{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# **Introduction**\n",
    "\n",
    "This guide follows the same format as [quickstart](00-quickstart.ipynb) but explores further functionality provided by twinLab. In this jupyter notebook we will:\n",
    "\n",
    "1. Upload a dataset to twinLab.\n",
    "2. List, view and summarise uploaded datasets.\n",
    "3. Use `Emulator.train` to create a surrogate model.\n",
    "4. List, view and summarise trained emulators.\n",
    "5. Use the model to make a prediction with `Emulator.predict`.\n",
    "6. Visualise the results and their uncertainty.\n",
    "7. Verify the model using `Emulator.sample`.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "          ====== TwinLab Client Initialisation ======\n",
      "          Version     : 2.0.0\n",
      "          Server      : https://twinlab.digilab.co.uk\n",
      "          Environment : /Users/mead/digiLab/twinLab-Demos/.env\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Standard imports\n",
    "from pprint import pprint\n",
    "\n",
    "# Third-party imports\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "\n",
    "# Project imports\n",
    "import twinlab as tl"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Your twinLab information**\n",
    "\n",
    "Confirm your twinLab version\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'cloud': '2.0.0',\n",
       " 'modal': '0.2.0',\n",
       " 'library': '1.3.0',\n",
       " 'image': 'twinlab-prod'}"
      ]
     },
     "execution_count": 2,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tl.versions()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "And view your user information, including how many credits you have.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'username': 'alexander', 'credits': 1000}"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tl.user_information()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Upload a dataset**\n",
    "\n",
    "Datasets must be data presented as a `pandas.DataFrame` object, or a filepaths which points to a csv file that can be parsed to a `pandas.DataFrame` object. **Both must be formatted with clearly labelled columns.** Here, we will label the input (predictor) variable `x` and the output variable `y`. In `twinlab`, data is expected to be in column-feature format, meaning each row represents a single data sample, and each column represents a data feature.\n",
    "\n",
    "`twinLab` contains a `Dataset` class with attirbutes and methods to process, view and summarise the dataset. Datasets must be created with a `dataset_id` which is used to access them. The dataset can be uploaded using the `upload` method.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.696469</td>\n",
       "      <td>-0.817374</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.286139</td>\n",
       "      <td>0.887656</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.226851</td>\n",
       "      <td>0.921553</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.551315</td>\n",
       "      <td>-0.326334</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.719469</td>\n",
       "      <td>-0.832518</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.423106</td>\n",
       "      <td>0.400669</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.980764</td>\n",
       "      <td>-0.164966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.684830</td>\n",
       "      <td>-0.960764</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.480932</td>\n",
       "      <td>0.340115</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.392118</td>\n",
       "      <td>0.845795</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          x         y\n",
       "0  0.696469 -0.817374\n",
       "1  0.286139  0.887656\n",
       "2  0.226851  0.921553\n",
       "3  0.551315 -0.326334\n",
       "4  0.719469 -0.832518\n",
       "5  0.423106  0.400669\n",
       "6  0.980764 -0.164966\n",
       "7  0.684830 -0.960764\n",
       "8  0.480932  0.340115\n",
       "9  0.392118  0.845795"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Dataframe is uploading.\n",
      "Processing dataset\n",
      "Dataset example_data was processed.\n"
     ]
    }
   ],
   "source": [
    "x = [\n",
    "    0.6964691855978616,\n",
    "    0.28613933495037946,\n",
    "    0.2268514535642031,\n",
    "    0.5513147690828912,\n",
    "    0.7194689697855631,\n",
    "    0.42310646012446096,\n",
    "    0.9807641983846155,\n",
    "    0.6848297385848633,\n",
    "    0.48093190148436094,\n",
    "    0.3921175181941505,\n",
    "]\n",
