kailaix

# modified version from http://edwardlib.org/tutorials/
from tensorflow_probability import edward2 as ed
import tensorflow as tf
import tensorflow_probability as tfp
import numpy as np

def logistic_regression(features):
  coeffs = ed.Normal(loc=0., scale=1.,
                     sample_shape=features.shape[1], name="coeffs")
  outcomes = ed.Bernoulli(logits=tf.tensordot(features, coeffs, [[1], [0]]),

kailaix

using LinearAlgebra
using PyPlot
using SparseArrays
# https://uu.diva-portal.org/smash/get/diva2:1148496/FULLTEXT01.pdf page 8
# https://regulation.pstat.ucsb.edu/sites/sa-wcmf6/5-Peng_ECIR_Model_Qidi.pdf page 13

# params
r0 = 0.5
L = 4.0
a = 1.0

kailaix

for n in 50 60 70 80 90 100
do
    julia euro_main.jl $n 2>&1 | tee -a euro$n.log &
done

wait %1 %2 %3 %4 %5 %6

for n in 50 70 90 110 130 150
do
    julia flap_main.jl $n 2>&1 | tee -a flap$n.log &

kailaix

std::string survey_fname;
std::string dir(__FILE__);
dir = dir.substr(0, dir.find_last_of("\\/"));

kailaix

using PyPlot
using ADCMEKit

NT = 2000
n = 100
Δt = 1.0/NT 
Δx = 1/n 

method = "Central"