diff --git a/.github/ISSUE_TEMPLATE.md b/.github/ISSUE_TEMPLATE.md
new file mode 100644
index 0000000..83d6e66
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE.md
@@ -0,0 +1,10 @@
+---
+name: Enhancement Template
+about: An enhancement for the project
+labels: enhancement
+title: ""
+---
+
+Description
+===========
+A clear and concise description of what the issue is about.
diff --git a/.github/ISSUE_TEMPLATE/bug-report.md b/.github/ISSUE_TEMPLATE/bug-report.md
new file mode 100644
index 0000000..7893908
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE/bug-report.md
@@ -0,0 +1,29 @@
+---
+name: Bug Report
+about: Create a report of a bug or problem
+labels: bug
+title: "bug: "
+---
+
+Describe the bug
+================
+A clear and concise description of what the bug is.
+
+To Reproduce
+============
+Steps to reproduce the behavior:
+1. Do X
+2. Type Y
+3. ...
+
+Expected behavior
+=================
+A clear and concise description of what you expected to happen.
+
+Screenshots
+===========
+If applicable, add screenshots to help explain your problem.
+
+Additional context
+==================
+Add any other context about the problem here.
diff --git a/.github/ISSUE_TEMPLATE/enhancement.md b/.github/ISSUE_TEMPLATE/enhancement.md
new file mode 100644
index 0000000..83589f4
--- /dev/null
+++ b/.github/ISSUE_TEMPLATE/enhancement.md
@@ -0,0 +1,22 @@
+---
+name: Enhancement
+about: New/updated functionality
+labels: enhancement
+title: "enhancement: "
+---
+
+Current Situation
+=================
+A clear and concise description of what the current functionality is.
+
+Enhancement
+===========
+A quick description of the proposed enhancement
+
+Reasoning
+=========
+Why should this enhancement be added to the repository?
+
+Implementation
+==============
+Overview of possible implementations
diff --git a/.github/PULL_REQUEST_TEMPLATE.md b/.github/PULL_REQUEST_TEMPLATE.md
new file mode 100644
index 0000000..b8a005b
--- /dev/null
+++ b/.github/PULL_REQUEST_TEMPLATE.md
@@ -0,0 +1,11 @@
+What does this PR do?
+=====================
+
+Why are we doing this?
+======================
+
+Testing performed
+=================
+
+Known bugs/limitations
+======================
diff --git a/ARCHITECTURE.md b/ARCHITECTURE.md
new file mode 100644
index 0000000..fbd0fdb
--- /dev/null
+++ b/ARCHITECTURE.md
@@ -0,0 +1,3 @@
+todo
+
+context: https://matklad.github.io//2021/02/06/ARCHITECTURE.md.html
diff --git a/CODE_OF_CONDUCT.md b/CODE_OF_CONDUCT.md
new file mode 100644
index 0000000..caf7325
--- /dev/null
+++ b/CODE_OF_CONDUCT.md
@@ -0,0 +1 @@
+Be excellent to each other
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
new file mode 100644
index 0000000..258cd57
--- /dev/null
+++ b/CONTRIBUTING.md
@@ -0,0 +1 @@
+todo
diff --git a/CONTRIBUTORS.md b/CONTRIBUTORS.md
new file mode 100644
index 0000000..258cd57
--- /dev/null
+++ b/CONTRIBUTORS.md
@@ -0,0 +1 @@
+todo
diff --git a/DOCKERFILE b/DOCKERFILE
new file mode 100644
index 0000000..e69de29
diff --git a/README.md b/README.md
index 6fb1538..a44b16b 100644
--- a/README.md
+++ b/README.md
@@ -1,2 +1,39 @@
-# snn-sound-localization
+# SNN Sound Localization
+
 Training spiking neural networks for sound localization
+
+## Workflow
+
+A detailed description can be found in the `CONTRIBUTING.md` file. Briefly, the `notebooks/` directory is a
+free-for-all, just try to keep your work in your own notebook to avoid conflicts. When you have a polished piece of work
+(e.g. to generate a figure for the paper), open a pull request to add it to the `spikeloc/` directory where the "finished"
+code lives. Code must be reviewed before being merged into `spikeloc/`.
+
+If you need help with using git/Github, just ask in the discord and someone will lend a hand!
+
+## Installation
+
+Multiple installation methods are supported: conda (environment.yml), poetry (pyproject.toml), pip
+(requirements.txt), docker (DOCKERFILE)
+
+### Conda
+
+1. `conda env create -f environment.yml`
+2. `conda activate spikeloc`
+
+### Poetry
+
+1. Install [Poetry](https://python-poetry.org/)
+2. (optional) Create a virtualenv: `python -m venv .venv`
+3. (optional) Source the newly created virtualenv: `source .venv/bin/activate`
+4. Run `poetry install`
+
+### Pip
+
+1. Create a virtualenv: `python -m venv .venv`
+2. Source the newly created virtualenv: `source .venv/bin/activate`
+3. Run `pip install -r requirements.txt`
+
+## Community
+
+Find us on Discord [here](https://discord.gg/Zpd6RYYyuf)
diff --git a/environment.yml b/environment.yml
new file mode 100644
index 0000000..89ba9fe
--- /dev/null
+++ b/environment.yml
@@ -0,0 +1,7 @@
+name: spikeloc
+channels:
+  - conda-forge
+dependencies:
+  - python>=3.8
+  - matplotlib
+  - jupyter
diff --git a/notebooks/diagrams/arch-full.png b/notebooks/diagrams/arch-full.png
new file mode 100644
index 0000000..a219299
Binary files /dev/null and b/notebooks/diagrams/arch-full.png differ
diff --git a/notebooks/diagrams/arch-membrane.png b/notebooks/diagrams/arch-membrane.png
new file mode 100644
index 0000000..c32c7fb
Binary files /dev/null and b/notebooks/diagrams/arch-membrane.png differ
diff --git a/notebooks/diagrams/arch-stimuli.png b/notebooks/diagrams/arch-stimuli.png
new file mode 100644
index 0000000..a377141
Binary files /dev/null and b/notebooks/diagrams/arch-stimuli.png differ
diff --git a/notebooks/diagrams/auditory-pathways.png b/notebooks/diagrams/auditory-pathways.png
new file mode 100644
index 0000000..6228caa
Binary files /dev/null and b/notebooks/diagrams/auditory-pathways.png differ
diff --git a/notebooks/introduction.ipynb b/notebooks/introduction.ipynb
new file mode 100644
index 0000000..2974807
--- /dev/null
+++ b/notebooks/introduction.ipynb
@@ -0,0 +1,1001 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "8d00f7ec",
+   "metadata": {},
+   "source": [
+    "# Introduction\n",
+    "\n",
+    "This is an introduction to the [collaborative modelling of the brain (COMOB)](https://comob-project.github.io/) project on sound localization using spiking neural networks.\n",
+    "\n",
+    "At the bottom is the notebook for the [2022 Cosyne tutorial](https://neural-reckoning.github.io/cosyne-tutorial-2022/) that started this whole thing off."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "58455480",
+   "metadata": {},
+   "source": [
+    "# Modelling questions / aims\n",
+    "\n",
+    "Starting point:\n",
+    "\n",
+    "* What are the best strategies for localising sounds with a spiking neural network?\n",
+    "* Can we train networks end-to-end to perform as well or better than hand-crafted solutions?\n",
+    "* Technical challenge: can we train delays with surrogate gradient descent?\n",
+    "* Can we understand what these trained networks are doing in a high level way?\n",
+    "* Do these networks do something similar to what has been proposed in the literature (labelled line models, hemispheric models, pattern match decoders) or something completely different?\n",
+    "* Do different optimal models emerge in different parameter regimes (head size, signal to noise ratio, multiple sound sources)?\n",
+    "* How do the results depend on the neuron model and available dynamics? For example, does adaptation matter and in which conditions?"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fd992acb",
+   "metadata": {},
+   "source": [
+    "# Background\n",
+    "\n",
+    "This is a VERY brief intro to the auditory system and sound localisation.\n",
+    "\n",
+    "Depending on the direction that a sound arrives from, the signals at the left/right ears are different, and we can use this to infer the direction the sound is arriving from.\n",
+    "\n",
+    "**ITD.** There’s an arrival time difference because depending on the direction the sound is coming from it has further to travel to one ear than the other, in a way that depends on head size. This interaural time difference (ITD) is frequency-dependent (larger ITDs at lower frequencies). These time differences are on the order of up to around 700 microseconds for a typical human, although effective ITDs can be as large as 1ms at low frequencies.\n",
+    "\n",
+    "For narrow-band signals like a tone, ITD is ambiguous because - for example - for a sine wave you could add a delay of 1/f and you would have the same signal. What is always unambiguous is the interaural phase difference (IPD). The duplex theory says that because of this we use ITD only at low frequencies where the IPDs and ITDs can be unambiguously translated. However, you can resolve this ambiguity by combining information across multiple frequencies, or by looking at ITDs in the envelope rather than the carrier of the signal. This is all still somewhat debated.\n",
+    "\n",
+    "**ILD.** There’s a level difference due essentially to the sound having to pass through the head making it quieter at one ear than the other. I think off the top of my head these go to a maximum of around 10-20 dB. This is also level dependent, with larger ILDs at higher frequencies.\n",
+    "\n",
+    "**Monaural filtering.** It’s actually possible - if you know the sound source - to localise the sound with just one ear because the shape of the pinna (the fleshy flappy bit we call our ears) filters the sound differently depending on the direction. You can learn these direction-dependent filters.\n",
+    "\n",
+    "**HRTF.** We can summarise all these transformations with a linear filter, the head-related transfer function (HRTF). We can measure these in people and animals. The model in my 2010 paper (below) is basically that we can set up neural filters that can match the acoustic filters, and we can detect that they’re matching with coincidence detection. It would be fascinating to see if this emerges as a strategy with surrogate gradient descent!\n",
+    "\n",
+    "**Cochlear filtering.** When the sound arrives at the ear it gets bandpass filtered into different frequency bands. The centre frequencies of these bands and bandwidths are roughly log scale, so that at higher frequencies there is a larger gap between the centre frequencies, but the bandwidths are larger, meaning the overlap stays around the same. In humans we have around 3000 filters per ear covering the 20 Hz - 20 kHz range (older adults will typically have lost some of their high frequencies). In my work, I often model these with a gammatone filter, which is a simple linear filter that matches the auditory system fairly well. It definitely misses a lot of interesting nonlinear stuff (cross-frequency effects, dynamic gain control, etc.), and whether or not that is relevant for this project is unclear.\n",
+    "\n",
+    "**Inner hair cells** are connected to the cochlea and have a graded synapse to the auditory nerve fibres. They can be modelled simply as a ReLU followed by being raised to the power ⅓ (compression). The latter may not be relevant for this project.\n",
+    "\n",
+    "**Auditory nerve fibres** are the first spiking neuron in the auditory system. A reasonable model is that they fire Poisson spikes with a time varying firing rate given by the output of the inner hair cell model. They are also adaptive, and you can have one, two or more vesicle pools to model this adaptation. Various models of different complexity can be used. Probably a single vesicle pool model is good enough for this project. Some simple models covered in this paper.\n",
+    "\n",
+    "![Auditory pathways](diagrams/auditory-pathways.png)\n",
+    "\n",
+    "After the auditory nerve, signals go to the **cochlear nucleus** where there are various cell types and computations, some of which include onset sensitive cells and cells that sharpen spike timing. From there they travel to the **superior olive** where there are the first binaural neurons, including the lateral superior olive (**LSO**, believed to process ILDs, often modelled as excitation/inhibition) and the medial superior olive (**MSO**, believed to process ITDs, often modelled with coincidence detection). Finally they go through various further stages before getting to the auditory cortex. If you’re familiar with the visual system, there’s a lot more going on here before you get to cortex.\n",
+    "\n",
+    "You can compute **tuning curves** for binaural cells, e.g. ITD tuning curves. You can form a distribution of the best delays (peak of the ITD tuning curve) and best frequencies (peak of the frequency tuning curve) and plot these (see the decoding paper below). You can ask what is the optimal way to decode sound localisation given the set of outputs of these. This is the subject of the decoding paper below. However, none of these questions are settled.\n",
+    "\n",
+    "What are the key mechanisms underlying all of this? How do they depend on the acoustic environment? Etc. Many questions without fully satisfying answers."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5b5bdf4d",
+   "metadata": {},
+   "source": [
+    "# Literature\n",
+    "\n",
+    "This is a very limited sample, not a comprehensive review. I’d read these papers and follow some of their references as a starting point to get us all on the same page.\n",
+    "\n",
+    "* [Decoding neural responses to temporal cues for sound localisation (2013)](http://neural-reckoning.org/pub_decoding_soundloc.html). My paper comparing the Jeffress labelled line decoder, David McAlpine’s hemispheric decoder, and our proposed pattern match / perceptron decoder. Non-spiking. This paper is a good starting point because it points to a lot of the relevant literature.\n",
+    "* [Spike-timing-based computation in sound localisation (2010)](http://neural-reckoning.org/pub_spike_timing_sound_loc.html) and [Learning to localise sounds with spiking neural networks (2010)](http://neural-reckoning.org/pub_learning_localisation.html). Two of my early papers using SNNs to model sound localisation based on coincidence detection. The first one is a hand-crafted network and the second one is a very simple-minded extension to show that this could be learned.\n",
+    "* [Deep neural network models of sound localization reveal how perception is adapted to real-world environments (2022)](https://www.nature.com/articles/s41562-021-01244-z) (and [biorxiv link](https://www.biorxiv.org/content/10.1101/2020.07.21.214486v1)). Recent paper from Josh McDermott’s lab doing a non-spiking version of something like what I’m proposing here. The big missing thing that they don’t cover is trying to understand how the learned model works."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "5687cf49",
+   "metadata": {},
+   "source": [
+    "# Technical challenges\n",
+    "\n",
+    "* Delay learning. Can we do this?\n",
+    "* Alternatives to surrogate gradient descent?\n",
+    "* Add a more realistic auditory periphery (cochlear filtering and more realistic spiking model).\n",
+    "* Number of time steps might be an issue for a more realistic model. May want to use dt=0.1ms and duration>=100ms so more than 1000 time steps.\n",
+    "* Add a more realistic sound localisation task (natural sounds, background noise, multiple sound sources).\n",
+    "* Consider multiple architectures, potentially matching the auditory system.\n",
+    "* Consider more complicated neuron models and perhaps make some of these neuron model parameters trainable; for what situations can that help?\n",
+    "* How to understand what the learned network does?\n",
+    "* Use regression instead of classification"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "dfb23669",
+   "metadata": {},
+   "source": [
+    "# Cosyne tutorial 2022 notebook\n",
+    "\n",
+    "In this notebook, we're going to use surrogate gradient descent to find a solution to the sound localisation problem we solved by hand in the previous notebook. The surrogate gradient descent approach and code is heavily inspired by (certainly not stolen) from [Friedemann Zenke's SPyTorch tutorial](https://github.com/fzenke/spytorch), which I recommend for a deeper dive into the maths."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "ee3c91b7",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import os\n",
+    "\n",
+    "import numpy as np\n",
+    "import matplotlib.pyplot as plt\n",
+    "from matplotlib.gridspec import GridSpec\n",
+    "\n",
+    "import torch\n",
+    "import torch.nn as nn\n",
+    "\n",
+    "dtype = torch.float\n",
+    "\n",
+    "# Check whether a GPU is available\n",
+    "if torch.cuda.is_available():\n",
+    "    device = torch.device(\"cuda\")     \n",
+    "else:\n",
+    "    device = torch.device(\"cpu\")\n",
+    "    \n",
+    "my_computer_is_slow = True # set this to True if using Colab"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "345a4686",
+   "metadata": {},
+   "source": [
+    "## Sound localisation stimuli"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "bd312e52",
+   "metadata": {},
+   "source": [
+    "The following function creates a set of stimuli that can be used for training or testing. We have two ears (0 and 1), and ear 1 will get a version of the signal delayed by an IPD we can write as $\\alpha$ in equations (``ipd`` in code). The basic signal is a sine wave as in the previous notebook, made positive, so $(1/2)(1+\\sin(\\theta)$. In addition, for each ear there will be $N_a$ neurons per ear (``anf_per_ear`` because these are auditory nerve fibres). Each neuron generates Poisson spikes at a certain firing rate, and these Poisson spike trains are independent. In addition, since it is hard to train delays, we seed it with uniformly distributed delays from a minimum of 0 to a maximum of $\\pi/2$ in each ear, so that the differences between the two ears can cover the range of possible IPDs ($-\\pi/2$ to $\\pi/2$). We do this directly by adding a phase delay to each neuron. So for ear $i\\in\\{0,1\\}$ and neuron $j$ at time $t$ the angle $\\theta=2\\pi f t+i\\alpha+j\\pi/2N_a$. Finally, we generate Poisson spike trains with a rate $R_\\mathrm{max}((1/2)(1+\\sin(\\theta)))^k$. $R_\\mathrm{max}$ (``rate_max``) is the maximum instantaneous firing rate, and $k$ (``envelope_power``) is a constant that sharpens the envelope. The higher $R_\\mathrm{max}$ and $k$ the easier the problem (try it out on the cell below to see why).\n",
+    "\n",
+    "Here's a picture of the architecture for the stimuli:\n",
+    "\n",
+    "![Stimuli architecture](diagrams/arch-stimuli.png)\n",
+    "\n",
+    "The functions below return two arrays ``ipd`` and ``spikes``. ``ipd`` is an array of length ``num_samples`` that gives the true IPD, and ``spikes`` is an array of 0 (no spike) and 1 (spike) of shape ``(num_samples, duration_steps, 2*anf_per_ear)``, where ``duration_steps`` is the number of time steps there are in the stimulus."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "5bb26693",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1000x400 with 8 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Not using Brian so we just use these constants to make equations look nicer below\n",
+    "second = 1\n",
+    "ms = 1e-3\n",
+    "Hz = 1\n",
+    "\n",
+    "# Stimulus and simulation parameters\n",
+    "dt = 1*ms            # large time step to make simulations run faster for tutorial\n",
+    "anf_per_ear = 100    # repeats of each ear with independent noise\n",
+    "envelope_power = 2   # higher values make sharper envelopes, easier\n",
+    "rate_max = 600*Hz   # maximum Poisson firing rate\n",
+    "f = 20*Hz            # stimulus frequency\n",
+    "duration = .1*second # stimulus duration\n",
+    "duration_steps = int(np.round(duration/dt))\n",
+    "input_size = 2*anf_per_ear\n",
+    "\n",
+    "# Generate an input signal (spike array) from array of true IPDs\n",
+    "def input_signal(ipd):\n",
+    "    num_samples = len(ipd)\n",
+    "    T = np.arange(duration_steps)*dt # array of times\n",
+    "    phi = 2*np.pi*(f*T+np.random.rand()) # array of phases corresponding to those times with random offset\n",
+    "    # each point in the array will have a different phase based on which ear it is\n",
+    "    # and its delay\n",
+    "    theta = np.zeros((num_samples, duration_steps, 2*anf_per_ear))\n",
+    "    # for each ear, we have anf_per_ear different phase delays from to pi/2 so\n",
+    "    # that the differences between the two ears can cover the full range from -pi/2 to pi/2\n",
+    "    phase_delays = np.linspace(0, np.pi/2, anf_per_ear)\n",
+    "    # now we set up these theta to implement that. Some numpy vectorisation logic here which looks a little weird,\n",
+    "    # but implements the idea in the text above.\n",
+    "    theta[:, :, :anf_per_ear] = phi[np.newaxis, :, np.newaxis]+phase_delays[np.newaxis, np.newaxis, :]\n",
+    "    theta[:, :, anf_per_ear:] = phi[np.newaxis, :, np.newaxis]+phase_delays[np.newaxis, np.newaxis, :]+ipd[:, np.newaxis, np.newaxis]\n",
+    "    # now generate Poisson spikes at the given firing rate as in the previous notebook\n",
+    "    spikes = np.random.rand(num_samples, duration_steps, 2*anf_per_ear)<rate_max*dt*(0.5*(1+np.sin(theta)))**envelope_power\n",
+    "    return spikes\n",
+    "\n",
+    "# Generate some true IPDs from U(-pi/2, pi/2) and corresponding spike arrays\n",
+    "def random_ipd_input_signal(num_samples, tensor=True):\n",
+    "    ipd = np.random.rand(num_samples)*np.pi-np.pi/2 # uniformly random in (-pi/2, pi/2)\n",
+    "    spikes = input_signal(ipd)\n",
+    "    if tensor:\n",
+    "        ipd = torch.tensor(ipd, device=device, dtype=dtype)        \n",
+    "        spikes = torch.tensor(spikes, device=device, dtype=dtype)\n",
+    "    return ipd, spikes\n",
+    "\n",
