forked from influxdata/influxdb-client-python
-
Notifications
You must be signed in to change notification settings - Fork 0
/
query_api.py
310 lines (237 loc) · 15.2 KB
/
query_api.py
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
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
"""
Querying InfluxDB by FluxLang.
Flux is InfluxData’s functional data scripting language designed for querying, analyzing, and acting on data.
"""
from typing import List, Generator, Any, Callable
from influxdb_client import Dialect
from influxdb_client.client._base import _BaseQueryApi
from influxdb_client.client.flux_table import FluxRecord, TableList, CSVIterator
class QueryOptions(object):
"""Query options."""
def __init__(self, profilers: List[str] = None, profiler_callback: Callable = None) -> None:
"""
Initialize query options.
:param profilers: list of enabled flux profilers
:param profiler_callback: callback function return profilers (FluxRecord)
"""
self.profilers = profilers
self.profiler_callback = profiler_callback
class QueryApi(_BaseQueryApi):
"""Implementation for '/api/v2/query' endpoint."""
def __init__(self, influxdb_client, query_options=QueryOptions()):
"""
Initialize query client.
:param influxdb_client: influxdb client
"""
super().__init__(influxdb_client=influxdb_client, query_options=query_options)
def query_csv(self, query: str, org=None, dialect: Dialect = _BaseQueryApi.default_dialect, params: dict = None) \
-> CSVIterator:
"""
Execute the Flux query and return results as a CSV iterator. Each iteration returns a row of the CSV file.
:param query: a Flux query
:param str, Organization org: specifies the organization for executing the query;
Take the ``ID``, ``Name`` or ``Organization``.
If not specified the default value from ``InfluxDBClient.org`` is used.
:param dialect: csv dialect format
:param params: bind parameters
:return: :class:`~Iterator[List[str]]` wrapped into :class:`~influxdb_client.client.flux_table.CSVIterator`
:rtype: CSVIterator
Serialization the query results to flattened list of values via :func:`~influxdb_client.client.flux_table.CSVIterator.to_values`:
.. code-block:: python
from influxdb_client import InfluxDBClient
with InfluxDBClient(url="http://localhost:8086", token="my-token", org="my-org") as client:
# Query: using CSV iterator
csv_iterator = client.query_api().query_csv('from(bucket:"my-bucket") |> range(start: -10m)')
# Serialize to values
output = csv_iterator.to_values()
print(output)
.. code-block:: python
[
['#datatype', 'string', 'long', 'dateTime:RFC3339', 'dateTime:RFC3339', 'dateTime:RFC3339', 'double', 'string', 'string', 'string']
['#group', 'false', 'false', 'true', 'true', 'false', 'false', 'true', 'true', 'true']
['#default', '_result', '', '', '', '', '', '', '', '']
['', 'result', 'table', '_start', '_stop', '_time', '_value', '_field', '_measurement', 'location']
['', '', '0', '2022-06-16', '2022-06-16', '2022-06-16', '24.3', 'temperature', 'my_measurement', 'New York']
['', '', '1', '2022-06-16', '2022-06-16', '2022-06-16', '25.3', 'temperature', 'my_measurement', 'Prague']
...
]
If you would like to turn off `Annotated CSV header's <https://docs.influxdata.com/influxdb/latest/reference/syntax/annotated-csv/>`_ you can use following code:
.. code-block:: python
from influxdb_client import InfluxDBClient, Dialect
with InfluxDBClient(url="http://localhost:8086", token="my-token", org="my-org") as client:
# Query: using CSV iterator
csv_iterator = client.query_api().query_csv('from(bucket:"my-bucket") |> range(start: -10m)',
dialect=Dialect(header=False, annotations=[]))
for csv_line in csv_iterator:
print(csv_line)
.. code-block:: python
[
['', '_result', '0', '2022-06-16', '2022-06-16', '2022-06-16', '24.3', 'temperature', 'my_measurement', 'New York']
['', '_result', '1', '2022-06-16', '2022-06-16', '2022-06-16', '25.3', 'temperature', 'my_measurement', 'Prague']
...
