强化学习(RL)

import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
from torch.autograd import Variable
import gym
import matplotlib.pyplot as plt
 
# 超参数
BATCH_SIZE = 32
LR = 0.01  # learning rate
# 强化学习的参数
EPSILON = 0.9  # greedy policy
GAMMA = 0.9  # reward discount
TARGET_REPLACE_ITER = 100  # target update frequency
MEMORY_CAPACITY = 2000
# 导入实验环境
env = gym.make('CartPole-v0')
env = env.unwrapped
N_ACTIONS = env.action_space.n
N_STATES = env.observation_space.shape[0]


class Net(nn.Module):
    def __init__(self, ):
        super(Net, self).__init__()
        self.fc1 = nn.Linear(N_STATES, 10)
        self.fc1.weight.data.normal_(0, 0.1)  # 初始化
        self.out = nn.Linear(10, N_ACTIONS)
        self.out.weight.data.normal_(0, 0.1)  # 初始化
 
    def forward(self, x):
        x = self.fc1(x)
        x = F.relu(x)
        actions_value = self.out(x)
        return actions_value
 
class DQN(object):
    def __init__(self):
        self.eval_net, self.target_net = Net(), Net()
        # 记录学习到多少步
        self.learn_step_counter = 0  # for target update
        self.memory_counter = 0  # for storing memory
        # 初始化memory
        self.memory = np.zeros((MEMORY_CAPACITY, N_STATES * 2 + 2))
        self.optimizer = torch.optim.Adam(self.eval_net.parameters(), lr=LR)
        self.loss_func = nn.MSELoss()
 
    def choose_action(self, x):
        x = Variable(torch.unsqueeze(torch.FloatTensor(x), 0))
        if np.random.uniform() < EPSILON:
            action_value = self.eval_net(x)
            #action = torch.max(action_value, 1)[1].data.numpy()[0, 0]
            action = torch.max(action_value, 1)[1].data.numpy()[0]
        else: # random
            action = np.random.randint(0, N_ACTIONS)
        return action
 
    # s:当前状态， a:动作, r:reward奖励, s_:下一步状态
    def store_transaction(self, s, a, r, s_):
        transaction = np.hstack((s, [a, r], s_))
        # replace the old memory with new memory
        index = self.memory_counter % MEMORY_CAPACITY
        self.memory[index, :] = transaction
        self.memory_counter += 1

    def learn(self):
        # target net update
        if self.learn_step_counter % TARGET_REPLACE_ITER == 0:
            self.target_net.load_state_dict(self.eval_net.state_dict())
 
        sample_index = np.random.choice(MEMORY_CAPACITY, BATCH_SIZE)
        b_memory = self.memory[sample_index, :]
        b_s = Variable(torch.FloatTensor(b_memory[:, :N_STATES]))
        b_a = Variable(torch.LongTensor(b_memory[:, N_STATES: N_STATES+1].astype(int)))
        b_r = Variable(torch.FloatTensor(b_memory[:, N_STATES + 1: N_STATES+2]))
        b_s_ = Variable(torch.FloatTensor(b_memory[:, -N_STATES: ]))
 
        q_eval = self.eval_net(b_s).gather(1, b_a)
        q_next = self.target_net(b_s_).detach()
        q_target = b_r + GAMMA * q_next.max(1)[0]
        loss = self.loss_func(q_eval, q_target)
        self.optimizer.zero_grad()
        loss.backward()
        self.optimizer.step()
 
plt.ion()

dqn = DQN()
last_time_steps = torch.FloatTensor([])
print('\nCollecting experience...')
for i_episode in range(4000):
    s = env.reset()
    episode_reward,t = 0,0  # 初始化本场游戏的得分
    while True:
        env.render()
 
        a = dqn.choose_action(s)
        # take action
        s_, r, done, info = env.step(a)
        episode_reward += r

        # modify the reward
        x, x_dot, theta, theta_dot = s_
        r1 = (env.x_threshold - abs(x)) / env.x_threshold - 0.8
        r2 = (env.theta_threshold_radians - abs(theta)) / env.theta_threshold_radians - 0.5
        r = r1 + r2
        t+=1

        dqn.store_transaction(s, a, r, s_)

        if dqn.memory_counter > MEMORY_CAPACITY:
            dqn.learn()
 
        if done:
            plt.figure(1)
            plt.clf()
            plt.title('Training...')
            plt.xlabel('Episode')
            plt.ylabel('Duration')
            plt.plot(last_time_steps.numpy())
            if len(last_time_steps) >= 100:
                means = last_time_steps.unfold(0, 100, 1).mean(1).view(-1)
                plt.plot(means.numpy())
            plt.pause(0.001)

            last_time_steps = torch.FloatTensor(np.hstack((last_time_steps.numpy(),[episode_reward])))    # 更新最近100场游戏的得分stack
            break
        s = s_

plt.ioff()
plt.show()

import pandas as pd
filename = 'C:\pycharm\DataMining\data\sales_data.xls'
data = pd.read_excel(filename, index_col='No')
data[data == u'好'] = 1
data[data == u'是'] = 1
data[data == u'高'] = 1
data[data != 1] = -1
#print(data)
x = pd.DataFrame(data.iloc[:, :3].astype(int))
#x = data.iloc[:, :3].values.astype(int) 
print(x)
y = pd.DataFrame(data.iloc[:, 3].astype(int))
print(y)


from sklearn.tree import DecisionTreeClassifier as DTC
dtc = DTC(criterion='entropy') #建立决策树模型，基于信息熵
dtc.fit(x, y)


from sklearn.tree import export_graphviz #可视化决策树
name = 'C:\pycharm\DataMining\data\\tree.dot'
with open(name, 'w') as f:
    f = export_graphviz(dtc, feature_names=x.columns, out_file=f)