masterdezign

#%%
import os
import numpy as np
import mne
from mne.preprocessing import compute_current_source_density
# %matplotlib qt

# First, we need to load the data
sample_data_folder = mne.datasets.sample.data_path()
sample_data_raw_file = os.path.join(sample_data_folder, 'MEG', 'sample',

masterdezign

Edit wpa_supplicant.conf and save it to the root of boot partition.
Replace the country code, ssid, and psk.
Full list of country codes: https://www.thinkpenguin.com/gnu-linux/country-code-list

On first boot, this file will be moved to /etc/wpa_supplicant/wpa_supplicant.conf where it may be edited later.

masterdezign

# First of all make sure Nix is up and running https://nixos.org/nix

# Clone Hasktorch
git clone https://github.com/hasktorch/hasktorch.git
cd hasktorch

NIX_PATH="nixpkgs=https://github.com/NixOS/nixpkgs/archive/release-19.09.tar.gz"
nix-env -iA cachix -f https://cachix.org/api/v1/install
cachix use hasktorch

masterdezign

# Concatenate images
ffmpeg -framerate 5 -pattern_type glob -i "*.jpg" output.mp4

# Compress
ffmpeg -i output.mp4 -vcodec libx265 -acodec aac -crf 23 output_compressed.mp4

masterdezign

#!/usr/bin/env python3

"""
Cellular automata in Python
"""

import sys

Z = '.'
O = '#'

masterdezign

-- 0. Download x.data and y.dat from https://www.kaggle.com/masterdezign/iris-with-onehotencoded-targets
-- 1. Install stack (command line interface is marked by $):
--   $ wget -qO- https://get.haskellstack.org/ | sh
-- (alternatively, curl -sSL https://get.haskellstack.org/ | sh)
-- 2. Install open-blas from https://www.openblas.net/ (needed for hmatrix package)
-- 3. Run
--   $ stack --resolver lts-10.6 --install-ghc runghc --package hmatrix-0.18.2.0 Iris.hs

import Numeric.LinearAlgebra as LA

masterdezign

descent1D gradF iterN gamma x0 = take iterN (iterate _descend x0)
  where
    _descend gamma' x = x - gamma' * gradF x
    
-- Suppose, we have a function F(x) = (x - 3)^2.
-- Therefore, Grad F(x) = 2 * (x - 3).
gradF_test x = 2 * (x - 3)

main = print (descent1D gradF_test 10 gamma 0.0)
  where gamma = 0.5

masterdezign

-- Run a one dimensional gradient descent written in Clash [1],
-- a high level language that compiles to Verilog and VHDL.
-- Gradient descent can be described by a formula:
--
-- a_n+1 = a_n - gamma * Grad F(a_n),
-- 
-- where the constant `gamma` is what is referred to in deep learning as
-- the learning rate.
--
-- [1] https://clash-lang.org/

masterdezign

{-
Brainf**k interpreter

Brainf**k is a Turing-complete programming language.

Instructions:
>   Increment data pointer so that it points to next location in memory.
<   Decrement data pointer so that it points to previous location in memory.
+   Increment the byte pointed by data pointer by 1. If it is already at its maximum value, 255, then new value will be 0.
-   Decrement the byte pointed by data pointer by 1. If it is at its minimum value, 0, then new value will be 255.

masterdezign

-- Worth reading http://www.geeksforgeeks.org/convex-hull-set-2-graham-scan/

import Text.Printf
import Data.List

type Point = (Double, Double)

-- Euclidean distance
dist :: (Double, Double) -> (Double, Double) -> Double
dist (x1, y1) (x2, y2) = sqrt (f x1 x2 + f y1 y2)