{
 "cells": [
  {
   "cell_type": "markdown",
   "source": [
    "PyAutoFit\n",
    "=========\n",
    "\n",
    "**PyAutoFit** is a probabilistic programming language which makes is simple to compose, customize and fit complex\n",
    "models to data.\n",
    "\n",
    "To illustrate the **PyAutoFit** API, we'll use an illustrative toy model of fitting a one-dimensional Gaussian to\n",
    "noisy 1D data.\n",
    "\n",
    "Lets first import autofit and the other libraries we'll need."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Jammy\\Code\\PyAuto\\autofit_workspace\n",
      "Working Directory has been set to C:\\Users\\Jammy\\Code\\PyAuto\\autofit_workspace\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "2021-09-12 16:51:14,657 - autoconf.conf - WARNING - Pushing new config with path C:\\Users\\Jammy\\Code\\PyAuto\\PyAutoFit\\autofit\\config\n"
     ]
    }
   ],
   "source": [
    "# The 5 lines below set up the notebook working directory and can be ignored for the overview.\n",
    "\n",
    "%matplotlib inline\n",
    "from pyprojroot import here\n",
    "workspace_path = str(here())\n",
    "%cd $workspace_path\n",
    "print(f\"Working Directory has been set to {workspace_path}\")\n",
    "\n",
    "import autofit as af\n",
    "import autofit.plot as aplt\n",
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "from os import path"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "Simple Model\n",
    "------------\n",
    "\n",
    "We now load and plot the ``data`` we'll fit:"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "outputs": [
    {
     "data": {
      "text/plain": "<Figure size 432x288 with 1 Axes>",
      "image/png": "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\n"
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "dataset_path = path.join(\"dataset\", \"example_1d\", \"gaussian_x1\")\n",
    "data = af.util.numpy_array_from_json(file_path=path.join(dataset_path, \"data.json\"))\n",
    "noise_map = af.util.numpy_array_from_json(\n",
    "    file_path=path.join(dataset_path, \"noise_map.json\")\n",
    ")\n",
    "\n",
    "xvalues = np.arange(data.shape[0])\n",
    "plt.plot(xvalues, data, color=\"k\")\n",
    "plt.title(\"1D Gaussian dataset.\")\n",
    "plt.xlabel(\"x values of profile\")\n",
    "plt.ylabel(\"Profile Normalization\")\n",
    "plt.show()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "We define our model, a 1D Gaussian, by writing a Python class using the format below:"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "outputs": [],
   "source": [
    "class Gaussian:\n",
    "\n",
    "    def __init__(\n",
    "        self,\n",
    "        centre=0.0,  # <- PyAutoFit recognises these\n",
    "        normalization=0.1,  # <- constructor arguments are\n",
    "        sigma=0.01,  # <- the Gaussian's parameters.\n",
    "    ):\n",
    "        self.centre = centre\n",
    "        self.normalization = normalization\n",
    "        self.sigma = sigma\n",
    "\n",
    "    \"\"\"\n",
    "    An instance of the Gaussian class will be available during model fitting.\n",
    "\n",
    "    This method will be used to fit the model to data and compute a likelihood.\n",
    "    \"\"\"\n",
    "\n",
    "    def model_data_1d_via_xvalues_from(self, xvalues):\n",
    "\n",
    "        transformed_xvalues = np.subtract(xvalues, self.centre)\n",
    "\n",
    "        return np.multiply(\n",
    "            np.divide(self.normalization, self.sigma * np.sqrt(2.0 * np.pi)),\n",
    "            np.exp(-0.5 * np.square(np.divide(transformed_xvalues, self.sigma))),\n",
    "        )\n"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "By writing the `Gaussian` class in this way, PyAutoFit treats it as a *model-component* which can be fitted to data\n",
    "via a `NonLinearSearch`.\n",
    "\n",
    "PyAutoFit calls this a `Model` and it can generate instances of the class from custom *priors*."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model `Gaussian` object: \n",