    "\n",
    "y = [\n",
    "    -0.8173739564129022,\n",
    "    0.8876561174050408,\n",
    "    0.921552660721474,\n",
    "    -0.3263338765412979,\n",
    "    -0.8325176123242133,\n",
    "    0.4006686354731812,\n",
    "    -0.16496626502368078,\n",
    "    -0.9607643657025954,\n",
    "    0.3401149876855609,\n",
    "    0.8457949914442409,\n",
    "]\n",
    "\n",
    "# Creating the dataframe using the above arrays\n",
    "df = pd.DataFrame({\"x\": x, \"y\": y})\n",
    "\n",
    "# View the dataset before uploading\n",
    "display(df)\n",
    "\n",
    "# Define the name of the dataset\n",
    "dataset_id = \"example_data\"\n",
    "\n",
    "# Intialise a Dataset object\n",
    "dataset = tl.Dataset(id=dataset_id)\n",
    "\n",
    "# Upload the dataset\n",
    "dataset.upload(df, verbose=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **View datasets**\n",
    "\n",
    "Once a dataset has been uploaded it can be easily accessed using built in twinLab functions. A list of all uploaded datasets can be produced, individual datasets can be viewed and summarised. This summary contains some basic statistics of the data.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['2DActive_Data',\n",
       " 'Excel-test',\n",
       " 'Falmouth-Mikey',\n",
       " 'New_Points',\n",
       " 'biscuits',\n",
       " 'eval_data',\n",
       " 'example_data',\n",
       " 'functional-data',\n",
       " 'functional-test-data',\n",
       " 'fusion',\n",
       " 'sampled-data',\n",
       " 'twinLab-logo']"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# List all datasets on cloud\n",
    "tl.list_datasets()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.696469</td>\n",
       "      <td>-0.817374</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.286139</td>\n",
       "      <td>0.887656</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.226851</td>\n",
       "      <td>0.921553</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.551315</td>\n",
       "      <td>-0.326334</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.719469</td>\n",
       "      <td>-0.832518</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>0.423106</td>\n",
       "      <td>0.400669</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>0.980764</td>\n",
       "      <td>-0.164966</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>0.684830</td>\n",
       "      <td>-0.960764</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>0.480932</td>\n",
       "      <td>0.340115</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>0.392118</td>\n",
       "      <td>0.845795</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "          x         y\n",
       "0  0.696469 -0.817374\n",
       "1  0.286139  0.887656\n",
       "2  0.226851  0.921553\n",
       "3  0.551315 -0.326334\n",
       "4  0.719469 -0.832518\n",
       "5  0.423106  0.400669\n",
       "6  0.980764 -0.164966\n",
       "7  0.684830 -0.960764\n",
       "8  0.480932  0.340115\n",
       "9  0.392118  0.845795"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# View the dataset\n",
    "dataset.view()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "      <th>y</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>count</th>\n",
       "      <td>10.000000</td>\n",
       "      <td>10.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>mean</th>\n",
       "      <td>0.544199</td>\n",
       "      <td>0.029383</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>std</th>\n",
       "      <td>0.229352</td>\n",
       "      <td>0.748191</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>min</th>\n",
       "      <td>0.226851</td>\n",
       "      <td>-0.960764</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25%</th>\n",
       "      <td>0.399865</td>\n",
       "      <td>-0.694614</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>50%</th>\n",
       "      <td>0.516123</td>\n",
       "      <td>0.087574</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75%</th>\n",
       "      <td>0.693559</td>\n",
       "      <td>0.734513</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>max</th>\n",
       "      <td>0.980764</td>\n",
       "      <td>0.921553</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               x          y\n",
       "count  10.000000  10.000000\n",
       "mean    0.544199   0.029383\n",
       "std     0.229352   0.748191\n",
       "min     0.226851  -0.960764\n",
       "25%     0.399865  -0.694614\n",
       "50%     0.516123   0.087574\n",
       "75%     0.693559   0.734513\n",
