 'CITY', 'type': 'STRING'}, {'name': 'CITY_SCHOOL_DISTRICT', 'type': 'STRING'}, 
        {'name': 'COUNTY_COURT_DISTRICT', 'type': 'STRING'}, {'name': 'CONGRESSIONAL_DISTRICT', 'type': 'STRING'}, 
        {'name': 'COURT_OF_APPEALS', 'type': 'STRING'}, {'name': 'EDU_SERVICE_CENTER_DISTRICT', 'type': 'STRING'}, 
        {'name': 'EXEMPTED_VILL_SCHOOL_DISTRICT', 'type': 'STRING'}, {'name': 'LIBRARY', 'type': 'STRING'}, 
        {'name': 'LOCAL_SCHOOL_DISTRICT', 'type': 'STRING'}, {'name': 'MUNICIPAL_COURT_DISTRICT', 'type': 'STRING'}, 
        {'name': 'PRECINCT_NAME', 'type': 'STRING'}, {'name': 'PRECINCT_CODE', 'type': 'STRING'}, 
        {'name': 'STATE_BOARD_OF_EDUCATION', 'type': 'STRING'}, {'name': 'STATE_REPRESENTATIVE_DISTRICT', 'type': 'STRING'}, 
        {'name': 'STATE_SENATE_DISTRICT', 'type': 'STRING'}, {'name': 'TOWNSHIP', 'type': 'STRING'}, 
        {'name': 'VILLAGE', 'type': 'STRING'}, {'name': 'WARD', 'type': 'STRING'}, 
        {'name': 'PRIMARY_03_07_2000', 'type': 'STRING'}, {'name': 'GENERAL_11_07_2000', 'type': 'INT64'}, 
        {'name': 'SPECIAL_05_08_2001', 'type': 'STRING'}, {'name': 'GENERAL_11_06_2001', 'type': 'INT64'}, 
        {'name': 'PRIMARY_05_07_2002', 'type': 'STRING'}, {'name': 'GENERAL_11_05_2002', 'type': 'INT64'}, 
        {'name': 'SPECIAL_05_06_2003', 'type': 'STRING'}, {'name': 'GENERAL_11_04_2003', 'type': 'INT64'}, 
        {'name': 'PRIMARY_03_02_2004', 'type': 'STRING'}, {'name': 'GENERAL_11_02_2004', 'type': 'INT64'}, 
        {'name': 'SPECIAL_02_08_2005', 'type': 'STRING'}, {'name': 'PRIMARY_05_03_2005', 'type': 'STRING'}, 
        {'name': 'PRIMARY_09_13_2005', 'type': 'STRING'}, {'name': 'GENERAL_11_08_2005', 'type': 'INT64'}, 
        {'name': 'SPECIAL_02_07_2006', 'type': 'STRING'}, {'name': 'PRIMARY_05_02_2006', 'type': 'STRING'}, 
        {'name': 'GENERAL_11_07_2006', 'type': 'INT64'}, {'name': 'PRIMARY_05_08_2007', 'type': 'STRING'}, 
        {'name': 'PRIMARY_09_11_2007', 'type': 'STRING'}, {'name': 'GENERAL_11_06_2007', 'type': 'INT64'}, 
        {'name': 'PRIMARY_11_06_2007', 'type': 'STRING'}, {'name': 'GENERAL_12_11_2007', 'type': 'INT64'}, 
        {'name': 'PRIMARY_03_04_2008', 'type': 'STRING'}, {'name': 'PRIMARY_10_14_2008', 'type': 'STRING'}, 
        {'name': 'GENERAL_11_04_2008', 'type': 'INT64'}, {'name': 'GENERAL_11_18_2008', 'type': 'INT64'}, 
        {'name': 'PRIMARY_05_05_2009', 'type': 'STRING'}, {'name': 'PRIMARY_09_08_2009', 'type': 'STRING'}, 
        {'name': 'PRIMARY_09_15_2009', 'type': 'STRING'}, {'name': 'PRIMARY_09_29_2009', 'type': 'STRING'}, 
        {'name': 'GENERAL_11_03_2009', 'type': 'INT64'}, {'name': 'PRIMARY_05_04_2010', 'type': 'STRING'}, 
        {'name': 'PRIMARY_07_13_2010', 'type': 'STRING'}, {'name': 'PRIMARY_09_07_2010', 'type': 'STRING'}, 
        {'name': 'GENERAL_11_02_2010', 'type': 'INT64'}, {'name': 'PRIMARY_05_03_2011', 'type': 'STRING'}, 
        {'name': 'PRIMARY_09_13_2011', 'type': 'STRING'}, {'name': 'GENERAL_11_08_2011', 'type': 'INT64'}, 
        {'name': 'PRIMARY_03_06_2012', 'type': 'STRING'}, {'name': 'GENERAL_11_06_2012', 'type': 'INT64'}, 
        {'name': 'PRIMARY_05_07_2013', 'type': 'STRING'}, {'name': 'PRIMARY_09_10_2013', 'type': 'STRING'}, 
        {'name': 'PRIMARY_10_01_2013', 'type': 'STRING'}, {'name': 'GENERAL_11_05_2013', 'type': 'INT64'}, 
        {'name': 'PRIMARY_05_06_2014', 'type': 'STRING'}, {'name': 'GENERAL_11_04_2014', 'type': 'INT64'}, 
        {'name': 'PRIMARY_05_05_2015', 'type': 'STRING'}, {'name': 'PRIMARY_09_15_2015', 'type': 'STRING'}, 
        {'name': 'GENERAL_11_03_2015', 'type': 'INT64'}, {'name': 'PRIMARY_03_15_2016', 'type': 'STRING'}, 
        {'name': 'GENERAL_06_07_2016', 'type': 'INT64'}, {'name': 'PRIMARY_09_13_2016', 'type': 'STRING'}, 
        {'name': 'GENERAL_11_08_2016', 'type': 'INT64'}, {'name': 'PRIMARY_05_02_2017', 'type': 'STRING'}, 
        {'name': 'PRIMARY_09_12_2017', 'type': 'STRING'}, {'name': 'GENERAL_11_07_2017', 'type': 'INT64'}, 
        {'name': 'PRIMARY_05_08_2018', 'type': 'STRING'}, {'name': 'GENERAL_08_07_2018', 'type': 'INT64'}, 
