João Faria j-faria

## cl_arguments.py
import sys

def fun():
  print 'fun'

def test():
  print 'test'

if __name__ == "__main__":
  if len(sys.argv) > 1 and sys.argv[1] == 'test':

## GLS
GLS periodogram

## pearsonr.f90
real(kind=8) function pearsonr(x, y) result(r)
    ! given two arrays x and y, this function computes their Pearson correlation coefficient r
    implicit none
    real(kind=8), dimension(:) :: x, y
    real(kind=8), dimension(size(x)) :: xt, yt
    real(kind=8) :: ax, ay, df, sxx, sxy, syy
    integer :: n

    if (size(x) /= size(y)) STOP 'Dimension mismatch in pearsonr'


## change_par_file.py
import fileinput
import os

# create a copy of the template parameter file
os.system('cp template_file new_file')

# for example, in the template you have
# par1 = 10
# par2 = 'some path'
# and you want to change to

## BayesCorr.py
#!/usr/env/python
# -*- coding: utf-8 -*-

# Written by Pedro Figueira.
#  Original version can be found at https://pedrofigueira@bitbucket.org/pedrofigueira/bayesiancorrelation
# Modified by João Faria

"""Bayesian Correlation.

Usage:

## hello.py
def HelloWorld:
    print 'Hello World, from Python'

## generate_from_cov_matrix.py
#!/usr/bin/env python
# -*- coding: utf-8 -*-

# Generate data with a particular correlation matrix
#
# A useful fact is that if you have a random vector x with covariance matrix Σ,
# then the random vector Ax has mean AE(x) and covariance matrix Ω=AΣA^T.
# So, if you start with data that has mean zero, multiplying by A will not
# change that.
#

## fisher_yates.py
#!/usr/bin/env python
# -*- coding: utf-8 -*-
#
# Shuffle an array in place using the Knuth-Fisher-Yates algorithm.

from random import randrange

def shuffle(x):
    """ Shuffle x in place using the Knuth-Fisher-Yates algorithm """
    for i in xrange(len(x)-1, 0, -1):

## jorge-noise-covmat.py
from numpy import *
from pylab import *
from glob import glob
from scipy.stats import nanmean


NN = '088'  # change this


fileglob = 'Residuals_NN' + NN + '_Index*'

## powernoise.py
from math import floor
from numpy import arange, exp, pi, flipud, append, conj, real
from numpy.fft import ifft
from numpy.random import randn


def powernoise(alpha, N, randpower=False, normalize=False):
	"""
	Generate samples of power law noise. The power spectrum
	of the signal scales as f^(-alpha).