       "max     0.980764   0.921553"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Get a statistical summary of the dataset\n",
    "dataset.summarise()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Train an emulator**\n",
    "\n",
    "The `Emulator` class is used to train and implement your surrogate models. As with datasets, an id is defined, this is what the model will be saved as in the cloud. When training a model the arguments are passed using a `TrainParams` object; `TrainParams` is a class that contains all the necessary parameters needed to train your model. To train the model we use the `Emulator.train` function, inputting the `TrainParams` object as an argument to this function.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model example_emulator has begun training.\n",
      "Training complete!\n",
      "\n"
     ]
    }
   ],
   "source": [
    "# Initialise emulator\n",
    "emulator_id = \"example_emulator\"\n",
    "\n",
    "emulator = tl.Emulator(id=emulator_id)\n",
    "\n",
    "# Define the training parameters for your emulator\n",
    "params = tl.TrainParams(train_test_ratio=1.0)\n",
    "\n",
    "# Train the mulator using the train method\n",
    "emulator.train(dataset=dataset, inputs=[\"x\"], outputs=[\"y\"], params=params, verbose=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **View emulators**\n",
    "\n",
    "Just as with datasets all saved emulators can be listed, viewed and summarised.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "['2DActiveGP',\n",
       " 'Example_emulator',\n",
       " 'Excel-emulator',\n",
       " 'Excel-model',\n",
       " 'Hello',\n",
       " 'backward-model',\n",
       " 'biscuits',\n",
       " 'campaign',\n",
       " 'decoder',\n",
       " 'example_emulator',\n",
       " 'fusion',\n",
       " 'gardening',\n",
       " 'my_emulator',\n",
       " 'new-campaign',\n",
       " 'twinLab-logo',\n",
       " 'universe']"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# List emulators\n",
    "tl.list_emulators()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'model_id': 'example_emulator',\n",
       " 'fidelity': None,\n",
       " 'estimator': 'gaussian_process_regression',\n",
       " 'estimator_kwargs': {'detrend': False,\n",
       "  'device': 'cpu',\n",
       "  'covar_module': None,\n",
       "  'estimator_type': None},\n",
       " 'decompose_input': False,\n",
       " 'input_explained_variance': 0.99,\n",
       " 'decompose_output': False,\n",
       " 'output_explained_variance': 0.99,\n",
       " 'train_test_ratio': 1.0,\n",
       " 'model_selection': False,\n",
       " 'model_selection_kwargs': {'seed': None,\n",
       "  'evaluation_metric': 'MSLL',\n",
       "  'val_ratio': 0.2,\n",
       "  'base_kernels': 'restricted',\n",
       "  'depth': 1,\n",
       "  'beam': None,\n",
       "  'resource_per_trial': {'cpu': 1, 'gpu': 0}},\n",
       " 'seed': None,\n",
       " 'inputs': ['x'],\n",
       " 'outputs': ['y'],\n",
       " 'dataset_id': 'example_data',\n",
       " 'modal_handle': 'fc-ktRp3Nc749lshsKZvgJH4y'}"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# View an emulator's parameters\n",
    "emulator.view()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'model_summary': {'data_diagnostics': {'inputs': {'x': {'25%': 0.39986475367672814,\n",
      "                                                         '50%': 0.5161233352836261,\n",
      "                                                         '75%': 0.693559323844612,\n",
      "                                                         'count': 10.0,\n",
      "                                                         'max': 0.9807641983846156,\n",
      "                                                         'mean': 0.544199352975335,\n",
      "                                                         'min': 0.2268514535642031,\n",
      "                                                         'std': 0.22935216613691597}},\n",
      "                                        'outputs': {'y': {'25%': -0.6946139364450011,\n",
      "                                                          '50%': 0.0875743613309401,\n",
      "                                                          '75%': 0.7345134024514759,\n",
      "                                                          'count': 10.0,\n",
      "                                                          'max': 0.921552660721474,\n",
      "                                                          'mean': 0.029383131672480845,\n",
      "                                                          'min': -0.9607643657025954,\n",