        {'name': 'GENERAL_11_06_2018', 'type': 'INT64'}, {'name': 'PRIMARY_05_07_2019', 'type': 'STRING'}, 
        {'name': 'PRIMARY_09_10_2019', 'type': 'STRING'}, {'name': 'GENERAL_11_05_2019', 'type': 'INT64'}]
    prim_list = ['PRIMARY-03/07/2000', 'SPECIAL-05/08/2001', 'PRIMARY-05/07/2002', 'SPECIAL-05/06/2003', 'PRIMARY-03/02/2004', 
            'SPECIAL-02/08/2005', 'PRIMARY-05/03/2005', 'PRIMARY-09/13/2005', 'SPECIAL-02/07/2006', 'PRIMARY-05/02/2006', 
            'PRIMARY-05/08/2007', 'PRIMARY-09/11/2007', 'PRIMARY-11/06/2007', 'PRIMARY-03/04/2008', 'PRIMARY-10/14/2008', 
            'PRIMARY-05/05/2009', 'PRIMARY-09/08/2009', 'PRIMARY-09/15/2009', 'PRIMARY-09/29/2009', 'PRIMARY-05/04/2010', 
            'PRIMARY-07/13/2010', 'PRIMARY-09/07/2010', 'PRIMARY-05/03/2011', 'PRIMARY-09/13/2011', 'PRIMARY-03/06/2012', 
            'PRIMARY-05/07/2013', 'PRIMARY-09/10/2013', 'PRIMARY-10/01/2013', 'PRIMARY-05/06/2014', 'PRIMARY-05/05/2015', 
            'PRIMARY-09/15/2015', 'PRIMARY-03/15/2016', 'PRIMARY-09/13/2016', 'PRIMARY-05/02/2017', 'PRIMARY-09/12/2017', 
            'PRIMARY-05/08/2018', 'PRIMARY-05/07/2019', 'PRIMARY-09/10/2019']
    prim_list = [f.replace('-', '_').replace('/', '_') for f in prim_list]
    gen_list = ['GENERAL-11/07/2000', 'GENERAL-11/06/2001', 'GENERAL-11/05/2002', 'GENERAL-11/04/2003', 'GENERAL-11/02/2004', 
           'GENERAL-11/08/2005', 'GENERAL-11/07/2006', 'GENERAL-11/06/2007', 'GENERAL-12/11/2007', 'GENERAL-11/04/2008', 
           'GENERAL-11/18/2008', 'GENERAL-11/03/2009', 'GENERAL-11/02/2010', 'GENERAL-11/08/2011', 'GENERAL-11/06/2012', 
           'GENERAL-11/05/2013', 'GENERAL-11/04/2014', 'GENERAL-11/03/2015', 'GENERAL-06/07/2016', 'GENERAL-11/08/2016', 
           'GENERAL-11/07/2017', 'GENERAL-08/07/2018', 'GENERAL-11/06/2018', 'GENERAL-11/05/2019']
    gen_list = [f.replace('-', '_').replace('/', '_') for f in gen_list]
    party_list = ['PARTY_AFFILIATION']
    df= [pd.read_csv(io.StringIO(str(requests.get('https://www6.sos.state.oh.us/ords/f?p=VOTERFTP:DOWNLOAD::FILE:NO:2:P2_PRODUCT_NUMBER:{}'.format(88+f), verify=False).text)),encoding='Latin1', low_memory=False) for f in range(1, 2) ]
    #df=[pd.read_csv('https://www6.sos.state.oh.us/ords/f?p=VOTERFTP:DOWNLOAD::FILE:NO:2:P2_PRODUCT_NUMBER:{}'.format(88+f), encoding='Latin1', low_memory=False) for f in range(1, 17)]
    df=pd.concat(df)
    df.columns = [f.replace('-', '_').replace('/', '_') for f in df.columns]
    df['birth_year'] = df['DATE_OF_BIRTH'].map(lambda x: str(x)[:-6]).astype(int)
    df['Age'] = datetime.datetime.now().year - df['birth_year']
    for f in prim_list:
        df.loc[df[f]=='D', f]='Democrat'
        df.loc[df[f]=='R', f]='Republican'
        df.loc[df[f]=='G', f]='Green'
        df.loc[df[f]=='E', f]='Reform'
        df.loc[df[f]=='L', f]='Libertarian'
        df.loc[df[f]=='C', f]='Constitution'
        df.loc[df[f]=='N', f]='Natural Law'
        df.loc[df[f]=='S', f]='Socialist'
        df.loc[df[f]=='X', f]='Without Affiliation'
        df.loc[(df[f]=='') | (df[f].isnull()==True) | (df[f]==0), f]='Not Voted'
    for f in party_list:
        df.loc[df[f]=='D', f]='Democrat'
        df.loc[df[f]=='R', f]='Republican'
        df.loc[df[f]=='G', f]='Green'
        df.loc[df[f]=='E', f]='Reform'
        df.loc[df[f]=='L', f]='Libertarian'
        df.loc[df[f]=='C', f]='Constitution'
        df.loc[df[f]=='N', f]='Natural Law'
        df.loc[df[f]=='S', f]='Socialist'
        df.loc[df[f]=='X', f]='Unaffiliated'
        df.loc[(df[f]=='') | (df[f].isnull()==True) | (df[f]==0), f]='Unaffiliated'
    for g in gen_list:  
        df.loc[(df[g]!='') & (df[g].isnull()!=True) & (df[g]!=0) & (df[g]!='NaN'), g]=1
        df.loc[(df[g]=='') | (df[g].isnull()==True) | (df[g]==0) | (df[g]=='NaN'), g]=0
    df[gen_list]=df[gen_list].astype(int)
    df[prim_list]=df[prim_list].astype(str)
    df[party_list]=df[party_list].astype(str)
    df.to_gbq(destination_table='Voterfile.OH_Voterfile', project_id='astute-acolyte-260912', if_exists='replace', table_schema=schema, reauth=False)

请注意，verify=False仅用于测试建议。不得用于生产。在我的机器上运行你的代码后Cloud Functions，我意识到两件事：

您的代码需要很长时间才能运行，因为它需要下载和处理文件。鉴于此，它应该被部署，Cloud Functions因为 Cloud Functions 的最大超时时间为 9 分钟，如您在此处看到的
要执行所有这些下载和转换，您的代码会占用大量内存。我尝试以最大可能的内存量（2GB）在 Cloud Functions 上运行，但它达到了内存的限制。

为此，您可以尝试在 Compute Engine 中使用虚拟机。在这种情况下，您还可以使用 Cloud Schedule 在您想要的确切时间打开和关闭您的虚拟机。你可以在这里找到教程

要在 Compute Engine 中创建 VM，您可以按照本教程从公共映像创建实例

请记住，在 Compute Engine 中使用虚拟机时，您将在虚拟机开启时支付处理费用，并在虚拟机开启或关闭时支付虚拟机磁盘的存储费用。创建 VM 后，您可以通过控制台访问它。您应该像在本地计算机中一样为您的代码在 VM 中准备环境。

配置好环境和可部署代码后，您可以使用crontab安排系统执行脚本。

现在我们有最后一步：配置云计划以在适当的时间打开和关闭您的虚拟机。你可以在这里找到教程。您应该安排您的虚拟机在您在 crontab 中定义的时间前几分钟打开。

python - 使用 Cloud Functions 和 Cloud Scheduler 创建到 BigQuery 的数据管道

2 回答 2

Related

Reference