+    "# Plot a few just to show how it looks\n",
+    "ipd, spikes = random_ipd_input_signal(8)\n",
+    "plt.figure(figsize=(10, 4), dpi=100)\n",
+    "for i in range(8):\n",
+    "    plt.subplot(2, 4, i+1)\n",
+    "    plt.imshow(spikes[i, :, :].T, aspect='auto', interpolation='nearest', cmap=plt.cm.gray_r)\n",
+    "    plt.title(f'True IPD = {int(ipd[i]*180/np.pi)} deg')\n",
+    "    if i>=4:\n",
+    "        plt.xlabel('Time (steps)')\n",
+    "    if i%4==0:\n",
+    "        plt.ylabel('Input neuron index')\n",
+    "plt.tight_layout()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "86605734",
+   "metadata": {},
+   "source": [
+    "Now the aim is to take these input spikes and infer the IPD. We can do this either by discretising and using a classification approach, or with a regression approach. For the moment, let's try it with a classification approach."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "177a735f",
+   "metadata": {},
+   "source": [
+    "## Classification approach\n",
+    "\n",
+    "We discretise the IPD range of $[-\\pi/2, \\pi/2]$ into $N_c$ (``num_classes``) equal width segments. Replace angle $\\phi$ with the integer part (floor) of $(\\phi+\\pi/2)N_c/\\pi$. We also convert the arrays into PyTorch tensors for later use. The algorithm will now guess the index $i$ of the segment, converting that to the midpoint of the segment $\\phi_i=a+(i+1/2)(b-a)/N_c$ when needed.\n",
+    "\n",
+    "The algorithm will work by outputting a length $N_c$ vector $y$ and the index of the maximum value of y will be the guess as to the class (1-hot encoding), i.e. $i_\\mathrm{est}=\\mathrm{argmax}_i y_i$. We will perform the training with a softmax and negative loss likelihood loss, which is a standard approach in machine learning."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "3f817078",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Number of classes = 12\n"
+     ]
+    }
+   ],
+   "source": [
+    "# classes at 15 degree increments\n",
+    "num_classes = 180//15\n",
+    "print(f'Number of classes = {num_classes}')\n",
+    "\n",
+    "def discretise(ipds):\n",
+    "    return ((ipds+np.pi/2)*num_classes/np.pi).long() # assumes input is tensor\n",
+    "\n",
+    "def continuise(ipd_indices): # convert indices back to IPD midpoints\n",
+    "    return (ipd_indices+0.5)/num_classes*np.pi-np.pi/2"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "2b857913",
+   "metadata": {},
+   "source": [
+    "## Membrane only (no spiking neurons)\n",
+    "\n",
+    "Before we get to spiking, we're going to warm up with a non-spiking network that shows some of the features of the full model but without any coincidence detection, it can't do the task. We basically create a neuron model that has everything except spiking, so the membrane potential dynamics are there and it takes spikes as input. The neuron model we'll use is just the LIF model we've already seen. We'll use a time constant $\\tau$ of 20 ms, and we pre-calculate a constant $\\alpha=\\exp(-dt/\\tau)$ so that updating the membrane potential $v$ is just multiplying by $\\alpha$ (as we saw in the first notebook). We store the input spikes in a vector $s$ of 0s and 1s for each time step, and multiply by the weight matrix $W$ to get the input, i.e. $v\\leftarrow \\alpha v+Ws$.\n",
+    "\n",
+    "We initialise the weight matrix $W$ uniformly with bounds proportionate to the inverse square root of the number of inputs (fairly standard, and works here).\n",
+    "\n",
+    "The output of this will be a vector of $N_c$ (``num_classes``) membrane potential traces. We sum these traces over time and use this as the output vector (the largest one will be our prediction of the class and therefore the IPD).\n",
+    "\n",
+    "![Membrane only architecture](diagrams/arch-membrane.png)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "7c7c60d9",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Weights and uniform weight initialisation\n",
+    "def init_weight_matrix():\n",
+    "    # Note that the requires_grad=True argument tells PyTorch that we'll be computing gradients with\n",
+    "    # respect to the values in this tensor and thereby learning those values. If you want PyTorch to\n",
+    "    # learn some gradients, make sure it has this on.\n",
+    "    W = nn.Parameter(torch.empty((input_size, num_classes), device=device, dtype=dtype, requires_grad=True))\n",
+    "    fan_in, _ = nn.init._calculate_fan_in_and_fan_out(W)\n",
+    "    bound = 1 / np.sqrt(fan_in)\n",
+    "    nn.init.uniform_(W, -bound, bound)\n",
+    "    return W\n",
+    "\n",
+    "# Run the simulation\n",
+    "def membrane_only(input_spikes, W, tau=20*ms):\n",
+    "    # Input has shape (batch_size, duration_steps, input_size)\n",
+    "    v = torch.zeros((batch_size, num_classes), device=device, dtype=dtype)\n",
+    "    # v_rec will store the membrane in each time step\n",
+    "    v_rec = [v]\n",
+    "    # Batch matrix multiplication all time steps\n",
+    "    # Equivalent to matrix multiply input_spikes[b, :, :] x W for all b, but faster\n",
+    "    h = torch.einsum(\"abc,cd->abd\", (input_spikes, W))\n",
+    "    # precalculate multiplication factor\n",
+    "    alpha = np.exp(-dt/tau)\n",
+    "    # Update membrane and spikes one time step at a time\n",
+    "    for t in range(duration_steps - 1):\n",
+    "        v = alpha*v + h[:, t, :]\n",
+    "        v_rec.append(v)\n",
+    "    # return the recorded membrane potentials stacked into a single tensor\n",
+    "    v_rec = torch.stack(v_rec, dim=1)  # (batch_size, duration_steps, num_classes)\n",
+    "    return v_rec"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "20840c40",
+   "metadata": {},
+   "source": [
+    "### Training\n",
+    "\n",
+    "We train this by dividing the input data into batches and computing gradients across batches. In this notebook, batch and data size is small so that it can be run on a laptop in a couple of minutes, but normally you'd use larger batches and more data. Let's start with the data."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "fc5fdc4f",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Parameters for training. These aren't optimal, but instead designed\n",
+    "# to give a reasonable result in a small amount of time for the tutorial!\n",
+    "if my_computer_is_slow:\n",
+    "    batch_size = 64\n",
+    "    n_training_batches = 64\n",
+    "else:\n",
+    "    batch_size = 128\n",
+    "    n_training_batches = 128\n",
+    "n_testing_batches = 32\n",
+    "num_samples = batch_size*n_training_batches\n",
+    "\n",
+    "# Generator function iterates over the data in batches\n",
+    "# We randomly permute the order of the data to improve learning\n",
+    "def data_generator(ipds, spikes):\n",
+    "    perm = torch.randperm(spikes.shape[0])\n",
+    "    spikes = spikes[perm, :, :]\n",
+    "    ipds = ipds[perm]\n",
+    "    n, _, _ = spikes.shape\n",
+    "    n_batch = n//batch_size\n",
+    "    for i in range(n_batch):\n",
+    "        x_local = spikes[i*batch_size:(i+1)*batch_size, :, :]\n",
+    "        y_local = ipds[i*batch_size:(i+1)*batch_size]\n",
+    "        yield x_local, y_local"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "6d0c463c",
+   "metadata": {},
+   "source": [
+    "Now we run the training. We generate the training data, initialise the weight matrix, set the training parameters, and run for a few epochs, printing the training loss as we go. We use the all-powerful Adam optimiser, softmax and negative log likelihood loss."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "7fb79463",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Want loss for epoch 1 to be about 2.48, multiply m by constant to get this\n",
+      "Epoch 1: loss=5.04371\n",
+      "Epoch 2: loss=3.02612\n",
+      "Epoch 3: loss=2.70813\n",
+      "Epoch 4: loss=2.50026\n",
+      "Epoch 5: loss=2.30678\n",
+      "Epoch 6: loss=2.26582\n",
+      "Epoch 7: loss=2.13161\n",
+      "Epoch 8: loss=1.99974\n",
+      "Epoch 9: loss=1.96945\n",
+      "Epoch 10: loss=1.86101\n"
+     ]
+    },
+    {
+     "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": [
+    "# Training parameters\n",
+    "nb_epochs = 10 # quick, it won't have converged\n",
+    "lr = 0.01 # learning rate\n",
+    "\n",
+    "# Generate the training data\n",
+    "ipds, spikes = random_ipd_input_signal(num_samples)\n",
+    "\n",
+    "# Initialise a weight matrix\n",
+    "W = init_weight_matrix()\n",
+    "\n",
+    "# Optimiser and loss function\n",
+    "optimizer = torch.optim.Adam([W], lr=lr)\n",
+    "log_softmax_fn = nn.LogSoftmax(dim=1)\n",
+    "loss_fn = nn.NLLLoss() # negative log likelihood loss\n",
+    "\n",
+    "print(f\"Want loss for epoch 1 to be about {-np.log(1/num_classes):.2f}, multiply m by constant to get this\")\n",
+    "\n",
+    "loss_hist = []\n",
+    "for e in range(nb_epochs):\n",
+    "    local_loss = []\n",
+    "    for x_local, y_local in data_generator(discretise(ipds), spikes):\n",
+    "        # Run network\n",
+    "        output = membrane_only(x_local, W)\n",
+    "        # Compute cross entropy loss\n",
+    "        m = torch.sum(output, 1)*0.01  # Sum time dimension\n",
+    "        loss = loss_fn(log_softmax_fn(m), y_local)\n",
+    "        local_loss.append(loss.item())\n",
+    "        # Update gradients\n",
+    "        optimizer.zero_grad()\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "\n",
+    "    loss_hist.append(np.mean(local_loss))\n",
+    "    print(\"Epoch %i: loss=%.5f\"%(e+1, np.mean(local_loss)))\n",
+    "\n",
+    "# Plot the loss function over time\n",
+    "plt.plot(loss_hist)\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.tight_layout()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "8b4fce85",
+   "metadata": {},
+   "source": [
+    "### Analysis of results\n",
+    "\n",
+    "Now we compute the training and test accuracy, and plot histograms and confusion matrices to understand the errors it's making."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "9cc91c87",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Chance accuracy level: 8.3%\n",
+      "\n",
+      "Train classifier accuracy: 33.8%\n",
+      "Train absolute error: 17.7 deg\n",
+      "\n",
+      "Test classifier accuracy: 7.6%\n",
+      "Test absolute error: 54.0 deg\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1000x400 with 2 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1000x400 with 2 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "def analyse(ipds, spikes, label, run):\n",
+    "    accs = []\n",
+    "    ipd_true = []\n",
+    "    ipd_est = []\n",
+    "    confusion = np.zeros((num_classes, num_classes))\n",
+    "    for x_local, y_local in data_generator(ipds, spikes):\n",
+    "        y_local_orig = y_local\n",
+    "        y_local = discretise(y_local)\n",
+    "        output = run(x_local)\n",
+    "        m = torch.sum(output, 1)  # Sum time dimension\n",
+    "        _, am = torch.max(m, 1)  # argmax over output units\n",
+    "        tmp = np.mean((y_local == am).detach().cpu().numpy())  # compare to labels\n",
+    "        for i, j in zip(y_local.detach().cpu().numpy(), am.detach().cpu().numpy()):\n",
+    "            confusion[j, i] += 1\n",
+    "        ipd_true.append(y_local_orig)\n",
+    "        ipd_est.append(continuise(am.detach().cpu().numpy()))\n",
+    "        accs.append(tmp)\n",
+    "    ipd_true = np.hstack(ipd_true)\n",
+    "    ipd_est = np.hstack(ipd_est)\n",
+    "    abs_errors_deg = abs(ipd_true-ipd_est)*180/np.pi\n",
+    "    print()\n",
+    "    print(f\"{label} classifier accuracy: {100*np.mean(accs):.1f}%\")\n",
+    "    print(f\"{label} absolute error: {np.mean(abs_errors_deg):.1f} deg\")\n",
+    "\n",
+    "    plt.figure(figsize=(10, 4), dpi=100)\n",
+    "    plt.subplot(121)\n",
+    "    plt.hist(ipd_true*180/np.pi, bins=num_classes, label='True')\n",
+    "    plt.hist(ipd_est*180/np.pi, bins=num_classes, label='Estimated')\n",
+    "    plt.xlabel(\"IPD\")\n",
+    "    plt.yticks([])\n",
+    "    plt.legend(loc='best')\n",
+    "    plt.title(label)\n",
+    "    plt.subplot(122)\n",
+    "    confusion /= np.sum(confusion, axis=0)[np.newaxis, :]\n",
+    "    plt.imshow(confusion, interpolation='nearest', aspect='auto', origin='lower', extent=(-90, 90, -90, 90))\n",
+    "    plt.xlabel('True IPD')\n",
+    "    plt.ylabel('Estimated IPD')\n",
+    "    plt.title('Confusion matrix')\n",
+    "    plt.tight_layout()    \n",
+    "\n",
+    "print(f\"Chance accuracy level: {100*1/num_classes:.1f}%\")\n",
+    "run_func = lambda x: membrane_only(x, W)\n",
+    "analyse(ipds, spikes, 'Train', run=run_func)\n",
+    "ipds_test, spikes_test = random_ipd_input_signal(batch_size*n_testing_batches)\n",
+    "analyse(ipds_test, spikes_test, 'Test', run=run_func)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "729b0bbf",
+   "metadata": {},
+   "source": [
+    "This poor performance isn't surprising because this network is not actually doing any coincidence detection, just a weighted sum of input spikes."
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "3bb91016",
+   "metadata": {},
+   "source": [
+    "## Spiking model\n",
+    "\n",
+    "Next we'll implement a version of the model with spikes to see how that changes performance. We'll just add a single hidden feed-forward layer of spiking neurons between the input and the output layers. This layer will be spiking, so we need to use the surrogate gradient descent approach.\n",
+    "\n",
+    "![Full architecture](diagrams/arch-full.png)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "03f5456e",
+   "metadata": {},
+   "source": [
+    "### Surrogate gradient descent\n",
+    "\n",
+    "First, this is the key part of surrogate gradient descent, a function where we override the computation of the gradient to replace it with a smoothed gradient. You can see that in the forward pass (method ``forward``) it returns the Heaviside function of the input (takes value 1 if the input is ``>0``) or value 0 otherwise. In the backwards pass, it returns the gradient of a sigmoid function."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "e5fabc7b",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "beta = 5\n",
+    "\n",
+    "class SurrGradSpike(torch.autograd.Function):\n",
+    "    @staticmethod\n",
+    "    def forward(ctx, input):\n",
+    "        ctx.save_for_backward(input)\n",
+    "        out = torch.zeros_like(input)\n",
+    "        out[input > 0] = 1.0\n",
+    "        return out\n",
+    "    @staticmethod\n",
+    "    def backward(ctx, grad_output):\n",
+    "        input, = ctx.saved_tensors\n",
+    "        # Original SPyTorch/SuperSpike gradient\n",
+    "        # This seems to be a typo or error? But it works well\n",
+    "        #grad = grad_output/(100*torch.abs(input)+1.0)**2\n",
+    "        # Sigmoid\n",
+    "        grad = grad_output*beta*torch.sigmoid(beta*input)*(1-torch.sigmoid(beta*input))\n",
+    "        return grad\n",
+    "\n",
+    "spike_fn  = SurrGradSpike.apply"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "911318ee",
+   "metadata": {},
+   "source": [
+    "### Updated model\n",
+    "\n",
+    "The code for the updated model is very similar to the membrane only layer. First, for initialisation we now need two weight matrices, $W_1$ from the input to the hidden layer, and $W_2$ from the hidden layer to the output layer. Second, we run two passes of the loop that you saw above for the membrane only model.\n",
+    "\n",
+    "The first pass computes the output spikes of the hidden layer. The second pass computes the output layer and is exactly the same as before except using the spikes from the hidden layer instead of the input layer.\n",
+    "\n",
+    "For the first pass, we modify the function in two ways.\n",
+    "\n",
+    "Firstly, we compute the spikes with the line ``s = spike_fn(v-1)``. In the forward pass this just computes the Heaviside function of $v-1$, i.e. returns 1 if $v>1$, otherwise 0, which is the spike threshold function for the LIF neuron. In the backwards pass, it returns a gradient of the smoothed version of the Heaviside function.\n",
+    "\n",
+    "The other line we change is the membrane potential update line. Now, we multiply by $1-s$ where ($s=1$ if there was a spike in the previous time step, otherwise $s=0$), so that the membrane potential is reset to 0 after a spike (but in a differentiable way rather than just setting it to 0)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "7b072bb5",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "num_hidden = 30\n",
+    "\n",
+    "# Weights and uniform weight initialisation\n",
+    "def init_weight_matrices():\n",
+    "    # Input to hidden layer\n",
+    "    W1 = nn.Parameter(torch.empty((input_size, num_hidden), device=device, dtype=dtype, requires_grad=True))\n",
+    "    fan_in, _ = nn.init._calculate_fan_in_and_fan_out(W)\n",
+    "    bound = 1 / np.sqrt(fan_in)\n",
+    "    nn.init.uniform_(W1, -bound, bound)\n",
+    "    # Hidden layer to output\n",
+    "    W2 = nn.Parameter(torch.empty((num_hidden, num_classes), device=device, dtype=dtype, requires_grad=True))\n",
+    "    fan_in, _ = nn.init._calculate_fan_in_and_fan_out(W)\n",
+    "    bound = 1 / np.sqrt(fan_in)\n",
+    "    nn.init.uniform_(W2, -bound, bound)\n",
+    "    return W1, W2\n",
+    "\n",
+    "# Run the simulation\n",
+    "def snn(input_spikes, W1, W2, tau=20*ms):\n",
+    "    # First layer: input to hidden\n",
+    "    v = torch.zeros((batch_size, num_hidden), device=device, dtype=dtype)\n",
+    "    s = torch.zeros((batch_size, num_hidden), device=device, dtype=dtype)\n",
+    "    s_rec = [s]\n",
+    "    h = torch.einsum(\"abc,cd->abd\", (input_spikes, W1))\n",
+    "    alpha = np.exp(-dt/tau)\n",
+    "    for t in range(duration_steps - 1):\n",
+    "        new_v = (alpha*v + h[:, t, :])*(1-s) # multiply by 0 after a spike\n",
+    "        s = spike_fn(v-1) # threshold of 1\n",
+    "        v = new_v\n",
+    "        s_rec.append(s)\n",
+    "    s_rec = torch.stack(s_rec, dim=1)\n",
+    "    # Second layer: hidden to output\n",
+    "    v = torch.zeros((batch_size, num_classes), device=device, dtype=dtype)\n",
+    "    s = torch.zeros((batch_size, num_classes), device=device, dtype=dtype)\n",
+    "    v_rec = [v]\n",
+    "    h = torch.einsum(\"abc,cd->abd\", (s_rec, W2))\n",
+    "    alpha = np.exp(-dt/tau)\n",
+    "    for t in range(duration_steps - 1):\n",
+    "        v = alpha*v + h[:, t, :]\n",
+    "        v_rec.append(v)\n",
+    "    v_rec = torch.stack(v_rec, dim=1)\n",
+    "    # Return recorded membrane potential of output\n",
+    "    return v_rec"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "0a1662e0",
+   "metadata": {},
+   "source": [
+    "### Training and analysing\n",
+    "\n",
+    "We train it as before, except that we modify the functions to take the two weight matrices into account."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "a5d558df",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Want loss for epoch 1 to be about 2.48, multiply m by constant to get this\n",
+      "Epoch 1: loss=2.12117\n",
+      "Epoch 2: loss=1.27166\n",
+      "Epoch 3: loss=0.97130\n",
+      "Epoch 4: loss=0.85132\n",
+      "Epoch 5: loss=0.73458\n",
+      "Epoch 6: loss=0.67741\n",
+      "Epoch 7: loss=0.60464\n",
+      "Epoch 8: loss=0.56484\n",
+      "Epoch 9: loss=0.55740\n",
+      "Epoch 10: loss=0.50806\n"
+     ]
+    },
+    {
+     "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": [
+    "# Training parameters\n",
+    "nb_epochs = 10 # quick, it won't have converged\n",
+    "lr = 0.01 # learning rate\n",
+    "\n",
+    "# Generate the training data\n",
+    "ipds, spikes = random_ipd_input_signal(num_samples)\n",
+    "\n",
+    "# Initialise a weight matrices\n",
+    "W1, W2 = init_weight_matrices()\n",
+    "\n",
+    "# Optimiser and loss function\n",
+    "optimizer = torch.optim.Adam([W1, W2], lr=lr)\n",
+    "log_softmax_fn = nn.LogSoftmax(dim=1)\n",
+    "loss_fn = nn.NLLLoss()\n",
+    "\n",
+    "print(f\"Want loss for epoch 1 to be about {-np.log(1/num_classes):.2f}, multiply m by constant to get this\")\n",
+    "\n",
+    "loss_hist = []\n",
+    "for e in range(nb_epochs):\n",
+    "    local_loss = []\n",
+    "    for x_local, y_local in data_generator(discretise(ipds), spikes):\n",
+    "        # Run network\n",
+    "        output = snn(x_local, W1, W2)\n",
+    "        # Compute cross entropy loss\n",
+    "        m = torch.mean(output, 1)  # Mean across time dimension\n",
+    "        loss = loss_fn(log_softmax_fn(m), y_local)\n",
+    "        local_loss.append(loss.item())\n",
+    "        # Update gradients\n",
+    "        optimizer.zero_grad()\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "\n",
+    "    loss_hist.append(np.mean(local_loss))\n",
+    "    print(\"Epoch %i: loss=%.5f\"%(e+1, np.mean(local_loss)))\n",
+    "\n",
+    "# Plot the loss function over time\n",
+    "plt.plot(loss_hist)\n",
+    "plt.xlabel('Epoch')\n",
+    "plt.ylabel('Loss')\n",
+    "plt.tight_layout()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "fde52021",
+   "metadata": {},
+   "source": [
+    "You might already see that the loss functions are lower than before, so maybe performance is better? Let's see."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "7f8a92ad",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Chance accuracy level: 8.3%\n",
+      "\n",
+      "Train classifier accuracy: 81.1%\n",