      "\n",
      "Gaussian (centre, UniformPrior, lower_limit = 0.0, upper_limit = 100.0), (normalization, UniformPrior, lower_limit = 0.0, upper_limit = 100.0), (sigma, GaussianPrior, mean = 10.0, sigma = 5.0)\n",
      "\n",
      " Model `Gaussian` Parameters: \n",
      "\n",
      "UniformPrior, lower_limit = 0.0, upper_limit = 100.0\n",
      "UniformPrior, lower_limit = 0.0, upper_limit = 100.0\n",
      "GaussianPrior, mean = 10.0, sigma = 5.0\n"
     ]
    }
   ],
   "source": [
    "model = af.Model(Gaussian)\n",
    "\n",
    "model.centre = af.UniformPrior(lower_limit=0.0, upper_limit=100.0)\n",
    "model.normalization = af.UniformPrior(lower_limit=0.0, upper_limit=100.0)\n",
    "model.sigma = af.GaussianPrior(mean=10.0, sigma=5.0)\n",
    "\n",
    "print(\"Model `Gaussian` object: \\n\")\n",
    "print(model)\n",
    "\n",
    "print(\"\\n Model `Gaussian` Parameters: \\n\")\n",
    "print(model.centre)\n",
    "print(model.normalization)\n",
    "print(model.sigma)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "All of the information about the model can be printed at once using its `info` attribute:"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "print(model.info)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "Using this `Model` we can create an `instance` of the model, by mapping a list of unit values to physical values\n",
    "via the prior on each parameter."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model Instance: \n",
      "\n",
      "<__main__.Gaussian object at 0x0000025968F34190>\n",
      "\n",
      "Instance Parameters: \n",
      "\n",
      "x =  50.0\n",
      "normalization =  50.0\n",
      "sigma =  10.0\n"
     ]
    }
   ],
   "source": [
    "instance = model.instance_from_unit_vector(unit_vector=[0.5, 0.5, 0.5])\n",
    "\n",
    "print(\"Model Instance: \\n\")\n",
    "print(instance)\n",
    "\n",
    "print(\"\\nInstance Parameters: \\n\")\n",
    "print(\"x = \", instance.centre)\n",
    "print(\"normalization = \", instance.normalization)\n",
    "print(\"sigma = \", instance.sigma)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "This instance of the `Gaussian` class contains the functionality of its original class, for example\n",
    "the `model_data_1d_via_xvalues_from` function:"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "outputs": [
    {
     "data": {
      "text/plain": "<Figure size 432x288 with 1 Axes>",
      "image/png": "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\n"
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "profile = instance.model_data_1d_via_xvalues_from(xvalues=xvalues)\n",
    "\n",
    "plt.plot(xvalues, profile, color=\"r\")\n",
    "plt.title(\"1D Model Gaussian.\")\n",
    "plt.xlabel(\"x values of profile\")\n",
    "plt.ylabel(\"Profile Normalization\")\n",
    "plt.show()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "A *model* fit now only requires that a **PyAutoFit** ``Analysis`` class is written, which combines the data, model and\n",
    "likelihood function and defines how the *model-fit* is performed using a `NonLinearSearch`."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "outputs": [],
   "source": [
    "class Analysis(af.Analysis):\n",
    "\n",
    "    def __init__(self, data, noise_map):\n",
    "\n",
    "        self.data = data\n",
    "        self.noise_map = noise_map\n",
    "\n",
    "    def log_likelihood_function(self, instance):\n",
    "\n",
    "        \"\"\"\n",
    "        The 'instance' that comes into this method is an instance of the Gaussian class\n",
    "        above, with the parameters set to values chosen by the non-linear search.\n",
    "\n",
    "        (The lines below are commented out to text printing later in the Notebook. They\n",
    "        illustrate how model parameters are passed to the `log_likelihood_function`\n",
    "        \"\"\"\n",
    "\n",
