def _import_bytes(buf, database, table, client, max_errors,
existing_table_rows, distkey, sortkey1, sortkey2, delimiter,
headers, credential_id, polling_interval, archive, hidden):
schema, table = table.split(".", 1)
db_id = client.get_database_id(database)
cred_id = credential_id or client.default_credential
delimiter = DELIMITERS.get(delimiter)
assert delimiter, "delimiter must be one of {}".format(DELIMITERS.keys())
kwargs = dict(schema=schema, name=table, remote_host_id=db_id,
credential_id=cred_id, max_errors=max_errors,
existing_table_rows=existing_table_rows, distkey=distkey,
sortkey1=sortkey1, sortkey2=sortkey2,
column_delimiter=delimiter, first_row_is_header=headers,
hidden=hidden)
import_job = client.imports.post_files(**kwargs)
put_response = requests.put(import_job.upload_uri, buf)
put_response.raise_for_status()
run_job_result = client._session.post(import_job.run_uri)
run_job_result.raise_for_status()
run_info = run_job_result.json()
fut = CivisFuture(client.imports.get_files_runs,
(run_info['importId'], run_info['id']),
polling_interval=polling_interval,
client=client,
poll_on_creation=False)
if archive:
def f(x):
return client.imports.put_archive(import_job.id, True)
fut.add_done_callback(f)
return fut
def civis_to_csv(filename, sql, database, job_name=None, api_key=None,
client=None, credential_id=None, include_header=True,
compression='none', delimiter=',', unquoted=False,
archive=False, hidden=True, polling_interval=None):
"""Export data from Civis to a local CSV file.
Parameters
----------
filename : str
Download exported data into this file.
sql : str, optional
The SQL select string to be executed.
database : str or int
Export data from this database. Can be the database name or ID.
job_name : str, optional
A name to give the job. If omitted, a random job name will be
used.
api_key : DEPRECATED str, optional
Your Civis API key. If not given, the :envvar:`CIVIS_API_KEY`
environment variable will be used.
client : :class:`civis.APIClient`, optional
If not provided, an :class:`civis.APIClient` object will be
created from the :envvar:`CIVIS_API_KEY`.
credential_id : str or int, optional
The ID of the database credential. If ``None``, the default
credential will be used.
include_header: bool, optional
If ``True``, the first line of the CSV will be headers.
Default: ``True``.
compression: str, optional
Type of compression to use, if any. One of ``'none'``, ``'zip'``, or
``'gzip'``. Default ``'none'``.
delimiter, str: optional
Which delimiter to use, if any. One of ``','``, ``'\t'``, or
``'|'``. Default: ``','``.
unquoted: bool, optional
Whether or not to quote fields. Default: ``False``.
polling_interval : int or float, optional
Number of seconds to wait between checks for query completion.
archive : bool, optional (deprecated)
If ``True``, archive the import job as soon as it completes.
hidden : bool, optional
If ``True`` (the default), this job will not appear in the Civis UI.
Returns
-------
results : :class:`~civis.futures.CivisFuture`
A `CivisFuture` object.
Examples
--------
>>> sql = "SELECT * FROM schema.table"
>>> fut = civis_to_csv("file.csv", sql, "my_database")
>>> fut.result() # Wait for job to complete
See Also
--------
civis.io.read_civis : Read table contents into memory.
civis.io.read_civis_sql : Read results of a SQL query into memory.
"""
if archive:
warnings.warn("`archive` is deprecated and will be removed in v2.0.0. "
"Use `hidden` instead.", FutureWarning)
if client is None:
client = APIClient(api_key=api_key, resources='all')
delimiter = DELIMITERS.get(delimiter)
if not delimiter:
raise ValueError("delimiter must be one of {}"
.format(DELIMITERS.keys()))
csv_settings = dict(include_header=include_header,
compression=compression,
column_delimiter=delimiter,
unquoted=unquoted,
filename_prefix=None,
force_multifile=False)
script_id, run_id = _sql_script(client, sql, database, job_name,
credential_id, hidden=hidden,
csv_settings=csv_settings)
fut = CivisFuture(client.scripts.get_sql_runs, (script_id, run_id),
polling_interval=polling_interval, client=client,
poll_on_creation=False)
download = _download_callback(script_id, run_id, client, filename)
fut.add_done_callback(download)
if archive:
def f(x):
return client.scripts.put_sql_archive(script_id, True)
fut.add_done_callback(f)
return fut
def read_civis_sql(sql, database, use_pandas=False, job_name=None,
api_key=None, client=None, credential_id=None,
polling_interval=None, archive=False,
hidden=True, **kwargs):
"""Read data from Civis using a custom SQL string.
