occucoder/format.py at master · blackmlengineer/occucoder · GitHub

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
import csv
import json

files = [
	"taxonomies/onet_2006.txt",
	"taxonomies/onet_2009.txt",
	"taxonomies/onet_2010.txt",
	"taxonomies/onet_2019.txt",
]


for file in files:
	template = {
		"taxonomy_level_codes" : ["8"],
		"taxonomies" : { "8" : []}
	}
	with open(file,"r") as f:
		csvf = csv.DictReader(f, delimiter = '\t')
		for row in csvf:
			template["taxonomies"]["8"].append({
				"id" : row["O*NET-SOC Code"],
				"name" : row["Title"],
				"description" : row["Description"]
			})
		with open(f"jobcoder/{file.split('.')[0]}.json","w") as fw:
			json.dump(template, fw, indent = 2)


template = {
	"taxonomy_level_codes" : ["6"],
	"taxonomies" : { "6" : []}
}
with open("taxonomies/soc_2000.csv","r") as f:
	csvf = csv.DictReader(f)
	for row in csvf:
		template["taxonomies"]["6"].append({
			"id" : row["2000 SOC code"],
			"name" : row["2000 SOC title"],
			"description" : row["2000 SOC definition"]
		})
	with open(f"jobcoder/taxonomies/soc_2000.json","w") as fw:
			json.dump(template, fw, indent = 2)


template = {
	"taxonomy_level_codes" : ["6"],
	"taxonomies" : { "6" : []}
}
with open("taxonomies/soc_2010.csv","r") as f:
	csvf = csv.DictReader(f)
	for row in csvf:
		template["taxonomies"]["6"].append({
			"id" : row["SOC Code"],
			"name" : row["SOC Title"],
			"description" : row["SOC Definition"]
		})
	with open(f"jobcoder/taxonomies/soc_2010.json","w") as fw:
			json.dump(template, fw, indent = 2)


template = {
	"taxonomy_level_codes" : [],
	"taxonomies" : {}
}
with open("taxonomies/soc_2018.csv","r") as f:
	csvf = csv.DictReader(f)
	for row in csvf:
		if row["SOC Group"] not in template["taxonomy_level_codes"]:
			template["taxonomy_level_codes"].append(row['SOC Group'])
			template["taxonomies"][row["SOC Group"]] = []

		template["taxonomies"][row["SOC Group"]].append({
			"id" : row["SOC Code"],
			"name" : row["SOC Title"],
			"description" : row["SOC Definition"]
		})
	with open(f"jobcoder/taxonomies/soc_2018.json","w") as fw:
			json.dump(template, fw, indent = 2)