`panel_structure_stats()` returns a generic `numpy` error if `ids` are negative

[NauelSerraino]

The function np.bincount(ids) returns a generic ValueError: 'list' argument must have no negative elements.

linearmodels/linearmodels/panel/model.py

Lines 97 to 102 in 9288df3

	def panel_structure_stats(ids: IntArray, name: str) -> Series:
	bc = np.bincount(ids)
	bc = bc[bc > 0]
	index = ["mean", "median", "max", "min", "total"]
	out = [bc.mean(), np.median(bc), bc.max(), bc.min(), bc.shape[0]]
	return Series(out, index=index, name=name)

In my case that happened due to some NaN within the entity effect, which lead to negative values (-1) in the ids.

In my opinion, both the properties entity_ids and time_ids should return an error if the elements in the index contains some NaN (since I had a quite hard time figuring it out).

linearmodels/linearmodels/panel/data.py

Lines 365 to 389 in 9288df3

	@property
	def entity_ids(self) -> IntArray:
	"""
	Get array containing entity group membership information
	Returns
	-------
	ndarray
	2d array containing entity ids corresponding dataframe view
	"""
	index = self.index
	return np.asarray(index.codes[0])[:, None]
	@property
	def time_ids(self) -> IntArray:
	"""
	Get array containing time membership information
	Returns
	-------
	ndarray
	2d array containing time ids corresponding dataframe view
	"""
	index = self.index
	return np.asarray(index.codes[1])[:, None]

If necessary, I would be happy to work on that.