    "        # print(\"Gaussian Instance:\")\n",
    "        # print(\"Centre = \", instance.centre)\n",
    "        # print(\"Normalization = \", instance.normalization)\n",
    "        # print(\"Sigma = \", instance.sigma)\n",
    "\n",
    "        \"\"\"\n",
    "        We fit the data with the Gaussian instance, using its\n",
    "        \"model_data_1d_via_xvalues_from\" function to create the model data.\n",
    "        \"\"\"\n",
    "\n",
    "        xvalues = np.arange(self.data.shape[0])\n",
    "\n",
    "        model_data = instance.model_data_1d_via_xvalues_from(xvalues=xvalues)\n",
    "        residual_map = self.data - model_data\n",
    "        chi_squared_map = (residual_map / self.noise_map) ** 2.0\n",
    "        log_likelihood = -0.5 * sum(chi_squared_map)\n",
    "\n",
    "        return log_likelihood\n"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "The ``Analysis`` class provides a model specific interface between **PyAutoFit** and the modeling software, allowing\n",
    "it to handle the 'heavy lifting' that comes with writing *model-fitting* software. This includes interfacing with the\n",
    "non-linear search, model-specific visualization during and the option of outputting results to a queryable database.\n",
    "\n",
    "Performing a fit with a non-linear search, for example `dynesty` (https://github.com/joshspeagle/dynesty),\n",
    "is performed as follows:"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Non-linear search running, this will take a minute or so.... \n",
      "\n",
      "2021-09-12 16:51:16,601 - autofit.non_linear.abstract_search - INFO - Creating search\n",
      "2021-09-12 16:51:16,602 - example_simple - INFO - Starting search\n",
      "2021-09-12 16:51:16,607 - example_simple - INFO - Saving path info\n",
      "2021-09-12 16:51:16,617 - example_simple - INFO - Not complete. Starting non-linear search.\n",
      "2021-09-12 16:51:16,619 - example_simple - INFO - number_of_cores == 1...\n",
      "2021-09-12 16:51:16,620 - example_simple - INFO - ...not using pool\n",
      "2021-09-12 16:51:16,622 - autofit.non_linear.initializer - INFO - Generating initial samples of model, which are subject to prior limits and other constraints.\n",
      "2021-09-12 16:51:16,643 - example_simple - INFO - No Dynesty samples found, beginning new non-linear search. \n",
      "2021-09-12 16:51:21,017 - example_simple - INFO - 5000 Iterations: Performing update (Visualization, outputting samples, etc.).\n",
      "2021-09-12 16:51:22,041 - example_simple - INFO - 10000 Iterations: Performing update (Visualization, outputting samples, etc.).\n",
      "2021-09-12 16:51:22,398 - example_simple - INFO - 15000 Iterations: Performing update (Visualization, outputting samples, etc.).\n",
      "2021-09-12 16:51:22,564 - example_simple - INFO - 20000 Iterations: Performing update (Visualization, outputting samples, etc.).\n",
      "2021-09-12 16:51:26,951 - example_simple - INFO - Removing zip file\n",
      "Non-linear search complete!\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "788it [00:04, 188.07it/s, +50 | bound: 39 | nc: 1 | ncall: 5052 | eff(%): 16.587 | loglstar:   -inf < -46.308 <    inf | logz: -63.429 +/-  0.843 | dlogz:  0.086 >  0.059]\n",
      "1012it [00:00, 1443.10it/s, +50 | bound: 49 | nc: 1 | ncall: 5818 | eff(%): 18.254 | loglstar:   -inf < -46.251 <    inf | logz: -63.434 +/-  0.794 | dlogz:  0.001 >  0.059]\n",
      "1012it [00:00, 1032506.85it/s, +50 | bound: 49 | nc: 1 | ncall: 5818 | eff(%): 18.254 | loglstar:   -inf < -46.251 <    inf | logz: -63.434 +/-  0.794 | dlogz:  0.001 >  0.059]\n"
     ]
    }
   ],
   "source": [
    "model = af.Model(Gaussian)\n",
    "\n",
    "analysis = Analysis(data=data, noise_map=noise_map)\n",
    "\n",
    "print(\"Non-linear search running, this will take a minute or so.... \\n\")\n",
    "\n",
    "search = af.DynestyStatic(nlive=50)\n",
    "result = search.fit(model=model, analysis=analysis)\n",
