column.py 文件源码

def substitute_values(self, vect):
        """
        Internal method to substitute integers into the vector, and construct
        metadata to convert back to the original vector.

        np.nan is always given -1, all other objects are given integers in
        order of apperence.

        Parameters
        ----------
        vect : np.array
            the vector in which to substitute values in
        """

        try:
            unique = np.unique(vect)
        except:
            unique = set(vect)

        unique = [
            x for x in unique if not isinstance(x, float) or not isnan(x)
        ]

        arr = np.copy(vect)
        for new_id, value in enumerate(unique):
            np.place(arr, arr==value, new_id)
            self.metadata[new_id] = value
        arr = arr.astype(np.float)
        np.place(arr, np.isnan(arr), -1)
        self.arr = arr

        if -1 in arr:
            self.metadata[-1] = self._missing_id