+      "Train absolute error: 4.9 deg\n",
+      "\n",
+      "Test classifier accuracy: 61.5%\n",
+      "Test absolute error: 8.2 deg\n"
+     ]
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1000x400 with 2 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1000x400 with 2 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "# Analyse\n",
+    "print(f\"Chance accuracy level: {100*1/num_classes:.1f}%\")\n",
+    "run_func = lambda x: snn(x, W1, W2)\n",
+    "analyse(ipds, spikes, 'Train', run=run_func)\n",
+    "ipds_test, spikes_test = random_ipd_input_signal(batch_size*n_testing_batches)\n",
+    "analyse(ipds_test, spikes_test, 'Test', run=run_func)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "26e19d66",
+   "metadata": {},
+   "source": [
+    "Yes! Performance is much better and now the confusion matrices look more like what you'd expect too. Let's take a look at the weight matrices."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "416c6383",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1000x400 with 4 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.figure(figsize=(10, 4), dpi=100)\n",
+    "plt.subplot(121)\n",
+    "plt.imshow(W1.detach().cpu().numpy(), interpolation='nearest', aspect='auto', origin='lower')\n",
+    "plt.ylabel('Input neuron index')\n",
+    "plt.xlabel('Hidden layer neuron index')\n",
+    "plt.colorbar(label=\"Weight\")\n",
+    "plt.subplot(122)\n",
+    "plt.imshow(W2.detach().cpu().numpy(), interpolation='nearest', aspect='auto', origin='lower')\n",
+    "plt.ylabel('Hidden layer neuron index')\n",
+    "plt.xlabel('Output neuron index')\n",
+    "plt.colorbar(label=\"Weight\")\n",
+    "plt.tight_layout()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "d5d19904",
+   "metadata": {},
+   "source": [
+    "Hmm, hard to interpret.\n",
+    "\n",
+    "**Exercise.** Any ideas?\n",
+    "\n",
+    "Here's what I've got so far..."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "cd305405",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1000x300 with 6 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 800x400 with 15 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "w1 = W1.detach().cpu().numpy()\n",
+    "w2 = W2.detach().cpu().numpy()\n",
+    "\n",
+    "# for each column of w1, compute the weighted mean and re-order according to that\n",
+    "A = np.arange(w1.shape[0])[:, None]\n",
+    "weighted_mean = np.mean((A*w1), axis=0)\n",
+    "weighted_mean[np.max(np.abs(w1), axis=0)<.5] = np.inf\n",
+    "I = np.argsort(weighted_mean)\n",
+    "w1 = w1[:, I]\n",
+    "w2 = w2[I, :]\n",
+    "\n",
+    "# Plot the re-ordered weight matrices\n",
+    "plt.figure(figsize=(10, 3), dpi=100)\n",
+    "plt.subplot(131)\n",
+    "plt.imshow(w1, interpolation='nearest', aspect='auto', origin='lower')\n",
+    "plt.ylabel('Input neuron index')\n",
+    "plt.xlabel('Hidden layer neuron index')\n",
+    "plt.title('$W_1$')\n",
+    "plt.colorbar()\n",
+    "plt.subplot(132)\n",
+    "plt.imshow(w2, interpolation='nearest', aspect='auto', origin='lower')\n",
+    "plt.ylabel('Hidden layer neuron index')\n",
+    "plt.xlabel('Output neuron index')\n",
+    "plt.title('$W_2$')\n",
+    "plt.colorbar()\n",
+    "plt.subplot(133)\n",
+    "plt.imshow(w1@w2, interpolation='nearest', aspect='auto', origin='lower')\n",
+    "plt.ylabel('Input neuron index')\n",
+    "plt.xlabel('Output neuron index')\n",
+    "plt.title('$W_1W_2$')\n",
+    "plt.colorbar()\n",
+    "plt.tight_layout()\n",
+    "\n",
+    "# Plot some sample weights for hidden neurons\n",
+    "I_nz, = (np.max(np.abs(w1), axis=0)>.5).nonzero()\n",
+    "plt.figure(figsize=(10, 5), dpi=80)\n",
+    "phi = np.linspace(-np.pi/2, np.pi/2, w1.shape[0]//2)\n",
+    "for i, j in list(enumerate(I_nz))[:15]:\n",
+    "    plt.subplot(3, 5, i+1)\n",
+    "    plt.plot(phi*180/np.pi, w1[:w1.shape[0]//2, j], label=\"Left ear\")\n",
+    "    plt.plot(phi*180/np.pi, w1[w1.shape[0]//2:, j], label=\"Right ear\")\n",
+    "plt.suptitle(\"Individual $W_1$ weights\")\n",
+    "plt.legend(loc='best')\n",
+    "plt.xlabel('Phase delay (deg)')\n",
+    "plt.tight_layout()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "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": "3.9.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}
diff --git a/poetry.lock b/poetry.lock
new file mode 100644
index 0000000..4cebae8
--- /dev/null
+++ b/poetry.lock
@@ -0,0 +1,1683 @@
+[[package]]
+name = "appnope"
+version = "0.1.2"
+description = "Disable App Nap on macOS >= 10.9"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "argon2-cffi"
+version = "21.3.0"
+description = "The secure Argon2 password hashing algorithm."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+argon2-cffi-bindings = "*"
+
+[package.extras]
+dev = ["pre-commit", "cogapp", "tomli", "coverage[toml] (>=5.0.2)", "hypothesis", "pytest", "sphinx", "sphinx-notfound-page", "furo"]
+docs = ["sphinx", "sphinx-notfound-page", "furo"]
+tests = ["coverage[toml] (>=5.0.2)", "hypothesis", "pytest"]
+
+[[package]]
+name = "argon2-cffi-bindings"
+version = "21.2.0"
+description = "Low-level CFFI bindings for Argon2"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+cffi = ">=1.0.1"
+
+[package.extras]
+dev = ["pytest", "cogapp", "pre-commit", "wheel"]
+tests = ["pytest"]
+
+[[package]]
+name = "asttokens"
+version = "2.0.5"
+description = "Annotate AST trees with source code positions"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+six = "*"
+
+[package.extras]
+test = ["astroid", "pytest"]
+
+[[package]]
+name = "attrs"
+version = "21.4.0"
+description = "Classes Without Boilerplate"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+
+[package.extras]
+dev = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "zope.interface", "furo", "sphinx", "sphinx-notfound-page", "pre-commit", "cloudpickle"]
+docs = ["furo", "sphinx", "zope.interface", "sphinx-notfound-page"]
+tests = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "zope.interface", "cloudpickle"]
+tests_no_zope = ["coverage[toml] (>=5.0.2)", "hypothesis", "pympler", "pytest (>=4.3.0)", "six", "mypy", "pytest-mypy-plugins", "cloudpickle"]
+
+[[package]]
+name = "backcall"
+version = "0.2.0"
+description = "Specifications for callback functions passed in to an API"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "beautifulsoup4"
+version = "4.10.0"
+description = "Screen-scraping library"
+category = "main"
+optional = false
+python-versions = ">3.0.0"
+
+[package.dependencies]
+soupsieve = ">1.2"
+
+[package.extras]
+html5lib = ["html5lib"]
+lxml = ["lxml"]
+
+[[package]]
+name = "bleach"
+version = "4.1.0"
+description = "An easy safelist-based HTML-sanitizing tool."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+packaging = "*"
+six = ">=1.9.0"
+webencodings = "*"
+
+[[package]]
+name = "cffi"
+version = "1.15.0"
+description = "Foreign Function Interface for Python calling C code."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+pycparser = "*"
+
+[[package]]
+name = "colorama"
+version = "0.4.4"
+description = "Cross-platform colored terminal text."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+
+[[package]]
+name = "cycler"
+version = "0.11.0"
+description = "Composable style cycles"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "debugpy"
+version = "1.6.0"
+description = "An implementation of the Debug Adapter Protocol for Python"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "decorator"
+version = "5.1.1"
+description = "Decorators for Humans"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+
+[[package]]
+name = "defusedxml"
+version = "0.7.1"
+description = "XML bomb protection for Python stdlib modules"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+
+[[package]]
+name = "entrypoints"
+version = "0.4"
+description = "Discover and load entry points from installed packages."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "executing"
+version = "0.8.3"
+description = "Get the currently executing AST node of a frame, and other information"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "fonttools"
+version = "4.31.2"
+description = "Tools to manipulate font files"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+all = ["fs (>=2.2.0,<3)", "lxml (>=4.0,<5)", "zopfli (>=0.1.4)", "lz4 (>=1.7.4.2)", "matplotlib", "sympy", "skia-pathops (>=0.5.0)", "brotlicffi (>=0.8.0)", "scipy", "brotli (>=1.0.1)", "munkres", "unicodedata2 (>=14.0.0)", "xattr"]
+graphite = ["lz4 (>=1.7.4.2)"]
+interpolatable = ["scipy", "munkres"]
+lxml = ["lxml (>=4.0,<5)"]
+pathops = ["skia-pathops (>=0.5.0)"]
+plot = ["matplotlib"]
+symfont = ["sympy"]
+type1 = ["xattr"]
+ufo = ["fs (>=2.2.0,<3)"]
+unicode = ["unicodedata2 (>=14.0.0)"]
+woff = ["zopfli (>=0.1.4)", "brotlicffi (>=0.8.0)", "brotli (>=1.0.1)"]
+
+[[package]]
+name = "importlib-resources"
+version = "5.6.0"
+description = "Read resources from Python packages"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+zipp = {version = ">=3.1.0", markers = "python_version < \"3.10\""}
+
+[package.extras]
+docs = ["sphinx", "jaraco.packaging (>=9)", "rst.linker (>=1.9)"]
+testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-cov", "pytest-enabler (>=1.0.1)", "pytest-black (>=0.3.7)", "pytest-mypy (>=0.9.1)"]
+
+[[package]]
+name = "ipykernel"
+version = "6.11.0"
+description = "IPython Kernel for Jupyter"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+appnope = {version = "*", markers = "platform_system == \"Darwin\""}
+debugpy = ">=1.0"
+ipython = ">=7.23.1"
+jupyter-client = ">=6.1.12"
+matplotlib-inline = ">=0.1"
+nest-asyncio = "*"
+psutil = "*"
+tornado = ">=6.1"
+traitlets = ">=5.1.0"
+
+[package.extras]
+test = ["pytest (>=6.0)", "pytest-cov", "flaky", "ipyparallel", "pre-commit", "pytest-timeout"]
+
+[[package]]
+name = "ipython"
+version = "8.2.0"
+description = "IPython: Productive Interactive Computing"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+appnope = {version = "*", markers = "sys_platform == \"darwin\""}
+backcall = "*"
+colorama = {version = "*", markers = "sys_platform == \"win32\""}
+decorator = "*"
+jedi = ">=0.16"
+matplotlib-inline = "*"
+pexpect = {version = ">4.3", markers = "sys_platform != \"win32\""}
+pickleshare = "*"
+prompt-toolkit = ">=2.0.0,<3.0.0 || >3.0.0,<3.0.1 || >3.0.1,<3.1.0"
+pygments = ">=2.4.0"
+stack-data = "*"
+traitlets = ">=5"
+
+[package.extras]
+all = ["black", "Sphinx (>=1.3)", "ipykernel", "nbconvert", "nbformat", "ipywidgets", "notebook", "ipyparallel", "qtconsole", "pytest (<7.1)", "pytest-asyncio", "testpath", "curio", "matplotlib (!=3.2.0)", "numpy (>=1.19)", "pandas", "trio"]
+black = ["black"]
+doc = ["Sphinx (>=1.3)"]
+kernel = ["ipykernel"]
+nbconvert = ["nbconvert"]
+nbformat = ["nbformat"]
+notebook = ["ipywidgets", "notebook"]
+parallel = ["ipyparallel"]
+qtconsole = ["qtconsole"]
+test = ["pytest (<7.1)", "pytest-asyncio", "testpath"]
+test_extra = ["pytest (<7.1)", "pytest-asyncio", "testpath", "curio", "matplotlib (!=3.2.0)", "nbformat", "numpy (>=1.19)", "pandas", "trio"]
+
+[[package]]
+name = "ipython-genutils"
+version = "0.2.0"
+description = "Vestigial utilities from IPython"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "ipywidgets"
+version = "7.7.0"
+description = "IPython HTML widgets for Jupyter"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+ipykernel = ">=4.5.1"
+ipython = {version = ">=4.0.0", markers = "python_version >= \"3.3\""}
+ipython-genutils = ">=0.2.0,<0.3.0"
+jupyterlab-widgets = {version = ">=1.0.0", markers = "python_version >= \"3.6\""}
+nbformat = ">=4.2.0"
+traitlets = ">=4.3.1"
+widgetsnbextension = ">=3.6.0,<3.7.0"
+
+[package.extras]
+test = ["pytest (>=3.6.0)", "pytest-cov", "mock"]
+
+[[package]]
+name = "jedi"
+version = "0.18.1"
+description = "An autocompletion tool for Python that can be used for text editors."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+parso = ">=0.8.0,<0.9.0"
+
+[package.extras]
+qa = ["flake8 (==3.8.3)", "mypy (==0.782)"]
+testing = ["Django (<3.1)", "colorama", "docopt", "pytest (<7.0.0)"]
+
+[[package]]
+name = "jinja2"
+version = "3.1.1"
+description = "A very fast and expressive template engine."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+MarkupSafe = ">=2.0"
+
+[package.extras]
+i18n = ["Babel (>=2.7)"]
+
+[[package]]
+name = "jsonschema"
+version = "4.4.0"
+description = "An implementation of JSON Schema validation for Python"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+attrs = ">=17.4.0"
+importlib-resources = {version = ">=1.4.0", markers = "python_version < \"3.9\""}
+pyrsistent = ">=0.14.0,<0.17.0 || >0.17.0,<0.17.1 || >0.17.1,<0.17.2 || >0.17.2"
+
+[package.extras]
+format = ["fqdn", "idna", "isoduration", "jsonpointer (>1.13)", "rfc3339-validator", "rfc3987", "uri-template", "webcolors (>=1.11)"]
+format_nongpl = ["fqdn", "idna", "isoduration", "jsonpointer (>1.13)", "rfc3339-validator", "rfc3986-validator (>0.1.0)", "uri-template", "webcolors (>=1.11)"]
+
+[[package]]
+name = "jupyter"
+version = "1.0.0"
+description = "Jupyter metapackage. Install all the Jupyter components in one go."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+ipykernel = "*"
+ipywidgets = "*"
+jupyter-console = "*"
+nbconvert = "*"
+notebook = "*"
+qtconsole = "*"
+
+[[package]]
+name = "jupyter-client"
+version = "7.2.1"
+description = "Jupyter protocol implementation and client libraries"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+entrypoints = "*"
+jupyter-core = ">=4.9.2"
+nest-asyncio = ">=1.5.4"
+python-dateutil = ">=2.8.2"
+pyzmq = ">=22.3"
+tornado = ">=6.0"
+traitlets = "*"
+
+[package.extras]
+doc = ["ipykernel", "myst-parser", "sphinx (>=1.3.6)", "sphinx-rtd-theme", "sphinxcontrib-github-alt"]
+test = ["codecov", "coverage", "ipykernel (>=6.5)", "ipython", "mypy", "pre-commit", "pytest", "pytest-asyncio (>=0.18)", "pytest-cov", "pytest-timeout"]
+
+[[package]]
+name = "jupyter-console"
+version = "6.4.3"
+description = "Jupyter terminal console"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+ipykernel = "*"
+ipython = "*"
+jupyter-client = ">=7.0.0"
+prompt-toolkit = ">=2.0.0,<3.0.0 || >3.0.0,<3.0.1 || >3.0.1,<3.1.0"
+pygments = "*"
+
+[package.extras]
+test = ["pexpect"]
+
+[[package]]
+name = "jupyter-core"
+version = "4.9.2"
+description = "Jupyter core package. A base package on which Jupyter projects rely."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+pywin32 = {version = ">=1.0", markers = "sys_platform == \"win32\" and platform_python_implementation != \"PyPy\""}
+traitlets = "*"
+
+[[package]]
+name = "jupyterlab-pygments"
+version = "0.1.2"
+description = "Pygments theme using JupyterLab CSS variables"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+pygments = ">=2.4.1,<3"
+
+[[package]]
+name = "jupyterlab-widgets"
+version = "1.1.0"
+description = "A JupyterLab extension."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "kiwisolver"
+version = "1.4.2"
+description = "A fast implementation of the Cassowary constraint solver"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "markupsafe"
+version = "2.1.1"
+description = "Safely add untrusted strings to HTML/XML markup."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "matplotlib"
+version = "3.5.1"
+description = "Python plotting package"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+cycler = ">=0.10"
+fonttools = ">=4.22.0"
+kiwisolver = ">=1.0.1"
+numpy = ">=1.17"
+packaging = ">=20.0"
+pillow = ">=6.2.0"
+pyparsing = ">=2.2.1"
+python-dateutil = ">=2.7"
+setuptools_scm = ">=4"
+
+[[package]]
+name = "matplotlib-inline"
+version = "0.1.3"
+description = "Inline Matplotlib backend for Jupyter"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+
+[package.dependencies]
+traitlets = "*"
+
+[[package]]
+name = "mistune"
+version = "0.8.4"
+description = "The fastest markdown parser in pure Python"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "nbclient"
+version = "0.5.13"
+description = "A client library for executing notebooks. Formerly nbconvert's ExecutePreprocessor."
+category = "main"
+optional = false
+python-versions = ">=3.7.0"
+
+[package.dependencies]
+jupyter-client = ">=6.1.5"
+nbformat = ">=5.0"
+nest-asyncio = "*"
+traitlets = ">=5.0.0"
+
+[package.extras]
+sphinx = ["Sphinx (>=1.7)", "sphinx-book-theme", "mock", "moto", "myst-parser"]
+test = ["ipython (<8.0.0)", "ipykernel", "ipywidgets (<8.0.0)", "pytest (>=4.1)", "pytest-asyncio", "pytest-cov (>=2.6.1)", "check-manifest", "flake8", "mypy", "xmltodict", "black", "pip (>=18.1)", "wheel (>=0.31.0)", "setuptools (>=38.6.0)", "twine (>=1.11.0)"]
+
+[[package]]
+name = "nbconvert"
+version = "6.4.5"
+description = "Converting Jupyter Notebooks"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+beautifulsoup4 = "*"
+bleach = "*"
+defusedxml = "*"
+entrypoints = ">=0.2.2"
+jinja2 = ">=2.4"
+jupyter-core = "*"
+jupyterlab-pygments = "*"
+MarkupSafe = ">=2.0"
+mistune = ">=0.8.1,<2"
+nbclient = ">=0.5.0,<0.6.0"
+nbformat = ">=4.4"
+pandocfilters = ">=1.4.1"
+pygments = ">=2.4.1"
+testpath = "*"
+traitlets = ">=5.0"
+
+[package.extras]
+all = ["pytest", "pytest-cov", "pytest-dependency", "ipykernel", "ipywidgets (>=7)", "pyppeteer (>=1,<1.1)", "tornado (>=4.0)", "sphinx (>=1.5.1)", "sphinx-rtd-theme", "nbsphinx (>=0.2.12)", "ipython"]
+docs = ["sphinx (>=1.5.1)", "sphinx-rtd-theme", "nbsphinx (>=0.2.12)", "ipython"]
+serve = ["tornado (>=4.0)"]
+test = ["pytest", "pytest-cov", "pytest-dependency", "ipykernel", "ipywidgets (>=7)", "pyppeteer (>=1,<1.1)"]
+webpdf = ["pyppeteer (>=1,<1.1)"]
+
+[[package]]
+name = "nbformat"
+version = "5.2.0"
+description = "The Jupyter Notebook format"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+jsonschema = ">=2.4,<2.5.0 || >2.5.0"
+jupyter-core = "*"
+traitlets = ">=4.1"
+
+[package.extras]
+fast = ["fastjsonschema"]
+test = ["check-manifest", "fastjsonschema", "testpath", "pytest"]
+
+[[package]]
+name = "nest-asyncio"
+version = "1.5.4"
+description = "Patch asyncio to allow nested event loops"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+
+[[package]]
+name = "notebook"
+version = "6.4.10"
+description = "A web-based notebook environment for interactive computing"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+argon2-cffi = "*"
+ipykernel = "*"
+ipython-genutils = "*"
+jinja2 = "*"
+jupyter-client = ">=5.3.4"
+jupyter-core = ">=4.6.1"
+nbconvert = ">=5"
+nbformat = "*"
+nest-asyncio = ">=1.5"
+prometheus-client = "*"
+pyzmq = ">=17"
+Send2Trash = ">=1.8.0"
+terminado = ">=0.8.3"
+tornado = ">=6.1"
+traitlets = ">=4.2.1"
+
+[package.extras]
+docs = ["sphinx", "nbsphinx", "sphinxcontrib-github-alt", "sphinx-rtd-theme", "myst-parser"]
+json-logging = ["json-logging"]
+test = ["pytest", "coverage", "requests", "nbval", "selenium", "pytest-cov", "requests-unixsocket"]
+
+[[package]]
+name = "numpy"
+version = "1.22.3"
+description = "NumPy is the fundamental package for array computing with Python."
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[[package]]
+name = "packaging"
+version = "21.3"
+description = "Core utilities for Python packages"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+pyparsing = ">=2.0.2,<3.0.5 || >3.0.5"
+
+[[package]]
+name = "pandocfilters"
+version = "1.5.0"
+description = "Utilities for writing pandoc filters in python"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+
+[[package]]
+name = "parso"
+version = "0.8.3"
+description = "A Python Parser"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.extras]
+qa = ["flake8 (==3.8.3)", "mypy (==0.782)"]
+testing = ["docopt", "pytest (<6.0.0)"]
+
+[[package]]
+name = "pexpect"
+version = "4.8.0"
+description = "Pexpect allows easy control of interactive console applications."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+ptyprocess = ">=0.5"
+
+[[package]]
+name = "pickleshare"
+version = "0.7.5"
+description = "Tiny 'shelve'-like database with concurrency support"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "pillow"
+version = "9.0.1"
+description = "Python Imaging Library (Fork)"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "prometheus-client"
+version = "0.13.1"
+description = "Python client for the Prometheus monitoring system."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.extras]
+twisted = ["twisted"]
+
+[[package]]
+name = "prompt-toolkit"
+version = "3.0.28"
+description = "Library for building powerful interactive command lines in Python"
+category = "main"
+optional = false
+python-versions = ">=3.6.2"
+
+[package.dependencies]
+wcwidth = "*"
+
+[[package]]
+name = "psutil"
+version = "5.9.0"
+description = "Cross-platform lib for process and system monitoring in Python."
+category = "main"
+optional = false
+python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+
+[package.extras]
+test = ["ipaddress", "mock", "unittest2", "enum34", "pywin32", "wmi"]
+
+[[package]]
+name = "ptyprocess"
+version = "0.7.0"
+description = "Run a subprocess in a pseudo terminal"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "pure-eval"
+version = "0.2.2"
+description = "Safely evaluate AST nodes without side effects"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.extras]
+tests = ["pytest"]
+
+[[package]]
+name = "py"
+version = "1.11.0"
+description = "library with cross-python path, ini-parsing, io, code, log facilities"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, !=3.4.*"
+
+[[package]]
+name = "pycparser"
+version = "2.21"
+description = "C parser in Python"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+
+[[package]]
+name = "pygments"
+version = "2.11.2"
+description = "Pygments is a syntax highlighting package written in Python."