    "\n",
    "print(\"Non-linear search complete!\")"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "The result object returned by the fit provides information on the results of the non-linear search.\n",
    "\n",
    "The `info` attribute shows the model in a readable format, including the priors specified above:"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "print(result.info)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "We can inspect the result's maximum likelihood instance, which is contained in its `Samples` object.."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<__main__.Gaussian object at 0x000002596E84ABE0>\n",
      "\n",
      " Model-fit Max Log-likelihood Parameter Estimates: \n",
      "\n",
      "Centre =  49.87536218548179\n",
      "Normalization =  25.24493233392997\n",
      "Sigma =  10.099733805147636\n"
     ]
    }
   ],
   "source": [
    "samples = result.samples\n",
    "\n",
    "max_log_likelihood_instance = samples.max_log_likelihood()\n",
    "\n",
    "print(max_log_likelihood_instance)\n",
    "\n",
    "print(\"\\n Model-fit Max Log-likelihood Parameter Estimates: \\n\")\n",
    "print(\"Centre = \", result.max_log_likelihood_instance.centre)\n",
    "print(\"Normalization = \", result.max_log_likelihood_instance.normalization)\n",
    "print(\"Sigma = \", result.max_log_likelihood_instance.sigma)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "We can plot this over our data to see the model indeed gives a good fit."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "outputs": [
    {
     "data": {
      "text/plain": "<Figure size 432x288 with 1 Axes>",
      "image/png": "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\n"
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "model_data = result.max_log_likelihood_instance.model_data_1d_via_xvalues_from(\n",
    "    xvalues=np.arange(data.shape[0])\n",
    ")\n",
    "plt.errorbar(\n",
    "    x=xvalues, y=data, yerr=noise_map, color=\"k\", ecolor=\"k\", elinewidth=1, capsize=2\n",
    ")\n",
    "plt.plot(xvalues, model_data, color=\"r\")\n",
    "plt.title(\"Dynesty model fit to 1D Gaussian dataset.\")\n",
    "plt.xlabel(\"x values of profile\")\n",
    "plt.ylabel(\"Profile normalization\")\n",
    "plt.show()\n",
    "plt.close()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "The Probability Density Functions (PDF's) of the results can be plotted using Dynesty's in-built visualization tools,\n",
    "which are wrapped via the `DynestyPlotter` object."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "outputs": [
    {
     "data": {
      "text/plain": "<Figure size 547.2x547.2 with 9 Axes>",
      "image/png": "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\n"
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "search_plotter = aplt.DynestyPlotter(samples=result.samples)\n",
    "search_plotter.cornerplot()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "The non-linear search `dynesty` above did not output results to hard-disk, which for quick model-fits and\n",
    "experimenting with different models is desirable.\n",
    "\n",
    "For many problems it is preferable for all results to be written to hard-disk. The benefits of doing this include:\n",
    "\n",
    "- Inspecting results in an ordered directory structure can be more efficient than using a Jupyter Notebook.\n",
    "- Results can be output on-the-fly, to check that a fit is progressing as expected mid way through.\n",
    "- An unfinished run can be resumed where it was terminated.\n",
    "- Additional information about a fit (e.g. visualization) can be output.\n",
    "- On high performance computers which use a batch system, this is the only way to transfer results.\n",
    "\n",
    "Any model-fit performed by **PyAutoFit** can be saved to hard-disk, by simply giving the non-linear search a\n",
    "`name`. A `path_prefix` can optionally be input to customize the output directory."
