pandas 和 numpy 的意思不同

Nothing extraordinary going on with numpy's version. It's the pandas version that's a little wacky.

我们来看看df['x'].mean():

>>> def test_it_2():
...   import pdb; pdb.set_trace()
...   df['x'].mean()
>>> test_it_2()
... # Some stepping/poking around that isn't important
(Pdb) l
2307
2308            if we have an ndarray as a value, then simply perform the operation,
2309            otherwise delegate to the object
2310
2311            """
2312 ->         delegate = self._values
2313            if isinstance(delegate, np.ndarray):
2314                # Validate that 'axis' is consistent with Series's single axis.
2315                self._get_axis_number(axis)
2316                if numeric_only:
2317                    raise NotImplementedError('Series.{0} does not implement '
(Pdb) delegate.dtype
dtype('float32')
(Pdb) l
2315                self._get_axis_number(axis)
2316                if numeric_only:
2317                    raise NotImplementedError('Series.{0} does not implement '
2318                                              'numeric_only.'.format(name))
2319                with np.errstate(all='ignore'):
2320 ->                 return op(delegate, skipna=skipna, **kwds)
2321
2322            return delegate._reduce(op=op, name=name, axis=axis, skipna=skipna,
2323                                    numeric_only=numeric_only,
2324                                    filter_type=filter_type, **kwds)

所以我们找到了问题所在，但现在事情变得有点奇怪:

(Pdb) op
<function nanmean at 0x000002CD8ACD4488>
(Pdb) op(delegate)
-9.0
(Pdb) delegate_64 = delegate.astype(np.float64)
(Pdb) op(delegate_64)
-9.000003749978807
(Pdb) delegate.mean()
-9.0000029
(Pdb) delegate_64.mean()
-9.0000037499788075
(Pdb) np.nanmean(delegate, dtype=np.float64)
-9.0000037499788075
(Pdb) np.nanmean(delegate, dtype=np.float32)
-9.0000029

(Pdb) import inspect
(Pdb) src = inspect.getsource(op).split("
")
(Pdb) for line in src: print(line)
@disallow('M8')
@bottleneck_switch()
def nanmean(values, axis=None, skipna=True):
    values, mask, dtype, dtype_max = _get_values(values, skipna, 0)

    dtype_sum = dtype_max
    dtype_count = np.float64
    if is_integer_dtype(dtype) or is_timedelta64_dtype(dtype):
        dtype_sum = np.float64
    elif is_float_dtype(dtype):
        dtype_sum = dtype
        dtype_count = dtype
    count = _get_counts(mask, axis, dtype=dtype_count)
    the_sum = _ensure_numeric(values.sum(axis, dtype=dtype_sum))

    if axis is not None and getattr(the_sum, 'ndim', False):
        the_mean = the_sum / count
        ct_mask = count == 0
        if ct_mask.any():
            the_mean[ct_mask] = np.nan
    else:
        the_mean = the_sum / count if count > 0 else np.nan

    return _wrap_results(the_mean, dtype)

import bottleneck as bn
...
class bottleneck_switch(object):

    def __init__(self, **kwargs):
        self.kwargs = kwargs

    def __call__(self, alt):
        bn_name = alt.__name__

        try:
            bn_func = getattr(bn, bn_name)
        except (AttributeError, NameError):  # pragma: no cover
            bn_func = None
    ...

                if (_USE_BOTTLENECK and skipna and
                        _bn_ok_dtype(values.dtype, bn_name)):
                    result = bn_func(values, axis=axis, **kwds)

(Pdb) l
 93                             result = np.empty(result_shape)
 94                             result.fill(0)
 95                             return result
 96
 97                     if (_USE_BOTTLENECK and skipna and
 98  ->                         _bn_ok_dtype(values.dtype, bn_name)):
 99                         result = bn_func(values, axis=axis, **kwds)
100
101                         # prefer to treat inf/-inf as NA, but must compute the fun
102                         # twice :(
103                         if _has_infs(result):
(Pdb) n
> d:anaconda3libsite-packagespandascore
anops.py(99)f()
-> result = bn_func(values, axis=axis, **kwds)
(Pdb) alt
<function nanmean at 0x000001D2C8C04378>
(Pdb) alt.__name__
'nanmean'
(Pdb) bn_func
<built-in function nanmean>
(Pdb) bn_name
'nanmean'
(Pdb) bn_func(values, axis=axis, **kwds)
-9.0

(Pdb) from pandas.core.nanops import _get_counts
(Pdb) from pandas.core.nanops import _get_values
(Pdb) from pandas.core.nanops import _ensure_numeric
(Pdb) values, mask, dtype, dtype_max = _get_values(delegate, skipna=skipna)
(Pdb) count = _get_counts(mask, axis=None, dtype=dtype)
(Pdb) count
900000.0
(Pdb) values.sum(axis=None, dtype=dtype) / count
-9.0000029

(Pdb) import bottleneck as bn
(Pdb) bn.nanmean(delegate)
-9.0
(Pdb) bn.nanmean(delegate.astype(np.float64))
-9.000003749978807

In [1]: import numpy as np; import pandas as pd

In [2]: x=np.random.normal(-9.8,.05,size=900000)

In [3]: y_32 = x.astype(np.float32)

In [13]: %timeit np.nanmean(y_32)
100 loops, best of 3: 5.72 ms per loop

In [14]: %timeit bn.nanmean(y_32)
1000 loops, best of 3: 854 µs per loop