# -*- coding:utf-8 -*-
"""
@Time: 2022/03/03 12:23
@Author: KI
@File: model.py
@Motto: Hungry And Humble
"""
from torch import nn
class ANN(nn.Module):
    def __init__(self, args, name):
        super(ANN, self).__init__()
        self.name = name
        self.len = 0
        self.loss = 0
        self.fc1 = nn.Linear(args.input_dim, 20)
        self.relu = nn.ReLU()
        self.sigmoid = nn.Sigmoid()
        self.dropout = nn.Dropout()
        self.fc2 = nn.Linear(20, 20)
        self.fc3 = nn.Linear(20, 20)
        self.fc4 = nn.Linear(20, 1)
    def forward(self, data):
        x = self.fc1(data)
        x = self.sigmoid(x)
        x = self.fc2(x)
        x = self.sigmoid(x)
        x = self.fc3(x)
        x = self.sigmoid(x)
        x = self.fc4(x)
        x = self.sigmoid(x)
        return x

# -*- coding:utf-8 -*-
"""
@Time: 2022/03/03 12:50
@Author: KI
@File: server.py
@Motto: Hungry And Humble
"""
import copy
import random
import numpy as np
import torch
from model import ANN
from client import train, test
class FedProx:
    def __init__(self, args):
        self.args = args
        self.nn = ANN(args=self.args, name='server').to(args.device)
        self.nns = []
        for i in range(self.args.K):
            temp = copy.deepcopy(self.nn)
            temp.name = self.args.clients[i]
            self.nns.append(temp)
    def server(self):
        for t in range(self.args.r):
            print('round', t + 1, ':')
            # sampling
            m = np.max([int(self.args.C * self.args.K), 1])
            index = random.sample(range(0, self.args.K), m)  # st
            # dispatch
            self.dispatch(index)
            # local updating
            self.client_update(index, t)
            # aggregation
            self.aggregation(index)
        return self.nn
    def aggregation(self, index):
        s = 0
        for j in index:
            # normal
            s += self.nns[j].len
        params = {}
        for k, v in self.nns[0].named_parameters():
            params[k] = torch.zeros_like(v.data)
        for j in index:
            for k, v in self.nns[j].named_parameters():
                params[k] += v.data * (self.nns[j].len / s)
        for k, v in self.nn.named_parameters():
            v.data = params[k].data.clone()
    def dispatch(self, index):
        for j in index:
            for old_params, new_params in zip(self.nns[j].parameters(), self.nn.parameters()):
                old_params.data = new_params.data.clone()
    def client_update(self, index, global_round):  # update nn
        for k in index:
            self.nns[k] = train(self.args, self.nns[k], self.nn, global_round)
    def global_test(self):
        model = self.nn
        model.eval()
        for client in self.args.clients:
            model.name = client
            test(self.args, model)

def train(args, model, server, global_round):
    model.train()
    Dtr, Dte = nn_seq_wind(model.name, args.B)
    model.len = len(Dtr)
    global_model = copy.deepcopy(server)
    if args.weight_decay != 0:
        lr = args.lr * pow(args.weight_decay, global_round)
    else:
        lr = args.lr
    if args.optimizer == 'adam':
        optimizer = torch.optim.Adam(model.parameters(), lr=lr,
                                     weight_decay=args.weight_decay)
    else:
        optimizer = torch.optim.SGD(model.parameters(), lr=lr,
                                    momentum=0.9, weight_decay=args.weight_decay)
    print('training...')
    loss_function = nn.MSELoss().to(args.device)
    loss = 0
    for epoch in range(args.E):
        for (seq, label) in Dtr:
            seq = seq.to(args.device)
            label = label.to(args.device)
            y_pred = model(seq)
            optimizer.zero_grad()
            # compute proximal_term
            proximal_term = 0.0
            for w, w_t in zip(model.parameters(), global_model.parameters()):
                proximal_term += (w - w_t).norm(2)
            loss = loss_function(y_pred, label) + (args.mu / 2) * proximal_term
            loss.backward()
            optimizer.step()
        print('epoch', epoch, ':', loss.item())
    return model

for w, w_t in zip(model.parameters(), global_model.parameters()):
    proximal_term += (w - w_t).norm(2)

python main.py