+category = "main"
+optional = false
+python-versions = ">=3.5"
+
+[[package]]
+name = "pyparsing"
+version = "3.0.7"
+description = "Python parsing module"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.extras]
+diagrams = ["jinja2", "railroad-diagrams"]
+
+[[package]]
+name = "pyrsistent"
+version = "0.18.1"
+description = "Persistent/Functional/Immutable data structures"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "python-dateutil"
+version = "2.8.2"
+description = "Extensions to the standard Python datetime module"
+category = "main"
+optional = false
+python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
+
+[package.dependencies]
+six = ">=1.5"
+
+[[package]]
+name = "pywin32"
+version = "303"
+description = "Python for Window Extensions"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "pywinpty"
+version = "2.0.5"
+description = "Pseudo terminal support for Windows from Python."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "pyzmq"
+version = "22.3.0"
+description = "Python bindings for 0MQ"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+cffi = {version = "*", markers = "implementation_name == \"pypy\""}
+py = {version = "*", markers = "implementation_name == \"pypy\""}
+
+[[package]]
+name = "qtconsole"
+version = "5.3.0"
+description = "Jupyter Qt console"
+category = "main"
+optional = false
+python-versions = ">= 3.7"
+
+[package.dependencies]
+ipykernel = ">=4.1"
+ipython-genutils = "*"
+jupyter-client = ">=4.1"
+jupyter-core = "*"
+pygments = "*"
+pyzmq = ">=17.1"
+qtpy = ">=2.0.1"
+traitlets = "*"
+
+[package.extras]
+doc = ["Sphinx (>=1.3)"]
+test = ["flaky", "pytest", "pytest-qt"]
+
+[[package]]
+name = "qtpy"
+version = "2.0.1"
+description = "Provides an abstraction layer on top of the various Qt bindings (PyQt5/6 and PySide2/6)."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+packaging = "*"
+
+[package.extras]
+test = ["pytest (>=6.0.0)", "pytest-cov (>=3.0.0)", "pytest-qt"]
+
+[[package]]
+name = "send2trash"
+version = "1.8.0"
+description = "Send file to trash natively under Mac OS X, Windows and Linux."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.extras]
+nativelib = ["pyobjc-framework-cocoa", "pywin32"]
+objc = ["pyobjc-framework-cocoa"]
+win32 = ["pywin32"]
+
+[[package]]
+name = "setuptools-scm"
+version = "6.4.2"
+description = "the blessed package to manage your versions by scm tags"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+packaging = ">=20.0"
+tomli = ">=1.0.0"
+
+[package.extras]
+test = ["pytest (>=6.2)", "virtualenv (>20)"]
+toml = ["setuptools (>=42)"]
+
+[[package]]
+name = "six"
+version = "1.16.0"
+description = "Python 2 and 3 compatibility utilities"
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
+
+[[package]]
+name = "soupsieve"
+version = "2.3.1"
+description = "A modern CSS selector implementation for Beautiful Soup."
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "stack-data"
+version = "0.2.0"
+description = "Extract data from python stack frames and tracebacks for informative displays"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+asttokens = "*"
+executing = "*"
+pure-eval = "*"
+
+[package.extras]
+tests = ["pytest", "typeguard", "pygments", "littleutils", "cython"]
+
+[[package]]
+name = "terminado"
+version = "0.13.3"
+description = "Tornado websocket backend for the Xterm.js Javascript terminal emulator library."
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+ptyprocess = {version = "*", markers = "os_name != \"nt\""}
+pywinpty = {version = ">=1.1.0", markers = "os_name == \"nt\""}
+tornado = ">=4"
+
+[package.extras]
+test = ["pytest"]
+
+[[package]]
+name = "testpath"
+version = "0.6.0"
+description = "Test utilities for code working with files and commands"
+category = "main"
+optional = false
+python-versions = ">= 3.5"
+
+[package.extras]
+test = ["pytest"]
+
+[[package]]
+name = "tomli"
+version = "2.0.1"
+description = "A lil' TOML parser"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "tornado"
+version = "6.1"
+description = "Tornado is a Python web framework and asynchronous networking library, originally developed at FriendFeed."
+category = "main"
+optional = false
+python-versions = ">= 3.5"
+
+[[package]]
+name = "traitlets"
+version = "5.1.1"
+description = "Traitlets Python configuration system"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+test = ["pytest"]
+
+[[package]]
+name = "wcwidth"
+version = "0.2.5"
+description = "Measures the displayed width of unicode strings in a terminal"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "webencodings"
+version = "0.5.1"
+description = "Character encoding aliases for legacy web content"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "widgetsnbextension"
+version = "3.6.0"
+description = "IPython HTML widgets for Jupyter"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+notebook = ">=4.4.1"
+
+[[package]]
+name = "zipp"
+version = "3.7.0"
+description = "Backport of pathlib-compatible object wrapper for zip files"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+docs = ["sphinx", "jaraco.packaging (>=8.2)", "rst.linker (>=1.9)"]
+testing = ["pytest (>=6)", "pytest-checkdocs (>=2.4)", "pytest-flake8", "pytest-cov", "pytest-enabler (>=1.0.1)", "jaraco.itertools", "func-timeout", "pytest-black (>=0.3.7)", "pytest-mypy"]
+
+[metadata]
+lock-version = "1.1"
+python-versions = "^3.8"
+content-hash = "fdedb00255a15875f8ee8294c72c811dccedc9c3360d4f11d2405925b3d85321"
+
+[metadata.files]
+appnope = [
+    {file = "appnope-0.1.2-py2.py3-none-any.whl", hash = "sha256:93aa393e9d6c54c5cd570ccadd8edad61ea0c4b9ea7a01409020c9aa019eb442"},
+    {file = "appnope-0.1.2.tar.gz", hash = "sha256:dd83cd4b5b460958838f6eb3000c660b1f9caf2a5b1de4264e941512f603258a"},
+]
+argon2-cffi = [
+    {file = "argon2-cffi-21.3.0.tar.gz", hash = "sha256:d384164d944190a7dd7ef22c6aa3ff197da12962bd04b17f64d4e93d934dba5b"},
+    {file = "argon2_cffi-21.3.0-py3-none-any.whl", hash = "sha256:8c976986f2c5c0e5000919e6de187906cfd81fb1c72bf9d88c01177e77da7f80"},
+]
+argon2-cffi-bindings = [
+    {file = "argon2-cffi-bindings-21.2.0.tar.gz", hash = "sha256:bb89ceffa6c791807d1305ceb77dbfacc5aa499891d2c55661c6459651fc39e3"},
+    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:ccb949252cb2ab3a08c02024acb77cfb179492d5701c7cbdbfd776124d4d2367"},
+    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9524464572e12979364b7d600abf96181d3541da11e23ddf565a32e70bd4dc0d"},
+    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b746dba803a79238e925d9046a63aa26bf86ab2a2fe74ce6b009a1c3f5c8f2ae"},
+    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:58ed19212051f49a523abb1dbe954337dc82d947fb6e5a0da60f7c8471a8476c"},
+    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-musllinux_1_1_aarch64.whl", hash = "sha256:bd46088725ef7f58b5a1ef7ca06647ebaf0eb4baff7d1d0d177c6cc8744abd86"},
+    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-musllinux_1_1_i686.whl", hash = "sha256:8cd69c07dd875537a824deec19f978e0f2078fdda07fd5c42ac29668dda5f40f"},
+    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-musllinux_1_1_x86_64.whl", hash = "sha256:f1152ac548bd5b8bcecfb0b0371f082037e47128653df2e8ba6e914d384f3c3e"},
+    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-win32.whl", hash = "sha256:603ca0aba86b1349b147cab91ae970c63118a0f30444d4bc80355937c950c082"},
+    {file = "argon2_cffi_bindings-21.2.0-cp36-abi3-win_amd64.whl", hash = "sha256:b2ef1c30440dbbcba7a5dc3e319408b59676e2e039e2ae11a8775ecf482b192f"},
+    {file = "argon2_cffi_bindings-21.2.0-cp38-abi3-macosx_10_9_universal2.whl", hash = "sha256:e415e3f62c8d124ee16018e491a009937f8cf7ebf5eb430ffc5de21b900dad93"},
+    {file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:3e385d1c39c520c08b53d63300c3ecc28622f076f4c2b0e6d7e796e9f6502194"},
+    {file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2c3e3cc67fdb7d82c4718f19b4e7a87123caf8a93fde7e23cf66ac0337d3cb3f"},
+    {file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6a22ad9800121b71099d0fb0a65323810a15f2e292f2ba450810a7316e128ee5"},
+    {file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f9f8b450ed0547e3d473fdc8612083fd08dd2120d6ac8f73828df9b7d45bb351"},
+    {file = "argon2_cffi_bindings-21.2.0-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:93f9bf70084f97245ba10ee36575f0c3f1e7d7724d67d8e5b08e61787c320ed7"},
+    {file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:3b9ef65804859d335dc6b31582cad2c5166f0c3e7975f324d9ffaa34ee7e6583"},
+    {file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d4966ef5848d820776f5f562a7d45fdd70c2f330c961d0d745b784034bd9f48d"},
+    {file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:20ef543a89dee4db46a1a6e206cd015360e5a75822f76df533845c3cbaf72670"},
+    {file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ed2937d286e2ad0cc79a7087d3c272832865f779430e0cc2b4f3718d3159b0cb"},
+    {file = "argon2_cffi_bindings-21.2.0-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:5e00316dabdaea0b2dd82d141cc66889ced0cdcbfa599e8b471cf22c620c329a"},
+]
+asttokens = [
+    {file = "asttokens-2.0.5-py2.py3-none-any.whl", hash = "sha256:0844691e88552595a6f4a4281a9f7f79b8dd45ca4ccea82e5e05b4bbdb76705c"},
+    {file = "asttokens-2.0.5.tar.gz", hash = "sha256:9a54c114f02c7a9480d56550932546a3f1fe71d8a02f1bc7ccd0ee3ee35cf4d5"},
+]
+attrs = [
+    {file = "attrs-21.4.0-py2.py3-none-any.whl", hash = "sha256:2d27e3784d7a565d36ab851fe94887c5eccd6a463168875832a1be79c82828b4"},
+    {file = "attrs-21.4.0.tar.gz", hash = "sha256:626ba8234211db98e869df76230a137c4c40a12d72445c45d5f5b716f076e2fd"},
+]
+backcall = [
+    {file = "backcall-0.2.0-py2.py3-none-any.whl", hash = "sha256:fbbce6a29f263178a1f7915c1940bde0ec2b2a967566fe1c65c1dfb7422bd255"},
+    {file = "backcall-0.2.0.tar.gz", hash = "sha256:5cbdbf27be5e7cfadb448baf0aa95508f91f2bbc6c6437cd9cd06e2a4c215e1e"},
+]
+beautifulsoup4 = [
+    {file = "beautifulsoup4-4.10.0-py3-none-any.whl", hash = "sha256:9a315ce70049920ea4572a4055bc4bd700c940521d36fc858205ad4fcde149bf"},
+    {file = "beautifulsoup4-4.10.0.tar.gz", hash = "sha256:c23ad23c521d818955a4151a67d81580319d4bf548d3d49f4223ae041ff98891"},
+]
+bleach = [
+    {file = "bleach-4.1.0-py2.py3-none-any.whl", hash = "sha256:4d2651ab93271d1129ac9cbc679f524565cc8a1b791909c4a51eac4446a15994"},
+    {file = "bleach-4.1.0.tar.gz", hash = "sha256:0900d8b37eba61a802ee40ac0061f8c2b5dee29c1927dd1d233e075ebf5a71da"},
+]
+cffi = [
+    {file = "cffi-1.15.0-cp27-cp27m-macosx_10_9_x86_64.whl", hash = "sha256:c2502a1a03b6312837279c8c1bd3ebedf6c12c4228ddbad40912d671ccc8a962"},
+    {file = "cffi-1.15.0-cp27-cp27m-manylinux1_i686.whl", hash = "sha256:23cfe892bd5dd8941608f93348c0737e369e51c100d03718f108bf1add7bd6d0"},
+    {file = "cffi-1.15.0-cp27-cp27m-manylinux1_x86_64.whl", hash = "sha256:41d45de54cd277a7878919867c0f08b0cf817605e4eb94093e7516505d3c8d14"},
+    {file = "cffi-1.15.0-cp27-cp27m-win32.whl", hash = "sha256:4a306fa632e8f0928956a41fa8e1d6243c71e7eb59ffbd165fc0b41e316b2474"},
+    {file = "cffi-1.15.0-cp27-cp27m-win_amd64.whl", hash = "sha256:e7022a66d9b55e93e1a845d8c9eba2a1bebd4966cd8bfc25d9cd07d515b33fa6"},
+    {file = "cffi-1.15.0-cp27-cp27mu-manylinux1_i686.whl", hash = "sha256:14cd121ea63ecdae71efa69c15c5543a4b5fbcd0bbe2aad864baca0063cecf27"},
+    {file = "cffi-1.15.0-cp27-cp27mu-manylinux1_x86_64.whl", hash = "sha256:d4d692a89c5cf08a8557fdeb329b82e7bf609aadfaed6c0d79f5a449a3c7c023"},
+    {file = "cffi-1.15.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0104fb5ae2391d46a4cb082abdd5c69ea4eab79d8d44eaaf79f1b1fd806ee4c2"},
+    {file = "cffi-1.15.0-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:91ec59c33514b7c7559a6acda53bbfe1b283949c34fe7440bcf917f96ac0723e"},
+    {file = "cffi-1.15.0-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:f5c7150ad32ba43a07c4479f40241756145a1f03b43480e058cfd862bf5041c7"},
+    {file = "cffi-1.15.0-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:00c878c90cb53ccfaae6b8bc18ad05d2036553e6d9d1d9dbcf323bbe83854ca3"},
+    {file = "cffi-1.15.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:abb9a20a72ac4e0fdb50dae135ba5e77880518e742077ced47eb1499e29a443c"},
+    {file = "cffi-1.15.0-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a5263e363c27b653a90078143adb3d076c1a748ec9ecc78ea2fb916f9b861962"},
+    {file = "cffi-1.15.0-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f54a64f8b0c8ff0b64d18aa76675262e1700f3995182267998c31ae974fbc382"},
+    {file = "cffi-1.15.0-cp310-cp310-win32.whl", hash = "sha256:c21c9e3896c23007803a875460fb786118f0cdd4434359577ea25eb556e34c55"},
+    {file = "cffi-1.15.0-cp310-cp310-win_amd64.whl", hash = "sha256:5e069f72d497312b24fcc02073d70cb989045d1c91cbd53979366077959933e0"},
+    {file = "cffi-1.15.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:64d4ec9f448dfe041705426000cc13e34e6e5bb13736e9fd62e34a0b0c41566e"},
+    {file = "cffi-1.15.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2756c88cbb94231c7a147402476be2c4df2f6078099a6f4a480d239a8817ae39"},
+    {file = "cffi-1.15.0-cp36-cp36m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3b96a311ac60a3f6be21d2572e46ce67f09abcf4d09344c49274eb9e0bf345fc"},
+    {file = "cffi-1.15.0-cp36-cp36m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:75e4024375654472cc27e91cbe9eaa08567f7fbdf822638be2814ce059f58032"},
+    {file = "cffi-1.15.0-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:59888172256cac5629e60e72e86598027aca6bf01fa2465bdb676d37636573e8"},
+    {file = "cffi-1.15.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:27c219baf94952ae9d50ec19651a687b826792055353d07648a5695413e0c605"},
+    {file = "cffi-1.15.0-cp36-cp36m-win32.whl", hash = "sha256:4958391dbd6249d7ad855b9ca88fae690783a6be9e86df65865058ed81fc860e"},
+    {file = "cffi-1.15.0-cp36-cp36m-win_amd64.whl", hash = "sha256:f6f824dc3bce0edab5f427efcfb1d63ee75b6fcb7282900ccaf925be84efb0fc"},
+    {file = "cffi-1.15.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:06c48159c1abed75c2e721b1715c379fa3200c7784271b3c46df01383b593636"},
+    {file = "cffi-1.15.0-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:c2051981a968d7de9dd2d7b87bcb9c939c74a34626a6e2f8181455dd49ed69e4"},
+    {file = "cffi-1.15.0-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:fd8a250edc26254fe5b33be00402e6d287f562b6a5b2152dec302fa15bb3e997"},
+    {file = "cffi-1.15.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:91d77d2a782be4274da750752bb1650a97bfd8f291022b379bb8e01c66b4e96b"},
+    {file = "cffi-1.15.0-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:45db3a33139e9c8f7c09234b5784a5e33d31fd6907800b316decad50af323ff2"},
+    {file = "cffi-1.15.0-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:263cc3d821c4ab2213cbe8cd8b355a7f72a8324577dc865ef98487c1aeee2bc7"},
+    {file = "cffi-1.15.0-cp37-cp37m-win32.whl", hash = "sha256:17771976e82e9f94976180f76468546834d22a7cc404b17c22df2a2c81db0c66"},
+    {file = "cffi-1.15.0-cp37-cp37m-win_amd64.whl", hash = "sha256:3415c89f9204ee60cd09b235810be700e993e343a408693e80ce7f6a40108029"},
+    {file = "cffi-1.15.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:4238e6dab5d6a8ba812de994bbb0a79bddbdf80994e4ce802b6f6f3142fcc880"},
+    {file = "cffi-1.15.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:0808014eb713677ec1292301ea4c81ad277b6cdf2fdd90fd540af98c0b101d20"},
+    {file = "cffi-1.15.0-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:57e9ac9ccc3101fac9d6014fba037473e4358ef4e89f8e181f8951a2c0162024"},
+    {file = "cffi-1.15.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8b6c2ea03845c9f501ed1313e78de148cd3f6cad741a75d43a29b43da27f2e1e"},
+    {file = "cffi-1.15.0-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:10dffb601ccfb65262a27233ac273d552ddc4d8ae1bf93b21c94b8511bffe728"},
+    {file = "cffi-1.15.0-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:786902fb9ba7433aae840e0ed609f45c7bcd4e225ebb9c753aa39725bb3e6ad6"},
+    {file = "cffi-1.15.0-cp38-cp38-win32.whl", hash = "sha256:da5db4e883f1ce37f55c667e5c0de439df76ac4cb55964655906306918e7363c"},
+    {file = "cffi-1.15.0-cp38-cp38-win_amd64.whl", hash = "sha256:181dee03b1170ff1969489acf1c26533710231c58f95534e3edac87fff06c443"},
+    {file = "cffi-1.15.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:45e8636704eacc432a206ac7345a5d3d2c62d95a507ec70d62f23cd91770482a"},
+    {file = "cffi-1.15.0-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:31fb708d9d7c3f49a60f04cf5b119aeefe5644daba1cd2a0fe389b674fd1de37"},
+    {file = "cffi-1.15.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:6dc2737a3674b3e344847c8686cf29e500584ccad76204efea14f451d4cc669a"},
+    {file = "cffi-1.15.0-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:74fdfdbfdc48d3f47148976f49fab3251e550a8720bebc99bf1483f5bfb5db3e"},
+    {file = "cffi-1.15.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ffaa5c925128e29efbde7301d8ecaf35c8c60ffbcd6a1ffd3a552177c8e5e796"},
+    {file = "cffi-1.15.0-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:3f7d084648d77af029acb79a0ff49a0ad7e9d09057a9bf46596dac9514dc07df"},
+    {file = "cffi-1.15.0-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:ef1f279350da2c586a69d32fc8733092fd32cc8ac95139a00377841f59a3f8d8"},
