{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "mediterranean-harbor",
   "metadata": {},
   "source": [
    "# Markov-Chain Monte Carlo in EasyVVUQ"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "efficient-nudist",
   "metadata": {},
   "source": [
    "**Author**: Vytautas Jancauskas, LRZ (jancauskas@lrz.de)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "outside-circle",
   "metadata": {},
   "source": [
    "We have a model that returns an array of 50 integers where each is supposed to have come from a Poisson distribution with an unknown mean. The model has four input parameters ```a, b, c, d``` and the values of the means depend on the values of those parameters (albeit in some unknown to us way). \n",
    "    This situation seems common in practice in cases where the author of a simulation wants to show that their code in some way is validated by real world data. If they have observed data and they have a simulation for the phenomenon that produced that data and they have measurements of the inputs for the simulation they could use the procedure here to see if the real world \"input\" parameters fall within a reasonable range of the simulation input parameters. For more information on Markov-Chain Monte Carlo you can start at the Wikipedia [page](https://en.wikipedia.org/wiki/Markov_chain_Monte_Carlo)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "extreme-scout",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T09:05:37.071870Z",
     "start_time": "2021-06-09T09:05:36.731777Z"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "piano-lodge",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T09:05:37.110984Z",
     "start_time": "2021-06-09T09:05:37.107421Z"
    }
   },
   "outputs": [],
   "source": [
    "def model(params):\n",
    "    import numpy as np\n",
    "    a = int(params['a'])\n",
    "    b = int(params['b'])\n",
    "    c = int(params['c'])\n",
    "    d = int(params['d'])\n",
    "    x = np.linspace(0, 1, 50)\n",
    "    return {'Values' : list(np.random.poisson(\n",
    "        a * (0.5 * np.sin(2.0 * np.pi * x) + 1.0) +\\\n",
    "        b * (0.5 * np.sin(4.0 * np.pi * x) + 1.0) +\\\n",
    "        c * (0.5 * np.sin(6.0 * np.pi * x) + 1.0) +\\\n",
    "        d * (0.5 * np.sin(8.0 * np.pi * x) + 1.0)))}"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "expired-accused",
   "metadata": {},
   "source": [
    "If we plot the values returned by the model with ```a = b = c = d = 50``` and repeat this 20 times we might get something like the figure below."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "periodic-vulnerability",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T09:05:37.445827Z",
     "start_time": "2021-06-09T09:05:37.114610Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "for _ in range(20):\n",
    "    plt.plot(model({'a': 50, 'b': 80, 'c': 50, 'd': 80})['Values'], '.')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "unable-department",
   "metadata": {},
   "source": [
    "Then we have an array of 50 values that came from the model. With ```a = 50, b = 80, c = 50 and d = 80```. We will treat them as our observed data. We want to know what input parameters of the model are most likely to result in the values in the ```observed``` array. Because suppose we forgot."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "level-produce",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T09:05:37.450077Z",
     "start_time": "2021-06-09T09:05:37.447730Z"
    }
   },
   "outputs": [],
   "source": [
    "observed = np.array([248, 311, 344, 370, 375, 369, 302, 306, 285, 281, 258, 248, 254,\n",
    "       273, 292, 268, 312, 269, 230, 244, 227, 219, 247, 233, 225, 238,\n",
    "       271, 307, 294, 299, 248, 249, 271, 255, 231, 225, 243, 279, 271,\n",
    "       294, 237, 247, 197, 180, 161, 168, 178, 207, 204, 258])"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "shaped-report",
   "metadata": {},
   "source": [
    "We are interested in $\\mathbb{E}(X | y)$ with $X = [A, B, C, D]^T$ where $A, B, C, D$ are the random variables representing the input parameters. For this we need to know the probability density $f_{X|y}$ where $y$ are our observed values. From Bayes theorem it follows that $f_{X|y}$ is proportional to $f_{Y|X}(y|X)f(X)$. We usually can infer $f(X)$ (the prior probability) in advance, in this case we will leave them flat. We will use Markov-Chain Monte Carlo (MCMC) to approximate the probability density $f_{X|y}(x)$. We assume that $y$ (our observed data) is 50 numbers from 50 Poisson distributions with unknown means. We will estimate those means by running the model multiple times and calculating the sample mean because that is the MLE estimate for a Poisson distributed random variable. Suppose we have $\\hat{\\lambda}_i$ that is the estimate. Then we have $f_{X|y}(x) = \\prod_{i = 1}^{50} \\frac{\\hat\\lambda_i^{y_i} \\exp(-\\hat\\lambda_i)}{{y_i}!}$ where $\\lambda_i$ is the estimated Poisson parameter for th $i$-th output variable and $y_i$ is the $i$-th value in the observed vector. Since it is often more convenient to work with log-likelihoods we arrive at $\\sum_{i = 1}^{50} \\left(y_i \\log(\\hat\\lambda_i) - \\hat\\lambda_i - \\log({y_i}!)\\right)$."
