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
|
#!/usr/bin/env python
"""
Do stuff with csv files.
"""
import optparse
import defapp
import csv
import operator
from collections import defaultdict as defdict
o = optparse.make_option
opts = [
o('-x', '--exchange', action='append', dest='col_xchg',
nargs=2, type='int',
help='Columns that should be switched with reorder.'),
o('-c', '--column', action='store', dest='col', type='int',
help='The column on which to operate.'),
# o(None, '--true', action='store_true', dest='truth',
# help='A boolean flag value.'),
# o(None, '--degree', action='store', type='float', dest='thruthiness',
# help='Not quite absolut truth.'),
]
defaults = {
'col' : 0,
'col_xcgh' : [],
}
def make_vector_op(op):
def vector_op(a, b, defvalue=0):
if len(a) > len(b):
shorter = b
longer = a
else:
shorter = a
longer = b
c = list(longer)
for i in xrange(len(shorter)):
c[i] = op(longer[i], shorter[i])
for i in xrange(len(shorter), len(longer)):
c[i] = op(longer[i], defvalue)
return c
return vector_op
def make_scalar_op(op):
def scalar_op(scalar, a):
return [op(x, scalar) for x in a]
return scalar_op
row_add = make_vector_op(operator.add)
row_min = make_vector_op(min)
row_max = make_vector_op(max)
def row_reduce(row_op, fixup=lambda key, rows, res: res):
def _reduce(order, by_key):
for key in order:
if key in by_key:
rows = by_key[key]
res = reduce(row_op, rows)
del by_key[key]
yield fixup(key, rows, res)
return _reduce
row_mul = make_scalar_op(operator.mul)
row_div = make_scalar_op(operator.div)
def transpose(rows):
rows = list(rows)
if rows:
r = len(rows)
c = max([len(x) for x in rows])
def at(x, y):
try:
return rows[x][y]
except IndexError:
return 0
for i in xrange(c):
yield [at(j, i) for j in xrange(r) ]
def reorder_columns(rows, xchg_pairs):
for r in rows:
print type(r)
for (x,y) in xchg_pairs:
r[x], r[y] = r[y], r[x]
yield r
def select_by_key(rows, col, cast=None):
by_key = defdict(list)
order = []
for r in rows:
key = r[col]
if cast:
by_key[key] += [[cast(x) for x in r]]
else:
by_key[key] += [r]
order += [key]
return (order, by_key)
class CsvApp(defapp.App):
def __init__(self):
defapp.App.__init__(self, opts, defaults)
self.options.col -= 1
self.options.col_xchg = [(x - 1, y - 1) for (x, y) in
self.options.col_xchg]
def transform(self, make_iterator, ordered=True):
"""Average all rows with the same key in a given column."""
files = list(self.args)
del files[0]
for fn in files:
try:
# read in content
rows = csv.reader(open(fn, 'r'))
# set up transformation
if ordered:
(order, by_key) = select_by_key(rows, self.options.col,
float)
rows = make_iterator(order, by_key)
else:
rows = make_iterator(rows)
# write out
csv.writer(self.outfile()).writerows(rows)
except IOError, ex:
self.err("%s:%s" % (fn, str(ex)))
except IndexError, ex:
self.err("%s: Sorry, index out of range." % fn)
def do_avg(self, _):
def fixup_avg(key, rows, res):
res = row_div(len(rows), res)
res[self.options.col] = key
return res
self.transform(row_reduce(row_add, fixup_avg))
def do_max(self, _):
self.transform(row_reduce(row_max))
def do_min(self, _):
self.transform(row_reduce(row_min))
def do_transpose(self, _):
self.transform(transpose, ordered=False)
def do_reorder(self, _):
self.transform(lambda rows: reorder_columns(rows,
self.options.col_xchg),
ordered=False)
if __name__ == '__main__':
CsvApp().launch()
|