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%% md\n"
    }
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "print(\"Non-linear search running, this will take a minute or so.... \\n\")\n",
    "\n",
    "search = af.DynestyStatic(\n",
    "    path_prefix=path.join(\"folder_0\", \"folder_1\"),\n",
    "    name=\"example_simple\",\n",
    "    nlive=50\n",
    ")\n",
    "result = search.fit(model=model, analysis=analysis)\n",
    "\n",
    "print(\"Non-linear search complete!\")"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "In the `autofit_workspace/output` directory you should find a folder containing the results of the model-fit\n",
    "for inspection, including text files containing the `model.info`, `results.info` and other information.\n",
    "\n",
    "The results are in a folder which is a collection of random characters. This is the 'unique_identifier' of\n",
    "the model-fit. This identifier is generated based on the model fitted and search used, such that an identical\n",
    "combination of model and search generates the same identifier. This ensures that rerunning an identical fit will\n",
    "use the existing results to resume the model-fit.\n",
    "\n",
    "Complex Model\n",
    "-------------\n",
    "\n",
    "It is straight forward to compose and customize more complex models with **PyAutoFit**.  To demonstrate this, we'll\n",
    "fit another 1D dataset that contains a Gaussian's and a symmetric Exponential profile."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "outputs": [
    {
     "data": {
      "text/plain": "<Figure size 432x288 with 1 Axes>",
      "image/png": "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\n"
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "dataset_path = path.join(\"dataset\", \"example_1d\", \"gaussian_x1__exponential_x1\")\n",
    "data = af.util.numpy_array_from_json(file_path=path.join(dataset_path, \"data.json\"))\n",
    "noise_map = af.util.numpy_array_from_json(\n",
    "    file_path=path.join(dataset_path, \"noise_map.json\")\n",
    ")\n",
    "\n",
    "xvalues = np.arange(data.shape[0])\n",
    "plt.plot(xvalues, data, color=\"k\")\n",
    "plt.title(\"1D Gaussian + Exponential dataset.\")\n",
    "plt.xlabel(\"x values of profile\")\n",
    "plt.ylabel(\"Profile Normalization\")\n",
    "plt.show()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "To fit the Exponential, we define a second Python class which will act as a *model-component* like the Gaussian did\n",
    "previously."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "outputs": [],
   "source": [
    "class Exponential:\n",
    "\n",
    "    def __init__(\n",
    "        self,\n",
    "        centre=0.0,     # <- PyAutoFit recognises these constructor arguments are the model\n",
    "        normalization=0.1,  # <- parameters of the Exponential.\n",
    "        rate=0.01,\n",
    "    ):\n",
    "        \"\"\"Represents a 1D Exponential profile symmetric about a centre, which may be treated as a model-component\n",
    "        of PyAutoFit the parameters of which are fitted for by a non-linear search.\n",
    "\n",
    "        Parameters\n",
    "        ----------\n",
    "        centre\n",
    "            The x coordinate of the profile centre.\n",
    "        normalization\n",
    "            Overall normalization normalisation of the `Gaussian` profile.\n",
    "        ratw\n",
    "            The decay rate controlling has fast the Exponential declines.\n",
    "        \"\"\"\n",
    "        self.centre = centre\n",
    "        self.normalization = normalization\n",
    "        self.rate = rate\n",
    "\n",
    "    def model_data_1d_via_xvalues_from(self, xvalues):\n",
    "        \"\"\"\n",
    "        Calculate the normalization of the profile on a line of Cartesian x coordinates.\n",
    "\n",
    "        The input xvalues are translated to a coordinate system centred on the Exponential, using its centre.\n",
    "\n",
    "        Parameters\n",
    "        ----------\n",
    "        values\n",
    "            The x coordinates in the original reference frame of the grid.\n",
    "        \"\"\"\n",
    "        transformed_xvalues = np.subtract(xvalues, self.centre)\n",
    "        return self.normalization * np.multiply(\n",
    "            self.rate, np.exp(-1.0 * self.rate * abs(transformed_xvalues))\n",
    "        )"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "We can compose a model from multiple *model-components* using the `Collection` object."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "outputs": [],