   ]
  },
  {
   "cell_type": "markdown",
   "id": "mechanical-fourth",
   "metadata": {},
   "source": [
    "## Sampling"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "tough-finish",
   "metadata": {},
   "source": [
    "First, mandatory imports."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "dominant-newman",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T09:05:40.036922Z",
     "start_time": "2021-06-09T09:05:37.451197Z"
    }
   },
   "outputs": [],
   "source": [
    "import easyvvuq as uq\n",
    "from easyvvuq.actions import ExecutePython, Actions\n",
    "import scipy.special\n",
    "import chaospy as cp\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "import os\n",
    "import json\n",
    "from tqdm.notebook import trange"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "superior-vinyl",
   "metadata": {},
   "source": [
    "We define parameter specification, encoder, decoder and the campaign object. See the more detailed tutorials on these EasyVVUQ elements [here](basic_tutorial.ipynb) and [here](vector_qoi_tutorial.ipynb)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "varied-advocacy",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T09:05:40.064975Z",
     "start_time": "2021-06-09T09:05:40.037834Z"
    }
   },
   "outputs": [],
   "source": [
    "params = {\n",
    "    \"a\": {\"type\": \"float\", \"min\": 0, \"max\": 100, \"default\": 50},\n",
    "    \"b\": {\"type\": \"float\", \"min\": 0, \"max\": 100, \"default\": 50},\n",
    "    \"c\": {\"type\": \"float\", \"min\": 0, \"max\": 100, \"default\": 50},\n",
    "    \"d\": {\"type\": \"float\", \"min\": 0, \"max\": 100, \"default\": 50},\n",
    "    \"outfile\": {\"type\": \"string\", \"default\": \"output.csv\"},\n",
    "    \"ensemble_id\": {\"type\": \"integer\", \"default\": 0},\n",
    "    \"chain_id\": {\"type\": \"integer\", \"default\": 0}\n",
    "}\n",
    "actions = Actions(ExecutePython(model))\n",
    "campaign = uq.Campaign(name=\"mcmc\", actions=actions, params=params, work_dir='.')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "collected-fundamental",
   "metadata": {},
   "source": [
    "We need initial values for our MCMC chains. Here we simply set it to a uniformly distributed value from the valid range for that parameter. Note that each input parameter gets an array of 5 numbers because we will use 5 chains later on."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "integral-demographic",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T09:05:40.068683Z",
     "start_time": "2021-06-09T09:05:40.065889Z"
    }
   },
   "outputs": [],
   "source": [
    "vary_init = {\n",
    "    \"a\": np.random.uniform(0, 100, size=5),\n",
    "    \"b\": np.random.uniform(0, 100, size=5),\n",
    "    \"c\": np.random.uniform(0, 100, size=5),\n",
    "    \"d\": np.random.uniform(0, 100, size=5)\n",
    "}"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "seven-superior",
