mw3i

---

documentclass: book bibliography: ./path/to/bibfile.bib csl: .csl fontsize: 12pt classoption: oneside link-citations: true color-links: true

linkcolor: BrickRed

urlcolor: "blue"

mw3i

# Creates ".bashtrash" directory if it doesn't exist; then it moves things to it
function trash {
    if [ ! -d "$HOME/.bashtrash" ]
    then
        mkdir "$HOME/.bashtrash"
    fi
    mv "$@" "$HOME/.bashtrash"
}

mw3i

## Python Commander
class simple_shell():
	def __init__(self):
		while True:
			self.listener()

	## Listener Function (required)
	def listener(self):
		self.user_input = input('---\nuser: ').split(' ')
		try:

mw3i

## std lib
import sys, os

## ext req
import autograd.numpy as np 
from autograd import grad
import autograd.scipy.signal as signal


## _ _ _ Get Model Output _ _ _ 

mw3i

## ext requirements
import numpy as np

# - - - - - - - - - - - - - - - - - -

    # -- Model --

# - - - - - - - - - - - - - - - - - -

## produces model outputs

mw3i

## ext requirements
import autograd.numpy as anp 
from autograd import grad


# - - - - - - - - - - - - - - - - - -

    # -- Model --

# - - - - - - - - - - - - - - - - - -

mw3i

'''
Implementation of LDA with Numpy (using covariance & scatter matrix), based on this tutorial by Sebastian Raschka: https://sebastianraschka.com/Articles/2014_python_lda.html
'''
import numpy as np 

def get_components(data: np.ndarray, labels: np.ndarray) -> np.ndarray: # <-- using covariance method
    label_set = np.unique(labels)
    class_means = np.array([
        data[labels == label,:].mean(axis = 0, keepdims = True) 
        for label in label_set

mw3i

'''
Implementation of PCA with Numpy (using covariance), based on this tutorial by Sebastian Raschka: https://sebastianraschka.com/Articles/2014_pca_step_by_step.html
'''
import numpy as np 

def get_components(data: np.ndarray) -> np.ndarray:
    cov_mat = np.cov(data.T) # <-- get the covariance matrix

    ## calculate eigenvalues of the covariance matrix
    eig_val, eig_vec = np.linalg.eig(cov_mat)