Advertisement
Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- In [359]: df = pandas.DataFrame({'x': 3 * ['a'] + 2 * ['b'], 'y': np.random.normal(size=5), 'z': np.random.normal(size=5)})
- In [360]: df
- Out[360]:
- x y z
- 0 a 0.201980 -0.470388
- 1 a 0.190846 -2.089032
- 2 a -1.131010 0.227859
- 3 b -0.263865 -1.906575
- 4 b -1.335956 -0.722087
- In [361]: df.groupby('x').apply(lambda x: pandas.DataFrame({'r': (x.y + x.z).sum() / x.z.sum(), 's': (x.y + x.z ** 2).sum() / x.z.sum()}))
- ---------------------------------------------------------------------------
- ValueError Traceback (most recent call last)
- /home/emarkley/work/src/partner_analysis2/main.py in <module>()
- ----> 1 df.groupby('x').apply(lambda x: pandas.DataFrame({'r': (x.y + x.z).sum() / x.z.sum(), 's': (x.y + x.z ** 2).sum() / x.z.sum()}))
- /usr/local/lib/python3.2/site-packages/pandas-0.8.2.dev-py3.2-linux-x86_64.egg/pandas/core/groupby.py in apply(self, func, *args, **kwargs)
- 267 applied : type depending on grouped object and function
- 268 """
- --> 269 return self._python_apply_general(func, *args, **kwargs)
- 270
- 271 def aggregate(self, func, *args, **kwargs):
- /usr/local/lib/python3.2/site-packages/pandas-0.8.2.dev-py3.2-linux-x86_64.egg/pandas/core/groupby.py in _python_apply_general(self, func, *args, **kwargs)
- 417 group_axes = _get_axes(group)
- 418
- --> 419 res = func(group, *args, **kwargs)
- 420
- 421 if not _is_indexed_like(res, group_axes):
- /home/emarkley/work/src/partner_analysis2/main.py in <lambda>(x)
- ----> 1 df.groupby('x').apply(lambda x: pandas.DataFrame({'r': (x.y + x.z).sum() / x.z.sum(), 's': (x.y + x.z ** 2).sum() / x.z.sum()}))
- /usr/local/lib/python3.2/site-packages/pandas-0.8.2.dev-py3.2-linux-x86_64.egg/pandas/core/frame.py in __init__(self, data, index, columns, dtype, copy)
- 371 mgr = self._init_mgr(data, index, columns, dtype=dtype, copy=copy)
- 372 elif isinstance(data, dict):
- --> 373 mgr = self._init_dict(data, index, columns, dtype=dtype)
- 374 elif isinstance(data, ma.MaskedArray):
- 375 mask = ma.getmaskarray(data)
- /usr/local/lib/python3.2/site-packages/pandas-0.8.2.dev-py3.2-linux-x86_64.egg/pandas/core/frame.py in _init_dict(self, data, index, columns, dtype)
- 454 # figure out the index, if necessary
- 455 if index is None:
- --> 456 index = extract_index(data)
- 457 else:
- 458 index = _ensure_index(index)
- /usr/local/lib/python3.2/site-packages/pandas-0.8.2.dev-py3.2-linux-x86_64.egg/pandas/core/frame.py in extract_index(data)
- 4719
- 4720 if not indexes and not raw_lengths:
- -> 4721 raise ValueError('If use all scalar values, must pass index')
- 4722
- 4723 if have_series or have_dicts:
- ValueError: If use all scalar values, must pass index
- In [362]: df.groupby('x').apply(lambda x: pandas.DataFrame({'r': (x.y + x.z).sum() / x.z.sum(), 's': (x.y + x.z ** 2).sum() / x.z.sum()}, index=[0]))
- Out[362]:
- r s
- x
- a 0 1.316605 -1.672293
- b 0 1.608606 -0.972593
- In [26]: df.groupby('x').apply(lambda x:
- Series({'r': (x.y + x.z).sum() / x.z.sum(),
- 's': (x.y + x.z ** 2).sum() / x.z.sum()}))
- Out[26]:
- r s
- x
- a -0.338590 -0.916635
- b 66.655533 102.566146
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement