guenter-r

# Check file sizes
sudo du -h --max-depth=1 | sort -hr | head -n 10
df -h


###### MOUNTING 
https://learn.microsoft.com/en-us/azure/virtual-machines/linux/attach-disk-portal?tabs=ubuntu

# Mount disk

guenter-r

using CSV
using DataFrames
using Statistics

data = CSV.read("./iris_data.txt",header=false)

## no more head
first(data,5)

# renaming column header

guenter-r

knn <- function(new,df,k){
  dist_df <- data.frame()

  for (i in 1:nrow(df)){
    distance <- 0
    # calculate distance
    for (j in 1:length(new)){
      distance <- distance + (new[j] - df[i,j])^2
    }
    

guenter-r

import bs4
def extract_reuters_news(path_file):
    file = open(path_file , 'r').read()
    soup = bs4.BeautifulSoup(path_file)
all_bodies = [el.text for el in soup.find_all('body')]
return all_bodies
path = './reuters001.html'
reuters = extract_reuters_news(path)

guenter-r

from numpy import linalg

def return_eig_triang(graph):
  w,v = linalg.eig(graph)
  w,v
  no_of_triangles = round(np.sum(w**3) / 6,1)
  return no_of_triangles # total triangles in the matrix

guenter-r

# create sparse dataset
connections_list = []

for i in range(31):
    connections = np.random.choice(21,2) # obviously, repeated values are likely, let's see whether we get triangles too..
    connections_list.append(list(connections))

print(connections_list)

guenter-r

x,y = [],[]

for element in connections_list:
    xi = element[0]
    yi = element[1]
    
    x.append(xi)
    x.append(yi) # make symmetric
    y.append(yi)
    y.append(xi) # make symmetric

guenter-r

# create sparse dataset
connections_list = []

for i in range(31):
    connections = np.random.choice(21,2) # obviously, repeated values are likely, let's see whether we get triangles too..
    connections_list.append(list(connections))

print(connections_list)

guenter-r

graph = np.array([
    [0,1,1,0,0,0,0,0],
    [1,0,1,1,1,0,0,1],
    [1,1,0,0,0,0,0,0],
    [0,1,0,0,1,0,1,1],
    [0,1,0,1,0,1,0,0],
    [0,0,0,0,1,0,0,0],
    [0,0,0,1,0,0,0,0],
    [0,1,0,1,0,0,0,0]
])