+    {file = "cffi-1.15.0-cp39-cp39-win32.whl", hash = "sha256:2a23af14f408d53d5e6cd4e3d9a24ff9e05906ad574822a10563efcef137979a"},
+    {file = "cffi-1.15.0-cp39-cp39-win_amd64.whl", hash = "sha256:3773c4d81e6e818df2efbc7dd77325ca0dcb688116050fb2b3011218eda36139"},
+    {file = "cffi-1.15.0.tar.gz", hash = "sha256:920f0d66a896c2d99f0adbb391f990a84091179542c205fa53ce5787aff87954"},
+]
+colorama = [
+    {file = "colorama-0.4.4-py2.py3-none-any.whl", hash = "sha256:9f47eda37229f68eee03b24b9748937c7dc3868f906e8ba69fbcbdd3bc5dc3e2"},
+    {file = "colorama-0.4.4.tar.gz", hash = "sha256:5941b2b48a20143d2267e95b1c2a7603ce057ee39fd88e7329b0c292aa16869b"},
+]
+cycler = [
+    {file = "cycler-0.11.0-py3-none-any.whl", hash = "sha256:3a27e95f763a428a739d2add979fa7494c912a32c17c4c38c4d5f082cad165a3"},
+    {file = "cycler-0.11.0.tar.gz", hash = "sha256:9c87405839a19696e837b3b818fed3f5f69f16f1eec1a1ad77e043dcea9c772f"},
+]
+debugpy = [
+    {file = "debugpy-1.6.0-cp310-cp310-macosx_10_15_x86_64.whl", hash = "sha256:eb1946efac0c0c3d411cea0b5ac772fbde744109fd9520fb0c5a51979faf05ad"},
+    {file = "debugpy-1.6.0-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:e3513399177dd37af4c1332df52da5da1d0c387e5927dc4c0709e26ee7302e8f"},
+    {file = "debugpy-1.6.0-cp310-cp310-win32.whl", hash = "sha256:5c492235d6b68f879df3bdbdb01f25c15be15682665517c2c7d0420e5658d71f"},
+    {file = "debugpy-1.6.0-cp310-cp310-win_amd64.whl", hash = "sha256:40de9ba137d355538432209d05e0f5fe5d0498dce761c39119ad4b950b51db31"},
+    {file = "debugpy-1.6.0-cp37-cp37m-macosx_10_15_x86_64.whl", hash = "sha256:0d383b91efee57dbb923ba20801130cf60450a0eda60bce25bccd937de8e323a"},
+    {file = "debugpy-1.6.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:1ff853e60e77e1c16f85a31adb8360bb2d98ca588d7ed645b7f0985b240bdb5e"},
+    {file = "debugpy-1.6.0-cp37-cp37m-win32.whl", hash = "sha256:8e972c717d95f56b6a3a7a29a5ede1ee8f2c3802f6f0e678203b0778eb322bf1"},
+    {file = "debugpy-1.6.0-cp37-cp37m-win_amd64.whl", hash = "sha256:a8aaeb53e87225141fda7b9081bd87155c1debc13e2f5a532d341112d1983b65"},
+    {file = "debugpy-1.6.0-cp38-cp38-macosx_10_15_x86_64.whl", hash = "sha256:132defb585b518955358321d0f42f6aa815aa15b432be27db654807707c70b2f"},
+    {file = "debugpy-1.6.0-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:8ee75844242b4537beb5899f3e60a578454d1f136b99e8d57ac424573797b94a"},
+    {file = "debugpy-1.6.0-cp38-cp38-win32.whl", hash = "sha256:a65a2499761d47df3e9ea9567109be6e73d412e00ac3ffcf74839f3ddfcdf028"},
+    {file = "debugpy-1.6.0-cp38-cp38-win_amd64.whl", hash = "sha256:bd980d533d0ddfc451e03a3bb32acb2900049fec39afc3425b944ebf0889be62"},
+    {file = "debugpy-1.6.0-cp39-cp39-macosx_10_15_x86_64.whl", hash = "sha256:245c7789a012f86210847ec7ee9f38c30a30d4c2223c3e111829a76c9006a5d0"},
+    {file = "debugpy-1.6.0-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:0e3aa2368883e83e7b689ddff3cafb595f7b711f6a065886b46a96a7fef874e7"},
+    {file = "debugpy-1.6.0-cp39-cp39-win32.whl", hash = "sha256:72bcfa97f3afa0064afc77ab811f48ad4a06ac330f290b675082c24437730366"},
+    {file = "debugpy-1.6.0-cp39-cp39-win_amd64.whl", hash = "sha256:30abefefd2ff5a5481162d613cb70e60e2fa80a5eb4c994717c0f008ed25d2e1"},
+    {file = "debugpy-1.6.0-py2.py3-none-any.whl", hash = "sha256:4de7777842da7e08652f2776c552070bbdd758557fdec73a15d7be0e4aab95ce"},
+    {file = "debugpy-1.6.0.zip", hash = "sha256:7b79c40852991f7b6c3ea65845ed0f5f6b731c37f4f9ad9c61e2ab4bd48a9275"},
+]
+decorator = [
+    {file = "decorator-5.1.1-py3-none-any.whl", hash = "sha256:b8c3f85900b9dc423225913c5aace94729fe1fa9763b38939a95226f02d37186"},
+    {file = "decorator-5.1.1.tar.gz", hash = "sha256:637996211036b6385ef91435e4fae22989472f9d571faba8927ba8253acbc330"},
+]
+defusedxml = [
+    {file = "defusedxml-0.7.1-py2.py3-none-any.whl", hash = "sha256:a352e7e428770286cc899e2542b6cdaedb2b4953ff269a210103ec58f6198a61"},
+    {file = "defusedxml-0.7.1.tar.gz", hash = "sha256:1bb3032db185915b62d7c6209c5a8792be6a32ab2fedacc84e01b52c51aa3e69"},
+]
+entrypoints = [
+    {file = "entrypoints-0.4-py3-none-any.whl", hash = "sha256:f174b5ff827504fd3cd97cc3f8649f3693f51538c7e4bdf3ef002c8429d42f9f"},
+    {file = "entrypoints-0.4.tar.gz", hash = "sha256:b706eddaa9218a19ebcd67b56818f05bb27589b1ca9e8d797b74affad4ccacd4"},
+]
+executing = [
+    {file = "executing-0.8.3-py2.py3-none-any.whl", hash = "sha256:d1eef132db1b83649a3905ca6dd8897f71ac6f8cac79a7e58a1a09cf137546c9"},
+    {file = "executing-0.8.3.tar.gz", hash = "sha256:c6554e21c6b060590a6d3be4b82fb78f8f0194d809de5ea7df1c093763311501"},
+]
+fonttools = [
+    {file = "fonttools-4.31.2-py3-none-any.whl", hash = "sha256:2df636a3f402ef14593c6811dac0609563b8c374bd7850e76919eb51ea205426"},
+    {file = "fonttools-4.31.2.zip", hash = "sha256:236b29aee6b113e8f7bee28779c1230a86ad2aac9a74a31b0aedf57e7dfb62a4"},
+]
+importlib-resources = [
+    {file = "importlib_resources-5.6.0-py3-none-any.whl", hash = "sha256:a9dd72f6cc106aeb50f6e66b86b69b454766dd6e39b69ac68450253058706bcc"},
+    {file = "importlib_resources-5.6.0.tar.gz", hash = "sha256:1b93238cbf23b4cde34240dd8321d99e9bf2eb4bc91c0c99b2886283e7baad85"},
+]
+ipykernel = [
+    {file = "ipykernel-6.11.0-py3-none-any.whl", hash = "sha256:62ec17caff6e4fa1dc87ef0a6f9eff5a5d6588bb585ab1e06897e7bec9eb2819"},
+    {file = "ipykernel-6.11.0.tar.gz", hash = "sha256:6712604531c96100f326440c11cb023da26819f2f34ba9d1ca0fb163401834e8"},
+]
+ipython = [
+    {file = "ipython-8.2.0-py3-none-any.whl", hash = "sha256:1b672bfd7a48d87ab203d9af8727a3b0174a4566b4091e9447c22fb63ea32857"},
+    {file = "ipython-8.2.0.tar.gz", hash = "sha256:70e5eb132cac594a34b5f799bd252589009905f05104728aea6a403ec2519dc1"},
+]
+ipython-genutils = [
+    {file = "ipython_genutils-0.2.0-py2.py3-none-any.whl", hash = "sha256:72dd37233799e619666c9f639a9da83c34013a73e8bbc79a7a6348d93c61fab8"},
+    {file = "ipython_genutils-0.2.0.tar.gz", hash = "sha256:eb2e116e75ecef9d4d228fdc66af54269afa26ab4463042e33785b887c628ba8"},
+]
+ipywidgets = [
+    {file = "ipywidgets-7.7.0-py2.py3-none-any.whl", hash = "sha256:e58ff58bc94d481e91ecb6e13a5cb96a87b6b8ade135e055603d0ca24593df38"},
+    {file = "ipywidgets-7.7.0.tar.gz", hash = "sha256:ab4a5596855a88b83761921c768707d65e5847068139bc1729ddfe834703542a"},
+]
+jedi = [
+    {file = "jedi-0.18.1-py2.py3-none-any.whl", hash = "sha256:637c9635fcf47945ceb91cd7f320234a7be540ded6f3e99a50cb6febdfd1ba8d"},
+    {file = "jedi-0.18.1.tar.gz", hash = "sha256:74137626a64a99c8eb6ae5832d99b3bdd7d29a3850fe2aa80a4126b2a7d949ab"},
+]
+jinja2 = [
+    {file = "Jinja2-3.1.1-py3-none-any.whl", hash = "sha256:539835f51a74a69f41b848a9645dbdc35b4f20a3b601e2d9a7e22947b15ff119"},
+    {file = "Jinja2-3.1.1.tar.gz", hash = "sha256:640bed4bb501cbd17194b3cace1dc2126f5b619cf068a726b98192a0fde74ae9"},
+]
+jsonschema = [
+    {file = "jsonschema-4.4.0-py3-none-any.whl", hash = "sha256:77281a1f71684953ee8b3d488371b162419767973789272434bbc3f29d9c8823"},
+    {file = "jsonschema-4.4.0.tar.gz", hash = "sha256:636694eb41b3535ed608fe04129f26542b59ed99808b4f688aa32dcf55317a83"},
+]
+jupyter = [
+    {file = "jupyter-1.0.0-py2.py3-none-any.whl", hash = "sha256:5b290f93b98ffbc21c0c7e749f054b3267782166d72fa5e3ed1ed4eaf34a2b78"},
+    {file = "jupyter-1.0.0.tar.gz", hash = "sha256:d9dc4b3318f310e34c82951ea5d6683f67bed7def4b259fafbfe4f1beb1d8e5f"},
+    {file = "jupyter-1.0.0.zip", hash = "sha256:3e1f86076bbb7c8c207829390305a2b1fe836d471ed54be66a3b8c41e7f46cc7"},
+]
+jupyter-client = [
+    {file = "jupyter_client-7.2.1-py3-none-any.whl", hash = "sha256:d10e31ac4b8364d1cb30ebcee9e5cc7b7eb5d23b76912be9ef3d4c75167fbc68"},
+    {file = "jupyter_client-7.2.1.tar.gz", hash = "sha256:aa177279e93205d0681ec0e2e210da01b22c5a1464a56abd455adcac64f0de91"},
+]
+jupyter-console = [
+    {file = "jupyter_console-6.4.3-py3-none-any.whl", hash = "sha256:e630bcb682c0088dda45688ad7c2424d4a825c8acf494cb036ced03ed0424841"},
+    {file = "jupyter_console-6.4.3.tar.gz", hash = "sha256:55f32626b0be647a85e3217ddcdb22db69efc79e8b403b9771eb9ecc696019b5"},
+]
+jupyter-core = [
+    {file = "jupyter_core-4.9.2-py3-none-any.whl", hash = "sha256:f875e4d27e202590311d468fa55f90c575f201490bd0c18acabe4e318db4a46d"},
+    {file = "jupyter_core-4.9.2.tar.gz", hash = "sha256:d69baeb9ffb128b8cd2657fcf2703f89c769d1673c851812119e3a2a0e93ad9a"},
+]
+jupyterlab-pygments = [
+    {file = "jupyterlab_pygments-0.1.2-py2.py3-none-any.whl", hash = "sha256:abfb880fd1561987efaefcb2d2ac75145d2a5d0139b1876d5be806e32f630008"},
+    {file = "jupyterlab_pygments-0.1.2.tar.gz", hash = "sha256:cfcda0873626150932f438eccf0f8bf22bfa92345b814890ab360d666b254146"},
+]
+jupyterlab-widgets = [
+    {file = "jupyterlab_widgets-1.1.0-py3-none-any.whl", hash = "sha256:c2a9bd3789f120f64d73268c066ed3b000c56bc1dda217be5cdc43e7b4ebad3f"},
+    {file = "jupyterlab_widgets-1.1.0.tar.gz", hash = "sha256:d5f41bc1713795385f718d44dcba47e1e1473c6289f28a95aa6b2c0782ee372a"},
+]
+kiwisolver = [
+    {file = "kiwisolver-1.4.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:6e395ece147f0692ca7cdb05a028d31b83b72c369f7b4a2c1798f4b96af1e3d8"},
+    {file = "kiwisolver-1.4.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0b7f50a1a25361da3440f07c58cd1d79957c2244209e4f166990e770256b6b0b"},
+    {file = "kiwisolver-1.4.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:3c032c41ae4c3a321b43a3650e6ecc7406b99ff3e5279f24c9b310f41bc98479"},
+    {file = "kiwisolver-1.4.2-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:1dcade8f6fe12a2bb4efe2cbe22116556e3b6899728d3b2a0d3b367db323eacc"},
+    {file = "kiwisolver-1.4.2-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:0e45e780a74416ef2f173189ef4387e44b5494f45e290bcb1f03735faa6779bf"},
+    {file = "kiwisolver-1.4.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:9d2bb56309fb75a811d81ed55fbe2208aa77a3a09ff5f546ca95e7bb5fac6eff"},
+    {file = "kiwisolver-1.4.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:69b2d6c12f2ad5f55104a36a356192cfb680c049fe5e7c1f6620fc37f119cdc2"},
+    {file = "kiwisolver-1.4.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:262c248c60f22c2b547683ad521e8a3db5909c71f679b93876921549107a0c24"},
+    {file = "kiwisolver-1.4.2-cp310-cp310-win32.whl", hash = "sha256:1008346a7741620ab9cc6c96e8ad9b46f7a74ce839dbb8805ddf6b119d5fc6c2"},
+    {file = "kiwisolver-1.4.2-cp310-cp310-win_amd64.whl", hash = "sha256:6ece2e12e4b57bc5646b354f436416cd2a6f090c1dadcd92b0ca4542190d7190"},
+    {file = "kiwisolver-1.4.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:b978afdb913ca953cf128d57181da2e8798e8b6153be866ae2a9c446c6162f40"},
+    {file = "kiwisolver-1.4.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7f88c4b8e449908eeddb3bbd4242bd4dc2c7a15a7aa44bb33df893203f02dc2d"},
+    {file = "kiwisolver-1.4.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e348f1904a4fab4153407f7ccc27e43b2a139752e8acf12e6640ba683093dd96"},
+    {file = "kiwisolver-1.4.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c839bf28e45d7ddad4ae8f986928dbf5a6d42ff79760d54ec8ada8fb263e097c"},
+    {file = "kiwisolver-1.4.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:8ae5a071185f1a93777c79a9a1e67ac46544d4607f18d07131eece08d415083a"},
+    {file = "kiwisolver-1.4.2-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:c222f91a45da9e01a9bc4f760727ae49050f8e8345c4ff6525495f7a164c8973"},
+    {file = "kiwisolver-1.4.2-cp37-cp37m-win32.whl", hash = "sha256:a4e8f072db1d6fb7a7cc05a6dbef8442c93001f4bb604f1081d8c2db3ca97159"},
+    {file = "kiwisolver-1.4.2-cp37-cp37m-win_amd64.whl", hash = "sha256:be9a650890fb60393e60aacb65878c4a38bb334720aa5ecb1c13d0dac54dd73b"},
+    {file = "kiwisolver-1.4.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:8ec2e55bf31b43aabe32089125dca3b46fdfe9f50afbf0756ae11e14c97b80ca"},
+    {file = "kiwisolver-1.4.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:1d1078ba770d6165abed3d9a1be1f9e79b61515de1dd00d942fa53bba79f01ae"},
+    {file = "kiwisolver-1.4.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:cbb5eb4a2ea1ffec26268d49766cafa8f957fe5c1b41ad00733763fae77f9436"},
+    {file = "kiwisolver-1.4.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2e6cda72db409eefad6b021e8a4f964965a629f577812afc7860c69df7bdb84a"},
+    {file = "kiwisolver-1.4.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b1605c7c38cc6a85212dfd6a641f3905a33412e49f7c003f35f9ac6d71f67720"},
+    {file = "kiwisolver-1.4.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:81237957b15469ea9151ec8ca08ce05656090ffabc476a752ef5ad7e2644c526"},
+    {file = "kiwisolver-1.4.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:240009fdf4fa87844f805e23f48995537a8cb8f8c361e35fda6b5ac97fcb906f"},
+    {file = "kiwisolver-1.4.2-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:240c2d51d098395c012ddbcb9bd7b3ba5de412a1d11840698859f51d0e643c4f"},
+    {file = "kiwisolver-1.4.2-cp38-cp38-win32.whl", hash = "sha256:8b6086aa6936865962b2cee0e7aaecf01ab6778ce099288354a7229b4d9f1408"},
+    {file = "kiwisolver-1.4.2-cp38-cp38-win_amd64.whl", hash = "sha256:0d98dca86f77b851350c250f0149aa5852b36572514d20feeadd3c6b1efe38d0"},
+    {file = "kiwisolver-1.4.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:91eb4916271655dfe3a952249cb37a5c00b6ba68b4417ee15af9ba549b5ba61d"},
+    {file = "kiwisolver-1.4.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:fa4d97d7d2b2c082e67907c0b8d9f31b85aa5d3ba0d33096b7116f03f8061261"},
+    {file = "kiwisolver-1.4.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:71469b5845b9876b8d3d252e201bef6f47bf7456804d2fbe9a1d6e19e78a1e65"},
+    {file = "kiwisolver-1.4.2-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:8ff3033e43e7ca1389ee59fb7ecb8303abb8713c008a1da49b00869e92e3dd7c"},
+    {file = "kiwisolver-1.4.2-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:89b57c2984f4464840e4b768affeff6b6809c6150d1166938ade3e22fbe22db8"},
+    {file = "kiwisolver-1.4.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ffbdb9a96c536f0405895b5e21ee39ec579cb0ed97bdbd169ae2b55f41d73219"},
+    {file = "kiwisolver-1.4.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8a830a03970c462d1a2311c90e05679da56d3bd8e78a4ba9985cb78ef7836c9f"},
+    {file = "kiwisolver-1.4.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f74f2a13af201559e3d32b9ddfc303c94ae63d63d7f4326d06ce6fe67e7a8255"},
+    {file = "kiwisolver-1.4.2-cp39-cp39-win32.whl", hash = "sha256:e677cc3626287f343de751e11b1e8a5b915a6ac897e8aecdbc996cd34de753a0"},
+    {file = "kiwisolver-1.4.2-cp39-cp39-win_amd64.whl", hash = "sha256:b3e251e5c38ac623c5d786adb21477f018712f8c6fa54781bd38aa1c60b60fc2"},
+    {file = "kiwisolver-1.4.2-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:0c380bb5ae20d829c1a5473cfcae64267b73aaa4060adc091f6df1743784aae0"},
+    {file = "kiwisolver-1.4.2-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:484f2a5f0307bc944bc79db235f41048bae4106ffa764168a068d88b644b305d"},
+    {file = "kiwisolver-1.4.2-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0e8afdf533b613122e4bbaf3c1e42c2a5e9e2d1dd3a0a017749a7658757cb377"},
+    {file = "kiwisolver-1.4.2-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:42f6ef9b640deb6f7d438e0a371aedd8bef6ddfde30683491b2e6f568b4e884e"},
+    {file = "kiwisolver-1.4.2.tar.gz", hash = "sha256:7f606d91b8a8816be476513a77fd30abe66227039bd6f8b406c348cb0247dcc9"},
+]
+markupsafe = [
+    {file = "MarkupSafe-2.1.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:86b1f75c4e7c2ac2ccdaec2b9022845dbb81880ca318bb7a0a01fbf7813e3812"},
+    {file = "MarkupSafe-2.1.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:f121a1420d4e173a5d96e47e9a0c0dcff965afdf1626d28de1460815f7c4ee7a"},
+    {file = "MarkupSafe-2.1.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a49907dd8420c5685cfa064a1335b6754b74541bbb3706c259c02ed65b644b3e"},
+    {file = "MarkupSafe-2.1.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:10c1bfff05d95783da83491be968e8fe789263689c02724e0c691933c52994f5"},
+    {file = "MarkupSafe-2.1.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b7bd98b796e2b6553da7225aeb61f447f80a1ca64f41d83612e6139ca5213aa4"},
+    {file = "MarkupSafe-2.1.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:b09bf97215625a311f669476f44b8b318b075847b49316d3e28c08e41a7a573f"},
+    {file = "MarkupSafe-2.1.1-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:694deca8d702d5db21ec83983ce0bb4b26a578e71fbdbd4fdcd387daa90e4d5e"},
+    {file = "MarkupSafe-2.1.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:efc1913fd2ca4f334418481c7e595c00aad186563bbc1ec76067848c7ca0a933"},
+    {file = "MarkupSafe-2.1.1-cp310-cp310-win32.whl", hash = "sha256:4a33dea2b688b3190ee12bd7cfa29d39c9ed176bda40bfa11099a3ce5d3a7ac6"},
+    {file = "MarkupSafe-2.1.1-cp310-cp310-win_amd64.whl", hash = "sha256:dda30ba7e87fbbb7eab1ec9f58678558fd9a6b8b853530e176eabd064da81417"},
+    {file = "MarkupSafe-2.1.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:671cd1187ed5e62818414afe79ed29da836dde67166a9fac6d435873c44fdd02"},
+    {file = "MarkupSafe-2.1.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3799351e2336dc91ea70b034983ee71cf2f9533cdff7c14c90ea126bfd95d65a"},
+    {file = "MarkupSafe-2.1.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e72591e9ecd94d7feb70c1cbd7be7b3ebea3f548870aa91e2732960fa4d57a37"},