      "                                                          'std': 0.7481906564998719}}},\n",
      "                   'estimator_diagnostics': {'covar_module': 'ScaleKernel(\\n'\n",
      "                                                             '  (base_kernel): '\n",
      "                                                             'MaternKernel(\\n'\n",
      "                                                             '    '\n",
      "                                                             '(lengthscale_prior): '\n",
      "                                                             'GammaPrior()\\n'\n",
      "                                                             '    '\n",
      "                                                             '(raw_lengthscale_constraint): '\n",
      "                                                             'Positive()\\n'\n",
      "                                                             '  )\\n'\n",
      "                                                             '  '\n",
      "                                                             '(outputscale_prior): '\n",
      "                                                             'GammaPrior()\\n'\n",
      "                                                             '  '\n",
      "                                                             '(raw_outputscale_constraint): '\n",
      "                                                             'Positive()\\n'\n",
      "                                                             ')',\n",
      "                                             'covar_module.base_kernel.lengthscale_prior.concentration': 3.0,\n",
      "                                             'covar_module.base_kernel.lengthscale_prior.rate': 6.0,\n",
      "                                             'covar_module.base_kernel.original_lengthscale': [[0.4232063885665337]],\n",
      "                                             'covar_module.base_kernel.raw_lengthscale': [[-0.6408405631160488]],\n",
      "                                             'covar_module.base_kernel.raw_lengthscale_constraint.lower_bound': 0.0,\n",
      "                                             'covar_module.base_kernel.raw_lengthscale_constraint.upper_bound': inf,\n",
      "                                             'covar_module.original_outputscale': 1.7130960752713094,\n",
      "                                             'covar_module.outputscale_prior.concentration': 2.0,\n",
      "                                             'covar_module.outputscale_prior.rate': 0.15000000596046448,\n",
      "                                             'covar_module.raw_outputscale': 1.514271061131159,\n",
      "                                             'covar_module.raw_outputscale_constraint.lower_bound': 0.0,\n",
      "                                             'covar_module.raw_outputscale_constraint.upper_bound': inf,\n",
      "                                             'input_transform._coefficient': [[0.7539127448204125]],\n",
      "                                             'input_transform._offset': [[0.2268514535642031]],\n",
      "                                             'likelihood.noise_covar.noise_prior.concentration': 1.100000023841858,\n",
      "                                             'likelihood.noise_covar.noise_prior.rate': 0.05000000074505806,\n",
      "                                             'likelihood.noise_covar.original_noise': [0.031576525703137535],\n",
      "                                             'likelihood.noise_covar.raw_noise': [0.031576525703137535],\n",
      "                                             'likelihood.noise_covar.raw_noise_constraint.lower_bound': 9.999999747378752e-05,\n",
      "                                             'likelihood.noise_covar.raw_noise_constraint.upper_bound': inf,\n",
      "                                             'mean_module': 'ConstantMean()',\n",
      "                                             'mean_module.original_constant': 0.21052500685316855,\n",
      "                                             'mean_module.raw_constant': 0.21052500685316855,\n",
      "                                             'outcome_transform._stdvs_sq': [[0.5597892584737093]],\n",
      "                                             'outcome_transform.means': [[0.029383131672480856]],\n",
      "                                             'outcome_transform.stdvs': [[0.7481906564998719]]},\n",
      "                   'transformer_diagnostics': []}}\n"