   "metadata": {},
   "source": [
    "Then we need to define the proposal distribution. It can be arbitrary (for example assymetrical). This is conditional on current chain position in the search space. In this case we will use a normal distribution with $mu = a, b, c, d$ and $\\sigma = 5$."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "chemical-student",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T09:05:40.072038Z",
     "start_time": "2021-06-09T09:05:40.069791Z"
    }
   },
   "outputs": [],
   "source": [
    "def proposal(x, b=2.5):\n",
    "    return cp.J(cp.Normal(x['a'], b), \n",
    "                cp.Normal(x['b'], b), \n",
    "                cp.Normal(x['c'], b), \n",
    "                cp.Normal(x['d'], b))"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "apparent-mounting",
   "metadata": {},
   "source": [
    "Next we want to construct the likelihood function. This function describes the probability that the observed data came from our model (assuming some fixed input parameters). In this case we will need the estimate of the Poisson mean for each of the 50 outputs of the simulation. These are the parameters $\\lambda$. Once we have those it is trivial to see what is the probability that each output came from a corresponding distribution. We then just multiply them together and take the logarithm (because of numerical issues this is preferable to straight up multiplying). This formula was derived above."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "binding-salon",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T09:05:40.076723Z",
     "start_time": "2021-06-09T09:05:40.074548Z"
    }
   },
   "outputs": [],
   "source": [
    "def get_likelihood(observed):\n",
    "    def likelihood(lmbda):\n",
    "        return (observed * np.log(lmbda) - lmbda - \n",
    "                scipy.special.gammaln(observed + 1.0)).sum()\n",
    "    return likelihood"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "broad-increase",
   "metadata": {},
   "source": [
    "Finally we put everything together. Note the estimator parameter to the MCMCSampler class. It is used to produce the estimate for the mean of the Poisson distribution. In this case we use sample mean because that is the MLE for Poisson $\\lambda$ parameter."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "perceived-cosmetic",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T09:05:40.086448Z",
     "start_time": "2021-06-09T09:05:40.078303Z"
    }
   },
   "outputs": [],
   "source": [
    "mcmc_sampler = uq.sampling.MCMCSampler(\n",
    "    vary_init, proposal, 'Values', n_chains=5,\n",
    "    likelihood=get_likelihood(observed), \n",
    "    estimator=lambda x: np.mean(x))\n",
    "sampler = uq.sampling.ReplicaSampler(mcmc_sampler, replicas=20)\n",
    "campaign.set_sampler(sampler)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "tender-ensemble",
   "metadata": {},
