How to keep column names when converting from pandas to numpy

Question

According to this post, I should be able to access the names of columns in an ndarray as a.dtype.names

Howevever, if I convert a pandas DataFrame to an ndarray with df.a

Answer 1

OK, here where I'm leaning:

class NDArrayWithColumns(np.ndarray):
    def __new__(cls, obj,  columns=None):
        obj = obj.view(cls)
        obj.columns = columns
        return obj

    def __array_finalize__(self, obj):
        if obj is None: return
        self.columns = getattr(obj, 'columns', None)

    @staticmethod
    def from_dataframe(df):
        cols = tuple(df.columns)
        arr = df.as_matrix(cols)
        return NDArrayWithColumns.from_array(arr,cols)

    @staticmethod
    def from_array(array,columns):
        if isinstance(array,NDArrayWithColumns):
            return array
        return NDArrayWithColumns(array,tuple(columns))

    def __str__(self):
        sup = np.ndarray.__str__(self)
        if self.columns:
            header = ", ".join(self.columns)
            header = "# " + header + "\n"
            return header+sup
        return sup

NAN = float("nan")
X = pd.DataFrame(dict(age=[40., NAN, 60.], sys_blood_pressure=[140.,150.,160.]))
arr = NDArrayWithColumns.from_dataframe(X)
print arr
print arr.columns
print arr.dtype

Gives:

# age, sys_blood_pressure
[[  40.  140.]
 [  nan  150.]
 [  60.  160.]]
('age', 'sys_blood_pressure')
float64

and can also be passed to types cython function expecting a ndarray[2,double_t].

UPDATE: this works pretty good except for some oddness when passing the type to ufuncs.