   "source": [
    "model = af.Collection(gaussian=Gaussian, exponential=Exponential)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "All of the information about this more complex model can be printed using its `info` attribute:"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "print(model.info)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "An `instance` of the model can be created like we did for a `Model` above."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Instance Parameters \n",
      "\n",
      "x (Gaussian) =  0.1\n",
      "normalization (Gaussian) =  0.2\n",
      "sigma (Gaussian) =  0.3\n",
      "x (Exponential) =  0.4\n",
      "normalization (Exponential) =  0.5\n",
      "sigma (Exponential) =  0.01\n"
     ]
    }
   ],
   "source": [
    "instance = model.instance_from_vector(vector=[0.1, 0.2, 0.3, 0.4, 0.5, 0.01])\n",
    "\n",
    "print(\"Instance Parameters \\n\")\n",
    "print(\"x (Gaussian) = \", instance.gaussian.centre)\n",
    "print(\"normalization (Gaussian) = \", instance.gaussian.normalization)\n",
    "print(\"sigma (Gaussian) = \", instance.gaussian.sigma)\n",
    "print(\"x (Exponential) = \", instance.exponential.centre)\n",
    "print(\"normalization (Exponential) = \", instance.exponential.normalization)\n",
    "print(\"sigma (Exponential) = \", instance.exponential.rate)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "There are many options for customizing a model, below we require that:\n",
    "\n",
    "- The `Gaussian` and `Exponential` share the same centre (reducing the dimensionality of parameter space by 1).\n",
    "- That the `Gaussian`'s `sigma` value is 10.0 (again reducing the dimensionality by 1).\n",
    "- That the `rate` parameter of the `Exponential` is above 0.0."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "outputs": [],
   "source": [
    "model.gaussian.centre = model.exponential.centre\n",
    "model.gaussian.sigma = 10.0\n",
    "model.exponential.add_assertion(model.exponential.rate > 0.0)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "We see these model customizations reflected in the `info` attribute:"
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "print(model.info)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "The `Analysis` class above was written assuming the input `instance` contained only a single `Gaussian` profile. The\n",
    "`Collection` contains multiple profiles, thus we must update the `Analysis` class to reflect this."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "outputs": [],
   "source": [
    "class Analysis(af.Analysis):\n",
    "\n",
    "    def __init__(self, data, noise_map):\n",
    "\n",
    "        self.data = data\n",
    "        self.noise_map = noise_map\n",
    "\n",
    "    def log_likelihood_function(self, instance):\n",
    "\n",
    "        xvalues = np.arange(self.data.shape[0])\n",
    "\n",
    "        \"\"\"\n",
    "        The instance, which now contains the `gaussian` and `exponential`, can be iterated over\n",
    "        and summed so our model-data is the combination of the two.\n",
    "        \"\"\"\n",
    "\n",
    "        model_data = sum(\n",
    "            [profile.model_data_1d_via_xvalues_from(xvalues=xvalues) for profile in instance]\n",
    "        )\n",
    "\n",
    "        residual_map = self.data - model_data\n",
    "        chi_squared_map = (residual_map / self.noise_map) ** 2.0\n",
    "        log_likelihood = -0.5 * sum(chi_squared_map)\n",
    "\n",
    "        return log_likelihood"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "We can now fit our more complex model as we did previously. Lets use the MCMC algorithm\n",
    "`Emcee` (https://github.com/dfm/emcee) this time."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Non-linear search running, this will take a minute or so.... \n",
      "\n",
      "2021-09-12 16:51:38,686 - autofit.non_linear.abstract_search - INFO - Creating search\n",
      "2021-09-12 16:51:38,688 - example_complex - INFO - Starting search\n",
      "2021-09-12 16:51:38,692 - example_complex - INFO - Saving path info\n",
      "2021-09-12 16:51:38,705 - example_complex - INFO - Not complete. Starting non-linear search.\n",
      "2021-09-12 16:51:38,707 - example_complex - INFO - number_of_cores == 1...\n",
      "2021-09-12 16:51:38,708 - example_complex - INFO - ...not using pool\n",