   "source": [
    "When we have workflows where each sampling stage relies on the results of the previous one (as is the case with MCMC) we need to call iterate on the campaign object and then use the Python keyword next to advance to the next sampling stage. This will return action statuses and we need to wait for them to finish in order to proceed."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "finite-reward",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T09:05:40.089775Z",
     "start_time": "2021-06-09T09:05:40.087701Z"
    }
   },
   "outputs": [],
   "source": [
    "iterator = campaign.iterate(mark_invalid=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "identified-above",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T10:00:39.005059Z",
     "start_time": "2021-06-09T09:05:40.090575Z"
    },
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "b47b908f378f4d38a009b69955c0da2c",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/10000 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n",
      "/Volumes/Samsung8TB/dpc/GIT/EasyVVUQ/env/lib/python3.9/site-packages/easyvvuq-0.9.3+141.gf9780783.dirty-py3.9.egg/easyvvuq/sampling/mcmc.py:130: RuntimeWarning: invalid value encountered in double_scalars\n",
      "  r = min(1.0, (f_y / self.f_x[chain_id]) * (q_xy / q_yx))\n"
     ]
    }
   ],
   "source": [
    "for _ in trange(10000):\n",
    "    next(iterator).collate()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "lightweight-biography",
   "metadata": {},
   "source": [
    "## Analysis"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "interior-automation",
   "metadata": {},
   "source": [
    "After calling analyse we will get an instance of MCMCAnalysisResults that contains information about our chains. It also lets us plot and analyse that data."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "noticed-freight",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T10:00:55.040243Z",
     "start_time": "2021-06-09T10:00:39.012319Z"
    }
   },
   "outputs": [],
   "source": [
    "result = campaign.analyse()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "alike-alliance",
   "metadata": {},
   "source": [
    "We will now plot the chains for each parameter. We can see that they indeed seem to converge to the input parameters used to generate observed data. Which was $a = 50, b = 80, c = 50, d = 80$."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "raising-chance",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T10:00:55.143987Z",
     "start_time": "2021-06-09T10:00:55.041604Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "result.plot_chains('a')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "brave-patio",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T10:00:55.206081Z",
     "start_time": "2021-06-09T10:00:55.144849Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "result.plot_chains('b')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "stock-vegetation",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T10:00:55.273882Z",
