khuangaf

from gensim.models import FastText
model_ted = FastText(sentences_ted, size=100, window=5, min_count=5, workers=4,sg=1)

khuangaf

model_ted.wv.most_similar(“man”)

khuangaf

from gensim.models import Word2Vec
model_ted = Word2Vec(sentences=sentences_ted, size=100, window=5, min_count=5, workers=4, sg=0)

khuangaf

# remove parenthesis 
input_text_noparens = re.sub(r'\([^)]*\)', '', input_text)
# store as list of sentences
sentences_strings_ted = []
for line in input_text_noparens.split('\n'):
    m = re.match(r'^(?:(?P<precolon>[^:]{,20}):)?(?P<postcolon>.*)$', line)
    sentences_strings_ted.extend(sent for sent in m.groupdict()['postcolon'].split('.') if sent)
# store as list of lists of words
sentences_ted = []
for sent_str in sentences_strings_ted:

khuangaf

import numpy as np
import os
from random import shuffle
import re
import urllib.request
import zipfile
import lxml.etree
#download the data
urllib.request.urlretrieve("https://wit3.fbk.eu/get.php?path=XML_releases/xml/ted_en-20160408.zip&filename=ted_en-20160408.zip", filename="ted_en-20160408.zip")
# extract subtitle

khuangaf

class Model(object):
    def __init__(self, *, policy, ob_space, ac_space, nbatch_act, nbatch_train,
                nsteps, ent_coef, vf_coef, max_grad_norm, training):
        sess = tf.get_default_session()
        if training:
            act_model = policy(sess, ob_space, ac_space, nbatch_act, 1, reuse=False)
        else:
            act_model = policy(sess, ob_space, ac_space, nbatch_act, 1, reuse=True)
        train_model = policy(sess, ob_space, ac_space, nbatch_train, nsteps, reuse=True)

khuangaf

class CnnPolicy(object):
    def __init__(self, sess, ob_space, ac_space, nbatch, nsteps, reuse=True): 
        ob_shape = (nbatch,) + ob_space.shape
        actdim = ac_space.shape[0]
        window_length = ob_space.shape[1] -1

        X = tf.placeholder(tf.float32, ob_shape, name='Ob') #obs
        with tf.variable_scope("model", reuse=reuse) as scope:
            w0 = tf.slice(X, [0,0,0,0],[-1,-1,1,1])
            x = tf.slice(X, [0,0,1,0],[-1,-1,-1,-1])

khuangaf

import gym.spaces
import gym.wrappers
import numpy as np


def concat_states(state):
    history = state["history"]
    weights = state["weights"]
    weight_insert_shape = (history.shape[0], 1, history.shape[2])
    if len(weights) - 1 == history.shape[0]:

khuangaf

class PortfolioEnv(gym.Env):
  def _step(self, action):
    """
    Step the env.
    Actions should be portfolio [w0...]
    - Where wn is a portfolio weight between 0 and 1. The first (w0) is cash_bias
    - cn is the portfolio conversion weights see PortioSim._step for description
    """
    logger.debug('action: %s', action)

khuangaf

class PortfolioSim(object):
  def _step(self, w1, y1):
    """
    Step.
    w1 - new action of portfolio weights - e.g. [0.1,0.9, 0.0]
    y1 - price relative vector also called return
        e.g. [1.0, 0.9, 1.1]
    Numbered equations are from https://arxiv.org/abs/1706.10059
    """
    w0 = self.w0