In Stefan1896/Company_Financials: Company Financials of S&P 500 companies
knitr::opts_chunk$set(out.width="100%", fig.height = 4.5, split=FALSE, fig.align = 'default', comment = NA)
options(dplyr.summarise.inform = FALSE)
knitr::opts_chunk$set(echo=TRUE, error=FALSE, message=FALSE, warning=FALSE)
options(scipen=999)
Introduction
This Markdown is part of a package where company financial data from S&P 500 companies is explored using a Shiny App. The aim of this Markdown is to perform all core back-end analysis of the application without any reactivity. This document will therefore be the template then for developing the Shiny App. The goal of the whole package is to learn how to develop an Shiny App as a package using the golem framework.
The dataset which is used in this project includes 505 rows with 14 variables.
Goals:
- Exploratory Overview of S&P 500 companies using Markdown and Shiny
- Learning the Golem Framework for developing Shiny Apps as a package
Preperations {.tabset}
Load Packages
First, relevant packages are loaded. We load a range of libraries for general data wrangling and general visualisation.
library(here) #used for folder navigation
library(readr) #used to read data as tibble
library(skimr) #used to get overview of data
library(janitor) #used to clean variable names
library(dplyr) #used for data wrangling
library(ggplot2) #used for graphs
library(gridExtra) #used for graphs (arrange in gridges)
Load Data
The data was downloaded from kaggle and stored locally (login necessary). The here package is used to locate the files relative to the project root. 10 out of 505 observations have at least one missing value.
financials <- read_csv(here("data-raw","company_financials.csv"))
cat(dim(financials[!complete.cases(financials),])[1], "out of", nrow(financials), "observations have at least one missing value.")
Data Overview and Preprocessing {.tabset}
Overview
We have a first look at the dataset:
skim(financials)
Notes:
-
There is some valuable information in this quick overview. The missing datapoints are in the variables Price/Earnings and Price/Book.
-
The variables are already classified as numeric and character. From the character variables, Sector is the only one which has not all unique characters.
-
Nearly all of the company Financials are right skewed.
-
The variable names are not clean, since they include spaces and variables which start with a number We clean them directly using the janitor package.
-
It is possible to calculate a sales variable, using the market cap and price/sales information. We can also calculate a Net Profit variable using earnings per share, market cap and price per share.
Preprocessing
Based on the notes from the Overview, we will clean the names and add a sales and a net profit variable to the data. We then again look at the final variable names:
#clean names and get sales variable
names_original <- c(names(financials), "Sales", "Net Profit")
names(financials) <- make_clean_names(names(financials))
financials <- financials %>% mutate(sales = market_cap/price_sales, net_profit = earnings_share * (market_cap/price))
names(financials)
Univariate Data Exploration {.tabset}
Numeric Variables
First, let us have a look at the distribution of the numeric variables (Company Financials):
#Save indicator whether variable is numeric or not
nums <- unlist(lapply(financials, is.numeric))
#save cleaned names and original names in vector (original names are used as title of x axis)
nums_names <- names(financials)[nums]
nums_original_names <- names_original[nums]
#loop through numeric variable names to plot each numeric variable (distribution)
p <- list()
j = 1
for(i in c(nums_names)){
p[[j]] <- ggplot(financials, aes_string(x=i)) +
geom_histogram(aes(y=..density..), colour="black", fill="white")+
geom_density(alpha=.2, fill="#009966")+
labs(x = nums_original_names[j], y = "") +
theme_classic() +
theme(axis.text.x = element_blank(),
axis.text.y = element_blank())
j = j+1
}
do.call(grid.arrange,p)
Notes:
-
Again, we see that many of the company financials are right skewed.
-
We will use cube root transformation in exploring relationships later.
Character Variable
Second, let us have a closer look at the character variables containing company Information. We will only look at sector, since this is the only character variable which not only has unique values for each datapoint.
ggplot(financials, aes(sector)) +
geom_bar(fill = "#009966", alpha = 0.2, color = "black") +
theme_classic() +
labs(x = "Sector", y = "Count") +
coord_flip()
Notes:
-
We have for all sectors at least 20 datapoints except for Telecommunication Services.
