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
|
#!/usr/bin/env python
# -*- coding: utf-8 -*-
"""
Collect the iceland_tourism dataset
See the README file for more information.
Author: G.J.J. van den Burg
License: This file is part of TCPD, see the top-level LICENSE file.
Copyright: 2019, The Alan Turing Institute
"""
import argparse
import hashlib
import json
import os
import xlrd
from functools import wraps
from urllib.request import urlretrieve
XLSX_URL = "https://web.archive.org/web/20191121170223if_/https://www.ferdamalastofa.is/static/files/ferdamalastofa/Frettamyndir/2019/nov/visitors-to-iceland-2002-2019-oct.xlsx"
MD5_XLSX = "ec777afd95b01ca901aa00475fc284e5"
MD5_JSON = "8bbac4ca95319a865f2d58ff564f063d"
NAME_XLSX = "visitors-to-iceland-2002-2019-oct.xlsx"
NAME_JSON = "iceland_tourism.json"
MONTHS = {
"January": 1,
"February": 2,
"March": 3,
"April": 4,
"May": 5,
"June": 6,
"July": 7,
"August": 8,
"September": 9,
"October": 10,
"November": 11,
"December": 12,
}
class ValidationError(Exception):
def __init__(self, filename):
self.message = (
"Validating the file '%s' failed. \n"
"Please raise an issue on the GitHub page for this project \n"
"if the error persists." % filename
)
def check_md5sum(filename, checksum):
with open(filename, "rb") as fp:
data = fp.read()
h = hashlib.md5(data).hexdigest()
return h == checksum
def validate(checksum):
"""Decorator that validates the target file."""
def validate_decorator(func):
@wraps(func)
def wrapper(*args, **kwargs):
target = kwargs.get("target_path", None)
if os.path.exists(target) and check_md5sum(target, checksum):
return
out = func(*args, **kwargs)
if not os.path.exists(target):
raise FileNotFoundError("Target file expected at: %s" % target)
if not check_md5sum(target, checksum):
raise ValidationError(target)
return out
return wrapper
return validate_decorator
@validate(MD5_XLSX)
def download_xlsx(target_path=None):
urlretrieve(XLSX_URL, target_path)
def format_ym(year, month):
midx = MONTHS[month]
return "%i-%02d" % (int(year), midx)
@validate(MD5_JSON)
def write_json(xlsx_path, target_path=None):
wb = xlrd.open_workbook(xlsx_path)
ws = wb.sheet_by_index(2)
# hardcoding these row indices, not worth doing it nicely
header = ws.row(2)
column_idx = [
i
for i, c in enumerate(header)
if c.ctype == xlrd.XL_CELL_NUMBER and 2003 <= c.value < 2020
]
visitors = []
r_offset = 3
for c in column_idx:
for r in range(r_offset, r_offset + 12):
cell = ws.cell(r, c)
if cell.ctype == xlrd.XL_CELL_EMPTY:
continue
year = header[c].value
month = ws.cell(r, 0).value
datestr = format_ym(year, month)
# eliminate some observations that were not in the original dataset
if datestr in ["2019-08", "2019-09", "2019-10"]:
continue
item = {"time": datestr, "value": int(cell.value)}
visitors.append(item)
name = "iceland_tourism"
longname = "Iceland Tourism"
data = {
"name": name,
"longname": longname,
"n_obs": len(visitors),
"n_dim": 1,
"time": {
"format": "%Y-%m",
"index": list(range(len(visitors))),
"raw": [v["time"] for v in visitors],
},
"series": [
{
"label": "Visitor Number",
"type": "int",
"raw": [v["value"] for v in visitors],
}
],
}
with open(target_path, "w") as fp:
json.dump(data, fp, indent="\t")
def collect(output_dir="."):
xlsx_path = os.path.join(output_dir, NAME_XLSX)
json_path = os.path.join(output_dir, NAME_JSON)
download_xlsx(target_path=xlsx_path)
write_json(xlsx_path, target_path=json_path)
def clean(output_dir="."):
xlsx_path = os.path.join(output_dir, NAME_XLSX)
json_path = os.path.join(output_dir, NAME_JSON)
if os.path.exists(xlsx_path):
os.unlink(xlsx_path)
if os.path.exists(json_path):
os.unlink(json_path)
def parse_args():
parser = argparse.ArgumentParser()
parser.add_argument(
"-o", "--output-dir", help="output directory to use", default="."
)
parser.add_argument(
"action",
choices=["collect", "clean"],
help="Action to perform",
default="collect",
nargs="?",
)
return parser.parse_args()
def main(output_dir="."):
args = parse_args()
if args.action == "collect":
collect(output_dir=args.output_dir)
elif args.action == "clean":
clean(output_dir=args.output_dir)
if __name__ == "__main__":
main()
|