+    {file = "MarkupSafe-2.1.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6fbf47b5d3728c6aea2abb0589b5d30459e369baa772e0f37a0320185e87c980"},
+    {file = "MarkupSafe-2.1.1-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:d5ee4f386140395a2c818d149221149c54849dfcfcb9f1debfe07a8b8bd63f9a"},
+    {file = "MarkupSafe-2.1.1-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:bcb3ed405ed3222f9904899563d6fc492ff75cce56cba05e32eff40e6acbeaa3"},
+    {file = "MarkupSafe-2.1.1-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:e1c0b87e09fa55a220f058d1d49d3fb8df88fbfab58558f1198e08c1e1de842a"},
+    {file = "MarkupSafe-2.1.1-cp37-cp37m-win32.whl", hash = "sha256:8dc1c72a69aa7e082593c4a203dcf94ddb74bb5c8a731e4e1eb68d031e8498ff"},
+    {file = "MarkupSafe-2.1.1-cp37-cp37m-win_amd64.whl", hash = "sha256:97a68e6ada378df82bc9f16b800ab77cbf4b2fada0081794318520138c088e4a"},
+    {file = "MarkupSafe-2.1.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:e8c843bbcda3a2f1e3c2ab25913c80a3c5376cd00c6e8c4a86a89a28c8dc5452"},
+    {file = "MarkupSafe-2.1.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:0212a68688482dc52b2d45013df70d169f542b7394fc744c02a57374a4207003"},
+    {file = "MarkupSafe-2.1.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8e576a51ad59e4bfaac456023a78f6b5e6e7651dcd383bcc3e18d06f9b55d6d1"},
+    {file = "MarkupSafe-2.1.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4b9fe39a2ccc108a4accc2676e77da025ce383c108593d65cc909add5c3bd601"},
+    {file = "MarkupSafe-2.1.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:96e37a3dc86e80bf81758c152fe66dbf60ed5eca3d26305edf01892257049925"},
+    {file = "MarkupSafe-2.1.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:6d0072fea50feec76a4c418096652f2c3238eaa014b2f94aeb1d56a66b41403f"},
+    {file = "MarkupSafe-2.1.1-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:089cf3dbf0cd6c100f02945abeb18484bd1ee57a079aefd52cffd17fba910b88"},
+    {file = "MarkupSafe-2.1.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:6a074d34ee7a5ce3effbc526b7083ec9731bb3cbf921bbe1d3005d4d2bdb3a63"},
+    {file = "MarkupSafe-2.1.1-cp38-cp38-win32.whl", hash = "sha256:421be9fbf0ffe9ffd7a378aafebbf6f4602d564d34be190fc19a193232fd12b1"},
+    {file = "MarkupSafe-2.1.1-cp38-cp38-win_amd64.whl", hash = "sha256:fc7b548b17d238737688817ab67deebb30e8073c95749d55538ed473130ec0c7"},
+    {file = "MarkupSafe-2.1.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:e04e26803c9c3851c931eac40c695602c6295b8d432cbe78609649ad9bd2da8a"},
+    {file = "MarkupSafe-2.1.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:b87db4360013327109564f0e591bd2a3b318547bcef31b468a92ee504d07ae4f"},
+    {file = "MarkupSafe-2.1.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:99a2a507ed3ac881b975a2976d59f38c19386d128e7a9a18b7df6fff1fd4c1d6"},
+    {file = "MarkupSafe-2.1.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:56442863ed2b06d19c37f94d999035e15ee982988920e12a5b4ba29b62ad1f77"},
+    {file = "MarkupSafe-2.1.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:3ce11ee3f23f79dbd06fb3d63e2f6af7b12db1d46932fe7bd8afa259a5996603"},
+    {file = "MarkupSafe-2.1.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:33b74d289bd2f5e527beadcaa3f401e0df0a89927c1559c8566c066fa4248ab7"},
+    {file = "MarkupSafe-2.1.1-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:43093fb83d8343aac0b1baa75516da6092f58f41200907ef92448ecab8825135"},
+    {file = "MarkupSafe-2.1.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:8e3dcf21f367459434c18e71b2a9532d96547aef8a871872a5bd69a715c15f96"},
+    {file = "MarkupSafe-2.1.1-cp39-cp39-win32.whl", hash = "sha256:d4306c36ca495956b6d568d276ac11fdd9c30a36f1b6eb928070dc5360b22e1c"},
+    {file = "MarkupSafe-2.1.1-cp39-cp39-win_amd64.whl", hash = "sha256:46d00d6cfecdde84d40e572d63735ef81423ad31184100411e6e3388d405e247"},
+    {file = "MarkupSafe-2.1.1.tar.gz", hash = "sha256:7f91197cc9e48f989d12e4e6fbc46495c446636dfc81b9ccf50bb0ec74b91d4b"},
+]
+matplotlib = [
+    {file = "matplotlib-3.5.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:456cc8334f6d1124e8ff856b42d2cc1c84335375a16448189999496549f7182b"},
+    {file = "matplotlib-3.5.1-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:8a77906dc2ef9b67407cec0bdbf08e3971141e535db888974a915be5e1e3efc6"},
+    {file = "matplotlib-3.5.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8e70ae6475cfd0fad3816dcbf6cac536dc6f100f7474be58d59fa306e6e768a4"},
+    {file = "matplotlib-3.5.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:53273c5487d1c19c3bc03b9eb82adaf8456f243b97ed79d09dded747abaf1235"},
+    {file = "matplotlib-3.5.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e3b6f3fd0d8ca37861c31e9a7cab71a0ef14c639b4c95654ea1dd153158bf0df"},
+    {file = "matplotlib-3.5.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e8c87cdaf06fd7b2477f68909838ff4176f105064a72ca9d24d3f2a29f73d393"},
+    {file = "matplotlib-3.5.1-cp310-cp310-win32.whl", hash = "sha256:e2f28a07b4f82abb40267864ad7b3a4ed76f1b1663e81c7efc84a9b9248f672f"},
+    {file = "matplotlib-3.5.1-cp310-cp310-win_amd64.whl", hash = "sha256:d70a32ee1f8b55eed3fd4e892f0286df8cccc7e0475c11d33b5d0a148f5c7599"},
+    {file = "matplotlib-3.5.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:68fa30cec89b6139dc559ed6ef226c53fd80396da1919a1b5ef672c911aaa767"},
+    {file = "matplotlib-3.5.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2e3484d8455af3fdb0424eae1789af61f6a79da0c80079125112fd5c1b604218"},
+    {file = "matplotlib-3.5.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e293b16cf303fe82995e41700d172a58a15efc5331125d08246b520843ef21ee"},
+    {file = "matplotlib-3.5.1-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:e3520a274a0e054e919f5b3279ee5dbccf5311833819ccf3399dab7c83e90a25"},
+    {file = "matplotlib-3.5.1-cp37-cp37m-win32.whl", hash = "sha256:2252bfac85cec7af4a67e494bfccf9080bcba8a0299701eab075f48847cca907"},
+    {file = "matplotlib-3.5.1-cp37-cp37m-win_amd64.whl", hash = "sha256:abf67e05a1b7f86583f6ebd01f69b693b9c535276f4e943292e444855870a1b8"},
+    {file = "matplotlib-3.5.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:6c094e4bfecd2fa7f9adffd03d8abceed7157c928c2976899de282f3600f0a3d"},
+    {file = "matplotlib-3.5.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:506b210cc6e66a0d1c2bb765d055f4f6bc2745070fb1129203b67e85bbfa5c18"},
+    {file = "matplotlib-3.5.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:b04fc29bcef04d4e2d626af28d9d892be6aba94856cb46ed52bcb219ceac8943"},
+    {file = "matplotlib-3.5.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:577ed20ec9a18d6bdedb4616f5e9e957b4c08563a9f985563a31fd5b10564d2a"},
+    {file = "matplotlib-3.5.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e486f60db0cd1c8d68464d9484fd2a94011c1ac8593d765d0211f9daba2bd535"},
+    {file = "matplotlib-3.5.1-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:b71f3a7ca935fc759f2aed7cec06cfe10bc3100fadb5dbd9c435b04e557971e1"},
+    {file = "matplotlib-3.5.1-cp38-cp38-win32.whl", hash = "sha256:d24e5bb8028541ce25e59390122f5e48c8506b7e35587e5135efcb6471b4ac6c"},
+    {file = "matplotlib-3.5.1-cp38-cp38-win_amd64.whl", hash = "sha256:778d398c4866d8e36ee3bf833779c940b5f57192fa0a549b3ad67bc4c822771b"},
+    {file = "matplotlib-3.5.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:bb1c613908f11bac270bc7494d68b1ef6e7c224b7a4204d5dacf3522a41e2bc3"},
+    {file = "matplotlib-3.5.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:edf5e4e1d5fb22c18820e8586fb867455de3b109c309cb4fce3aaed85d9468d1"},
+    {file = "matplotlib-3.5.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:40e0d7df05e8efe60397c69b467fc8f87a2affeb4d562fe92b72ff8937a2b511"},
+    {file = "matplotlib-3.5.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7a350ca685d9f594123f652ba796ee37219bf72c8e0fc4b471473d87121d6d34"},
+    {file = "matplotlib-3.5.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:3e66497cd990b1a130e21919b004da2f1dc112132c01ac78011a90a0f9229778"},
+    {file = "matplotlib-3.5.1-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:87900c67c0f1728e6db17c6809ec05c025c6624dcf96a8020326ea15378fe8e7"},
+    {file = "matplotlib-3.5.1-cp39-cp39-win32.whl", hash = "sha256:b8a4fb2a0c5afbe9604f8a91d7d0f27b1832c3e0b5e365f95a13015822b4cd65"},
+    {file = "matplotlib-3.5.1-cp39-cp39-win_amd64.whl", hash = "sha256:fe8d40c434a8e2c68d64c6d6a04e77f21791a93ff6afe0dce169597c110d3079"},
+    {file = "matplotlib-3.5.1-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:34a1fc29f8f96e78ec57a5eff5e8d8b53d3298c3be6df61e7aa9efba26929522"},
+    {file = "matplotlib-3.5.1-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:b19a761b948e939a9e20173aaae76070025f0024fc8f7ba08bef22a5c8573afc"},
+    {file = "matplotlib-3.5.1-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:6803299cbf4665eca14428d9e886de62e24f4223ac31ab9c5d6d5339a39782c7"},
+    {file = "matplotlib-3.5.1-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:14334b9902ec776461c4b8c6516e26b450f7ebe0b3ef8703bf5cdfbbaecf774a"},
+    {file = "matplotlib-3.5.1.tar.gz", hash = "sha256:b2e9810e09c3a47b73ce9cab5a72243a1258f61e7900969097a817232246ce1c"},
+]
+matplotlib-inline = [
+    {file = "matplotlib-inline-0.1.3.tar.gz", hash = "sha256:a04bfba22e0d1395479f866853ec1ee28eea1485c1d69a6faf00dc3e24ff34ee"},
+    {file = "matplotlib_inline-0.1.3-py3-none-any.whl", hash = "sha256:aed605ba3b72462d64d475a21a9296f400a19c4f74a31b59103d2a99ffd5aa5c"},
+]
+mistune = [
+    {file = "mistune-0.8.4-py2.py3-none-any.whl", hash = "sha256:88a1051873018da288eee8538d476dffe1262495144b33ecb586c4ab266bb8d4"},
+    {file = "mistune-0.8.4.tar.gz", hash = "sha256:59a3429db53c50b5c6bcc8a07f8848cb00d7dc8bdb431a4ab41920d201d4756e"},
+]
+nbclient = [
+    {file = "nbclient-0.5.13-py3-none-any.whl", hash = "sha256:47ac905af59379913c1f8f541098d2550153cf8dc58553cbe18c702b181518b0"},
+    {file = "nbclient-0.5.13.tar.gz", hash = "sha256:40c52c9b5e3c31faecaee69f202b3f53e38d7c1c563de0fadde9d7eda0fdafe8"},
+]
+nbconvert = [
+    {file = "nbconvert-6.4.5-py3-none-any.whl", hash = "sha256:e01d219f55cc79f9701c834d605e8aa3acf35725345d3942e3983937f368ce14"},
+    {file = "nbconvert-6.4.5.tar.gz", hash = "sha256:21163a8e2073c07109ca8f398836e45efdba2aacea68d6f75a8a545fef070d4e"},
+]
+nbformat = [
+    {file = "nbformat-5.2.0-py3-none-any.whl", hash = "sha256:3e30424e8291b2188347f5c3ba5273ed3766f12f8c5137c2e456a0815f36e785"},
+    {file = "nbformat-5.2.0.tar.gz", hash = "sha256:93df0b9c67221d38fb970c48f6d361819a6c388299a0ef3171bbb912edfe1324"},
+]
+nest-asyncio = [
+    {file = "nest_asyncio-1.5.4-py3-none-any.whl", hash = "sha256:3fdd0d6061a2bb16f21fe8a9c6a7945be83521d81a0d15cff52e9edee50101d6"},
+    {file = "nest_asyncio-1.5.4.tar.gz", hash = "sha256:f969f6013a16fadb4adcf09d11a68a4f617c6049d7af7ac2c676110169a63abd"},
+]
+notebook = [
+    {file = "notebook-6.4.10-py3-none-any.whl", hash = "sha256:49cead814bff0945fcb2ee07579259418672ac175d3dc3d8102a4b0a656ed4df"},
+    {file = "notebook-6.4.10.tar.gz", hash = "sha256:2408a76bc6289283a8eecfca67e298ec83c67db51a4c2e1b713dd180bb39e90e"},
+]
+numpy = [
+    {file = "numpy-1.22.3-cp310-cp310-macosx_10_14_x86_64.whl", hash = "sha256:92bfa69cfbdf7dfc3040978ad09a48091143cffb778ec3b03fa170c494118d75"},
+    {file = "numpy-1.22.3-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:8251ed96f38b47b4295b1ae51631de7ffa8260b5b087808ef09a39a9d66c97ab"},
+    {file = "numpy-1.22.3-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:48a3aecd3b997bf452a2dedb11f4e79bc5bfd21a1d4cc760e703c31d57c84b3e"},
+    {file = "numpy-1.22.3-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:a3bae1a2ed00e90b3ba5f7bd0a7c7999b55d609e0c54ceb2b076a25e345fa9f4"},
+    {file = "numpy-1.22.3-cp310-cp310-win32.whl", hash = "sha256:f950f8845b480cffe522913d35567e29dd381b0dc7e4ce6a4a9f9156417d2430"},
+    {file = "numpy-1.22.3-cp310-cp310-win_amd64.whl", hash = "sha256:08d9b008d0156c70dc392bb3ab3abb6e7a711383c3247b410b39962263576cd4"},
+    {file = "numpy-1.22.3-cp38-cp38-macosx_10_14_x86_64.whl", hash = "sha256:201b4d0552831f7250a08d3b38de0d989d6f6e4658b709a02a73c524ccc6ffce"},
+    {file = "numpy-1.22.3-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:f8c1f39caad2c896bc0018f699882b345b2a63708008be29b1f355ebf6f933fe"},
+    {file = "numpy-1.22.3-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:568dfd16224abddafb1cbcce2ff14f522abe037268514dd7e42c6776a1c3f8e5"},
+    {file = "numpy-1.22.3-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ca688e1b9b95d80250bca34b11a05e389b1420d00e87a0d12dc45f131f704a1"},
+    {file = "numpy-1.22.3-cp38-cp38-win32.whl", hash = "sha256:e7927a589df200c5e23c57970bafbd0cd322459aa7b1ff73b7c2e84d6e3eae62"},
+    {file = "numpy-1.22.3-cp38-cp38-win_amd64.whl", hash = "sha256:07a8c89a04997625236c5ecb7afe35a02af3896c8aa01890a849913a2309c676"},
+    {file = "numpy-1.22.3-cp39-cp39-macosx_10_14_x86_64.whl", hash = "sha256:2c10a93606e0b4b95c9b04b77dc349b398fdfbda382d2a39ba5a822f669a0123"},
+    {file = "numpy-1.22.3-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:fade0d4f4d292b6f39951b6836d7a3c7ef5b2347f3c420cd9820a1d90d794802"},
+    {file = "numpy-1.22.3-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5bfb1bb598e8229c2d5d48db1860bcf4311337864ea3efdbe1171fb0c5da515d"},
+    {file = "numpy-1.22.3-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:97098b95aa4e418529099c26558eeb8486e66bd1e53a6b606d684d0c3616b168"},
+    {file = "numpy-1.22.3-cp39-cp39-win32.whl", hash = "sha256:fdf3c08bce27132395d3c3ba1503cac12e17282358cb4bddc25cc46b0aca07aa"},
+    {file = "numpy-1.22.3-cp39-cp39-win_amd64.whl", hash = "sha256:639b54cdf6aa4f82fe37ebf70401bbb74b8508fddcf4797f9fe59615b8c5813a"},
+    {file = "numpy-1.22.3-pp38-pypy38_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c34ea7e9d13a70bf2ab64a2532fe149a9aced424cd05a2c4ba662fd989e3e45f"},
+    {file = "numpy-1.22.3.zip", hash = "sha256:dbc7601a3b7472d559dc7b933b18b4b66f9aa7452c120e87dfb33d02008c8a18"},
+]
+packaging = [
+    {file = "packaging-21.3-py3-none-any.whl", hash = "sha256:ef103e05f519cdc783ae24ea4e2e0f508a9c99b2d4969652eed6a2e1ea5bd522"},
+    {file = "packaging-21.3.tar.gz", hash = "sha256:dd47c42927d89ab911e606518907cc2d3a1f38bbd026385970643f9c5b8ecfeb"},
+]
+pandocfilters = [
+    {file = "pandocfilters-1.5.0-py2.py3-none-any.whl", hash = "sha256:33aae3f25fd1a026079f5d27bdd52496f0e0803b3469282162bafdcbdf6ef14f"},
+    {file = "pandocfilters-1.5.0.tar.gz", hash = "sha256:0b679503337d233b4339a817bfc8c50064e2eff681314376a47cb582305a7a38"},
+]
+parso = [
+    {file = "parso-0.8.3-py2.py3-none-any.whl", hash = "sha256:c001d4636cd3aecdaf33cbb40aebb59b094be2a74c556778ef5576c175e19e75"},
+    {file = "parso-0.8.3.tar.gz", hash = "sha256:8c07be290bb59f03588915921e29e8a50002acaf2cdc5fa0e0114f91709fafa0"},
+]
+pexpect = [
+    {file = "pexpect-4.8.0-py2.py3-none-any.whl", hash = "sha256:0b48a55dcb3c05f3329815901ea4fc1537514d6ba867a152b581d69ae3710937"},
+    {file = "pexpect-4.8.0.tar.gz", hash = "sha256:fc65a43959d153d0114afe13997d439c22823a27cefceb5ff35c2178c6784c0c"},
+]
+pickleshare = [
+    {file = "pickleshare-0.7.5-py2.py3-none-any.whl", hash = "sha256:9649af414d74d4df115d5d718f82acb59c9d418196b7b4290ed47a12ce62df56"},
+    {file = "pickleshare-0.7.5.tar.gz", hash = "sha256:87683d47965c1da65cdacaf31c8441d12b8044cdec9aca500cd78fc2c683afca"},
+]
+pillow = [
+    {file = "Pillow-9.0.1-1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a5d24e1d674dd9d72c66ad3ea9131322819ff86250b30dc5821cbafcfa0b96b4"},
+    {file = "Pillow-9.0.1-1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:2632d0f846b7c7600edf53c48f8f9f1e13e62f66a6dbc15191029d950bfed976"},
+    {file = "Pillow-9.0.1-1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:b9618823bd237c0d2575283f2939655f54d51b4527ec3972907a927acbcc5bfc"},
+    {file = "Pillow-9.0.1-cp310-cp310-macosx_10_10_universal2.whl", hash = "sha256:9bfdb82cdfeccec50aad441afc332faf8606dfa5e8efd18a6692b5d6e79f00fd"},
+    {file = "Pillow-9.0.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:5100b45a4638e3c00e4d2320d3193bdabb2d75e79793af7c3eb139e4f569f16f"},
+    {file = "Pillow-9.0.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:528a2a692c65dd5cafc130de286030af251d2ee0483a5bf50c9348aefe834e8a"},
+    {file = "Pillow-9.0.1-cp310-cp310-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0f29d831e2151e0b7b39981756d201f7108d3d215896212ffe2e992d06bfe049"},
+    {file = "Pillow-9.0.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:855c583f268edde09474b081e3ddcd5cf3b20c12f26e0d434e1386cc5d318e7a"},
+    {file = "Pillow-9.0.1-cp310-cp310-win32.whl", hash = "sha256:d9d7942b624b04b895cb95af03a23407f17646815495ce4547f0e60e0b06f58e"},
+    {file = "Pillow-9.0.1-cp310-cp310-win_amd64.whl", hash = "sha256:81c4b81611e3a3cb30e59b0cf05b888c675f97e3adb2c8672c3154047980726b"},
+    {file = "Pillow-9.0.1-cp37-cp37m-macosx_10_10_x86_64.whl", hash = "sha256:413ce0bbf9fc6278b2d63309dfeefe452835e1c78398efb431bab0672fe9274e"},
+    {file = "Pillow-9.0.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:80fe64a6deb6fcfdf7b8386f2cf216d329be6f2781f7d90304351811fb591360"},
+    {file = "Pillow-9.0.1-cp37-cp37m-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cef9c85ccbe9bee00909758936ea841ef12035296c748aaceee535969e27d31b"},
