yujuwon

import pickle
import random
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
%matplotlib inline

def unpickle(file):
    fo = open(file, 'rb')
    dict = pickle.load(fo)

yujuwon

import pickle
import random
import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
%matplotlib inline

def unpickle(file):
    fo = open(file, 'rb')
    dict = pickle.load(fo)

yujuwon

from yahoo_finance import Share
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
import random
%matplotlib inline

class DecisionPolicy:
    def select_action(self, current_state, step):
        pass

yujuwon

import pickle
import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

def unpickle(file):
    fo = open(file, 'rb')
    dict = pickle.load(fo)
    fo.close()
    return dict

yujuwon

import numpy as np
import tensorflow as tf
from sklearn import datasets

class Autoencoder:
    def __init__(self, input_dim, hidden_dim, epoch=250, batch_size=10, learning_rate=0.001):
        self.epoch = epoch
        self.learning_rate = learning_rate
        self.batch_size = batch_size
        

yujuwon

import numpy as np
import tensorflow as tf

class HMM(object):
    def __init__(self, initial_prob, trans_prob, obs_prob):
        self.N = np.size(initial_prob)
        self.initial_prob = initial_prob
        self.trans_prob = trans_prob
        self.emission = tf.constant(obs_prob)
        

yujuwon

import numpy as np
import tensorflow as tf

class HMM(object):
    def __init__(self, initial_prob, trans_prob, obs_prob):
        self.N = np.size(initial_prob)
        self.initial_prob = initial_prob
        self.trans_prob = trans_prob
        self.emission = tf.constant(obs_prob)
        

yujuwon

import numpy as np
import matplotlib.pyplot as plt
%matplotlib inline

def traindata():
    x1_label0 = np.random.normal(1, 1, (100, 1))
    x2_label0 = np.random.normal(1, 1, (100, 1))
    x1_label1 = np.random.normal(5, 1, (100, 1))
    x2_label1 = np.random.normal(4, 1, (100, 1))
    x1_label2 = np.random.normal(8, 1, (100, 1))

yujuwon

import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
%matplotlib inline

learning_rate = 0.1
training_epochs = 2000

def sigmoid(x):
    return 1. / (1. + np.exp(-x))

yujuwon

import numpy as np
import tensorflow as tf
import matplotlib.pyplot as plt
%matplotlib inline

learning_rate = 0.01
training_epochs = 1000

def sigmoid(x):
    return 1. / (1. + np.exp(-x))