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
|
# -*- coding: utf-8 -*-
"""
DataFrame client for InfluxDB
"""
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
from __future__ import unicode_literals
import math
import pandas as pd
from .client import InfluxDBClient
def _pandas_time_unit(time_precision):
unit = time_precision
if time_precision == 'm':
unit = 'ms'
elif time_precision == 'u':
unit = 'us'
elif time_precision == 'n':
unit = 'ns'
assert unit in ('s', 'ms', 'us', 'ns')
return unit
class DataFrameClient(InfluxDBClient):
"""
The ``DataFrameClient`` object holds information necessary to connect
to InfluxDB. Requests can be made to InfluxDB directly through the client.
The client reads and writes from pandas DataFrames.
"""
EPOCH = pd.Timestamp('1970-01-01 00:00:00.000+00:00')
def write_points(self, dataframe, measurement, tags=None,
time_precision=None, database=None, retention_policy=None,
batch_size=None):
"""
Write to multiple time series names.
:param dataframe: data points in a DataFrame
:param measurement: name of measurement
:param tags: dictionary of tags, with string key-values
:param time_precision: [Optional, default None] Either 's', 'ms', 'u'
or 'n'.
:param batch_size: [Optional] Value to write the points in batches
instead of all at one time. Useful for when doing data dumps from
one database to another or when doing a massive write operation
:type batch_size: int
"""
if batch_size:
number_batches = int(math.ceil(
len(dataframe) / float(batch_size)))
for batch in range(number_batches):
start_index = batch * batch_size
end_index = (batch + 1) * batch_size
points = self._convert_dataframe_to_json(
dataframe.ix[start_index:end_index].copy(),
measurement, tags, time_precision
)
super(DataFrameClient, self).write_points(
points, time_precision, database, retention_policy)
return True
else:
points = self._convert_dataframe_to_json(
dataframe, measurement, tags, time_precision
)
super(DataFrameClient, self).write_points(
points, time_precision, database, retention_policy)
return True
def query(self, query, chunked=False, database=None):
"""
Quering data into a DataFrame.
:param chunked: [Optional, default=False] True if the data shall be
retrieved in chunks, False otherwise.
"""
results = super(DataFrameClient, self).query(query, database=database)
if query.upper().startswith("SELECT"):
if len(results) > 0:
return self._to_dataframe(results)
else:
return {}
else:
return results
def _to_dataframe(self, rs):
result = {}
if isinstance(rs, list):
return map(self._to_dataframe, rs)
for key, data in rs.items():
name, tags = key
if tags is None:
key = name
else:
key = (name, tuple(sorted(tags.items())))
df = pd.DataFrame(data)
df.time = pd.to_datetime(df.time)
df.set_index('time', inplace=True)
df.index = df.index.tz_localize('UTC')
df.index.name = None
result[key] = df
return result
def _convert_dataframe_to_json(self, dataframe, measurement, tags=None,
time_precision=None):
if not isinstance(dataframe, pd.DataFrame):
raise TypeError('Must be DataFrame, but type was: {0}.'
.format(type(dataframe)))
if not (isinstance(dataframe.index, pd.tseries.period.PeriodIndex) or
isinstance(dataframe.index, pd.tseries.index.DatetimeIndex)):
raise TypeError('Must be DataFrame with DatetimeIndex or \
PeriodIndex.')
dataframe.index = dataframe.index.to_datetime()
if dataframe.index.tzinfo is None:
dataframe.index = dataframe.index.tz_localize('UTC')
# Convert column to strings
dataframe.columns = dataframe.columns.astype('str')
# Convert dtype for json serialization
dataframe = dataframe.astype('object')
precision_factor = {
"n": 1,
"u": 1e3,
"ms": 1e6,
"s": 1e9,
"m": 1e9 * 60,
"h": 1e9 * 3600,
}.get(time_precision, 1)
points = [
{'measurement': measurement,
'tags': tags if tags else {},
'fields': rec,
'time': int(ts.value / precision_factor)
}
for ts, rec in zip(dataframe.index, dataframe.to_dict('record'))]
return points
def _datetime_to_epoch(self, datetime, time_precision='s'):
seconds = (datetime - self.EPOCH).total_seconds()
if time_precision == 'h':
return seconds / 3600
elif time_precision == 'm':
return seconds / 60
elif time_precision == 's':
return seconds
elif time_precision == 'ms':
return seconds * 1e3
elif time_precision == 'u':
return seconds * 1e6
elif time_precision == 'n':
return seconds * 1e9
|