Parameters
----------
sql : str, optional
The SQL select string to be executed.
database : str or int
Execute the query against this database. Can be the database name
or ID.
use_pandas : bool, optional
If ``True``, return a :class:`pandas:pandas.DataFrame`. Otherwise,
return a list of results from :func:`python:csv.reader`.
job_name : str, optional
A name to give the job. If omitted, a random job name will be
used.
api_key : DEPRECATED str, optional
Your Civis API key. If not given, the :envvar:`CIVIS_API_KEY`
environment variable will be used.
client : :class:`civis.APIClient`, optional
If not provided, an :class:`civis.APIClient` object will be
created from the :envvar:`CIVIS_API_KEY`.
credential_id : str or int, optional
The database credential ID. If ``None``, the default credential
will be used.
polling_interval : int or float, optional
Number of seconds to wait between checks for query completion.
archive : bool, optional (deprecated)
If ``True``, archive the import job as soon as it completes.
hidden : bool, optional
If ``True`` (the default), this job will not appear in the Civis UI.
**kwargs : kwargs
Extra keyword arguments are passed into
:func:`pandas:pandas.read_csv` if `use_pandas` is ``True`` or
passed into :func:`python:csv.reader` if `use_pandas` is
``False``.
Returns
-------
data : :class:`pandas:pandas.DataFrame` or list
A list of rows (with header as first row) if `use_pandas` is
``False``, otherwise a `pandas` `DataFrame`. Note that if
`use_pandas` is ``False``, no parsing of types is performed and
each row will be a list of strings.
Raises
------
ImportError
If `use_pandas` is ``True`` and `pandas` is not installed.
Examples
--------
>>> sql = "SELECT * FROM schema.table"
>>> df = read_civis_sql(sql, "my_database", use_pandas=True)
>>> col_a = df["column_a"]
>>> data = read_civis_sql(sql, "my_database")
>>> columns = data.pop(0)
>>> col_a_index = columns.index("column_a")
>>> col_a = [row[col_a_index] for row in data]
Notes
-----
This reads the data into memory.
See Also
--------
civis.io.read_civis : Read directly into memory without SQL.
civis.io.civis_to_csv : Write directly to a CSV file.
"""
if client is None:
client = APIClient(api_key=api_key, resources='all')
if use_pandas and NO_PANDAS:
raise ImportError("use_pandas is True but pandas is not installed.")
if archive:
warnings.warn("`archive` is deprecated and will be removed in v2.0.0. "
"Use `hidden` instead.", FutureWarning)
script_id, run_id = _sql_script(client, sql, database,
job_name, credential_id,
hidden=hidden)
fut = CivisFuture(client.scripts.get_sql_runs, (script_id, run_id),
polling_interval=polling_interval, client=client,
poll_on_creation=False)
if archive:
def f(x):
return client.scripts.put_sql_archive(script_id, True)
fut.add_done_callback(f)
fut.result()
outputs = client.scripts.get_sql_runs(script_id, run_id)["output"]
if not outputs:
raise EmptyResultError("Query {} returned no output."
.format(script_id))
url = outputs[0]["path"]
if use_pandas:
data = pd.read_csv(url, **kwargs)
else:
r = requests.get(url)
r.raise_for_status()
data = list(csv.reader(StringIO(r.text), **kwargs))
return data
def civis_to_csv(filename,
sql,
database,
job_name=None,
api_key=None,
credential_id=None,
archive=False,
hidden=True,
polling_interval=None):
"""Export data from Civis to a local CSV file.
Parameters
----------
filename : str
Download exported data into this file.
sql : str, optional
The SQL select string to be executed.
database : str or int
Export data from this database. Can be the database name or ID.
job_name : str, optional
A name to give the job. If omitted, a random job name will be
used.
api_key : str, optional
Your Civis API key. If not given, the :envvar:`CIVIS_API_KEY`
environment variable will be used.
credential_id : str or int, optional
The ID of the database credential. If ``None``, the default
credential will be used.
polling_interval : int or float, optional
Number of seconds to wait between checks for query completion.
archive : bool, optional (deprecated)
If ``True``, archive the import job as soon as it completes.
hidden : bool, optional
If ``True`` (the default), this job will not appear in the Civis UI.
Returns
-------
results : :class:`~civis.futures.CivisFuture`
A `CivisFuture` object.
Examples
--------
>>> sql = "SELECT * FROM schema.table"
>>> fut = civis_to_csv("file.csv", sql, "my_database")
>>> fut.result() # Wait for job to complete
See Also
--------
civis.io.read_civis : Read table contents into memory.
civis.io.read_civis_sql : Read results of a SQL query into memory.
