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
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Dataset conversion script
Author: G.J.J. van den Burg
"""
import argparse
import clevercsv
import json
SAMPLE = 10
def date_to_iso(datestr):
mm, dd, yyyy = list(map(int, datestr.split("/")))
return f"{yyyy}-{mm:02d}-{dd:02d}"
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument("input_file", help="File to convert")
parser.add_argument("output_file", help="File to write to")
return parser.parse_args()
def main():
args = parse_args()
with open(args.input_file, "r", newline="", encoding="ascii") as fp:
reader = clevercsv.reader(
fp, delimiter=",", quotechar="", escapechar=""
)
rows = list(reader)
rows = rows[5:]
rows = list(reversed(rows))
rows = [r for i, r in enumerate(rows) if i % SAMPLE == 0]
idx2000 = next((i for i, x in enumerate(rows) if x[0].endswith("2000")))
rows = rows[idx2000:]
name = "brent_spot"
longname = "Brent Spot Price"
time = [date_to_iso(r[0]) for r in rows]
time_fmt = "%Y-%m-%d"
values = [float(r[1]) for r in rows]
series = [{"label": "Dollars/Barrel", "type": "float", "raw": values}]
data = {
"name": name,
"longname": longname,
"n_obs": len(time),
"n_dim": len(series),
"time": {
"type": "string",
"format": time_fmt,
"index": list(range(len(time))),
"raw": time,
},
"series": series,
}
with open(args.output_file, "w") as fp:
json.dump(data, fp, indent="\t")
if __name__ == "__main__":
main()
|