     ]
    }
   ],
   "source": [
    "# View the status of a campaign\n",
    "pprint(emulator.summarise())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Prediction using the trained emulators**\n",
    "\n",
    "The surrogate model is now trained and saved to the cloud under the `emulator_id`. It can now be used to make predictions. First define a dataset of inputs for which you want to find outputs; ensure that this is a `pandas.DataFrame` object. Then call `Emulator.predict` with the keyword arguments being the evaluation dataset.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>x</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.000000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.007874</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.015748</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.023622</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.031496</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>123</th>\n",
       "      <td>0.968504</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>124</th>\n",
       "      <td>0.976378</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>125</th>\n",
       "      <td>0.984252</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>126</th>\n",
       "      <td>0.992126</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>127</th>\n",
       "      <td>1.000000</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>128 rows × 1 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            x\n",
       "0    0.000000\n",
       "1    0.007874\n",
       "2    0.015748\n",
       "3    0.023622\n",
       "4    0.031496\n",
       "..        ...\n",
       "123  0.968504\n",
       "124  0.976378\n",
       "125  0.984252\n",
       "126  0.992126\n",
       "127  1.000000\n",
       "\n",
       "[128 rows x 1 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "          y         y\n",
      "0  0.617689  0.656265\n",
      "1  0.629105  0.640576\n",
      "2  0.640630  0.624421\n",
      "3  0.652252  0.607809\n",
      "4  0.663957  0.590755\n"
     ]
    }
   ],
   "source": [
    "# Define the inputs for the dataset\n",
    "x_eval = np.linspace(0, 1, 128)\n",
    "\n",
    "# Convert to a dataframe\n",
    "df_eval = pd.DataFrame({\"x\": x_eval})\n",
    "display(df_eval)\n",
    "\n",
    "# Predict the results\n",
    "predictions = emulator.predict(df_eval)\n",
    "result_df = pd.concat([predictions[0], predictions[1]], axis=1)\n",
    "df_mean, df_stdev = result_df.iloc[:,0], result_df.iloc[:,1]\n",
    "df_mean, df_stdev = df_mean.values, df_stdev.values\n",
    "print(result_df.head())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Viewing the results**\n",
    "\n",
    "`Emulator.predict` outputs mean values for each input and their standard deviation; this gives the abilty to nicely visualise the uncertainty in results.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot parameters\n",
    "nsigs = [1, 2]\n",
    "color = \"blue\"\n",
    "alpha = 0.5\n",
    "plot_training_data = True\n",
    "plot_model_mean = True\n",
    "plot_model_bands = True\n",
    "\n",
    "# Plot results\n",
    "grid = df_eval[\"x\"]\n",
    "mean = df_mean\n",
    "err = df_stdev\n",
    "if plot_model_bands:\n",
    "    label = r\"Model prediction\"\n",
    "    plt.fill_between(grid, np.nan, np.nan, lw=0, color=color, alpha=alpha, label=label)\n",
    "    for isig, nsig in enumerate(nsigs):\n",
    "        plt.fill_between(\n",
    "            grid,\n",
    "            mean - nsig * err,\n",
    "            mean + nsig * err,\n",
    "            lw=0,\n",
    "            color=color,\n",
    "            alpha=alpha / (isig + 1),\n",
    "        )\n",
    "if plot_model_mean:\n",
    "    label = r\"Model prediction\" if not plot_model_bands else None\n",
    "    plt.plot(grid, mean, color=color, alpha=alpha, label=label)\n",
    "if plot_training_data:\n",
    "    plt.plot(df[\"x\"], df[\"y\"], \".\", color=\"black\", label=\"Training data\")\n",
    "plt.xlim((0.0, 1.0))\n",
    "plt.xlabel(r\"$X$\")\n",
    "plt.ylabel(r\"$y$\")\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Sampling from an emulator**\n",
    "\n",
    "The `Emulator.sample` function can be used to retrieve a number of results from your model. It requires the inputs for which you want the values and how many outputs to calculate for each.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead tr th {\n",
       "        text-align: left;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th colspan=\"21\" halign=\"left\">y</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>...</th>\n",
