import numpy as np
from collections.abc import Callable
from params import RbmParams
from state import RbmState
from matrix import sample, prob, rms_error_accu
from status import Status

class Entity:
	def __init__(self, shape: tuple[int, int], params: RbmParams):
		self.state = RbmState.from_layer_params(shape)
		self.params = params

	def train(self, batch: np.ndarray, cd_func: Callable, status: Status):
		training_remain = batch.shape[0]
		batch_size = min(self.params.mini_batch_size, training_remain)
		if batch_size == 0:
			batch_size = training_remain

		status.on_change()
		d_progress = 100.0 / (training_remain*self.params.num_epochs)
		progress = 0
		batch_row_index = 0
		keep_running = True
		while training_remain > 0 and keep_running:
			batch_size_remain = min(batch_size, training_remain)
			mini_batch = batch[batch_row_index:batch_row_index + batch_size_remain]
			training_remain -= batch_size_remain
			batch_row_index += batch_size_remain

			inc_bv = np.zeros(self.state.b_v.shape)
			inc_bh = np.zeros(self.state.b_h.shape)
			inc_whv = np.zeros(self.state.w_hv.shape)

			v_states = mini_batch
			if self.params.do_batch_sample:
				v_states = sample(mini_batch)

			for epochs in range(self.params.num_epochs):
				# Contrastive divergence learning: calculate gradients
				dwhv, dbv, dbh = cd_func(v_states, self.params, self.v_to_ph, self.h_to_pv)

				# Adjust weight and biases
				kl = self.params.learning_rate/batch_size
				inc_bv = self.params.momentum*inc_bv + kl*dbv
				inc_bh = self.params.momentum*inc_bh + kl*dbh
				inc_whv = self.params.momentum*inc_whv + kl*dwhv - self.params.weight_decay*self.state.w_hv

				self.state.b_v += inc_bv
				self.state.b_h += inc_bh
				self.state.w_hv += inc_whv

				# check if status update is needed
				if status.want_report(round(progress)):
					# Calculate	error
					err_rms = rms_error_accu(mini_batch - self.h_to_pv(self.v_to_ph(v_states)))
					if not status.on_change({"progress": {"value": round(progress), "unit": "%"},
											 "err_rms": {"value": err_rms, "unit": ""}}):
						keep_running = False
						break

				progress += d_progress*batch_size_remain

		# Update final status
		err_rms = rms_error_accu(batch - self.h_to_pv(self.v_to_ph(batch)))
		status.on_change({"progress": {"value": round(progress), "unit": "%"},
						  "err_rms_total": {"value": err_rms, "unit": ""}})

	def v_to_ph(self, v: np.ndarray) -> np.ndarray:
		state = self.state.v_to_h(v)
		if self.params.do_gaussian_hidden:
			return state

		return prob(state)

	def h_to_pv(self, h: np.ndarray) -> np.ndarray:
		state = self.state.h_to_v(h)
		if self.params.do_gaussian_visible:
			return state

		return prob(state)


	def gibbs_v_to_h(self, v: np.ndarray) -> np.ndarray:
		h = self.v_to_ph(v)
		for i in range(self.params.num_gibbs_samples-1):
			h = self.h_to_pv(h)
			h = self.v_to_ph(h)

		return h

	def gibbs_h_to_v(self, h: np.ndarray) -> np.ndarray:
		v = self.h_to_pv(h)
		for i in range(self.params.num_gibbs_samples-1):
			v = self.v_to_ph(v)
			v = self.h_to_pv(v)

		return v

if __name__ == "__main__":
	print("Test: [passed]")