     "start_time": "2021-06-09T10:00:55.207459Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "result.plot_chains('c')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "authentic-special",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T10:00:55.334457Z",
     "start_time": "2021-06-09T10:00:55.275342Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "result.plot_chains('d')"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "liquid-teacher",
   "metadata": {},
   "source": [
    "We can also plot histograms of the parameters. This can let us determine the shape of the distribution of that parameter and determine confidence intervals, etc."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "molecular-picnic",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T10:00:55.398320Z",
     "start_time": "2021-06-09T10:00:55.335543Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAX0AAAD4CAYAAAAAczaOAAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjMuMywgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy/Il7ecAAAACXBIWXMAAAsTAAALEwEAmpwYAAASMklEQVR4nO3dbYxc113H8e8Pp6RPRE3kTXC9ruwiU3Ai+rQyKZWqQoAYUtVBIpIrlVolkqEyUBCo2PCi8MKSeW4rkUgmDXWhNLICVayWNjUuVYXUNt0+Jk4aYpoo3tqNFyqggOSS9M+LuYFhPWt7Z9azO3u+H2l17z333Lnn+Ni/vT5z70yqCklSG75rpRsgSRofQ1+SGmLoS1JDDH1JaoihL0kNuWKlG3Ax69evr82bN690MyRpYqxfv57777///qrasXDfqg/9zZs3Mzs7u9LNkKSJkmT9oHKndySpIRcN/SR3Jzmb5KEB+34jSfX/RkmyP8nJJI8mubmv/NVJHuz2vSdJlq8bkqRLcSlX+u8DzpsXSrIJ+Angyb6ybcAu4PrumDuSrOt23wnsAbZ2P+e9piTp8rpo6FfVp4BvDtj1J8A7gP7PcdgJ3FNV56rqceAksD3JBuCqqvp09T734f3AraM2XpK0NEPN6Sd5I/D1qvrygl0bgVN923Nd2cZufWG5JGmMlnz3TpLnA78N/OSg3QPK6gLli51jD72pIF7ykpcstYmSpEUMc6X/fcAW4MtJngCmgS8k+V56V/Cb+upOA6e78ukB5QNV1aGqmqmqmampqSGaKEkaZMmhX1UPVtW1VbW5qjbTC/RXVdU3gKPAriRXJtlC7w3bB6rqDPCtJDd2d+28Bbhv+bohSboUl3LL5geBTwMvSzKX5PbF6lbVCeAI8DDwMWBvVT3T7X4bcBe9N3f/CfjoiG2XJC1RVvuXqMzMzJRP5Go12rzvI0Mf+8TBW5axJdL5kny+qmYWlvtEriQ1xNCXpIYY+pLUEENfkhpi6EtSQwx9SWqIoS9JDTH0Jakhhr4kNWTVf0eutBaN8jQv+ESvhueVviQ1xNCXpIYY+pLUEENfkhpi6EtSQwx9SWqIoS9JDTH0Jakhhr4kNcTQl6SGGPqS1BBDX5IactHQT3J3krNJHuor+4MkX03ylSQfSvKivn37k5xM8miSm/vKX53kwW7fe5Jk2XsjSbqgS7nSfx+wY0HZMeCGqvoh4B+B/QBJtgG7gOu7Y+5Isq475k5gD7C1+1n4mpKky+yioV9VnwK+uaDs41X1dLf5GWC6W98J3FNV56rqceAksD3JBuCqqvp0VRXwfuDWZeqDJOkSLcec/s8DH+3WNwKn+vbNdWUbu/WF5QMl2ZNkNsns/Pz8MjRRkgQjhn6S3waeBj7wbNGAanWB8oGq6lBVzVTVzNTU1ChNlCT1Gfqbs5LsBt4A3NRN2UDvCn5TX7Vp4HRXPj2gXJI0RkNd6SfZAfwm8Maq+q++XUeBXUmuTLKF3hu2D1TVGeBbSW7s7tp5C3DfiG2XJC3RRa/0k3wQeD2wPskc8E56d+tcCRzr7rz8TFX9YlWdSHIEeJjetM/eqnqme6m30bsT6Hn03gP4KJKksbpo6FfVmwYUv/cC9Q8ABwaUzwI3LKl1kqRl5RO5ktQQQ1+SGmLoS1JDDH1JaoihL0kNMfQlqSGGviQ1xNCXpIYY+pLUEENfkhpi6EtSQwx9SWqIoS9JDTH0Jakhhr4kNcTQl6SGGPqS1BBDX5IaYuhLUkMMfUlqiKEvSQ25aOgnuTvJ2SQP9ZVdk+RYkse65dV9+/YnOZnk0SQ395W/OsmD3b73JMnyd0eSdCGXcqX/PmDHgrJ9wPGq2goc77ZJsg3YBVzfHXNHknXdMXcCe4Ct3c/C15QkXWYXDf2q+hTwzQXFO4HD3fph4Na+8nuq6lxVPQ6cBLYn2QBcVVWfrqoC3t93jCRpTIad07+uqs4AdMtru/KNwKm+enNd2cZufWH5QEn2JJlNMjs/Pz9kEyVJCy33G7mD5unrAuUDVdWhqpqpqpmpqalla5wktW7Y0H+qm7KhW57tyueATX31poHTXfn0gHJJ0hgNG/pHgd3d+m7gvr7yXUmuTLKF3hu2D3RTQN9KcmN3185b+o6RJI3JFRerkOSDwOuB9UnmgHcCB4EjSW4HngRuA6iqE0mOAA8DTwN7q+qZ7qXeRu9OoOcBH+1+JEljdNHQr6o3LbLrpkXqHwAODCifBW5YUuskScvKJ3IlqSGGviQ15KLTO5JWn837PjL0sU8cvGUZW6JJY+hr4hmA0qVzekeSGmLoS1JDDH1JaoihL0kNMfQlqSGGviQ1xNCXpIYY+pLUEENfkhpi6EtSQwx9SWqIoS9JDTH0Jakhhr4kNcTQl6SGGPqS1BBDX5IaMlLoJ/m1JCeSPJTkg0mem+SaJMeSPNYtr+6rvz/JySSPJrl59OZLkpZi6NBPshH4FWCmqm4A1gG7gH3A8araChzvtkmyrdt/PbADuCPJutGaL0lailGnd64AnpfkCuD5wGlgJ3C4238YuLVb3wncU1Xnqupx4CSwfcTzS5KWYOjQr6qvA38IPAmcAf6tqj4OXFdVZ7o6Z4Bru0M2Aqf6XmKuKztPkj1JZpPMzs/PD9tESdICo0zvXE3v6n0L8GLgBUnefKFDBpTVoIpVdaiqZqpqZmpqatgmSpIWGGV658eBx6tqvqr+G/gb4EeAp5JsAOiWZ7v6c8CmvuOn6U0HSZLGZJTQfxK4McnzkwS4CXgEOArs7ursBu7r1o8Cu5JcmWQLsBV4YITzS5KW6IphD6yqzya5F/gC8DTwReAQ8ELgSJLb6f1iuK2rfyLJEeDhrv7eqnpmxPZLkpZg6NAHqKp3Au9cUHyO3lX/oPoHgAOjnFOSNDyfyJWkhhj6ktQQQ1+SGmLoS1JDRnojV5p0m/d9ZKWbII2VV/qS1BBDX5IaYuhLUkMMfUlqiKEvSQ0x9CWpIYa+JDXE0Jekhhj6ktQQQ1+SGmLoS1JDDH1JaoihL0kNMfQlqSGGviQ1xNCXpIaMFPpJXpTk3iRfTfJIktckuSbJsSSPdcur++rvT3IyyaNJbh69+ZKkpRj1m7PeDXysqn42yXcDzwd+CzheVQeT7AP2Ab+ZZBuwC7geeDHwd0m+v6qeGbENWgX8BippMgx9pZ/kKuB1wHsBqurbVfWvwE7gcFftMHBrt74TuKeqzlXV48BJYPuw55ckLd0o0zsvBeaBP0/yxSR3JXkBcF1VnQHoltd29TcCp/qOn+vKzpNkT5LZJLPz8/MjNFGS1G+U0L8CeBVwZ1W9EvhPelM5i8mAshpUsaoOVdVMVc1MTU2N0ERJUr9RQn8OmKuqz3bb99L7JfBUkg0A3fJsX/1NfcdPA6dHOL8kaYmGDv2q+gZwKsnLuqKbgIeBo8Durmw3cF+3fhTYleTKJFuArcADw55fkrR0o96988vAB7o7d74GvJXeL5IjSW4HngRuA6iqE0mO0PvF8DSw1zt3JGm8Rgr9qvoSMDNg102L1D8AHBjlnJKk4flEriQ1ZNTpHUkTZpQH6Z44eMsytkQrwSt9SWqIoS9JDTH0Jakhhr4kNcTQl6SGGPqS1BBDX5IaYuhLUkMMfUlqiKEvSQ0x9CWpIYa+JDXE0Jekhhj6ktQQQ1+SGmLoS1JDDH1JaoihL0kNMfQlqSEjh36SdUm+mOTD3fY1SY4leaxbXt1Xd3+Sk0keTXLzqOeWJC3Nclzpvx14pG97H3C8qrYCx7ttkmwDdgHXAzuAO5KsW4bzS5Iu0Uihn2QauAW4q694J3C4Wz8M3NpXfk9Vnauqx4GTwPZRzi9JWppRr/TfBbwD+E5f2XVVdQagW17blW8ETvXVm+vKzpNkT5LZJLPz8/MjNlGS9Kwrhj0wyRuAs1X1+SSvv5RDBpTVoIpVdQg4BDAzMzOwjpbf5n0fWekmSLrMhg594LXAG5P8NPBc4Kokfwk8lWRDVZ1JsgE429WfAzb1HT8NnB7h/JKkJRp6eqeq9lfVdFVtpvcG7Seq6s3AUWB3V203cF+3fhTYleTKJFuArcADQ7dckrRko1zpL+YgcCTJ7cCTwG0AVXUiyRHgYeBpYG9VPXMZzi9JWsSyhH5VfRL4ZLf+L8BNi9Q7ABxYjnNKkpbOJ3IlqSGGviQ1xNCXpIYY+pLUEENfkhpi6EtSQwx9SWqIoS9JDTH0Jakhl+NjGCStUaN8EusTB29ZxpZoWF7pS1JDDH1JaoihL0kNMfQlqSG+kStpLHwTeHXwSl+SGmLoS1JDDH1JaoihL0kN8Y3cVcg3vCRdLl7pS1JDhg79JJuS/H2SR5KcSPL2rvyaJMeSPNYtr+47Zn+Sk0keTXLzcnRAknTpRrnSfxr49ar6QeBGYG+SbcA+4HhVbQWOd9t0+3YB1wM7gDuSrBul8ZKkpRk69KvqTFV9oVv/FvAIsBHYCRzuqh0Gbu3WdwL3VNW5qnocOAlsH/b8kqSlW5Y5/SSbgVcCnwWuq6oz0PvFAFzbVdsInOo7bK4rkySNycihn+SFwF8Dv1pV/36hqgPKapHX3JNkNsns/Pz8qE2UJHVGCv0kz6EX+B+oqr/pip9KsqHbvwE425XPAZv6Dp8GTg963ao6VFUzVTUzNTU1ShMlSX1GuXsnwHuBR6rqj/t2HQV2d+u7gfv6yncluTLJFmAr8MCw55ckLd0oD2e9Fvg54MEkX+rKfgs4CBxJcjvwJHAbQFWdSHIEeJjenT97q+qZEc4vqRGjPLAIPrTYb+jQr6p/YPA8PcBNixxzADgw7DklSaPxiVxJaoihL0kNMfQlqSGGviQ1xNCXpIYY+pLUEL9EZY0Z9X5mSWuboX8ZGLySViundySpIV7pS1rz/N7p/