Group-Project.Rmd

---
title: "Group Project"
author: "Frances Scott-Weis"
date: "2/5/2022"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
library(dplyr)
```

Set-up
```{r}
# Passwords <- read.delim(file = "C:/Users/franc/Downloads/rockyousubset.txt", header = FALSE, sep = "\t", dec = ".")
#   Passwords <- read.delim(file = "C:/Users/franc/Downloads/rockyousubset.txt", header = FALSE, sep = "\t") %>%  collect()
  
Passwords <-   read.csv(file = "C:/Users/franc/Downloads/rockyousubset.csv", 
                      sep = "\t", header=FALSE) 
Passwords_list <- Passwords$V1

Passwords %>%  group_by(large = if_else(nchar(V1) > 30, 1, 0)) %>% summarise(n())  

Passwords_corrected <- Passwords %>%  filter(nchar(V1) <= 30) 
Password_list <- Passwords_corrected$V1
```

Password Length
```{r}
#Length
lengths = c(1:length(Password_list))
for (i in 1:length(Password_list)) {
  lengths[i] <- nchar(Password_list[i])
}
hist(lengths, xlim = )
df <- data.frame(mean = mean(lengths), sd = sd(lengths))
knitr::kable(df)
t.test(lengths)
```

Number of unique characters
```{r} 
# Number of unique characters
uniqchars <- function(x) length(unique(strsplit(x, "")[[1]]))
length_unique = c(1:length(Password_list))
for (i in 1:length(Password_list)) {
  length_unique[i] <- uniqchars(Password_list[i])
}
hist(length_unique)
df <- data.frame(mean = mean(length_unique), sd = sd(length_unique))
knitr::kable(df)
t.test(length_unique)
```

#Number of numbers
```{r}
# gsub("[^0-9]+", "", "hello6578")
lengths_numbers = c(1:length(Password_list))
for (i in 1:length(Password_list)) {
  lengths_numbers[i] <- nchar(gsub("[^0-9]+", "", Password_list[i]))
}
hist(lengths_numbers)
df <- data.frame(mean = mean(lengths_numbers), sd = sd(lengths_numbers))
knitr::kable(df)
t.test(lengths_numbers)
```

#Number of symbols
```{r}
library(stringr)
length_symbols = c(1:length(Password_list))
for (i in 1:length(Password_list)) {
  symbols_1 <- str_extract_all(Password_list[i], "\\W")
  symbols_count <- nchar(gsub("[^,]+", "", symbols_1 ))+1
  length_symbols[i] <- symbols_count
  } 
hist(length_symbols)
df <- data.frame(mean = mean(length_symbols), sd = sd(length_symbols))
knitr::kable(df)
t.test(length_symbols)
```

# Number of symbols and numbers
```{r}
library(stringr)
length_num_symbols = c(1:length(Password_list))
for (i in 1:length(Password_list)) {
  symbols_1 <- str_extract_all(Password_list[i], "\\W") 
  symbols_count <- nchar(gsub("[^,]+", "", symbols_1 ))+1
  num_count <- nchar(gsub("[^0-9]+", "", Password_list[i]))
  length_num_symbols[i] <- symbols_count+ num_count
  } 
hist(length_num_symbols)
df <- data.frame(mean = mean(length_num_symbols), sd = sd(length_num_symbols))
knitr::kable(df)
t.test(length_num_symbols)
```


#Longest string of repeating sequential characters 
```{r}
#!/usr/bin/perl
use List::Util "reduce";
my $string = "this aaa and bbbb for ### ## ppppppp";
my $max = reduce { length($b) > length($a) ? $b : $a } "", 
                    $string =~ /((.)\2+)/gs;
print "$max\n";
```