+    {file = "Pillow-9.0.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1d19397351f73a88904ad1aee421e800fe4bbcd1aeee6435fb62d0a05ccd1030"},
+    {file = "Pillow-9.0.1-cp37-cp37m-win32.whl", hash = "sha256:d21237d0cd37acded35154e29aec853e945950321dd2ffd1a7d86fe686814669"},
+    {file = "Pillow-9.0.1-cp37-cp37m-win_amd64.whl", hash = "sha256:ede5af4a2702444a832a800b8eb7f0a7a1c0eed55b644642e049c98d589e5092"},
+    {file = "Pillow-9.0.1-cp38-cp38-macosx_10_10_x86_64.whl", hash = "sha256:b5b3f092fe345c03bca1e0b687dfbb39364b21ebb8ba90e3fa707374b7915204"},
+    {file = "Pillow-9.0.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:335ace1a22325395c4ea88e00ba3dc89ca029bd66bd5a3c382d53e44f0ccd77e"},
+    {file = "Pillow-9.0.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:db6d9fac65bd08cea7f3540b899977c6dee9edad959fa4eaf305940d9cbd861c"},
+    {file = "Pillow-9.0.1-cp38-cp38-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f154d173286a5d1863637a7dcd8c3437bb557520b01bddb0be0258dcb72696b5"},
+    {file = "Pillow-9.0.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:14d4b1341ac07ae07eb2cc682f459bec932a380c3b122f5540432d8977e64eae"},
+    {file = "Pillow-9.0.1-cp38-cp38-win32.whl", hash = "sha256:effb7749713d5317478bb3acb3f81d9d7c7f86726d41c1facca068a04cf5bb4c"},
+    {file = "Pillow-9.0.1-cp38-cp38-win_amd64.whl", hash = "sha256:7f7609a718b177bf171ac93cea9fd2ddc0e03e84d8fa4e887bdfc39671d46b00"},
+    {file = "Pillow-9.0.1-cp39-cp39-macosx_10_10_x86_64.whl", hash = "sha256:80ca33961ced9c63358056bd08403ff866512038883e74f3a4bf88ad3eb66838"},
+    {file = "Pillow-9.0.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1c3c33ac69cf059bbb9d1a71eeaba76781b450bc307e2291f8a4764d779a6b28"},
+    {file = "Pillow-9.0.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:12875d118f21cf35604176872447cdb57b07126750a33748bac15e77f90f1f9c"},
+    {file = "Pillow-9.0.1-cp39-cp39-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:514ceac913076feefbeaf89771fd6febde78b0c4c1b23aaeab082c41c694e81b"},
+    {file = "Pillow-9.0.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d3c5c79ab7dfce6d88f1ba639b77e77a17ea33a01b07b99840d6ed08031cb2a7"},
+    {file = "Pillow-9.0.1-cp39-cp39-win32.whl", hash = "sha256:718856856ba31f14f13ba885ff13874be7fefc53984d2832458f12c38205f7f7"},
+    {file = "Pillow-9.0.1-cp39-cp39-win_amd64.whl", hash = "sha256:f25ed6e28ddf50de7e7ea99d7a976d6a9c415f03adcaac9c41ff6ff41b6d86ac"},
+    {file = "Pillow-9.0.1-pp37-pypy37_pp73-macosx_10_10_x86_64.whl", hash = "sha256:011233e0c42a4a7836498e98c1acf5e744c96a67dd5032a6f666cc1fb97eab97"},
+    {file = "Pillow-9.0.1-pp37-pypy37_pp73-manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:253e8a302a96df6927310a9d44e6103055e8fb96a6822f8b7f514bb7ef77de56"},
+    {file = "Pillow-9.0.1-pp37-pypy37_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6295f6763749b89c994fcb6d8a7f7ce03c3992e695f89f00b741b4580b199b7e"},
+    {file = "Pillow-9.0.1-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:a9f44cd7e162ac6191491d7249cceb02b8116b0f7e847ee33f739d7cb1ea1f70"},
+    {file = "Pillow-9.0.1.tar.gz", hash = "sha256:6c8bc8238a7dfdaf7a75f5ec5a663f4173f8c367e5a39f87e720495e1eed75fa"},
+]
+prometheus-client = [
+    {file = "prometheus_client-0.13.1-py3-none-any.whl", hash = "sha256:357a447fd2359b0a1d2e9b311a0c5778c330cfbe186d880ad5a6b39884652316"},
+    {file = "prometheus_client-0.13.1.tar.gz", hash = "sha256:ada41b891b79fca5638bd5cfe149efa86512eaa55987893becd2c6d8d0a5dfc5"},
+]
+prompt-toolkit = [
+    {file = "prompt_toolkit-3.0.28-py3-none-any.whl", hash = "sha256:30129d870dcb0b3b6a53efdc9d0a83ea96162ffd28ffe077e94215b233dc670c"},
+    {file = "prompt_toolkit-3.0.28.tar.gz", hash = "sha256:9f1cd16b1e86c2968f2519d7fb31dd9d669916f515612c269d14e9ed52b51650"},
+]
+psutil = [
+    {file = "psutil-5.9.0-cp27-cp27m-manylinux2010_i686.whl", hash = "sha256:55ce319452e3d139e25d6c3f85a1acf12d1607ddedea5e35fb47a552c051161b"},
+    {file = "psutil-5.9.0-cp27-cp27m-manylinux2010_x86_64.whl", hash = "sha256:7336292a13a80eb93c21f36bde4328aa748a04b68c13d01dfddd67fc13fd0618"},
+    {file = "psutil-5.9.0-cp27-cp27mu-manylinux2010_i686.whl", hash = "sha256:cb8d10461c1ceee0c25a64f2dd54872b70b89c26419e147a05a10b753ad36ec2"},
+    {file = "psutil-5.9.0-cp27-cp27mu-manylinux2010_x86_64.whl", hash = "sha256:7641300de73e4909e5d148e90cc3142fb890079e1525a840cf0dfd39195239fd"},
+    {file = "psutil-5.9.0-cp27-none-win32.whl", hash = "sha256:ea42d747c5f71b5ccaa6897b216a7dadb9f52c72a0fe2b872ef7d3e1eacf3ba3"},
+    {file = "psutil-5.9.0-cp27-none-win_amd64.whl", hash = "sha256:ef216cc9feb60634bda2f341a9559ac594e2eeaadd0ba187a4c2eb5b5d40b91c"},
+    {file = "psutil-5.9.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:90a58b9fcae2dbfe4ba852b57bd4a1dded6b990a33d6428c7614b7d48eccb492"},
+    {file = "psutil-5.9.0-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ff0d41f8b3e9ebb6b6110057e40019a432e96aae2008951121ba4e56040b84f3"},
+    {file = "psutil-5.9.0-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:742c34fff804f34f62659279ed5c5b723bb0195e9d7bd9907591de9f8f6558e2"},
+    {file = "psutil-5.9.0-cp310-cp310-win32.whl", hash = "sha256:8293942e4ce0c5689821f65ce6522ce4786d02af57f13c0195b40e1edb1db61d"},
+    {file = "psutil-5.9.0-cp310-cp310-win_amd64.whl", hash = "sha256:9b51917c1af3fa35a3f2dabd7ba96a2a4f19df3dec911da73875e1edaf22a40b"},
+    {file = "psutil-5.9.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:e9805fed4f2a81de98ae5fe38b75a74c6e6ad2df8a5c479594c7629a1fe35f56"},
+    {file = "psutil-5.9.0-cp36-cp36m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c51f1af02334e4b516ec221ee26b8fdf105032418ca5a5ab9737e8c87dafe203"},
+    {file = "psutil-5.9.0-cp36-cp36m-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:32acf55cb9a8cbfb29167cd005951df81b567099295291bcfd1027365b36591d"},
+    {file = "psutil-5.9.0-cp36-cp36m-win32.whl", hash = "sha256:e5c783d0b1ad6ca8a5d3e7b680468c9c926b804be83a3a8e95141b05c39c9f64"},
+    {file = "psutil-5.9.0-cp36-cp36m-win_amd64.whl", hash = "sha256:d62a2796e08dd024b8179bd441cb714e0f81226c352c802fca0fd3f89eeacd94"},
+    {file = "psutil-5.9.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:3d00a664e31921009a84367266b35ba0aac04a2a6cad09c550a89041034d19a0"},
+    {file = "psutil-5.9.0-cp37-cp37m-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:7779be4025c540d1d65a2de3f30caeacc49ae7a2152108adeaf42c7534a115ce"},
+    {file = "psutil-5.9.0-cp37-cp37m-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:072664401ae6e7c1bfb878c65d7282d4b4391f1bc9a56d5e03b5a490403271b5"},
+    {file = "psutil-5.9.0-cp37-cp37m-win32.whl", hash = "sha256:df2c8bd48fb83a8408c8390b143c6a6fa10cb1a674ca664954de193fdcab36a9"},
+    {file = "psutil-5.9.0-cp37-cp37m-win_amd64.whl", hash = "sha256:1d7b433519b9a38192dfda962dd8f44446668c009833e1429a52424624f408b4"},
+    {file = "psutil-5.9.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:c3400cae15bdb449d518545cbd5b649117de54e3596ded84aacabfbb3297ead2"},
+    {file = "psutil-5.9.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b2237f35c4bbae932ee98902a08050a27821f8f6dfa880a47195e5993af4702d"},
+    {file = "psutil-5.9.0-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:1070a9b287846a21a5d572d6dddd369517510b68710fca56b0e9e02fd24bed9a"},
+    {file = "psutil-5.9.0-cp38-cp38-win32.whl", hash = "sha256:76cebf84aac1d6da5b63df11fe0d377b46b7b500d892284068bacccf12f20666"},
+    {file = "psutil-5.9.0-cp38-cp38-win_amd64.whl", hash = "sha256:3151a58f0fbd8942ba94f7c31c7e6b310d2989f4da74fcbf28b934374e9bf841"},
+    {file = "psutil-5.9.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:539e429da49c5d27d5a58e3563886057f8fc3868a5547b4f1876d9c0f007bccf"},
+    {file = "psutil-5.9.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:58c7d923dc209225600aec73aa2c4ae8ea33b1ab31bc11ef8a5933b027476f07"},
+    {file = "psutil-5.9.0-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3611e87eea393f779a35b192b46a164b1d01167c9d323dda9b1e527ea69d697d"},
+    {file = "psutil-5.9.0-cp39-cp39-win32.whl", hash = "sha256:4e2fb92e3aeae3ec3b7b66c528981fd327fb93fd906a77215200404444ec1845"},
+    {file = "psutil-5.9.0-cp39-cp39-win_amd64.whl", hash = "sha256:7d190ee2eaef7831163f254dc58f6d2e2a22e27382b936aab51c835fc080c3d3"},
+    {file = "psutil-5.9.0.tar.gz", hash = "sha256:869842dbd66bb80c3217158e629d6fceaecc3a3166d3d1faee515b05dd26ca25"},
+]
+ptyprocess = [
+    {file = "ptyprocess-0.7.0-py2.py3-none-any.whl", hash = "sha256:4b41f3967fce3af57cc7e94b888626c18bf37a083e3651ca8feeb66d492fef35"},
+    {file = "ptyprocess-0.7.0.tar.gz", hash = "sha256:5c5d0a3b48ceee0b48485e0c26037c0acd7d29765ca3fbb5cb3831d347423220"},
+]
+pure-eval = [
+    {file = "pure_eval-0.2.2-py3-none-any.whl", hash = "sha256:01eaab343580944bc56080ebe0a674b39ec44a945e6d09ba7db3cb8cec289350"},
+    {file = "pure_eval-0.2.2.tar.gz", hash = "sha256:2b45320af6dfaa1750f543d714b6d1c520a1688dec6fd24d339063ce0aaa9ac3"},
+]
+py = [
+    {file = "py-1.11.0-py2.py3-none-any.whl", hash = "sha256:607c53218732647dff4acdfcd50cb62615cedf612e72d1724fb1a0cc6405b378"},
+    {file = "py-1.11.0.tar.gz", hash = "sha256:51c75c4126074b472f746a24399ad32f6053d1b34b68d2fa41e558e6f4a98719"},
+]
+pycparser = [
+    {file = "pycparser-2.21-py2.py3-none-any.whl", hash = "sha256:8ee45429555515e1f6b185e78100aea234072576aa43ab53aefcae078162fca9"},
+    {file = "pycparser-2.21.tar.gz", hash = "sha256:e644fdec12f7872f86c58ff790da456218b10f863970249516d60a5eaca77206"},
+]
+pygments = [
+    {file = "Pygments-2.11.2-py3-none-any.whl", hash = "sha256:44238f1b60a76d78fc8ca0528ee429702aae011c265fe6a8dd8b63049ae41c65"},
+    {file = "Pygments-2.11.2.tar.gz", hash = "sha256:4e426f72023d88d03b2fa258de560726ce890ff3b630f88c21cbb8b2503b8c6a"},
+]
+pyparsing = [
+    {file = "pyparsing-3.0.7-py3-none-any.whl", hash = "sha256:a6c06a88f252e6c322f65faf8f418b16213b51bdfaece0524c1c1bc30c63c484"},
+    {file = "pyparsing-3.0.7.tar.gz", hash = "sha256:18ee9022775d270c55187733956460083db60b37d0d0fb357445f3094eed3eea"},
+]
+pyrsistent = [
+    {file = "pyrsistent-0.18.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:df46c854f490f81210870e509818b729db4488e1f30f2a1ce1698b2295a878d1"},
+    {file = "pyrsistent-0.18.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5d45866ececf4a5fff8742c25722da6d4c9e180daa7b405dc0a2a2790d668c26"},
+    {file = "pyrsistent-0.18.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4ed6784ceac462a7d6fcb7e9b663e93b9a6fb373b7f43594f9ff68875788e01e"},
+    {file = "pyrsistent-0.18.1-cp310-cp310-win32.whl", hash = "sha256:e4f3149fd5eb9b285d6bfb54d2e5173f6a116fe19172686797c056672689daf6"},
+    {file = "pyrsistent-0.18.1-cp310-cp310-win_amd64.whl", hash = "sha256:636ce2dc235046ccd3d8c56a7ad54e99d5c1cd0ef07d9ae847306c91d11b5fec"},
+    {file = "pyrsistent-0.18.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:e92a52c166426efbe0d1ec1332ee9119b6d32fc1f0bbfd55d5c1088070e7fc1b"},
+    {file = "pyrsistent-0.18.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d7a096646eab884bf8bed965bad63ea327e0d0c38989fc83c5ea7b8a87037bfc"},
+    {file = "pyrsistent-0.18.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:cdfd2c361b8a8e5d9499b9082b501c452ade8bbf42aef97ea04854f4a3f43b22"},
+    {file = "pyrsistent-0.18.1-cp37-cp37m-win32.whl", hash = "sha256:7ec335fc998faa4febe75cc5268a9eac0478b3f681602c1f27befaf2a1abe1d8"},
+    {file = "pyrsistent-0.18.1-cp37-cp37m-win_amd64.whl", hash = "sha256:6455fc599df93d1f60e1c5c4fe471499f08d190d57eca040c0ea182301321286"},
+    {file = "pyrsistent-0.18.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:fd8da6d0124efa2f67d86fa70c851022f87c98e205f0594e1fae044e7119a5a6"},
+    {file = "pyrsistent-0.18.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:7bfe2388663fd18bd8ce7db2c91c7400bf3e1a9e8bd7d63bf7e77d39051b85ec"},
+    {file = "pyrsistent-0.18.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0e3e1fcc45199df76053026a51cc59ab2ea3fc7c094c6627e93b7b44cdae2c8c"},
+    {file = "pyrsistent-0.18.1-cp38-cp38-win32.whl", hash = "sha256:b568f35ad53a7b07ed9b1b2bae09eb15cdd671a5ba5d2c66caee40dbf91c68ca"},
+    {file = "pyrsistent-0.18.1-cp38-cp38-win_amd64.whl", hash = "sha256:d1b96547410f76078eaf66d282ddca2e4baae8964364abb4f4dcdde855cd123a"},
+    {file = "pyrsistent-0.18.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:f87cc2863ef33c709e237d4b5f4502a62a00fab450c9e020892e8e2ede5847f5"},
+    {file = "pyrsistent-0.18.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6bc66318fb7ee012071b2792024564973ecc80e9522842eb4e17743604b5e045"},
+    {file = "pyrsistent-0.18.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:914474c9f1d93080338ace89cb2acee74f4f666fb0424896fcfb8d86058bf17c"},
+    {file = "pyrsistent-0.18.1-cp39-cp39-win32.whl", hash = "sha256:1b34eedd6812bf4d33814fca1b66005805d3640ce53140ab8bbb1e2651b0d9bc"},
+    {file = "pyrsistent-0.18.1-cp39-cp39-win_amd64.whl", hash = "sha256:e24a828f57e0c337c8d8bb9f6b12f09dfdf0273da25fda9e314f0b684b415a07"},
+    {file = "pyrsistent-0.18.1.tar.gz", hash = "sha256:d4d61f8b993a7255ba714df3aca52700f8125289f84f704cf80916517c46eb96"},
+]
+python-dateutil = [
+    {file = "python-dateutil-2.8.2.tar.gz", hash = "sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86"},
+    {file = "python_dateutil-2.8.2-py2.py3-none-any.whl", hash = "sha256:961d03dc3453ebbc59dbdea9e4e11c5651520a876d0f4db161e8674aae935da9"},
+]
+pywin32 = [
+    {file = "pywin32-303-cp310-cp310-win32.whl", hash = "sha256:6fed4af057039f309263fd3285d7b8042d41507343cd5fa781d98fcc5b90e8bb"},
+    {file = "pywin32-303-cp310-cp310-win_amd64.whl", hash = "sha256:51cb52c5ec6709f96c3f26e7795b0bf169ee0d8395b2c1d7eb2c029a5008ed51"},
+    {file = "pywin32-303-cp311-cp311-win32.whl", hash = "sha256:d9b5d87ca944eb3aa4cd45516203ead4b37ab06b8b777c54aedc35975dec0dee"},
+    {file = "pywin32-303-cp311-cp311-win_amd64.whl", hash = "sha256:fcf44032f5b14fcda86028cdf49b6ebdaea091230eb0a757282aa656e4732439"},
+    {file = "pywin32-303-cp36-cp36m-win32.whl", hash = "sha256:aad484d52ec58008ca36bd4ad14a71d7dd0a99db1a4ca71072213f63bf49c7d9"},
+    {file = "pywin32-303-cp36-cp36m-win_amd64.whl", hash = "sha256:2a09632916b6bb231ba49983fe989f2f625cea237219530e81a69239cd0c4559"},
+    {file = "pywin32-303-cp37-cp37m-win32.whl", hash = "sha256:b1675d82bcf6dbc96363fca747bac8bff6f6e4a447a4287ac652aa4b9adc796e"},
+    {file = "pywin32-303-cp37-cp37m-win_amd64.whl", hash = "sha256:c268040769b48a13367221fced6d4232ed52f044ffafeda247bd9d2c6bdc29ca"},
+    {file = "pywin32-303-cp38-cp38-win32.whl", hash = "sha256:5f9ec054f5a46a0f4dfd72af2ce1372f3d5a6e4052af20b858aa7df2df7d355b"},
+    {file = "pywin32-303-cp38-cp38-win_amd64.whl", hash = "sha256:793bf74fce164bcffd9d57bb13c2c15d56e43c9542a7b9687b4fccf8f8a41aba"},
+    {file = "pywin32-303-cp39-cp39-win32.whl", hash = "sha256:7d3271c98434617a11921c5ccf74615794d97b079e22ed7773790822735cc352"},
+    {file = "pywin32-303-cp39-cp39-win_amd64.whl", hash = "sha256:79cbb862c11b9af19bcb682891c1b91942ec2ff7de8151e2aea2e175899cda34"},
+]
+pywinpty = [
+    {file = "pywinpty-2.0.5-cp310-none-win_amd64.whl", hash = "sha256:f86c76e2881c37e69678cbbf178109f8da1fa8584db24d58e1b9369b0276cfcb"},
+    {file = "pywinpty-2.0.5-cp37-none-win_amd64.whl", hash = "sha256:ff9b52f182650cfdf3db1b264a6fe0963eb9d996a7a1fa843ac406c1e32111f8"},
+    {file = "pywinpty-2.0.5-cp38-none-win_amd64.whl", hash = "sha256:651ee1467bd7eb6f64d44dbc954b7ab7d15ab6d8adacc4e13299692c67c5d5d2"},
+    {file = "pywinpty-2.0.5-cp39-none-win_amd64.whl", hash = "sha256:e59a508ae78374febada3e53b5bbc90b5ad07ae68cbfd72a2e965f9793ae04f3"},
+    {file = "pywinpty-2.0.5.tar.gz", hash = "sha256:e125d3f1804d8804952b13e33604ad2ca8b9b2cac92b27b521c005d1604794f8"},
+]
+pyzmq = [
+    {file = "pyzmq-22.3.0-cp310-cp310-macosx_10_15_universal2.whl", hash = "sha256:6b217b8f9dfb6628f74b94bdaf9f7408708cb02167d644edca33f38746ca12dd"},
+    {file = "pyzmq-22.3.0-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:2841997a0d85b998cbafecb4183caf51fd19c4357075dfd33eb7efea57e4c149"},
+    {file = "pyzmq-22.3.0-cp310-cp310-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:f89468059ebc519a7acde1ee50b779019535db8dcf9b8c162ef669257fef7a93"},
+    {file = "pyzmq-22.3.0-cp310-cp310-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:ea12133df25e3a6918718fbb9a510c6ee5d3fdd5a346320421aac3882f4feeea"},
+    {file = "pyzmq-22.3.0-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:76c532fd68b93998aab92356be280deec5de8f8fe59cd28763d2cc8a58747b7f"},
+    {file = "pyzmq-22.3.0-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:f907c7359ce8bf7f7e63c82f75ad0223384105f5126f313400b7e8004d9b33c3"},
+    {file = "pyzmq-22.3.0-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:902319cfe23366595d3fa769b5b751e6ee6750a0a64c5d9f757d624b2ac3519e"},
+    {file = "pyzmq-22.3.0-cp310-cp310-win32.whl", hash = "sha256:67db33bea0a29d03e6eeec55a8190e033318cee3cbc732ba8fd939617cbf762d"},
+    {file = "pyzmq-22.3.0-cp310-cp310-win_amd64.whl", hash = "sha256:7661fc1d5cb73481cf710a1418a4e1e301ed7d5d924f91c67ba84b2a1b89defd"},
+    {file = "pyzmq-22.3.0-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:79244b9e97948eaf38695f4b8e6fc63b14b78cc37f403c6642ba555517ac1268"},
+    {file = "pyzmq-22.3.0-cp36-cp36m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ab888624ed68930442a3f3b0b921ad7439c51ba122dbc8c386e6487a658e4a4e"},