]
""" # noqa: E501
org = self._org_param(org)
response = self._query_api.post_query(org=org, query=self._create_query(query, dialect, params),
async_req=False, _preload_content=False)
return self._to_csv(response)
def query_raw(self, query: str, org=None, dialect=_BaseQueryApi.default_dialect, params: dict = None):
"""
Execute synchronous Flux query and return result as raw unprocessed result as a str.
:param query: a Flux query
:param str, Organization org: specifies the organization for executing the query;
Take the ``ID``, ``Name`` or ``Organization``.
If not specified the default value from ``InfluxDBClient.org`` is used.
:param dialect: csv dialect format
:param params: bind parameters
:return: str
"""
org = self._org_param(org)
result = self._query_api.post_query(org=org, query=self._create_query(query, dialect, params), async_req=False,
_preload_content=False)
return result
def query(self, query: str, org=None, params: dict = None) -> TableList:
"""Execute synchronous Flux query and return result as a :class:`~influxdb_client.client.flux_table.FluxTable` list.
:param query: the Flux query
:param str, Organization org: specifies the organization for executing the query;
Take the ``ID``, ``Name`` or ``Organization``.
If not specified the default value from ``InfluxDBClient.org`` is used.
:param params: bind parameters
:return: :class:`~influxdb_client.client.flux_table.FluxTable` list wrapped into
:class:`~influxdb_client.client.flux_table.TableList`
:rtype: TableList
Serialization the query results to flattened list of values via :func:`~influxdb_client.client.flux_table.TableList.to_values`:
.. code-block:: python
from influxdb_client import InfluxDBClient
with InfluxDBClient(url="http://localhost:8086", token="my-token", org="my-org") as client:
# Query: using Table structure
tables = client.query_api().query('from(bucket:"my-bucket") |> range(start: -10m)')
# Serialize to values
output = tables.to_values(columns=['location', '_time', '_value'])
print(output)
.. code-block:: python
[
['New York', datetime.datetime(2022, 6, 7, 11, 3, 22, 917593, tzinfo=tzutc()), 24.3],
['Prague', datetime.datetime(2022, 6, 7, 11, 3, 22, 917593, tzinfo=tzutc()), 25.3],
...
]
Serialization the query results to JSON via :func:`~influxdb_client.client.flux_table.TableList.to_json`:
.. code-block:: python
from influxdb_client import InfluxDBClient
with InfluxDBClient(url="http://localhost:8086", token="my-token", org="my-org") as client:
# Query: using Table structure
tables = client.query_api().query('from(bucket:"my-bucket") |> range(start: -10m)')
# Serialize to JSON
output = tables.to_json(indent=5)
print(output)
.. code-block:: javascript
[
{
"_measurement": "mem",
"_start": "2021-06-23T06:50:11.897825+00:00",
"_stop": "2021-06-25T06:50:11.897825+00:00",
"_time": "2020-02-27T16:20:00.897825+00:00",
"region": "north",
"_field": "usage",
"_value": 15
},
{
"_measurement": "mem",
"_start": "2021-06-23T06:50:11.897825+00:00",
"_stop": "2021-06-25T06:50:11.897825+00:00",
"_time": "2020-02-27T16:20:01.897825+00:00",
"region": "west",
"_field": "usage",
"_value": 10
},
...
]
""" # noqa: E501
org = self._org_param(org)
response = self._query_api.post_query(org=org, query=self._create_query(query, self.default_dialect, params),
async_req=False, _preload_content=False, _return_http_data_only=False)
return self._to_tables(response, query_options=self._get_query_options())
def query_stream(self, query: str, org=None, params: dict = None) -> Generator['FluxRecord', Any, None]:
"""
Execute synchronous Flux query and return stream of FluxRecord as a Generator['FluxRecord'].
:param query: the Flux query
:param str, Organization org: specifies the organization for executing the query;
Take the ``ID``, ``Name`` or ``Organization``.
If not specified the default value from ``InfluxDBClient.org`` is used.
:param params: bind parameters
:return: Generator['FluxRecord']
"""
org = self._org_param(org)
response = self._query_api.post_query(org=org, query=self._create_query(query, self.default_dialect, params),
async_req=False, _preload_content=False, _return_http_data_only=False)
return self._to_flux_record_stream(response, query_options=self._get_query_options())
def query_data_frame(self, query: str, org=None, data_frame_index: List[str] = None, params: dict = None,
use_extension_dtypes: bool = False):
"""
Execute synchronous Flux query and return Pandas DataFrame.