       "      <th>90</th>\n",
       "      <th>91</th>\n",
       "      <th>92</th>\n",
       "      <th>93</th>\n",
       "      <th>94</th>\n",
       "      <th>95</th>\n",
       "      <th>96</th>\n",
       "      <th>97</th>\n",
       "      <th>98</th>\n",
       "      <th>99</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1.264127</td>\n",
       "      <td>1.259498</td>\n",
       "      <td>0.664856</td>\n",
       "      <td>1.290327</td>\n",
       "      <td>-1.061115</td>\n",
       "      <td>0.063356</td>\n",
       "      <td>1.326666</td>\n",
       "      <td>1.789418</td>\n",
       "      <td>-0.009024</td>\n",
       "      <td>1.259869</td>\n",
       "      <td>...</td>\n",
       "      <td>0.939294</td>\n",
       "      <td>0.362207</td>\n",
       "      <td>0.011521</td>\n",
       "      <td>1.053759</td>\n",
       "      <td>-0.409518</td>\n",
       "      <td>1.014478</td>\n",
       "      <td>0.751929</td>\n",
       "      <td>1.641282</td>\n",
       "      <td>0.826082</td>\n",
       "      <td>0.469116</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1.263028</td>\n",
       "      <td>1.274143</td>\n",
       "      <td>0.643489</td>\n",
       "      <td>1.300232</td>\n",
       "      <td>-0.994251</td>\n",
       "      <td>0.108671</td>\n",
       "      <td>1.342242</td>\n",
       "      <td>1.764897</td>\n",
       "      <td>0.008574</td>\n",
       "      <td>1.246439</td>\n",
       "      <td>...</td>\n",
       "      <td>0.978143</td>\n",
       "      <td>0.343955</td>\n",
       "      <td>0.050809</td>\n",
       "      <td>1.024005</td>\n",
       "      <td>-0.418823</td>\n",
       "      <td>1.016179</td>\n",
       "      <td>0.779650</td>\n",
       "      <td>1.598208</td>\n",
       "      <td>0.826613</td>\n",
       "      <td>0.468406</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1.260150</td>\n",
       "      <td>1.283785</td>\n",
       "      <td>0.621806</td>\n",
       "      <td>1.308611</td>\n",
       "      <td>-0.921023</td>\n",
       "      <td>0.157252</td>\n",
       "      <td>1.354430</td>\n",
       "      <td>1.740139</td>\n",
       "      <td>0.031373</td>\n",
       "      <td>1.232385</td>\n",
       "      <td>...</td>\n",
       "      <td>1.014755</td>\n",
       "      <td>0.328073</td>\n",
       "      <td>0.091420</td>\n",
       "      <td>0.993893</td>\n",
       "      <td>-0.423898</td>\n",
       "      <td>1.014795</td>\n",
       "      <td>0.809190</td>\n",
       "      <td>1.552288</td>\n",
       "      <td>0.830950</td>\n",
       "      <td>0.468252</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1.256019</td>\n",
       "      <td>1.290381</td>\n",
       "      <td>0.602094</td>\n",
       "      <td>1.315111</td>\n",
       "      <td>-0.842858</td>\n",
       "      <td>0.207179</td>\n",
       "      <td>1.363444</td>\n",
       "      <td>1.714233</td>\n",
       "      <td>0.056631</td>\n",
       "      <td>1.218001</td>\n",
       "      <td>...</td>\n",
       "      <td>1.048197</td>\n",
       "      <td>0.315876</td>\n",
       "      <td>0.130009</td>\n",
       "      <td>0.965887</td>\n",
       "      <td>-0.424134</td>\n",
       "      <td>1.010628</td>\n",
       "      <td>0.840416</td>\n",
       "      <td>1.503579</td>\n",
       "      <td>0.839256</td>\n",
       "      <td>0.469101</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1.249843</td>\n",
       "      <td>1.294567</td>\n",
       "      <td>0.584412</td>\n",
       "      <td>1.319314</td>\n",
       "      <td>-0.762038</td>\n",
       "      <td>0.258642</td>\n",
       "      <td>1.367987</td>\n",
       "      <td>1.686284</td>\n",
       "      <td>0.081911</td>\n",
       "      <td>1.204734</td>\n",
       "      <td>...</td>\n",
       "      <td>1.077572</td>\n",
       "      <td>0.307563</td>\n",
       "      <td>0.166610</td>\n",
       "      <td>0.942370</td>\n",
       "      <td>-0.419536</td>\n",
       "      <td>1.003131</td>\n",
       "      <td>0.871847</td>\n",
       "      <td>1.452200</td>\n",
       "      <td>0.851765</td>\n",
       "      <td>0.470634</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>123</th>\n",
       "      <td>-0.243466</td>\n",
       "      <td>-0.376759</td>\n",
       "      <td>-0.222920</td>\n",
       "      <td>-0.164613</td>\n",
       "      <td>-0.123029</td>\n",
       "      <td>-0.107526</td>\n",
       "      <td>-0.491095</td>\n",
       "      <td>-0.200305</td>\n",
       "      <td>-0.075683</td>\n",