"""
if archive:
warnings.warn(
"`archive` is deprecated and will be removed in v2.0.0. "
"Use `hidden` instead.", FutureWarning)
client = APIClient(api_key=api_key)
script_id, run_id = _sql_script(client,
sql,
database,
job_name,
credential_id,
hidden=hidden)
fut = CivisFuture(client.scripts.get_sql_runs, (script_id, run_id),
polling_interval=polling_interval,
api_key=api_key,
poll_on_creation=False)
download = _download_callback(script_id, run_id, client, filename)
fut.add_done_callback(download)
if archive:
def f(x):
return client.scripts.put_sql_archive(script_id, True)
fut.add_done_callback(f)
return fut
def civis_to_csv(filename,
sql,
database,
job_name=None,
api_key=None,
client=None,
credential_id=None,
include_header=True,
compression='none',
delimiter=',',
unquoted=False,
archive=False,
hidden=True,
polling_interval=None):
"""Export data from Civis to a local CSV file.
The custom SQL string will be executed twice; once to attempt to
retrieve headers and once to retrieve the data. This is done to
use a more performant method for retrieving the data. The first
execution of the custom SQL is controlled such that changes in
state cannot occur (e.g., INSERT, UPDATE, DELETE, etc.).
Parameters
----------
filename : str
Download exported data into this file.
sql : str, optional
The SQL select string to be executed.
database : str or int
Export data from this database. Can be the database name or ID.
job_name : str, optional
A name to give the job. If omitted, a random job name will be
used.
api_key : DEPRECATED str, optional
Your Civis API key. If not given, the :envvar:`CIVIS_API_KEY`
environment variable will be used.
client : :class:`civis.APIClient`, optional
If not provided, an :class:`civis.APIClient` object will be
created from the :envvar:`CIVIS_API_KEY`.
credential_id : str or int, optional
The ID of the database credential. If ``None``, the default
credential will be used.
include_header: bool, optional
If ``True``, the first line of the CSV will be headers.
Default: ``True``.
compression: str, optional
Type of compression to use, if any. One of ``'none'``, ``'zip'``, or
``'gzip'``. Default ``'none'``. ``'gzip'`` currently returns a file
with no compression unless include_header is set to False. In a
future release, a ``'gzip'`` compressed file will be returned for
all cases.
delimiter: str, optional
Which delimiter to use, if any. One of ``','``, ``'\t'``, or
``'|'``. Default: ``','``.
unquoted: bool, optional
Whether or not to quote fields. Default: ``False``.
polling_interval : int or float, optional
Number of seconds to wait between checks for query completion.
archive : bool, optional (deprecated)
If ``True``, archive the import job as soon as it completes.
hidden : bool, optional
If ``True`` (the default), this job will not appear in the Civis UI.
Returns
-------
results : :class:`~civis.futures.CivisFuture`
A `CivisFuture` object.
Examples
--------
>>> sql = "SELECT * FROM schema.table"
>>> fut = civis_to_csv("file.csv", sql, "my_database")
>>> fut.result() # Wait for job to complete
See Also
--------
civis.io.read_civis : Read table contents into memory.
civis.io.read_civis_sql : Read results of a SQL query into memory.
"""
if archive:
warnings.warn(
"`archive` is deprecated and will be removed in v2.0.0. "
"Use `hidden` instead.", FutureWarning)
if client is None:
client = APIClient(api_key=api_key, resources='all')
db_id = client.get_database_id(database)
credential_id = credential_id or client.default_credential
# don't fix bug that would cause breaking change for now
# when gzip compression is requested, a gzip file is not actually returned
# instead the gzip file is decompressed during download
if compression == 'gzip' and include_header:
compression = 'none'
# don't support parallel unload; the output format
# is different which would introduce a breaking change
headers = b''
delimiter = DELIMITERS.get(delimiter)
if not delimiter:
raise ValueError("delimiter must be one of {}".format(
DELIMITERS.keys()))
# always set compression to gzip to reduce I/O
csv_settings = dict(include_header=include_header,
compression='gzip',
column_delimiter=delimiter,
unquoted=unquoted,
filename_prefix=None,
force_multifile=False)
script_id, run_id = _sql_script(client,
sql,
db_id,
job_name,
credential_id,
hidden=hidden,
csv_settings=csv_settings)
fut = CivisFuture(client.scripts.get_sql_runs, (script_id, run_id),
polling_interval=polling_interval,
client=client,
poll_on_creation=False)
download = _download_callback(script_id, run_id, filename, headers,
compression)
fut.add_done_callback(download)
if archive:
def f(x):
return client.scripts.put_sql_archive(script_id, True)
fut.add_done_callback(f)
return fut
def read_civis_sql(sql,
database,
use_pandas=False,
job_name=None,
api_key=None,
client=None,
credential_id=None,
polling_interval=None,
archive=False,
hidden=True,
**kwargs):
"""Read data from Civis using a custom SQL string.