.. note:: If the ``query`` returns tables with differing schemas than the client generates a :class:`~DataFrame` for each of them.
:param query: the Flux query
:param str, Organization org: specifies the organization for executing the query;
Take the ``ID``, ``Name`` or ``Organization``.
If not specified the default value from ``InfluxDBClient.org`` is used.
:param data_frame_index: the list of columns that are used as DataFrame index
:param params: bind parameters
:param use_extension_dtypes: set to ``True`` to use panda's extension data types.
Useful for queries with ``pivot`` function.
When data has missing values, column data type may change (to ``object`` or ``float64``).
Nullable extension types (``Int64``, ``Float64``, ``boolean``) support ``panda.NA`` value.
For more info, see https://pandas.pydata.org/docs/user_guide/missing_data.html.
:return: :class:`~DataFrame` or :class:`~List[DataFrame]`
.. warning:: For the optimal processing of the query results use the ``pivot() function`` which align results as a table.
.. code-block:: text
from(bucket:"my-bucket")
|> range(start: -5m, stop: now())
|> filter(fn: (r) => r._measurement == "mem")
|> pivot(rowKey:["_time"], columnKey: ["_field"], valueColumn: "_value")
For more info see:
- https://docs.influxdata.com/resources/videos/pivots-in-flux/
- https://docs.influxdata.com/flux/latest/stdlib/universe/pivot/
- https://docs.influxdata.com/flux/latest/stdlib/influxdata/influxdb/schema/fieldsascols/
""" # noqa: E501
_generator = self.query_data_frame_stream(query, org=org, data_frame_index=data_frame_index, params=params,
use_extension_dtypes=use_extension_dtypes)
return self._to_data_frames(_generator)
def query_data_frame_stream(self, query: str, org=None, data_frame_index: List[str] = None, params: dict = None,
use_extension_dtypes: bool = False):
"""
Execute synchronous Flux query and return stream of Pandas DataFrame as a :class:`~Generator[DataFrame]`.
.. note:: If the ``query`` returns tables with differing schemas than the client generates a :class:`~DataFrame` for each of them.
:param query: the Flux query
:param str, Organization org: specifies the organization for executing the query;
Take the ``ID``, ``Name`` or ``Organization``.
If not specified the default value from ``InfluxDBClient.org`` is used.
:param data_frame_index: the list of columns that are used as DataFrame index
:param params: bind parameters
:param use_extension_dtypes: set to ``True`` to use panda's extension data types.
Useful for queries with ``pivot`` function.
When data has missing values, column data type may change (to ``object`` or ``float64``).
Nullable extension types (``Int64``, ``Float64``, ``boolean``) support ``panda.NA`` value.
For more info, see https://pandas.pydata.org/docs/user_guide/missing_data.html.
:return: :class:`~Generator[DataFrame]`
.. warning:: For the optimal processing of the query results use the ``pivot() function`` which align results as a table.
.. code-block:: text
from(bucket:"my-bucket")
|> range(start: -5m, stop: now())
|> filter(fn: (r) => r._measurement == "mem")
|> pivot(rowKey:["_time"], columnKey: ["_field"], valueColumn: "_value")
For more info see:
- https://docs.influxdata.com/resources/videos/pivots-in-flux/
- https://docs.influxdata.com/flux/latest/stdlib/universe/pivot/
- https://docs.influxdata.com/flux/latest/stdlib/influxdata/influxdb/schema/fieldsascols/
""" # noqa: E501
org = self._org_param(org)
response = self._query_api.post_query(org=org, query=self._create_query(query, self.default_dialect, params,
dataframe_query=True),
async_req=False, _preload_content=False, _return_http_data_only=False)
return self._to_data_frame_stream(data_frame_index=data_frame_index,
response=response,
query_options=self._get_query_options(),
use_extension_dtypes=use_extension_dtypes)
def __del__(self):
"""Close QueryAPI."""
pass