       "      <td>-0.080205</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.130376</td>\n",
       "      <td>-0.088158</td>\n",
       "      <td>0.005756</td>\n",
       "      <td>-0.193393</td>\n",
       "      <td>-0.067758</td>\n",
       "      <td>-0.131498</td>\n",
       "      <td>-0.122326</td>\n",
       "      <td>-0.211535</td>\n",
       "      <td>-0.343941</td>\n",
       "      <td>-0.117467</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>124</th>\n",
       "      <td>-0.237385</td>\n",
       "      <td>-0.361383</td>\n",
       "      <td>-0.176733</td>\n",
       "      <td>-0.150867</td>\n",
       "      <td>-0.107936</td>\n",
       "      <td>-0.042114</td>\n",
       "      <td>-0.411948</td>\n",
       "      <td>-0.214185</td>\n",
       "      <td>-0.082167</td>\n",
       "      <td>-0.053210</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.099505</td>\n",
       "      <td>-0.143001</td>\n",
       "      <td>-0.020947</td>\n",
       "      <td>-0.184918</td>\n",
       "      <td>-0.064551</td>\n",
       "      <td>-0.152278</td>\n",
       "      <td>-0.089314</td>\n",
       "      <td>-0.181028</td>\n",
       "      <td>-0.336784</td>\n",
       "      <td>-0.087687</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>125</th>\n",
       "      <td>-0.229653</td>\n",
       "      <td>-0.344955</td>\n",
       "      <td>-0.129858</td>\n",
       "      <td>-0.138228</td>\n",
       "      <td>-0.093384</td>\n",
       "      <td>0.024250</td>\n",
       "      <td>-0.334807</td>\n",
       "      <td>-0.228415</td>\n",
       "      <td>-0.090190</td>\n",
       "      <td>-0.028539</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.063867</td>\n",
       "      <td>-0.199541</td>\n",
       "      <td>-0.047168</td>\n",
       "      <td>-0.171532</td>\n",
       "      <td>-0.062122</td>\n",
       "      <td>-0.173057</td>\n",
       "      <td>-0.057060</td>\n",
       "      <td>-0.150006</td>\n",
       "      <td>-0.333920</td>\n",
       "      <td>-0.053370</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>126</th>\n",
       "      <td>-0.220961</td>\n",
       "      <td>-0.326984</td>\n",
       "      <td>-0.082629</td>\n",
       "      <td>-0.126160</td>\n",
       "      <td>-0.080773</td>\n",
       "      <td>0.088925</td>\n",
       "      <td>-0.260510</td>\n",
       "      <td>-0.242954</td>\n",
       "      <td>-0.099340</td>\n",
       "      <td>-0.005383</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.024045</td>\n",
       "      <td>-0.256805</td>\n",
       "      <td>-0.072422</td>\n",
       "      <td>-0.153905</td>\n",
       "      <td>-0.059526</td>\n",
       "      <td>-0.193384</td>\n",
       "      <td>-0.026572</td>\n",
       "      <td>-0.118515</td>\n",
       "      <td>-0.335199</td>\n",
       "      <td>-0.014476</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>127</th>\n",
       "      <td>-0.211589</td>\n",
       "      <td>-0.307667</td>\n",
       "      <td>-0.034203</td>\n",
       "      <td>-0.113222</td>\n",
       "      <td>-0.070149</td>\n",
       "      <td>0.152874</td>\n",
       "      <td>-0.191118</td>\n",
       "      <td>-0.259736</td>\n",
       "      <td>-0.108993</td>\n",
       "      <td>0.016120</td>\n",
       "      <td>...</td>\n",
       "      <td>0.019210</td>\n",
       "      <td>-0.314823</td>\n",
       "      <td>-0.096437</td>\n",
       "      <td>-0.133574</td>\n",
       "      <td>-0.056565</td>\n",
       "      <td>-0.213358</td>\n",
       "      <td>0.001427</td>\n",
       "      <td>-0.087783</td>\n",
       "      <td>-0.339115</td>\n",
       "      <td>0.027192</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>128 rows × 100 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            y                                                              \\\n",
       "            0         1         2         3         4         5         6   \n",
       "0    1.264127  1.259498  0.664856  1.290327 -1.061115  0.063356  1.326666   \n",
       "1    1.263028  1.274143  0.643489  1.300232 -0.994251  0.108671  1.342242   \n",
       "2    1.260150  1.283785  0.621806  1.308611 -0.921023  0.157252  1.354430   \n",
       "3    1.256019  1.290381  0.602094  1.315111 -0.842858  0.207179  1.363444   \n",
       "4    1.249843  1.294567  0.584412  1.319314 -0.762038  0.258642  1.367987   \n",
       "..        ...       ...       ...       ...       ...       ...       ...   \n",
       "123 -0.243466 -0.376759 -0.222920 -0.164613 -0.123029 -0.107526 -0.491095   \n",