-
When exploring the relationship of sector with company financials, we will exclude Telecommunaction Services since the number of datapoints is too low.
Multivariate Data Exploration
In this sections, we will explore the relationships of our character variable sector with the company financials as well as the relationships between different company financials. The goal here is to give a quick overview of the relationships in the data, there will be no further statistics like effect sizes to further explore the size of effects. Since we are dealing with a lot of extreme values and skeweness, a Cube Root Transfomration will be used for some analysis. We will only concentrate on financials which do have a desired meaning for us. For example, price will not be explored, since this is only gives information about the price per share, which is not meaningful for our analysis without looking also at the number of shares issued.
Cube root transformation:
The cube root transformation involves converting x to x^(1/3). This is a fairly strong transformation with a substantial effect on distribution shape: but is weaker than the logarithm. It can be applied to negative and zero values too.
Top/Bottom 10 Companies {.tabset}
First, let us look at the top and botton 10 companies of several financials:
selected_financials <- c("price_earnings", "market_cap", "ebitda", "price_sales","price_book", "sales","net_profit")
indicator <- nums_names %in% selected_financials
selected_original_names <- nums_original_names[indicator]
top <- list()
bot <- list()
j = 1
for(i in c(selected_financials)){
top[[j]] <- financials %>% arrange(desc(!!sym(i))) %>% head(10) %>%
ggplot(aes(x=reorder(name, !!sym(i)), y = !!sym(i))) +
geom_bar(stat = "identity", fill = "#009966", alpha = 0.2, color = "black") +
labs(x = "", y = "") +
ggtitle(paste("Top 10 -", selected_original_names[j])) +
theme_classic() +
coord_flip()
j = j+1
}
j = 1
for(i in c(selected_financials)){
bot[[j]] <- financials %>% arrange(desc(!!sym(i))) %>% tail(10) %>%
ggplot(aes(x=reorder(name, !!sym(i)), y = !!sym(i))) +
geom_bar(stat = "identity", fill = "indianred", alpha = 0.2, color = "black") +
labs(x = "", y = "") +
ggtitle(paste("Bottom 10 -", selected_original_names[j])) +
theme_classic() +
coord_flip()
j = j+1
}
Price/Earnings
top[[1]]
bot[[1]]
Market Cap
top[[2]]
bot[[2]]
EBITDA
top[[3]]
bot[[3]]
Price/Sales
top[[4]]
bot[[4]]
Price/Book
top[[5]]
bot[[5]]
Sales
top[[6]]
bot[[6]]
Net Profit
top[[7]]
bot[[7]]
Relationship Sector/Financials {.tabset}
#make function for cube_root formatting
cube_root <- function(x) {
sign(x) * abs(x)^(1/3)
}
#loop through numeric variable names to plot each numeric variable cube root transformatted with sector
pt <- list()
j = 1
for(i in c(nums_names)){
pt[[j]] <- financials %>% filter(sector != "Telecommunication Services") %>%
ggplot(aes(x=sector, y = cube_root(!!sym(i)))) +
geom_boxplot(outlier.shape = NA) +
geom_jitter(width=0.1, alpha=0.2, color = "#009966") +
labs(x = "", y = paste(nums_original_names[j], "- Cube Root transformatted")) +
theme_classic() +
coord_flip()
j = j+1
}
Price/Earnings
pt[[2]]
Dividend Yield
financials %>% filter(sector != "Telecommunication Services") %>%
ggplot(aes(x=sector, y = dividend_yield)) +
geom_boxplot(outlier.shape = NA) +
geom_jitter(width=0.1, alpha=0.2, color = "#009966") +
labs(x = "", y = "Dividend Yield") +
theme_classic() +
coord_flip()
Market Cap
pt[[7]]
EBITDA
pt[[8]]
Price/Sales
pt[[9]]
Price/Book
pt[[10]]
Sales
pt[[11]]
Net Profit
pt[[12]]
Relationship Financials {.tabset}
Similar to the graphs with sector, we will now for each relevant financial variable plot its relationship to the others. For all graphs in this section Cube root transformation is used. In general, we see a positiv relationship between the market cap, revenue (sales) and profit (EBITDA and net profit) variables, as expected.
Price/Earnings
indicator <- nums_names %in% selected_financials[selected_financials != "price_earnings"]
selected_original_names <- nums_original_names[indicator]
#loop through selected financial variable names without sales to plot each numeric variable cube root transformated with selected variable
ps <- list()
j = 1
for(i in c(selected_financials[selected_financials != "price_earnings"])){
ps[[j]] <- financials %>%
ggplot(aes(x=price_earnings^(1/3), y = cube_root(!!sym(i)))) +
geom_point(col = "black", alpha = 0.2) +
geom_smooth(method='lm', formula= y~x, color = "#009966") +
labs(x = "", y = "") +
ggtitle(paste("Price/Earnings vs", selected_original_names[j])) +
theme_classic()
j = j+1
}
do.call(grid.arrange,ps)
Market Cap
indicator <- nums_names %in% selected_financials[selected_financials != "market_cap"]
selected_original_names <- nums_original_names[indicator]
#loop through selected financial variable names without sales to plot each numeric variable cube root transformated with selected variable
ps <- list()
j = 1
for(i in c(selected_financials[selected_financials != "market_cap"])){
ps[[j]] <- financials %>%
ggplot(aes(x=market_cap^(1/3), y = cube_root(!!sym(i)))) +
geom_point(col = "black", alpha = 0.2) +
geom_smooth(method='lm', formula= y~x, color = "#009966") +
labs(x = "", y = "") +
ggtitle(paste("Market Cap vs", selected_original_names[j])) +
theme_classic()
j = j+1
}
do.call(grid.arrange,ps)
EBITDA
indicator <- nums_names %in% selected_financials[selected_financials != "ebitda"]
selected_original_names <- nums_original_names[indicator]
#loop through selected financial variable names without sales to plot each numeric variable cube root transformated with selected variable
ps <- list()
j = 1
for(i in c(selected_financials[selected_financials != "ebitda"])){
ps[[j]] <- financials %>%
ggplot(aes(x=ebitda^(1/3), y = cube_root(!!sym(i)))) +
geom_point(col = "black", alpha = 0.2) +
geom_smooth(method='lm', formula= y~x, color = "#009966") +
labs(x = "", y = "") +
ggtitle(paste("EBITDA vs", selected_original_names[j])) +
theme_classic()
j = j+1
}
do.call(grid.arrange,ps)
Price/Sales
indicator <- nums_names %in% selected_financials[selected_financials != "price_sales"]
selected_original_names <- nums_original_names[indicator]
#loop through selected financial variable names without sales to plot each numeric variable cube root transformated with selected variable
ps <- list()
j = 1
for(i in c(selected_financials[selected_financials != "price_sales"])){
ps[[j]] <- financials %>%
ggplot(aes(x=price_sales^(1/3), y = cube_root(!!sym(i)))) +
geom_point(col = "black", alpha = 0.2) +
geom_smooth(method='lm', formula= y~x, color = "#009966") +
labs(x = "", y = "") +
ggtitle(paste("Price/Sales vs", selected_original_names[j])) +
theme_classic()
j = j+1
}
do.call(grid.arrange,ps)
Price/Book
indicator <- nums_names %in% selected_financials[selected_financials != "price_book"]
selected_original_names <- nums_original_names[indicator]
#loop through selected financial variable names without sales to plot each numeric variable cube root transformated with selected variable
ps <- list()
j = 1
for(i in c(selected_financials[selected_financials != "price_book"])){
ps[[j]] <- financials %>%
ggplot(aes(x=price_book^(1/3), y = cube_root(!!sym(i)))) +
geom_point(col = "black", alpha = 0.2) +
geom_smooth(method='lm', formula= y~x, color = "#009966") +
labs(x = "", y = "") +
ggtitle(paste("Price/Book vs", selected_original_names[j])) +
theme_classic()
j = j+1
}
do.call(grid.arrange,ps)
Sales
indicator <- nums_names %in% selected_financials[selected_financials != "sales"]
selected_original_names <- nums_original_names[indicator]
#loop through selected financial variable names without sales to plot each numeric variable cube root transformated with selected variable
