Closed
Description
Using the latest git version of pandas (705b677) I have exerienced the
following problems:
In [1]: a = pd.DataFrame(index=pd.Index(xrange(1,11)))
In [2]: a['foo'] = np.zeros(10, dtype=np.float)
In [3]: a['bar'] = np.zeros(10, dtype=np.complex)
In [4]: a.ix[2:5, 'bar']
Out[4]:
2 0j
3 0j
4 0j
5 0j
Name: bar, dtype: complex128
In [5]: a.ix[2:5, 'bar'] = np.array([2.33j, 1.23+0.1j, 2.2])
# invalid input (RHS has wrong size) -> does not throw an exception!
# (The reason why no exception is thrown is because of the different
# dtype of a['foo'] - see ``In[9]-In[10]``
In [6]: a
Out[6]:
foo bar
1 0 0j
2 0 2.33j
3 0 2.33j
4 0 2.33j
5 0 2.33j
6 0 0j
7 0 0j
8 0 0j
9 0 0j
10 0 0j
In [7]: a.ix[2:5, 'bar'] = np.array([2.33j, 1.23+0.1j, 2.2, 1.0]) # valid
In [8]: a
Out[8]:
foo bar
1 0 0j
2 0 2.33j
3 0 (1.23+0.1j)
4 0 (2.2+0j)
5 0 (1+0j)
6 0 0j
7 0 0j
8 0 0j
9 0 0j
10 0 0j
In [9]: a = pd.DataFrame(index=pd.Index(xrange(1,11)))
In [10]: a['bar'] = np.zeros(10, dtype=np.complex)
In [11]: a.ix[2:5, 'bar'] = np.array([2.33j, 1.23+0.1j, 2.2])
# invalid RHS-> exception raised OK!
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-11-bde45910cde6> in <module>()
----> 1 a.ix[2:5, 'bar'] = np.array([2.33j, 1.23+0.1j, 2.2])
/home/thomas/.local/lib/python2.7/site-packages/pandas-0.12.0_1098_g705b677-py2.7-linux-x86_64.egg/pandas/core/indexing.pyc in __setitem__(self, key, value)
92 indexer = self._convert_to_indexer(key, is_setter=True)
93
---> 94 self._setitem_with_indexer(indexer, value)
95
96 def _has_valid_type(self, k, axis):
/home/thomas/.local/lib/python2.7/site-packages/pandas-0.12.0_1098_g705b677-py2.7-linux-x86_64.egg/pandas/core/indexing.pyc in _setitem_with_indexer(self, indexer, value)
387 value = self._align_panel(indexer, value)
388
--> 389 self.obj._data = self.obj._data.setitem(indexer,value)
390 self.obj._maybe_update_cacher(clear=True)
391
/home/thomas/.local/lib/python2.7/site-packages/pandas-0.12.0_1098_g705b677-py2.7-linux-x86_64.egg/pandas/core/internals.pyc in setitem(self, *args, **kwargs)
2182
2183 def setitem(self, *args, **kwargs):
-> 2184 return self.apply('setitem', *args, **kwargs)
2185
2186 def putmask(self, *args, **kwargs):
/home/thomas/.local/lib/python2.7/site-packages/pandas-0.12.0_1098_g705b677-py2.7-linux-x86_64.egg/pandas/core/internals.pyc in apply(self, f, *args, **kwargs)
2162
2163 else:
-> 2164 applied = getattr(blk, f)(*args, **kwargs)
2165
2166 if isinstance(applied, list):
/home/thomas/.local/lib/python2.7/site-packages/pandas-0.12.0_1098_g705b677-py2.7-linux-x86_64.egg/pandas/core/internals.pyc in setitem(self, indexer, value)
580 try:
581 # set and return a block
--> 582 values[indexer] = value
583
584 # coerce and try to infer the dtypes of the result
ValueError: could not broadcast input array from shape (3) into shape (4)Here is the 2nd problem:
In [1]: b = pd.DataFrame(index=pd.Index(xrange(1,11)))
In [2]: b['foo'] = np.zeros(10, dtype=np.float)
In [3]: b['bar'] = np.zeros(10, dtype=np.complex)
In [4]: b
Out[4]:
foo bar
1 0 0j
2 0 0j
3 0 0j
4 0 0j
5 0 0j
6 0 0j
7 0 0j
8 0 0j
9 0 0j
10 0 0j
In [5]: b[2:5]
Out[5]:
foo bar
3 0 0j
4 0 0j
5 0 0j
In [6]: b[2:5] = np.arange(1,4)*1j
# invalid input (wrong size on RHS)
In [7]: b
Out[7]:
foo bar
1 0j 0j
2 0j 0j
3 1j 2j
4 1j 2j
5 1j 2j
6 0j 0j
7 0j 0j
8 0j 0j
9 0j 0j
10 0j 0j
# why does the expression in ``In [6]`` change the dtype of b['foo'].
# Is this intended ?
In [8]: b[2:5] = np.arange(1,4)*1j # invalid input (wrong size on RHS)
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-8-a729140e3f7f> in <module>()
----> 1 b[2:5] = np.arange(1,4)*1j # invalid input (wrong size on RHS)
/home/thomas/.local/lib/python2.7/site-packages/pandas-0.12.0_1098_g705b677-py2.7-linux-x86_64.egg/pandas/core/frame.pyc in __setitem__(self, key, value)
1831 indexer = _convert_to_index_sliceable(self, key)
1832 if indexer is not None:
-> 1833 return self._setitem_slice(indexer, value)
1834
1835 if isinstance(key, (Series, np.ndarray, list)):
/home/thomas/.local/lib/python2.7/site-packages/pandas-0.12.0_1098_g705b677-py2.7-linux-x86_64.egg/pandas/core/frame.pyc in _setitem_slice(self, key, value)
1842
1843 def _setitem_slice(self, key, value):
-> 1844 self.ix._setitem_with_indexer(key, value)
1845
1846 def _setitem_array(self, key, value):
/home/thomas/.local/lib/python2.7/site-packages/pandas-0.12.0_1098_g705b677-py2.7-linux-x86_64.egg/pandas/core/indexing.pyc in _setitem_with_indexer(self, indexer, value)
387 value = self._align_panel(indexer, value)
388
--> 389 self.obj._data = self.obj._data.setitem(indexer,value)
390 self.obj._maybe_update_cacher(clear=True)
391
/home/thomas/.local/lib/python2.7/site-packages/pandas-0.12.0_1098_g705b677-py2.7-linux-x86_64.egg/pandas/core/internals.pyc in setitem(self, *args, **kwargs)
2182
2183 def setitem(self, *args, **kwargs):
-> 2184 return self.apply('setitem', *args, **kwargs)
2185
2186 def putmask(self, *args, **kwargs):
/home/thomas/.local/lib/python2.7/site-packages/pandas-0.12.0_1098_g705b677-py2.7-linux-x86_64.egg/pandas/core/internals.pyc in apply(self, f, *args, **kwargs)
2162
2163 else:
-> 2164 applied = getattr(blk, f)(*args, **kwargs)
2165
2166 if isinstance(applied, list):
/home/thomas/.local/lib/python2.7/site-packages/pandas-0.12.0_1098_g705b677-py2.7-linux-x86_64.egg/pandas/core/internals.pyc in setitem(self, indexer, value)
580 try:
581 # set and return a block
--> 582 values[indexer] = value
583
584 # coerce and try to infer the dtypes of the result
ValueError: could not broadcast input array from shape (3) into shape (3,2)