Bigquery - insert a new row of data into a table using python

Question

I read a lot of google bigquery-python docs, but I can't figure out how to manage bigquery files using python code.

First, I create a new table as shown below.

credentials = GoogleCredentials.get_application_default()
service = build('bigquery', 'v2', credentials = credentials)

project_id = 'my_project'
dataset_id = 'my_dataset'
table_id = 'my_table'

project_ref = {'projectId': project_id}
dataset_ref = {'datasetId': dataset_id,
               'projectId': project_id}
table_ref = {'tableId': table_id,
             'datasetId': dataset_id,
             'projectId': project_id}

dataset = {'datasetReference': dataset_ref}
table = {'tableReference': table_ref}
table['schema'] = {'fields': [
    {'name': 'id', 'type': 'string'},
...
]}

table = service.tables().insert(body = table, **dataset_ref).execute()

And then I want to insert data into this table, so I tried to do as shown below.

fetch_list = []
patch = {'key': 'value'}
fetch_list.append(patch)

table = service.tables().patch(body = fetch_list, **table_ref).execute()

But nothing happened.

How to update new data in bigquery table?

Please show me some code examples.

Answer 1

  UPDATE November 2018:

The answer to this question is already outdated, as the Google cloud client has changed significantly since the last message.

; , ( Python ).

Original Answer:

, BQ.

, python-api, , : bq-python-api ( , , , ).

2 , BQ. - , , . :

import uuid
def stream_data(self, table, data, schema):
    # first checks if table already exists. If it does not, then create it
    r = self.service.tables().list(projectId=your_project_id,
                                     datasetId=your_dataset_id).execute()
    table_exists = [row['tableReference']['tableId'] for row in
                    r['tables'] if
                    row['tableReference']['tableId'] == table]
    if not table_exists:
        body = {
            'tableReference': {
                'tableId': table,
                'projectId': your_project_id,
                'datasetId': your_dataset_id
            },
            'schema': schema
        }
        self.service.tables().insert(projectId=your_project_id,
                                     datasetId=your_dataset_id,
                                     body=body).execute()

    # with table created, now we can stream the data
    # to do so we'll use the tabledata().insertall() function.
    body = {
        'rows': [
            {
                'json': data,
                'insertId': str(uuid.uuid4())
            }
        ]
    }
    self.service.tabledata().insertAll(projectId=your_project_id),
                                       datasetId=your_dataset_id,
                                       tableId=table,
                                         body=body).execute(num_retries=5)

self.service service.

data, :

data = {u'days_validated': '20', u'days_trained': '80', u'navigated_score': '1', u'description': 'First trial of top seller alg. No filter nor any condition is applied. Skus not present in train count as rank=0.5', u'init_cv_date': '2016-03-06', u'metric': 'rank', u'unix_date': '1461610020241117', u'purchased_score': '10', u'result': '0.32677139316724546', u'date': '2016-04-25', u'carted_score': '3', u'end_cv_date': '2016-03-25'}

schema:

schema = {u'fields': [{u'type': u'STRING', u'name': u'date', u'mode': u'NULLABLE'}, {u'type': u'INTEGER', u'name': u'unix_date', u'mode': u'NULLABLE'}, {u'type': u'STRING', u'name': u'init_cv_date', u'mode': u'NULLABLE'}, {u'type': u'STRING', u'name': u'end_cv_date', u'mode': u'NULLABLE'}, {u'type': u'INTEGER', u'name': u'days_trained', u'mode': u'NULLABLE'}, {u'type': u'INTEGER', u'name': u'days_validated', u'mode': u'NULLABLE'}, {u'type': u'INTEGER', u'name': u'navigated_score', u'mode': u'NULLABLE'}, {u'type': u'INTEGER', u'name': u'carted_score', u'mode': u'NULLABLE'}, {u'type': u'INTEGER', u'name': u'purchased_score', u'mode': u'NULLABLE'}, {u'type': u'STRING', u'name': u'description', u'mode': u'NULLABLE'}, {u'type': u'STRING', u'name': u'metric', u'mode': u'NULLABLE'}, {u'type': u'FLOAT', u'name': u'result', u'mode': u'NULLABLE'}]}

- . , . , , :

def create_table_from_query(self,
                            query,
                            dest_table,
                            how):
    body = {
        'configuration': {
            'query': {
                'destinationTable': {
                    'projectId': your_project_id,
                    'tableId': dest_table,
                    'datasetId': your_dataset_id
                },
                'writeDisposition': how,
                'query': query,
            },
        }
    }

    response = self.connector.jobs().insert(projectId=self._project_id,
                                            body=body).execute()
    self.wait_job_completion(response['jobReference']['jobId'])

def wait_job_completion(self, job_id):
    while True:
        response = self.connector.jobs().get(projectId=self._project_id,
                                             jobId=job_id).execute()
        if response['status']['state'] == 'DONE':
            return

how (, "WRITE_TRUNCATE" "WRITE_APPEND").

CSV , , configuration :

"configuration": {
  "load": {
    "fieldDelimiter": "\t"
    "sourceFormat": "CSV"
    "destinationTable": {
      "projectId": your_project_id,
      "tableId": table_id,
      "datasetId": your_dataset_id
    },
    "writeDisposition": "WRITE_TRUNCATE"
    "schema": schema,
    "sourceUris": file_location_in_google_cloud_storage
  },
}

( CSV , . JSON, ).

() ( wait_job_completion). , .

, ,

Answer 2

:

1. josn csv API ,

2. BigQuery

: BigQuery, GCS?

,