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
|
"""
Import VIX - CBOE Volatility Index - from "vix-daily.csv" file into InfluxDB 2.0
https://datahub.io/core/finance-vix#data
"""
from collections import OrderedDict
from csv import DictReader
import reactivex as rx
from reactivex import operators as ops
from influxdb_client import Point, InfluxDBClient, WriteOptions
def parse_row(row: OrderedDict):
"""Parse row of CSV file into Point with structure:
financial-analysis,type=vix-daily close=18.47,high=19.82,low=18.28,open=19.82 1198195200000000000
CSV format:
Date,VIX Open,VIX High,VIX Low,VIX Close\n
2004-01-02,17.96,18.68,17.54,18.22\n
2004-01-05,18.45,18.49,17.44,17.49\n
2004-01-06,17.66,17.67,16.19,16.73\n
2004-01-07,16.72,16.75,15.5,15.5\n
2004-01-08,15.42,15.68,15.32,15.61\n
2004-01-09,16.15,16.88,15.57,16.75\n
...
:param row: the row of CSV file
:return: Parsed csv row to [Point]
"""
"""
For better performance is sometimes useful directly create a LineProtocol to avoid unnecessary escaping overhead:
"""
# from datetime import timezone
# import ciso8601
# from influxdb_client.client.write.point import EPOCH
#
# time = (ciso8601.parse_datetime(row["Date"]).replace(tzinfo=timezone.utc) - EPOCH).total_seconds() * 1e9
# return f"financial-analysis,type=vix-daily" \
# f" close={float(row['VIX Close'])},high={float(row['VIX High'])},low={float(row['VIX Low'])},open={float(row['VIX Open'])} " \
# f" {int(time)}"
return Point("financial-analysis") \
.tag("type", "vix-daily") \
.field("open", float(row['VIX Open'])) \
.field("high", float(row['VIX High'])) \
.field("low", float(row['VIX Low'])) \
.field("close", float(row['VIX Close'])) \
.time(row['Date'])
"""
Converts vix-daily.csv into sequence of data point
"""
data = rx \
.from_iterable(DictReader(open('vix-daily.csv', 'r'))) \
.pipe(ops.map(lambda row: parse_row(row)))
with InfluxDBClient(url="http://localhost:8086", token="my-token", org="my-org", debug=True) as client:
"""
Create client that writes data in batches with 50_000 items.
"""
with client.write_api(write_options=WriteOptions(batch_size=50_000, flush_interval=10_000)) as write_api:
"""
Write data into InfluxDB
"""
write_api.write(bucket="my-bucket", record=data)
"""
Querying max value of CBOE Volatility Index
"""
query = 'from(bucket:"my-bucket")' \
' |> range(start: 0, stop: now())' \
' |> filter(fn: (r) => r._measurement == "financial-analysis")' \
' |> max()'
result = client.query_api().query(query=query)
"""
Processing results
"""
print()
print("=== results ===")
print()
for table in result:
for record in table.records:
print('max {0:5} = {1}'.format(record.get_field(), record.get_value()))
|