ps <- list()
j = 1
for(i in c(selected_financials[selected_financials != "sales"])){
ps[[j]] <- financials %>%
ggplot(aes(x=sales^(1/3), y = cube_root(!!sym(i)))) +
geom_point(col = "black", alpha = 0.2) +
geom_smooth(method='lm', formula= y~x, color = "#009966") +
labs(x = "", y = "") +
ggtitle(paste("Sales vs", selected_original_names[j])) +
theme_classic()
j = j+1
}
do.call(grid.arrange,ps)
Net Profit
indicator <- nums_names %in% selected_financials[selected_financials != "net_profit"]
selected_original_names <- nums_original_names[indicator]
#loop through selected financial variable names to plot each numeric variable cube root transformated with sector
ps <- list()
j = 1
for(i in c(selected_financials[selected_financials != "net_profit"])){
ps[[j]] <- financials %>%
ggplot(aes(x=net_profit^(1/3), y = cube_root(!!sym(i)))) +
geom_point(col = "black", alpha = 0.2) +
geom_smooth(method='lm', formula= y~x, color = "#009966") +
labs(x = "", y = "") +
ggtitle(paste("Net Profit vs", selected_original_names[j])) +
theme_classic()
j = j+1
}
do.call(grid.arrange,ps)
Stefan1896/Company_Financials documentation built on March 19, 2023, 1:05 p.m.
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
knitr::opts_chunk$set(out.width="100%", fig.height = 4.5, split=FALSE, fig.align = 'default', comment = NA) options(dplyr.summarise.inform = FALSE) knitr::opts_chunk$set(echo=TRUE, error=FALSE, message=FALSE, warning=FALSE) options(scipen=999)
Introduction
This Markdown is part of a package where company financial data from S&P 500 companies is explored using a Shiny App. The aim of this Markdown is to perform all core back-end analysis of the application without any reactivity. This document will therefore be the template then for developing the Shiny App. The goal of the whole package is to learn how to develop an Shiny App as a package using the golem framework.
The dataset which is used in this project includes 505 rows with 14 variables.
Goals:
- Exploratory Overview of S&P 500 companies using Markdown and Shiny
- Learning the Golem Framework for developing Shiny Apps as a package
Preperations {.tabset}
Load Packages
First, relevant packages are loaded. We load a range of libraries for general data wrangling and general visualisation.
library(here) #used for folder navigation library(readr) #used to read data as tibble library(skimr) #used to get overview of data library(janitor) #used to clean variable names library(dplyr) #used for data wrangling library(ggplot2) #used for graphs library(gridExtra) #used for graphs (arrange in gridges)
Load Data
The data was downloaded from kaggle and stored locally (login necessary). The here package is used to locate the files relative to the project root. 10 out of 505 observations have at least one missing value.
financials <- read_csv(here("data-raw","company_financials.csv")) cat(dim(financials[!complete.cases(financials),])[1], "out of", nrow(financials), "observations have at least one missing value.")
Data Overview and Preprocessing {.tabset}
Overview
We have a first look at the dataset:
skim(financials)
Notes:
-
There is some valuable information in this quick overview. The missing datapoints are in the variables Price/Earnings and Price/Book.
-
The variables are already classified as numeric and character. From the character variables, Sector is the only one which has not all unique characters.
-
Nearly all of the company Financials are right skewed.
-
The variable names are not clean, since they include spaces and variables which start with a number We clean them directly using the janitor package.
-
It is possible to calculate a sales variable, using the market cap and price/sales information. We can also calculate a Net Profit variable using earnings per share, market cap and price per share.
