ponyExpress/wrang.py at master · Gabxi/ponyExpress · 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
from wrangler import dw
import sys

if(len(sys.argv) < 3):
	sys.exit('Error: Please include an input and output file.  Example python script.py input.csv output.csv')

w = dw.DataWrangler()

# Split data repeatedly on newline  into  rows
w.add(dw.Split(column=["data"],
               table=0,
               status="active",
               drop=True,
               result="row",
               update=False,
               insert_position="right",
               row=None,
               on="\n",
               before=None,
               after=None,
               ignore_between=None,
               which=1,
               max=0,
               positions=None,
               quote_character=None))

# Split data repeatedly on ','
w.add(dw.Split(column=["data"],
               table=0,
               status="active",
               drop=True,
               result="column",
               update=False,
               insert_position="right",
               row=None,
               on=",",
               before=None,
               after=None,
               ignore_between=None,
               which=1,
               max=0,
               positions=None,
               quote_character=None))

# Delete  rows where split2 = 'Discontinued'
w.add(dw.Filter(column=[],
                table=0,
                status="active",
                drop=False,
                row=dw.Row(column=[],
             table=0,
             status="active",
             drop=False,
             conditions=[dw.Eq(column=[],
            table=0,
            status="active",
            drop=False,
            lcol="split2",
            value="Discontinued",
            op_str="=")])))

# Delete  rows where split5 = '0'
w.add(dw.Filter(column=[],
                table=0,
                status="active",
                drop=False,
                row=dw.Row(column=[],
             table=0,
             status="active",
             drop=False,
             conditions=[dw.Eq(column=[],
            table=0,
            status="active",
            drop=False,
            lcol="split5",
            value="0",
            op_str="=")])))

w.apply_to_file(sys.argv[1]).print_csv(sys.argv[2])