k-means clustering elbow method

library(ggplot2)
library("ggpubr")
theme_set(
  theme_bw() +
    theme(legend.position = "top")
  )

var <- "mpg"
#Doesn't work
mtcars$var
#These both work, but note that what they return is different
# the first is a vector, the second is a data.frame
mtcars[[var]]
mtcars[var]

# load packages
require(FactoMineR)
require(ggplot2)
# load data tea
data(tea)
# select these columns
newtea = tea[, c("Tea", "How", "how", "sugar", "where", "always")]
# take a look
head(newtea)


# number of categories per variable
cats = apply(newtea, 2, function(x) nlevels(as.factor(x)))
cats

# apply MCA
mca1 = MCA(newtea, graph = FALSE)

# table of eigenvalues
mca1$eig


# data frames for ggplot
mca1_vars_df = data.frame(mca1$var$coord, Variable = rep(names(cats), 
                                                         cats))
mca1_obs_df = data.frame(mca1$ind$coord)

# plot of variable categories
ggplot(data = mca1_vars_df,
       aes(x = Dim.1, y = Dim.2, label = rownames(mca1_vars_df))) + 
  geom_hline(yintercept = 0, colour = "gray70") + geom_vline(xintercept = 0, 
                                              colour = "gray70") +
  geom_text(aes(colour = Variable)) + 
  ggtitle("MCA plot of variables using R package FactoMineR")


# XXX ---------------------------------------------------------------------

Base_acm <- Base %>% select(P1_1, P3_1, P3_2, P3_3)
Base_acm$P1_1 <- as.factor(Base_acm$P1_1)
Base_acm$P3_1 <- as.factor(Base_acm$P3_1)
Base_acm$P3_2 <- as.factor(Base_acm$P3_2)
Base_acm$P3_3 <- as.factor(Base_acm$P3_3)

cats=apply(Base_acm, 2, function(x) nlevels(as.factor(x)))

mca2 = MCA(Base_acm, graph = FALSE)

# data frames for ggplot
mca2_vars_df = data.frame(mca2$var$coord, Variable = rep(names(cats), 
                                                         cats))
mca2_obs_df = data.frame(mca2$ind$coord)

# plot of variable categories
ggplot(data = mca2_vars_df,
       aes(x = Dim.1, y = Dim.2, label = rownames(mca2_vars_df))) + 
  geom_hline(yintercept = 0, colour = "gray70") + geom_vline(xintercept = 0, 
                                                        colour = "gray70") +
  geom_text(aes(colour = Variable)) + 
  ggtitle("MCA plot of variables using R package FactoMineR")

factoextra::fviz_screeplot(mca2, addlabels = TRUE, ylim = c(0, 45))

x <- data$variable_xaxis
y <- data$variable_yaxis

plot(x, y, main = "Main title",
     xlab = "X axis title", ylab = "Y axis title",
     pch = 19, frame = FALSE)
abline(lm(y ~ x, data = mtcars), col = "blue")

qplot(x-coordinate, y-coordinate, data=data_frame, geom = c("point", "smooth")

g <- ggplot(data_set, aes(x-variable, y-variable) 

g + geom_point()

x <- data$variable_xaxis
y <- data$variable_yaxis

plot(x, y, main = "Main title",
     xlab = "X axis title", ylab = "Y axis title",
     pch = 19, frame = FALSE)
abline(lm(y ~ x, data = mtcars), col = "blue")

library(tidyverse)

df$column <- df$column str_to_title(df$column) #Standardize caps

#Two options 
df$column <- str_replace(df$column, "old", "new") #Option 1, uses str_replace
df$column <- gsub("old", "new", df$column) #Option 2, uses str_replace  

# make data frame 
a <- data.frame( x =  c(1,2,3,4)) 
b <- data.frame( y =  c(1,2,3,4,5,6))
subset(b, !(y %in% a$x)) #Pulls values from frame b that are not in frame a

dir <- "directory of archives"

directories <- as.list(file.path(dir, list.files(dir, pattern = ".*.csv")))

dataframes <- map(directories , rio::import)

dataset <- plyr::ldply(dataframes, data.frame)

str_order(
  x,
  decreasing = FALSE,
  na_last = TRUE,
  locale = "en",
  numeric = FALSE,
  ...
)
  
# Examples 
  
  str_order(letters)
#>  [1]  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25
#> [26] 26
str_sort(letters)
#>  [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s"
#> [20] "t" "u" "v" "w" "x" "y" "z"

str_order(letters, locale = "haw")
#>  [1]  1  5  9 15 21  2  3  4  6  7  8 10 11 12 13 14 16 17 18 19 20 22 23 24 25
#> [26] 26
str_sort(letters, locale = "haw")
#>  [1] "a" "e" "i" "o" "u" "b" "c" "d" "f" "g" "h" "j" "k" "l" "m" "n" "p" "q" "r"
#> [20] "s" "t" "v" "w" "x" "y" "z"

x <- c("100a10", "100a5", "2b", "2a")
str_sort(x)
#> [1] "100a10" "100a5"  "2a"     "2b"    
str_sort(x, numeric = TRUE)
#> [1] "2a"     "2b"     "100a5"  "100a10"

# Account
statement <- read.csv("statement.csv", stringsAsFactors = F, sep = ";")

# Get rid of irrelevant columns
statement <- statement[2:13]

# Statement money flows
rahavoog <- statement[statement$Reatüüp == 20,]
rahavoog$Summa <- as.numeric(gsub(",", ".", rahavoog$Summa))

#Outlier Removal Function
remove_outliers <- function(dataframe, column, na.rm = TRUE) {
  Q1 <- quantile(column, .25)
  Q3 <- quantile(column, .75)
  IQR <- IQR(column)
  dataframe <- subset(dataframe, column> (Q1 - 1.5*IQR) & column< (Q3 + 1.5*IQR))
}

#Not looping
df_1 <-remove_outliers(df_1,df_1$Column1)

#Loop through a list of column names
for(i in Column_List){
  df_1 <- remove_outliers(df_1, df_1[[i]])
}  

if (1 != 2)
  stop("something is wrong")

try(log("not a number"), silent = TRUE)
print("errors can't stop me")