Gerard Martinez Rosell GerardBCN

## manipulation_explorer.ipynb

      
              1 file
            
          
              1 fork
            
          
              0 comments
            
          
              1 star
            
          
                GerardBCN
                / manipulation_explorer.ipynb
            
            
              Created
              July 16, 2018 12:48
            
              
                Statistical analysis of Bitcoin price manipulation by Tether issuance in late 2017
              
          
        Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## policy_iterator_RL_gridworld.ipynb

      
              1 file
            
          
              5 forks
            
          
              0 comments
            
          
              4 stars
            
          
                GerardBCN
                / policy_iterator_RL_gridworld.ipynb
            
            
              Created
              December 20, 2018 13:59
            
              
                Policy iterator for RL applied to gridworld
              
          
        Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## monte_carlo.ipynb

      
              1 file
            
          
              2 forks
            
          
              0 comments
            
          
              3 stars
            
          
                GerardBCN
                / monte_carlo.ipynb
            
            
              Last active
              July 31, 2020 01:58
            
              
                State-value function approximation for the gridworld task using Monte Carlo simulations
              
          
        Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## gist:9e0357c70873a2cfe5788d610b2d8261

      
              1 file
            
          
              2 forks
            
          
              0 comments
            
          
              1 star
            
          
                GerardBCN
                / gist:9e0357c70873a2cfe5788d610b2d8261
            
            
              Created
              December 24, 2018 19:13
            
              
                Using temporal-difference - TD(0) or one-step TD to solve the gridworld task
              
          
        Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## stock_price_autoencoding.ipynb

      
              1 file
            
          
              14 forks
            
          
              1 comment
            
          
              30 stars
            
          
                GerardBCN
                / stock_price_autoencoding.ipynb
            
            
              Created
              January 18, 2019 21:15
            
              
                Stock market Bitcoin data compression with autoencoders
              
          
        Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## tickbar_generator.py
# expects a numpy array with trades
# each trade is composed of: [time, price, quantity]
def generate_tickbars(ticks, frequency=1000):
    times = ticks[:,0]
    prices = ticks[:,1]
    volumes = ticks[:,2]
    res = np.zeros(shape=(len(range(frequency, len(prices), frequency)), 6))
    it = 0
    for i in range(frequency, len(prices), frequency):
        res[it][0] = times[i-1]                        # time

## returns.py
def returns(candles_close_prices):
    return np.diff(np.log(candles_close_prices))

## Durbin-watson.md

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                GerardBCN
                / Durbin-watson.md
            
            
              Last active
              April 23, 2019 15:46
            
          
Value
Meaning


DB-statistic << 2
positive serial correlation


DB-statistic ~ 2
no first-order correlation


DB-statistic >> 2
negative serial correlation


## dollarbar_generator.py
import numpy as np

# expects a numpy array with trades
# each trade is composed of: [time, price, quantity]
def generate_dollarbars(trades, frequency=1000):
    times = trades[:,0]
    prices = trades[:,1]
    volumes = trades[:,2]
    ans = np.zeros(shape=(len(prices), 6))
    candle_counter = 0

## volumebar_generator.py
import numpy as np

# expects a numpy array with trades
# each trade is composed of: [time, price, quantity]
def generate_volumebars(trades, frequency=10):
    times = trades[:,0]
    prices = trades[:,1]
    volumes = trades[:,2]
    ans = np.zeros(shape=(len(prices), 6))
    candle_counter = 0
	# expects a numpy array with trades
	# each trade is composed of: [time, price, quantity]
	def generate_tickbars(ticks, frequency=1000):
	times = ticks[:,0]
	prices = ticks[:,1]
	volumes = ticks[:,2]
	res = np.zeros(shape=(len(range(frequency, len(prices), frequency)), 6))
	it = 0
	for i in range(frequency, len(prices), frequency):
	res[it][0] = times[i-1] # time
	def returns(candles_close_prices):
	return np.diff(np.log(candles_close_prices))
Value	Meaning
DB-statistic << 2	positive serial correlation
DB-statistic ~ 2	no first-order correlation
DB-statistic >> 2	negative serial correlation
	import numpy as np

	# expects a numpy array with trades
	# each trade is composed of: [time, price, quantity]
	def generate_dollarbars(trades, frequency=1000):
	times = trades[:,0]
	prices = trades[:,1]
	volumes = trades[:,2]
	ans = np.zeros(shape=(len(prices), 6))
	candle_counter = 0