lucastheis

lucastheis

lucastheis

import theano as th
import theano.tensor as tt

def gaussian_kernel(x, y, sigma=1.):
    return tt.exp(-tt.sum(tt.square(x - y)) / sigma**2)
    
def gram_matrix(X, Y, kernel):
    M = X.shape[0]
    N = Y.shape[0]
    

lucastheis

from multiprocessing import Process, Pool, Queue

def f(q0):
    for i in range(100):
        q0.put(i)
        
def g(q0, q1):
    while True:
        q1.put(q0.get())

lucastheis

#ifndef GSM_H
#define GSM_H

#include "Eigen/Core"
#include "distribution.h"
#include "exception.h"
#include <iostream>
#include <cmath>

using namespace Eigen;

lucastheis

lucastheis

import sys

from matplotlib.pyplot import *
from numpy import *
from numpy.random import *



def autocorr(X, N, d=1):
	"""

lucastheis

#!/usr/bin/env python

"""
Manage and display experimental results.
"""

__license__ = 'MIT License <http://www.opensource.org/licenses/mit-license.php>'
__author__ = 'Lucas Theis <lucas@theis.io>'
__docformat__ = 'epytext'
__version__ = '0.4.3'

lucastheis

__author__ = 'Lucas Theis <lucas@theis.io>'
__license__ = 'MIT License <http://www.opensource.org/licenses/mit-license.php>'

import sys

from numpy import *
from numpy.random import *
from matplotlib.pyplot import *
from scipy.special import gammaln
from scipy.stats import norm, invgamma

lucastheis

import sys

from numpy import *
from numpy.random import *
from matplotlib.pyplot import *
from scipy.stats import *

p17 = .05
p18 = .03