+OVviQ1xNCXpIYY+pLUEENfkhpi6EtSQwx9SWqIoS9JDfE+fUm6gLV2j7+hvwg/SkHSWrSmQ9/glqT/zzl9SWqIoS9JDRn79E6SHcC7gXXAXVV1cNxtkKRxWI1vAo/1Sj/JOuBPgZ8CtgFvSrJtnG2QpJaNe3pnO3Cyqr5WVd8G7gF2jrkNktSscU/vbARO9W3PAT+8sFKSPcCebvM/kjw6wjnXA/88wvGrhf1YPdZCH2Bt9GMt9AEG9CO/N9LrLfpnMu7Qz4CyOq+g6hBwaFlOmMxW1cxyvNZKsh+rx1roA6yNfqyFPsB4+zHu6Z05YFPf9jRwesxtkKRmjTv0PwdsTbIlyXcDu4CjY26DJDVrrNM7VfV0kl8C7qd3y+bdVXXiMp92WaaJVgH7sXqshT7A2ujHWugDjLEfqTpvSl2StEb5RK4kNcTQl6SGrKnQT/LcJA8k+XKSE0l+tyv/nSRfT/Kl7uenV7qtF5NkXZIvJvlwt31NkmNJHuuWV690Gy/FgH5M4lg8keTBrr2zXdlEjccifZjEsXhRknuTfDXJI0leM4FjMagPYxuLNRX6wDngx6rq5cArgB1Jbuz2/UlVvaL7+dsVa+GlezvwSN/2PuB4VW0Fjnfbk2BhP2DyxgLgR7v2Pnsv9SSOx8I+wOSNxbuBj1XVDwAvp/d3a9LGYlAfYExjsaZCv3r+o9t8Tvczce9UJ5kGbgHu6iveCRzu1g8Dt465WUu2SD/Wiokbj0mX5CrgdcB7Aarq21X1r0zQWFygD2OzpkIf/nc64UvAWeBYVX222/VLSb6S5O7V/t8/4F3AO4Dv9JVdV1VnALrltSvQrqV6F+f3AyZrLKB34fDxJJ/vPiIEJm88BvUBJmssXgrMA3/eTRneleQFTNZYLNYHGNNYrLnQr6pnquoV9J723Z7kBuBO4PvoTfmcAf5oxRp4EUneAJytqs+vdFtGcYF+TMxY9HltVb2K3qfD7k3yupVu0BAG9WHSxuIK4FXAnVX1SuA/Wf1TOQst1oexjcWaC/1ndf9l+iSwo6qe6n4ZfAf4M3qf9rlavRZ4Y5In6H0K6Y8l+UvgqSQbALrl2ZVr4iUZ2I8JGwsAqup0tzwLfIhemydqPAb1YQLHYg6Y6/vf+730AnSSxmJgH8Y5Fmsq9JNMJXlRt/484MeBrz77F6LzM8BDK9C8S1JV+6tquqo20/uYik9U1ZvpfVzF7q7abuC+FWriJVmsH5M0FgBJXpDke55dB36SXpsnZjwW68OkjUVVfQM4leRlXdFNwMNM0Fgs1odxjsVa+2L0DcDh9L6s5buAI1X14SR/keQV9OY1nwB+YeWaOLSDwJEktwNPAretcHuG9fsTNhbXAR9KAr1/L39VVR9L8jkmZzwW68Mk/rv4ZeAD6X1219eAt9L9W5+QsYDBfXjPuMbCj2GQpIasqekdSdKFGfqS1BBDX5IaYuhLUkMMfUlqiKEvSQ0x9CWpIf8DHqWxhpALCiAAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "result.plot_hist('a', skip=1000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "severe-congo",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T10:00:55.457834Z",
     "start_time": "2021-06-09T10:00:55.399367Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "result.plot_hist('b', skip=1000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "nasty-scholarship",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T10:00:55.515619Z",
     "start_time": "2021-06-09T10:00:55.458752Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "result.plot_hist('c', skip=1000)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "boolean-theater",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2021-06-09T10:00:55.570637Z",
     "start_time": "2021-06-09T10:00:55.516488Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "result.plot_hist('d', skip=1000)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.4"
  },
  "latex_envs": {
   "LaTeX_envs_menu_present": true,
   "autoclose": false,
   "autocomplete": true,
   "bibliofile": "biblio.bib",
   "cite_by": "apalike",
   "current_citInitial": 1,
   "eqLabelWithNumbers": true,
   "eqNumInitial": 1,
   "hotkeys": {
    "equation": "Ctrl-E",
    "itemize": "Ctrl-I"
   },
   "labels_anchors": false,
   "latex_user_defs": false,
   "report_style_numbering": false,
   "user_envs_cfg": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}