       "124 -0.237385 -0.361383 -0.176733 -0.150867 -0.107936 -0.042114 -0.411948   \n",
       "125 -0.229653 -0.344955 -0.129858 -0.138228 -0.093384  0.024250 -0.334807   \n",
       "126 -0.220961 -0.326984 -0.082629 -0.126160 -0.080773  0.088925 -0.260510   \n",
       "127 -0.211589 -0.307667 -0.034203 -0.113222 -0.070149  0.152874 -0.191118   \n",
       "\n",
       "                                   ...                                \\\n",
       "            7         8         9  ...        90        91        92   \n",
       "0    1.789418 -0.009024  1.259869  ...  0.939294  0.362207  0.011521   \n",
       "1    1.764897  0.008574  1.246439  ...  0.978143  0.343955  0.050809   \n",
       "2    1.740139  0.031373  1.232385  ...  1.014755  0.328073  0.091420   \n",
       "3    1.714233  0.056631  1.218001  ...  1.048197  0.315876  0.130009   \n",
       "4    1.686284  0.081911  1.204734  ...  1.077572  0.307563  0.166610   \n",
       "..        ...       ...       ...  ...       ...       ...       ...   \n",
       "123 -0.200305 -0.075683 -0.080205  ... -0.130376 -0.088158  0.005756   \n",
       "124 -0.214185 -0.082167 -0.053210  ... -0.099505 -0.143001 -0.020947   \n",
       "125 -0.228415 -0.090190 -0.028539  ... -0.063867 -0.199541 -0.047168   \n",
       "126 -0.242954 -0.099340 -0.005383  ... -0.024045 -0.256805 -0.072422   \n",
       "127 -0.259736 -0.108993  0.016120  ...  0.019210 -0.314823 -0.096437   \n",
       "\n",
       "                                                                           \n",
       "           93        94        95        96        97        98        99  \n",
       "0    1.053759 -0.409518  1.014478  0.751929  1.641282  0.826082  0.469116  \n",
       "1    1.024005 -0.418823  1.016179  0.779650  1.598208  0.826613  0.468406  \n",
       "2    0.993893 -0.423898  1.014795  0.809190  1.552288  0.830950  0.468252  \n",
       "3    0.965887 -0.424134  1.010628  0.840416  1.503579  0.839256  0.469101  \n",
       "4    0.942370 -0.419536  1.003131  0.871847  1.452200  0.851765  0.470634  \n",
       "..        ...       ...       ...       ...       ...       ...       ...  \n",
       "123 -0.193393 -0.067758 -0.131498 -0.122326 -0.211535 -0.343941 -0.117467  \n",
       "124 -0.184918 -0.064551 -0.152278 -0.089314 -0.181028 -0.336784 -0.087687  \n",
       "125 -0.171532 -0.062122 -0.173057 -0.057060 -0.150006 -0.333920 -0.053370  \n",
       "126 -0.153905 -0.059526 -0.193384 -0.026572 -0.118515 -0.335199 -0.014476  \n",
       "127 -0.133574 -0.056565 -0.213358  0.001427 -0.087783 -0.339115  0.027192  \n",
       "\n",
       "[128 rows x 100 columns]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Define the sample inputs\n",
    "sample_inputs = pd.DataFrame({\"x\": np.linspace(0, 1, 128)})\n",
    "\n",
    "# Define number of samples to calculate for each input\n",
    "num_samples = 100\n",
    "\n",
    "# Calculate the samples using twinLab\n",
    "sample_result = emulator.sample(sample_inputs, num_samples)\n",
    "\n",
    "# View the results in the form of a dataframe\n",
    "display(sample_result)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Viewing the results**\n",
    "\n",
    "The results can be plotted over the top of the previous graph giving a nice visualisation of the sampled data, with the model's uncertainity.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Plot parameters\n",
    "color_curve = \"blue\"\n",
    "alpha_curve = 0.10\n",
    "color_data = \"black\"\n",
    "plot_training_data = True\n",
    "plot_model_bands = False\n",
    "\n",
    "# Plot samples drawn from the model\n",
    "if plot_training_data:\n",
    "    plt.plot(df[\"x\"], df[\"y\"], \".\", color=color_data, label=\"Training data\")\n",
    "plt.plot(sample_inputs, sample_result[\"y\"], color=color_curve, alpha=alpha_curve)\n",
    "plt.xlim((0.0, 1.0))\n",
    "plt.xlabel(r\"$X$\")\n",
    "plt.ylabel(r\"$y$\")\n",
    "plt.legend()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### **Deleting datasets and emulators**\n",
    "\n",
    "To keep your cloud storage tidy you should delete your datasets and emulators when you are finished with them. `Emulator.delete` and `Dataset.delete` deletes the emulators and the datasets from the cloud storage respectively.\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Delete dataset\n",
    "dataset.delete()\n",
    "\n",
    "# Delete emulator\n",
    "emulator.delete()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "twinlab-demos-5eekO54e-py3.11",
   "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": "3.11.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}