WinstonCampeau

library(readr)
library(stringr)
oos <- read_csv("Documents/oos.txt", col_names = FALSE)

flatoos <- str_flatten(oos$X1, " ")

splitflatoos <- strsplit(flatoos, " ")

nchar(splitflatoos[[1]][1])

WinstonCampeau

md <- read.csv(file.choose(), header=T) #This is not working, need to use FILE, IMPORT DATASET, FROM TEXT(BASE), then select csv, DESELECT "Strings as Factors", IMPORT

#removes leading and trailing numbers from sequences

for(i in 1:nrow(md)){
  md[i,] <- substr(md[i,], 3, nchar(md[i,])-2)
}


#Check for even length stem

WinstonCampeau

#Collatz Conjecture
#Will produce graph and number of steps to converge to 1


collatz <- function(start_val, show_me) {
  if(missing(show_me)){
    show_me <- start_val
  }
  n <- start_val
  comp <- c()

WinstonCampeau

#Where seed commences the generation of all future numbers
#number is the number of resultant generated numbers
#show_list allows you to see the lsit of generated numbers
#raw changes the numbers from strings to numeric (1 = strings, 0 = numeric)

#I used this method to teach student's a little about simulation, probabilities, and p-values. 
#I have them do the middle square method by hand using a 4-digit seed
#They quickly learn the pitfalls of the MSM and such a small length seed (can easily converge to 0 or cycle -- although sometimes with desirable results!)
#They then use excel or google sheets and the binom.dist function to get a dirty p-value. (Pick the lower count of heads and tails as your successes and then multiply by 2 for two-tailed)
#Student's can then comment on the simulation, how to improve the simulation; they discover the concept of probabilities, fair coins, and the utility of statistical testing.

WinstonCampeau

CATCHALL <- function(NUM_RESAMPLES, KFOLDS, INDIVIDUAL_PLOTS) {
  
  if(nargs()==0){
    NUM_RESAMPLES <- 100
    KFOLDS <- 5
    INDIVIDUAL_PLOTS <- 0
  }
  
  cat("Please select your data; The data must be (X_COLUMN, Y_COLUMN) and csv file type\nIf you did not enter a number of bootstrap resamples, the default is set to 100 - double for jackknife - and defaults to 5 kfolds")
  cat("\n")

WinstonCampeau

# seed requires an even length number, no restrictions on length
# number is the number of numbers you wish to be generated
# raw=1 returns raw data, aka "0429" instead of 429
# this method is horrible, but still often used as a teaching method 

MSM <- function(seed, number, raw) {
  options("scipen" = 2*nchar(seed))
  
  if(missing(number)) {
    number <- 15

WinstonCampeau

#Generates dictionary of regional sets (id:array). Regional sets can vary in species composition and number of populations (I consider each element a population). 

import numpy as np
import random
reg_sets = {}
global_set = []
n_set = []
unique = {}

#Adjust number of regional sets, number of species, and number of populations in each set

WinstonCampeau

#Three traders F1, F2, and F3 each have a front wheel of a tricycle and three traders R1, R2, and R3 each have one rear wheel of a tricycle. 
#To construct a tricycle, two rear wheels and one front wheel are required. The value of a coalition is the number of tricycles it can construct.
# E.g. v(FRR) = 1, v(RR) = 0 v(FR) = 0.

#Let A be the front wheels and B be the rear wheels

A={1,2,3}
B={4,5,6}

subset_dictionary = {}

WinstonCampeau

#Code generated with the help of Dr. Brett Stevens @ Carleton University
#input matrices are easily generated by, G.reduced_adjacency_matrix()

#Mutual information is minimized when p(x,y)=p(x)*p(y). Otherwise, the joint probability is equal to the product of the marginals 

def mutual_entropy(input_matrix):
    
    matrix_sum = (matrix([1]*input_matrix.nrows())*input_matrix*(matrix([1]*input_matrix.ncols())).transpose())[0][0]
    
    row_probabilities = (input_matrix*(matrix([1]*input_matrix.ncols())).transpose()).transpose()[0]

WinstonCampeau

#Code produced with the help of Dr. Brett Stevens @ Carleton University
#Add all potential missing edges in a bigraph and with weight

#First copy some bigraph G and generate list of known edges 

auxillary_graph = G.copy()
edge_list = []
for edge in auxillary_graph.edges():
    edge_list.append((edge[0],edge[1]))