def rec_groupby(a, keynames, *fun_fields_name):
'''A special version of np_groupby for record arrays, somewhat similar
to the function found in matplotlib.mlab.rec_groupby.
This is basically a wrapper around np_groupy that automatically
generates lambda's like the ones in the np_groupby doc string.
That same call would look like this using rec_grouby:
rec_groupby(a, ['m', 'n'], (np.mean, 'o', 'mean_o'),
(np.std, 'o', 'std_o'),
(np.min, 'p', 'min_p'))
and the second function could be written as:
def compute_some_thing(x):
o, p = x['o'], x['p']
return np.mean(o) / np.std(o) * np.min(p)
rec_groupby(a, ['m', 'n'],
(compute_some_thing, ['o', 'p'], 'its_complicated'))
In general, this function is faster than matplotlib.mlab, but not
as fast as pandas and probably misses some corner cases for each :)
'''
keynames = list(keynames) if islistlike(keynames) else [keynames]
keyarr = fields_view(a, keynames)
funs, fields_list, names = zip(*fun_fields_name)
functions = [_outfielder(fun, fields)
for fun, fields, name in fun_fields_name]
names = [i[-1] for i in fun_fields_name]
return np_groupby(keyarr, a, *functions, names=keynames + names)
def fields_view(arr, fields):
'''Select fields from a record array without a copy
Taken from:
http://stackoverflow.com/questions/15182381/how-to-return-a-view-of-several-columns-in-numpy-structured-array
'''
fields = fields if islistlike(fields) else [fields]
newdtype = np.dtype({name: arr.dtype.fields[name] for name in fields})
return np.ndarray(arr.shape, newdtype, arr, 0, arr.strides)