      "2021-09-12 16:51:38,716 - autofit.non_linear.initializer - INFO - Generating initial samples of model, which are subject to prior limits and other constraints.\n",
      "2021-09-12 16:51:38,741 - example_complex - INFO - No Emcee samples found, beginning new non-linear search.\n",
      "2021-09-12 16:51:42,182 - example_complex - INFO - 2500 Iterations: Performing update (Visualization, outputting samples, etc.).\n",
      "2021-09-12 16:51:43,405 - example_complex - INFO - Emcee sampling complete.\n",
      "2021-09-12 16:51:43,407 - example_complex - INFO - 5000 Iterations: Performing update (Visualization, outputting samples, etc.).\n",
      "2021-09-12 16:51:44,509 - root - WARNING - Too few points to create valid contours\n",
      "2021-09-12 16:51:47,090 - example_complex - INFO - Removing zip file\n",
      "Non-linear search complete!\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 200/200 [00:03<00:00, 58.57it/s]\n"
     ]
    }
   ],
   "source": [
    "analysis = Analysis(data=data, noise_map=noise_map)\n",
    "\n",
    "print(\"Non-linear search running, this will take a minute or so.... \\n\")\n",
    "\n",
    "search = af.Emcee(name=\"example_complex\", nwalkers=30, nsteps=200)\n",
    "result = search.fit(model=model, analysis=analysis)\n",
    "\n",
    "print(\"Non-linear search complete!\")"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "We again print the result's `info` to see a summary of the results."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [],
   "source": [
    "print(result.info)"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "Because our fit used a `Collection` (as opposed to a `Model`) the `Result` instance returns the\n",
    "results for both the `gaussian` and `exponential`."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Max Log Likelihood `Gaussian` Instance:\n",
      "Centre =  50.06566274749798\n",
      "Normalization =  23.307841741378876\n",
      "Sigma =  10.0 \n",
      "\n",
      "Max Log Likelihood Exponential Instance:\n",
      "Centre =  50.06566274749798\n",
      "Normalization =  40.887884816774886\n",
      "Sigma =  0.05165278497637013 \n",
      "\n"
     ]
    }
   ],
   "source": [
    "samples = result.samples\n",
    "\n",
    "max_log_likelihood_instance = samples.max_log_likelihood()\n",
    "\n",
    "print(max_log_likelihood_instance)\n",
    "\n",
    "print(\"Max Log Likelihood `Gaussian` Instance:\")\n",
    "print(\"Centre = \", max_log_likelihood_instance.gaussian.centre)\n",
    "print(\"Normalization = \", max_log_likelihood_instance.gaussian.normalization)\n",
    "print(\"Sigma = \", max_log_likelihood_instance.gaussian.sigma, \"\\n\")\n",
    "print(\"Max Log Likelihood Exponential Instance:\")\n",
    "print(\"Centre = \", max_log_likelihood_instance.exponential.centre)\n",
    "print(\"Normalization = \", max_log_likelihood_instance.exponential.normalization)\n",
    "print(\"Sigma = \", max_log_likelihood_instance.exponential.rate, \"\\n\")"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "We can again use this to plot the model fit."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "outputs": [
    {
     "data": {
      "text/plain": "<Figure size 432x288 with 1 Axes>",
      "image/png": "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\n"
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "model_gaussian = max_log_likelihood_instance.gaussian.model_data_1d_via_xvalues_from(\n",
    "    xvalues=np.arange(data.shape[0])\n",
    ")\n",
    "model_exponential = max_log_likelihood_instance.exponential.model_data_1d_via_xvalues_from(\n",
    "    xvalues=np.arange(data.shape[0])\n",
    ")\n",
    "model_data = model_gaussian + model_exponential\n",
    "\n",
    "plt.errorbar(\n",
    "    x=xvalues, y=data, yerr=noise_map, color=\"k\", ecolor=\"k\", elinewidth=1, capsize=2\n",
    ")\n",
    "plt.plot(range(data.shape[0]), model_data, color=\"r\")\n",
    "plt.plot(range(data.shape[0]), model_gaussian, \"--\")\n",
    "plt.plot(range(data.shape[0]), model_exponential, \"--\")\n",
    "plt.title(\"Emcee model fit to 1D Gaussian + Exponential dataset.\")\n",
    "plt.xlabel(\"x values of profile\")\n",
    "plt.ylabel(\"Profile normalization\")\n",
    "plt.show()\n",
    "plt.close()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "The Probability Density Functions (PDF's) of the results can be plotted using the Emcee's visualization\n",
    "tool `corner.py`, which is wrapped via the `EmceePlotter` object."
