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
|
# -*- coding: utf-8 -*-
# <nbformat>3.0</nbformat>
# <codecell>
data = """type,price,quantity
Apples
Cortland,0.30,24
Red Delicious,0.40,24
Oranges
Navel,0.50,12
"""
# <codecell>
import petl.interactive as etl
from petl.io import StringSource
# <codecell>
tbl1 = (etl
.fromcsv(StringSource(data))
)
tbl1
# <headingcell level=2>
# Option 1 - using existing petl functions
# <codecell>
def make_room_for_category(row):
if len(row) == 1:
return (row[0], 'X', 'X', 'X')
else:
return (None,) + tuple(row)
tbl2 = tbl1.rowmap(make_room_for_category, fields=['category', 'type', 'price', 'quantity'])
tbl2
# <codecell>
tbl3 = tbl2.filldown()
tbl3
# <codecell>
tbl4 = tbl3.ne('type', 'X')
tbl4
# <headingcell level=2>
# Option 2 - custom transformer
# <codecell>
class CustomTransformer(object):
def __init__(self, source):
self.source = source
def __iter__(self):
it = iter(self.source)
# construct new header
source_fields = it.next()
out_fields = ('category',) + tuple(source_fields)
yield out_fields
# transform data
current_category = None
for row in it:
if len(row) == 1:
current_category = row[0]
else:
yield (current_category,) + tuple(row)
# <codecell>
tbl5 = CustomTransformer(tbl1)
# <codecell>
# just so it formats nicely as HTML in the notebook...
etl.wrap(tbl5)
|