+    {file = "pyzmq-22.3.0-cp36-cp36m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:18cd854b423fce44951c3a4d3e686bac8f1243d954f579e120a1714096637cc0"},
+    {file = "pyzmq-22.3.0-cp36-cp36m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:de8df0684398bd74ad160afdc2a118ca28384ac6f5e234eb0508858d8d2d9364"},
+    {file = "pyzmq-22.3.0-cp36-cp36m-musllinux_1_1_i686.whl", hash = "sha256:62bcade20813796c426409a3e7423862d50ff0639f5a2a95be4b85b09a618666"},
+    {file = "pyzmq-22.3.0-cp36-cp36m-musllinux_1_1_x86_64.whl", hash = "sha256:ea5a79e808baef98c48c884effce05c31a0698c1057de8fc1c688891043c1ce1"},
+    {file = "pyzmq-22.3.0-cp36-cp36m-win32.whl", hash = "sha256:3c1895c95be92600233e476fe283f042e71cf8f0b938aabf21b7aafa62a8dac9"},
+    {file = "pyzmq-22.3.0-cp36-cp36m-win_amd64.whl", hash = "sha256:851977788b9caa8ed011f5f643d3ee8653af02c5fc723fa350db5125abf2be7b"},
+    {file = "pyzmq-22.3.0-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:b4ebed0977f92320f6686c96e9e8dd29eed199eb8d066936bac991afc37cbb70"},
+    {file = "pyzmq-22.3.0-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:42abddebe2c6a35180ca549fadc7228d23c1e1f76167c5ebc8a936b5804ea2df"},
+    {file = "pyzmq-22.3.0-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:c1e41b32d6f7f9c26bc731a8b529ff592f31fc8b6ef2be9fa74abd05c8a342d7"},
+    {file = "pyzmq-22.3.0-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.whl", hash = "sha256:be4e0f229cf3a71f9ecd633566bd6f80d9fa6afaaff5489492be63fe459ef98c"},
+    {file = "pyzmq-22.3.0-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:08c4e315a76ef26eb833511ebf3fa87d182152adf43dedee8d79f998a2162a0b"},
+    {file = "pyzmq-22.3.0-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:badb868fff14cfd0e200eaa845887b1011146a7d26d579aaa7f966c203736b92"},
+    {file = "pyzmq-22.3.0-cp37-cp37m-win32.whl", hash = "sha256:7c58f598d9fcc52772b89a92d72bf8829c12d09746a6d2c724c5b30076c1f11d"},
+    {file = "pyzmq-22.3.0-cp37-cp37m-win_amd64.whl", hash = "sha256:2b97502c16a5ec611cd52410bdfaab264997c627a46b0f98d3f666227fd1ea2d"},
+    {file = "pyzmq-22.3.0-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:d728b08448e5ac3e4d886b165385a262883c34b84a7fe1166277fe675e1c197a"},
+    {file = "pyzmq-22.3.0-cp38-cp38-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:480b9931bfb08bf8b094edd4836271d4d6b44150da051547d8c7113bf947a8b0"},
+    {file = "pyzmq-22.3.0-cp38-cp38-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:7dc09198e4073e6015d9a8ea093fc348d4e59de49382476940c3dd9ae156fba8"},
+    {file = "pyzmq-22.3.0-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0ca6cd58f62a2751728016d40082008d3b3412a7f28ddfb4a2f0d3c130f69e74"},
+    {file = "pyzmq-22.3.0-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:468bd59a588e276961a918a3060948ae68f6ff5a7fa10bb2f9160c18fe341067"},
+    {file = "pyzmq-22.3.0-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:c88fa7410e9fc471e0858638f403739ee869924dd8e4ae26748496466e27ac59"},
+    {file = "pyzmq-22.3.0-cp38-cp38-win32.whl", hash = "sha256:c0f84360dcca3481e8674393bdf931f9f10470988f87311b19d23cda869bb6b7"},
+    {file = "pyzmq-22.3.0-cp38-cp38-win_amd64.whl", hash = "sha256:f762442bab706fd874064ca218b33a1d8e40d4938e96c24dafd9b12e28017f45"},
+    {file = "pyzmq-22.3.0-cp39-cp39-macosx_10_15_universal2.whl", hash = "sha256:954e73c9cd4d6ae319f1c936ad159072b6d356a92dcbbabfd6e6204b9a79d356"},
+    {file = "pyzmq-22.3.0-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:f43b4a2e6218371dd4f41e547bd919ceeb6ebf4abf31a7a0669cd11cd91ea973"},
+    {file = "pyzmq-22.3.0-cp39-cp39-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:acebba1a23fb9d72b42471c3771b6f2f18dcd46df77482612054bd45c07dfa36"},
+    {file = "pyzmq-22.3.0-cp39-cp39-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:cf98fd7a6c8aaa08dbc699ffae33fd71175696d78028281bc7b832b26f00ca57"},
+    {file = "pyzmq-22.3.0-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d072f7dfbdb184f0786d63bda26e8a0882041b1e393fbe98940395f7fab4c5e2"},
+    {file = "pyzmq-22.3.0-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:53f4fd13976789ffafedd4d46f954c7bb01146121812b72b4ddca286034df966"},
+    {file = "pyzmq-22.3.0-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:d1b5d457acbadcf8b27561deeaa386b0217f47626b29672fa7bd31deb6e91e1b"},
+    {file = "pyzmq-22.3.0-cp39-cp39-win32.whl", hash = "sha256:e6a02cf7271ee94674a44f4e62aa061d2d049001c844657740e156596298b70b"},
+    {file = "pyzmq-22.3.0-cp39-cp39-win_amd64.whl", hash = "sha256:d3dcb5548ead4f1123851a5ced467791f6986d68c656bc63bfff1bf9e36671e2"},
+    {file = "pyzmq-22.3.0-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:3a4c9886d61d386b2b493377d980f502186cd71d501fffdba52bd2a0880cef4f"},
+    {file = "pyzmq-22.3.0-pp37-pypy37_pp73-manylinux_2_12_i686.manylinux2010_i686.whl", hash = "sha256:80e043a89c6cadefd3a0712f8a1322038e819ebe9dbac7eca3bce1721bcb63bf"},
+    {file = "pyzmq-22.3.0-pp37-pypy37_pp73-manylinux_2_12_x86_64.manylinux2010_x86_64.whl", hash = "sha256:1621e7a2af72cced1f6ec8ca8ca91d0f76ac236ab2e8828ac8fe909512d566cb"},
+    {file = "pyzmq-22.3.0-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:d6157793719de168b199194f6b6173f0ccd3bf3499e6870fac17086072e39115"},
+    {file = "pyzmq-22.3.0.tar.gz", hash = "sha256:8eddc033e716f8c91c6a2112f0a8ebc5e00532b4a6ae1eb0ccc48e027f9c671c"},
+]
+qtconsole = [
+    {file = "qtconsole-5.3.0-py3-none-any.whl", hash = "sha256:75f2ded876444454edcb5a53262149e33b53db3a4a53116b7c3df52830905b0f"},
+    {file = "qtconsole-5.3.0.tar.gz", hash = "sha256:8e3520fdc75e46abc4cc6cffeca16fa2652754109b8ae839fa28e27d1eba5625"},
+]
+qtpy = [
+    {file = "QtPy-2.0.1-py3-none-any.whl", hash = "sha256:d93f2c98e97387fcc9d623d509772af5b6c15ab9d8f9f4c5dfbad9a73ad34812"},
+    {file = "QtPy-2.0.1.tar.gz", hash = "sha256:adfd073ffbd2de81dc7aaa0b983499ef5c59c96adcfdcc9dea60d42ca885eb8f"},
+]
+send2trash = [
+    {file = "Send2Trash-1.8.0-py3-none-any.whl", hash = "sha256:f20eaadfdb517eaca5ce077640cb261c7d2698385a6a0f072a4a5447fd49fa08"},
+    {file = "Send2Trash-1.8.0.tar.gz", hash = "sha256:d2c24762fd3759860a0aff155e45871447ea58d2be6bdd39b5c8f966a0c99c2d"},
+]
+setuptools-scm = [
+    {file = "setuptools_scm-6.4.2-py3-none-any.whl", hash = "sha256:acea13255093849de7ccb11af9e1fb8bde7067783450cee9ef7a93139bddf6d4"},
+    {file = "setuptools_scm-6.4.2.tar.gz", hash = "sha256:6833ac65c6ed9711a4d5d2266f8024cfa07c533a0e55f4c12f6eff280a5a9e30"},
+]
+six = [
+    {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
+    {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
+]
+soupsieve = [
+    {file = "soupsieve-2.3.1-py3-none-any.whl", hash = "sha256:1a3cca2617c6b38c0343ed661b1fa5de5637f257d4fe22bd9f1338010a1efefb"},
+    {file = "soupsieve-2.3.1.tar.gz", hash = "sha256:b8d49b1cd4f037c7082a9683dfa1801aa2597fb11c3a1155b7a5b94829b4f1f9"},
+]
+stack-data = [
+    {file = "stack_data-0.2.0-py3-none-any.whl", hash = "sha256:999762f9c3132308789affa03e9271bbbe947bf78311851f4d485d8402ed858e"},
+    {file = "stack_data-0.2.0.tar.gz", hash = "sha256:45692d41bd633a9503a5195552df22b583caf16f0b27c4e58c98d88c8b648e12"},
+]
+terminado = [
+    {file = "terminado-0.13.3-py3-none-any.whl", hash = "sha256:874d4ea3183536c1782d13c7c91342ef0cf4e5ee1d53633029cbc972c8760bd8"},
+    {file = "terminado-0.13.3.tar.gz", hash = "sha256:94d1cfab63525993f7d5c9b469a50a18d0cdf39435b59785715539dd41e36c0d"},
+]
+testpath = [
+    {file = "testpath-0.6.0-py3-none-any.whl", hash = "sha256:8ada9f80a2ac6fb0391aa7cdb1a7d11cfa8429f693eda83f74dde570fe6fa639"},
+    {file = "testpath-0.6.0.tar.gz", hash = "sha256:2f1b97e6442c02681ebe01bd84f531028a7caea1af3825000f52345c30285e0f"},
+]
+tomli = [
+    {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
+    {file = "tomli-2.0.1.tar.gz", hash = "sha256:de526c12914f0c550d15924c62d72abc48d6fe7364aa87328337a31007fe8a4f"},
+]
+tornado = [
+    {file = "tornado-6.1-cp35-cp35m-macosx_10_9_x86_64.whl", hash = "sha256:d371e811d6b156d82aa5f9a4e08b58debf97c302a35714f6f45e35139c332e32"},
+    {file = "tornado-6.1-cp35-cp35m-manylinux1_i686.whl", hash = "sha256:0d321a39c36e5f2c4ff12b4ed58d41390460f798422c4504e09eb5678e09998c"},
+    {file = "tornado-6.1-cp35-cp35m-manylinux1_x86_64.whl", hash = "sha256:9de9e5188a782be6b1ce866e8a51bc76a0fbaa0e16613823fc38e4fc2556ad05"},
+    {file = "tornado-6.1-cp35-cp35m-manylinux2010_i686.whl", hash = "sha256:61b32d06ae8a036a6607805e6720ef00a3c98207038444ba7fd3d169cd998910"},
+    {file = "tornado-6.1-cp35-cp35m-manylinux2010_x86_64.whl", hash = "sha256:3e63498f680547ed24d2c71e6497f24bca791aca2fe116dbc2bd0ac7f191691b"},
+    {file = "tornado-6.1-cp35-cp35m-manylinux2014_aarch64.whl", hash = "sha256:6c77c9937962577a6a76917845d06af6ab9197702a42e1346d8ae2e76b5e3675"},
+    {file = "tornado-6.1-cp35-cp35m-win32.whl", hash = "sha256:6286efab1ed6e74b7028327365cf7346b1d777d63ab30e21a0f4d5b275fc17d5"},
+    {file = "tornado-6.1-cp35-cp35m-win_amd64.whl", hash = "sha256:fa2ba70284fa42c2a5ecb35e322e68823288a4251f9ba9cc77be04ae15eada68"},
+    {file = "tornado-6.1-cp36-cp36m-macosx_10_9_x86_64.whl", hash = "sha256:0a00ff4561e2929a2c37ce706cb8233b7907e0cdc22eab98888aca5dd3775feb"},
+    {file = "tornado-6.1-cp36-cp36m-manylinux1_i686.whl", hash = "sha256:748290bf9112b581c525e6e6d3820621ff020ed95af6f17fedef416b27ed564c"},
+    {file = "tornado-6.1-cp36-cp36m-manylinux1_x86_64.whl", hash = "sha256:e385b637ac3acaae8022e7e47dfa7b83d3620e432e3ecb9a3f7f58f150e50921"},
+    {file = "tornado-6.1-cp36-cp36m-manylinux2010_i686.whl", hash = "sha256:25ad220258349a12ae87ede08a7b04aca51237721f63b1808d39bdb4b2164558"},
+    {file = "tornado-6.1-cp36-cp36m-manylinux2010_x86_64.whl", hash = "sha256:65d98939f1a2e74b58839f8c4dab3b6b3c1ce84972ae712be02845e65391ac7c"},
+    {file = "tornado-6.1-cp36-cp36m-manylinux2014_aarch64.whl", hash = "sha256:e519d64089b0876c7b467274468709dadf11e41d65f63bba207e04217f47c085"},
+    {file = "tornado-6.1-cp36-cp36m-win32.whl", hash = "sha256:b87936fd2c317b6ee08a5741ea06b9d11a6074ef4cc42e031bc6403f82a32575"},
+    {file = "tornado-6.1-cp36-cp36m-win_amd64.whl", hash = "sha256:cc0ee35043162abbf717b7df924597ade8e5395e7b66d18270116f8745ceb795"},
+    {file = "tornado-6.1-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:7250a3fa399f08ec9cb3f7b1b987955d17e044f1ade821b32e5f435130250d7f"},
+    {file = "tornado-6.1-cp37-cp37m-manylinux1_i686.whl", hash = "sha256:ed3ad863b1b40cd1d4bd21e7498329ccaece75db5a5bf58cd3c9f130843e7102"},
+    {file = "tornado-6.1-cp37-cp37m-manylinux1_x86_64.whl", hash = "sha256:dcef026f608f678c118779cd6591c8af6e9b4155c44e0d1bc0c87c036fb8c8c4"},
+    {file = "tornado-6.1-cp37-cp37m-manylinux2010_i686.whl", hash = "sha256:70dec29e8ac485dbf57481baee40781c63e381bebea080991893cd297742b8fd"},
+    {file = "tornado-6.1-cp37-cp37m-manylinux2010_x86_64.whl", hash = "sha256:d3f7594930c423fd9f5d1a76bee85a2c36fd8b4b16921cae7e965f22575e9c01"},
+    {file = "tornado-6.1-cp37-cp37m-manylinux2014_aarch64.whl", hash = "sha256:3447475585bae2e77ecb832fc0300c3695516a47d46cefa0528181a34c5b9d3d"},
+    {file = "tornado-6.1-cp37-cp37m-win32.whl", hash = "sha256:e7229e60ac41a1202444497ddde70a48d33909e484f96eb0da9baf8dc68541df"},
+    {file = "tornado-6.1-cp37-cp37m-win_amd64.whl", hash = "sha256:cb5ec8eead331e3bb4ce8066cf06d2dfef1bfb1b2a73082dfe8a161301b76e37"},
+    {file = "tornado-6.1-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:20241b3cb4f425e971cb0a8e4ffc9b0a861530ae3c52f2b0434e6c1b57e9fd95"},
+    {file = "tornado-6.1-cp38-cp38-manylinux1_i686.whl", hash = "sha256:c77da1263aa361938476f04c4b6c8916001b90b2c2fdd92d8d535e1af48fba5a"},
+    {file = "tornado-6.1-cp38-cp38-manylinux1_x86_64.whl", hash = "sha256:fba85b6cd9c39be262fcd23865652920832b61583de2a2ca907dbd8e8a8c81e5"},
+    {file = "tornado-6.1-cp38-cp38-manylinux2010_i686.whl", hash = "sha256:1e8225a1070cd8eec59a996c43229fe8f95689cb16e552d130b9793cb570a288"},
+    {file = "tornado-6.1-cp38-cp38-manylinux2010_x86_64.whl", hash = "sha256:d14d30e7f46a0476efb0deb5b61343b1526f73ebb5ed84f23dc794bdb88f9d9f"},
+    {file = "tornado-6.1-cp38-cp38-manylinux2014_aarch64.whl", hash = "sha256:8f959b26f2634a091bb42241c3ed8d3cedb506e7c27b8dd5c7b9f745318ddbb6"},
+    {file = "tornado-6.1-cp38-cp38-win32.whl", hash = "sha256:34ca2dac9e4d7afb0bed4677512e36a52f09caa6fded70b4e3e1c89dbd92c326"},
+    {file = "tornado-6.1-cp38-cp38-win_amd64.whl", hash = "sha256:6196a5c39286cc37c024cd78834fb9345e464525d8991c21e908cc046d1cc02c"},
+    {file = "tornado-6.1-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:f0ba29bafd8e7e22920567ce0d232c26d4d47c8b5cf4ed7b562b5db39fa199c5"},
+    {file = "tornado-6.1-cp39-cp39-manylinux1_i686.whl", hash = "sha256:33892118b165401f291070100d6d09359ca74addda679b60390b09f8ef325ffe"},
+    {file = "tornado-6.1-cp39-cp39-manylinux1_x86_64.whl", hash = "sha256:7da13da6f985aab7f6f28debab00c67ff9cbacd588e8477034c0652ac141feea"},
+    {file = "tornado-6.1-cp39-cp39-manylinux2010_i686.whl", hash = "sha256:e0791ac58d91ac58f694d8d2957884df8e4e2f6687cdf367ef7eb7497f79eaa2"},
+    {file = "tornado-6.1-cp39-cp39-manylinux2010_x86_64.whl", hash = "sha256:66324e4e1beede9ac79e60f88de548da58b1f8ab4b2f1354d8375774f997e6c0"},
+    {file = "tornado-6.1-cp39-cp39-manylinux2014_aarch64.whl", hash = "sha256:a48900ecea1cbb71b8c71c620dee15b62f85f7c14189bdeee54966fbd9a0c5bd"},
+    {file = "tornado-6.1-cp39-cp39-win32.whl", hash = "sha256:d3d20ea5782ba63ed13bc2b8c291a053c8d807a8fa927d941bd718468f7b950c"},
+    {file = "tornado-6.1-cp39-cp39-win_amd64.whl", hash = "sha256:548430be2740e327b3fe0201abe471f314741efcb0067ec4f2d7dcfb4825f3e4"},
+    {file = "tornado-6.1.tar.gz", hash = "sha256:33c6e81d7bd55b468d2e793517c909b139960b6c790a60b7991b9b6b76fb9791"},
+]
+traitlets = [
+    {file = "traitlets-5.1.1-py3-none-any.whl", hash = "sha256:2d313cc50a42cd6c277e7d7dc8d4d7fedd06a2c215f78766ae7b1a66277e0033"},
+    {file = "traitlets-5.1.1.tar.gz", hash = "sha256:059f456c5a7c1c82b98c2e8c799f39c9b8128f6d0d46941ee118daace9eb70c7"},
+]
+wcwidth = [
+    {file = "wcwidth-0.2.5-py2.py3-none-any.whl", hash = "sha256:beb4802a9cebb9144e99086eff703a642a13d6a0052920003a230f3294bbe784"},
+    {file = "wcwidth-0.2.5.tar.gz", hash = "sha256:c4d647b99872929fdb7bdcaa4fbe7f01413ed3d98077df798530e5b04f116c83"},
+]
+webencodings = [
+    {file = "webencodings-0.5.1-py2.py3-none-any.whl", hash = "sha256:a0af1213f3c2226497a97e2b3aa01a7e4bee4f403f95be16fc9acd2947514a78"},
+    {file = "webencodings-0.5.1.tar.gz", hash = "sha256:b36a1c245f2d304965eb4e0a82848379241dc04b865afcc4aab16748587e1923"},
+]
+widgetsnbextension = [
+    {file = "widgetsnbextension-3.6.0-py2.py3-none-any.whl", hash = "sha256:4fd321cad39fdcf8a8e248a657202d42917ada8e8ed5dd3f60f073e0d54ceabd"},
+    {file = "widgetsnbextension-3.6.0.tar.gz", hash = "sha256:e84a7a9fcb9baf3d57106e184a7389a8f8eb935bf741a5eb9d60aa18cc029a80"},
+]
+zipp = [
+    {file = "zipp-3.7.0-py3-none-any.whl", hash = "sha256:b47250dd24f92b7dd6a0a8fc5244da14608f3ca90a5efcd37a3b1642fac9a375"},
+    {file = "zipp-3.7.0.tar.gz", hash = "sha256:9f50f446828eb9d45b267433fd3e9da8d801f614129124863f9c51ebceafb87d"},
+]
diff --git a/pyproject.toml b/pyproject.toml
new file mode 100644
index 0000000..088ff9d
--- /dev/null
+++ b/pyproject.toml
@@ -0,0 +1,18 @@
+[tool.poetry]
+name = "spikeloc"
+version = "0.0.1"
+description = "Collaborative project for modelling sound localization with SNNs"
+authors = ["Your Name <you@example.com>"]
+license = "MIT"
+
+[tool.poetry.dependencies]
+python = "^3.8"
+matplotlib = "^3.5.1"
+jupyter = "^1.0.0"
+numpy = "^1.22.3"
+
+[tool.poetry.dev-dependencies]
+
+[build-system]
+requires = ["poetry-core>=1.0.0"]
+build-backend = "poetry.core.masonry.api"
diff --git a/requirements.txt b/requirements.txt
new file mode 100644
index 0000000..a02749f
--- /dev/null
+++ b/requirements.txt
@@ -0,0 +1,69 @@
+argon2-cffi==21.3.0
+argon2-cffi-bindings==21.2.0
+asttokens==2.0.5
+attrs==21.4.0
+backcall==0.2.0
+beautifulsoup4==4.10.0
+bleach==4.1.0
+cffi==1.15.0
+cycler==0.11.0
+debugpy==1.6.0
+decorator==5.1.1
+defusedxml==0.7.1
+entrypoints==0.4
+executing==0.8.3
+fonttools==4.31.2
+ipykernel==6.11.0
+ipython==8.2.0
+ipython-genutils==0.2.0
+ipywidgets==7.7.0
+jedi==0.18.1
+Jinja2==3.1.1
+jsonschema==4.4.0
+jupyter==1.0.0
+jupyter-client==7.2.1
+jupyter-console==6.4.3
+jupyter-core==4.9.2
+jupyterlab-pygments==0.1.2
+jupyterlab-widgets==1.1.0
+kiwisolver==1.4.2
+MarkupSafe==2.1.1
+matplotlib==3.5.1
+matplotlib-inline==0.1.3
+mistune==0.8.4
+nbclient==0.5.13
+nbconvert==6.4.5
+nbformat==5.2.0
+nest-asyncio==1.5.4
+notebook==6.4.10
+numpy==1.22.3
+packaging==21.3
+pandocfilters==1.5.0
+parso==0.8.3
+pexpect==4.8.0
+pickleshare==0.7.5
+Pillow==9.0.1
+prometheus-client==0.13.1
+prompt-toolkit==3.0.28
+psutil==5.9.0
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pycparser==2.21
+Pygments==2.11.2
+pyparsing==3.0.7
+pyrsistent==0.18.1
+python-dateutil==2.8.2
+pyzmq==22.3.0
+qtconsole==5.3.0
+QtPy==2.0.1
+Send2Trash==1.8.0
+six==1.16.0
+soupsieve==2.3.1
+stack-data==0.2.0
+terminado==0.13.3
+testpath==0.6.0
+tornado==6.1
+traitlets==5.1.1
+wcwidth==0.2.5
+webencodings==0.5.1
+widgetsnbextension==3.6.0
diff --git a/spikeloc/__init__.py b/spikeloc/__init__.py
new file mode 100644
index 0000000..e69de29