   ],
   "metadata": {
    "collapsed": false
   }
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2021-09-12 16:52:17,689 - root - WARNING - Too few points to create valid contours\n"
     ]
    },
    {
     "data": {
      "text/plain": "<Figure size 698.4x698.4 with 16 Axes>",
      "image/png": "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\n"
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "search_plotter = aplt.EmceePlotter(samples=result.samples)\n",
    "search_plotter.corner()"
   ],
   "metadata": {
    "collapsed": false,
    "pycharm": {
     "name": "#%%\n"
    }
   }
  },
  {
   "cell_type": "markdown",
   "source": [
    "Congratulations, you've  completed the **PyAutoFit** introduction!\n",
    "\n",
    "So, What Next?\n",
    "--------------\n",
    "\n",
    "This notebook has given you an overview of the **PyAutoFit** API, which is expanded on throughout the workspace and\n",
    "at the [following readthedocs page](https://pyautofit.readthedocs.io/en/latest/overview/model_fit.html).\n",
    "\n",
    "This API acts as the foundation for using many of **PyAutoFit**'s advanced features, such as:\n",
    "\n",
    "- [Database tools for loading and manipulating large libraries of results in a Jupyter notebook.](https://pyautofit.readthedocs.io/en/latest/features/database.html)\n",
    "- [Fitting large datasets with a graphical model](https://pyautofit.readthedocs.io/en/latest/howtofit/chapter_graphical_models.html)\n",
    "- [Performing massively parallel grid searches of non-linear searches.](https://pyautofit.readthedocs.io/en/latest/features/search_grid_search.html)\n",
    "- [Chaining non-linear searches back-to-back to break a complex model-fits into sequences of simpler model-fits](https://pyautofit.readthedocs.io/en/latest/features/search_chaining.html)\n",
    "- [Sensitivity mapping over a model or dataset to determine when complex model features become detectable](https://pyautofit.readthedocs.io/en/latest/features/sensitivity_mapping.html)\n",
    "\n",
    "We recommend you next start the **HowToFit** Jupyter notebook lectures, which provide a detailed description of the\n",
    "**PyAutoFit** API, give more details on how to compose and fit models and a more detailed description of the\n",
    "`Result` object and database analysis tools.\n",
    "\n",
    "The `autofit_workspace/*/model` package also provides cookbooks that act as a concise API reference for model composition.\n",
    "\n",
    "If you wish to add your own *model-component* to your `autofit_workspace` to perform your own model-fitting task,\n",
    "checkout the script `autofit_workspace/*/overview/new_model_component/new_model_compnent.ipynb`, which explains\n",
    "how to set up the **PyAutoFit** configuration files associated with your model.\n",
    "\n",
    "You can install **PyAutoFit** on your system and clone the `autofit_workspace` and `howtofit` tutorials\n",
    "following the instructions on our readthedocs:\n",
    "\n",
    " https://pyautofit.readthedocs.io/en/latest/installation/overview.html\n",
    "\n",
    "Alternatively, you can begin the tutorials on Binder by going to the folder `howtofit/chapter_1_introduction` at\n",
    "the following link `https://mybinder.org/v2/gh/Jammy2211/autofit_workspace/HEAD`."
   ],
   "metadata": {
    "collapsed": false
   }
  }
 ],
 "metadata": {
  "anaconda-cloud": {},
  "kernelspec": {
   "name": "pycharm-be979b41",
   "language": "python",
   "display_name": "PyCharm (Results)"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}