I am trying to group by multiple fields a table that has already been read in using petl (that is, it's a petl type). I am trying with the following piece of code:
import petl as etl
from collections import OrderedDict
csv_ea_flood_def = r'............' #Path to csv table
ea_flood_def = etl.fromcsv(csv_ea_flood_def)
aggreg = OrderedDict()
aggreg['count'] = len
aggreg['sum_length'] = 'length', sum
EA_Defence_Types = etl.aggregate(
ea_flood_def,
key = ('prot_type', 'asset_type', 'description'),
aggregation = aggreg,
)
This piece of code does not throw any error. However, the resulting table seems to be empty or corrupt in some way:
print(EA_Defence_Types[0]) will throw:
('prot_type', 'asset_type', 'description', 'count', 'sum_length') #which is fine
print(EA_Defence_Types[1]) will throw:
Traceback (most recent call last):
File "def_failure_prob.py", line 514, in <module>
main()
File "def_failure_prob.py", line 504, in main
def_fail_prob(con, cursor)
File "def_failure_prob.py", line 111, in def_fail_prob
print(EA_Defence_Types[1])
File "C:\ProgramData\Anaconda3\envs\env1\lib\site-packages\petl\util\base.py", line 172, in __getitem__
return super(Table, self).__getitem__(item)
File "C:\ProgramData\Anaconda3\envs\env1\lib\site-packages\petl\util\base.py", line 33, in __getitem__
return next(islice(self, item, item+1))
File "C:\ProgramData\Anaconda3\envs\env1\lib\site-packages\petl\transform\reductions.py", line 308, in itermultiaggregate
for k, rows in rowgroupby(it, key):
File "C:\ProgramData\Anaconda3\envs\env1\lib\site-packages\petl\util\base.py", line 715, in <genexpr>
return ((k.inner, vals) for (k, vals) in git)
File "C:\ProgramData\Anaconda3\envs\env1\lib\site-packages\petl\util\base.py", line 699, in <genexpr>
it = (Record(row, flds) for row in it)
File "C:\ProgramData\Anaconda3\envs\env1\lib\site-packages\petl\transform\sorts.py", line 354, in _iternocache
for row in _mergesorted(getkey, reverse, *chunkiters):
File "C:\ProgramData\Anaconda3\envs\env1\lib\site-packages\petl\transform\sorts.py", line 164, in _heapqmergesorted
for element in heapq.merge(*keyed_iterables):
File "C:\ProgramData\Anaconda3\envs\env1\lib\heapq.py", line 350, in merge
h_append([next(), order * direction, next])
File "C:\ProgramData\Anaconda3\envs\env1\lib\site-packages\petl\transform\sorts.py", line 162, in <genexpr>
keyed_iterables = [(_Keyed(key(obj), obj) for obj in iterable)
File "C:\ProgramData\Anaconda3\envs\env1\lib\site-packages\petl\transform\sorts.py", line 124, in _iterchunk
yield pickle.load(f)
TypeError: __new__() missing 1 required positional argument: 'flds'
I have no idea what that error could mean.
