tjvananne

# references:
# https://rud.is/b/2016/02/14/making-faceted-heatmaps-with-ggplot2/ 
# This is basically the TL;DR and it also uses a built-in dataset to foster reproducibility


library(ggplot2)
library(viridis)

gg <- ggplot(airquality, aes(x=Day, y=Month, fill=Temp))
gg <- gg + geom_tile(color='White', size=0.1)

tjvananne

# generic data dictionary creation using base-R

#' a couple notes: this could of course be done much faster using
#' third party packages, but I like to provide base-R solutions before
#' branching out into packages just in case they aren't available
#' 
#' Also, this could be done in a much less verbose and modular way,
#' but I did want to also demonstrate the "Functional Programming" 

tjvananne

#' A word vector is a giant matrix of words, and each word contains a numeric array that represents the semantic
#' meaning of that word. This is useful so we can discover relationships and analogies between words programmatically.
#' The classic example is "king" minus "man" plus "woman" is most similar to "queen"


# function definition --------------------------------------------------------------------------

    # input .txt file, exports list of list of values and character vector of names (words)
    proc_pretrained_vec <- function(p_vec) {

tjvananne

# xgboost feature importance ----------------------------------------------------------------

    #' Author: Taylor Van Anne
    #' 7/25/2017
    #' 
    #' This script is a simple demonstration of:
    #' 1) using cross validation to determine the optimal number of iterations for your xgboost model
    #' 2) runs xgboost with that number of iterations

tjvananne

#' Most basic form of a TryCatch function in R
#' tryCatch() takes two arguments: "expr" and "finally"
#' 
#' "expr" is the expression you want to try. It will run as much
#' as it can until coming across an error. When it hits an error, it
#' will stop processing the code in the expression brackets and move
#' to whatever is inside of the "finally" brackets. 
#' 

tjvananne

# set up a stepsize
alpha = 0.003

# set up a number of iteration
iter = 500

# define the gradient of f(x) = x^4 - 3*x^3 + 2

tjvananne

'''
Simply display the contents of the webcam with optional mirroring using OpenCV 
via the new Pythonic cv2 interface.  Press <esc> to quit.
'''

import cv2

def show_webcam(mirror=False):
  cam = cv2.VideoCapture(0)
	while True:

tjvananne

#' Target Shuffling 
#' Author: Taylor Van Anne
#' 
#' Note: this is just my interpretation of what target shuffling means
#' to me. I think there are a few different ways to actually conduct 
#' the shuffling, but this is a single approach. 
#' 
#' A different approach than what I did here would be to shuffle the

tjvananne

#=========================================================================
#STAT W4400 
#Homework 03 
# yl3394, Yanjin Li 
#Problem 1 AdaBoost 
#=========================================================================
# In this problem I will implement AdaBoost algorithm in R. The algorithm 
# requires two auxiliary functions, to train and to evaluate the weak leaner.
# And, then we will have the third function for implementing the resulting 
# boosting classifier. Here, we will use the decision stumps as our weak 

tjvananne

library(lubridate)  #   <3 tidyverse


# this is likely not the most efficient way to generate unix time stamps, but it is intuitive to me
# I like to see how it is done step by step
# to make this more efficient, you could store  the "epoch" value outside the function so it
# doesn't have to be calculated every time you call the function
time_since_epoch <- function() {