The custom SQL string will be executed twice; once to attempt to
retrieve headers and once to retrieve the data. This is done to
use a more performant method for retrieving the data. The first
execution of the custom SQL is controlled such that changes in
state cannot occur (e.g., INSERT, UPDATE, DELETE, etc.).
Parameters
----------
sql : str, optional
The SQL select string to be executed.
database : str or int
Execute the query against this database. Can be the database name
or ID.
use_pandas : bool, optional
If ``True``, return a :class:`pandas:pandas.DataFrame`. Otherwise,
return a list of results from :func:`python:csv.reader`.
job_name : str, optional
A name to give the job. If omitted, a random job name will be
used.
api_key : DEPRECATED str, optional
Your Civis API key. If not given, the :envvar:`CIVIS_API_KEY`
environment variable will be used.
client : :class:`civis.APIClient`, optional
If not provided, an :class:`civis.APIClient` object will be
created from the :envvar:`CIVIS_API_KEY`.
credential_id : str or int, optional
The database credential ID. If ``None``, the default credential
will be used.
polling_interval : int or float, optional
Number of seconds to wait between checks for query completion.
archive : bool, optional (deprecated)
If ``True``, archive the import job as soon as it completes.
hidden : bool, optional
If ``True`` (the default), this job will not appear in the Civis UI.
**kwargs : kwargs
Extra keyword arguments are passed into
:func:`pandas:pandas.read_csv` if `use_pandas` is ``True`` or
passed into :func:`python:csv.reader` if `use_pandas` is
``False``.
Returns
-------
data : :class:`pandas:pandas.DataFrame` or list
A list of rows (with header as first row) if `use_pandas` is
``False``, otherwise a `pandas` `DataFrame`. Note that if
`use_pandas` is ``False``, no parsing of types is performed and
each row will be a list of strings.
Raises
------
ImportError
If `use_pandas` is ``True`` and `pandas` is not installed.
Examples
--------
>>> sql = "SELECT * FROM schema.table"
>>> df = read_civis_sql(sql, "my_database", use_pandas=True)
>>> col_a = df["column_a"]
>>> data = read_civis_sql(sql, "my_database")
>>> columns = data.pop(0)
>>> col_a_index = columns.index("column_a")
>>> col_a = [row[col_a_index] for row in data]
Notes
-----
This reads the data into memory.
See Also
--------
civis.io.read_civis : Read directly into memory without SQL.
civis.io.civis_to_csv : Write directly to a CSV file.
"""
if client is None:
client = APIClient(api_key=api_key, resources='all')
if use_pandas and NO_PANDAS:
raise ImportError("use_pandas is True but pandas is not installed.")
if archive:
warnings.warn(
"`archive` is deprecated and will be removed in v2.0.0. "
"Use `hidden` instead.", FutureWarning)
db_id = client.get_database_id(database)
credential_id = credential_id or client.default_credential
# determine if we can request headers separately; if we can then Platform
# will perform a parallel unload which is significantly more performant
# we start by assuming headers are requested
ovrd_include_header, headers = _include_header(client, sql, True, db_id,
credential_id,
polling_interval)
# if we retrieved headers then we are performing a parallel unload
# in which case we need to specify backslash as the escapechar
if headers is not None:
kwargs['escapechar'] = '\\'
csv_settings = dict(include_header=ovrd_include_header, compression='gzip')
script_id, run_id = _sql_script(client,
sql,
db_id,
job_name,
credential_id,
csv_settings=csv_settings,
hidden=hidden)
fut = CivisFuture(client.scripts.get_sql_runs, (script_id, run_id),
polling_interval=polling_interval,
client=client,
poll_on_creation=False)
if archive:
def f(x):
return client.scripts.put_sql_archive(script_id, True)
fut.add_done_callback(f)
fut.result()
outputs = client.scripts.get_sql_runs(script_id, run_id)["output"]
if not outputs:
raise EmptyResultError(
"Query {} returned no output.".format(script_id))
url = outputs[0]["path"]
file_id = outputs[0]["file_id"]
log.debug('Exported results to Civis file %s (%s)',
outputs[0]["output_name"], file_id)
if use_pandas:
# allows users to enter their own names parameter
_kwargs = {'names': headers}
_kwargs.update(kwargs)
_kwargs['compression'] = 'gzip'
data = pd.read_csv(url, **_kwargs)
else:
response = requests.get(url, stream=True)
response.raise_for_status()
with StringIO() as buf:
if headers:
buf.write(','.join(headers) + '\n')
_decompress_stream(response, buf, write_bytes=False)
buf.seek(0)
data = list(csv.reader(buf, **kwargs))
return data