Preprocessing
Based on the notes from the Overview, we will clean the names and add a sales and a net profit variable to the data. We then again look at the final variable names:
#clean names and get sales variable names_original <- c(names(financials), "Sales", "Net Profit") names(financials) <- make_clean_names(names(financials)) financials <- financials %>% mutate(sales = market_cap/price_sales, net_profit = earnings_share * (market_cap/price)) names(financials)
Univariate Data Exploration {.tabset}
Numeric Variables
First, let us have a look at the distribution of the numeric variables (Company Financials):
#Save indicator whether variable is numeric or not nums <- unlist(lapply(financials, is.numeric)) #save cleaned names and original names in vector (original names are used as title of x axis) nums_names <- names(financials)[nums] nums_original_names <- names_original[nums] #loop through numeric variable names to plot each numeric variable (distribution) p <- list() j = 1 for(i in c(nums_names)){ p[[j]] <- ggplot(financials, aes_string(x=i)) + geom_histogram(aes(y=..density..), colour="black", fill="white")+ geom_density(alpha=.2, fill="#009966")+ labs(x = nums_original_names[j], y = "") + theme_classic() + theme(axis.text.x = element_blank(), axis.text.y = element_blank()) j = j+1 } do.call(grid.arrange,p)
Notes:
-
Again, we see that many of the company financials are right skewed.
-
We will use cube root transformation in exploring relationships later.
Character Variable
Second, let us have a closer look at the character variables containing company Information. We will only look at sector, since this is the only character variable which not only has unique values for each datapoint.
ggplot(financials, aes(sector)) + geom_bar(fill = "#009966", alpha = 0.2, color = "black") + theme_classic() + labs(x = "Sector", y = "Count") + coord_flip()
Notes:
-
We have for all sectors at least 20 datapoints except for Telecommunication Services.
-
When exploring the relationship of sector with company financials, we will exclude Telecommunaction Services since the number of datapoints is too low.
Multivariate Data Exploration
In this sections, we will explore the relationships of our character variable sector with the company financials as well as the relationships between different company financials. The goal here is to give a quick overview of the relationships in the data, there will be no further statistics like effect sizes to further explore the size of effects. Since we are dealing with a lot of extreme values and skeweness, a Cube Root Transfomration will be used for some analysis. We will only concentrate on financials which do have a desired meaning for us. For example, price will not be explored, since this is only gives information about the price per share, which is not meaningful for our analysis without looking also at the number of shares issued.
Cube root transformation:
The cube root transformation involves converting x to x^(1/3). This is a fairly strong transformation with a substantial effect on distribution shape: but is weaker than the logarithm. It can be applied to negative and zero values too.
Top/Bottom 10 Companies {.tabset}
First, let us look at the top and botton 10 companies of several financials:
selected_financials <- c("price_earnings", "market_cap", "ebitda", "price_sales","price_book", "sales","net_profit") indicator <- nums_names %in% selected_financials selected_original_names <- nums_original_names[indicator] top <- list() bot <- list() j = 1 for(i in c(selected_financials)){ top[[j]] <- financials %>% arrange(desc(!!sym(i))) %>% head(10) %>% ggplot(aes(x=reorder(name, !!sym(i)), y = !!sym(i))) + geom_bar(stat = "identity", fill = "#009966", alpha = 0.2, color = "black") + labs(x = "", y = "") + ggtitle(paste("Top 10 -", selected_original_names[j])) + theme_classic() + coord_flip() j = j+1 } j = 1 for(i in c(selected_financials)){ bot[[j]] <- financials %>% arrange(desc(!!sym(i))) %>% tail(10) %>% ggplot(aes(x=reorder(name, !!sym(i)), y = !!sym(i))) + geom_bar(stat = "identity", fill = "indianred", alpha = 0.2, color = "black") + labs(x = "", y = "") + ggtitle(paste("Bottom 10 -", selected_original_names[j])) + theme_classic() + coord_flip() j = j+1 }
Price/Earnings
top[[1]]
bot[[1]]
Market Cap
top[[2]]
bot[[2]]
EBITDA
top[[3]]
bot[[3]]
Price/Sales
top[[4]]
bot[[4]]
Price/Book
top[[5]]
bot[[5]]
Sales
top[[6]]
bot[[6]]
Net Profit
top[[7]]
bot[[7]]
Relationship Sector/Financials {.tabset}
#make function for cube_root formatting cube_root <- function(x) { sign(x) * abs(x)^(1/3) } #loop through numeric variable names to plot each numeric variable cube root transformatted with sector pt <- list() j = 1 for(i in c(nums_names)){ pt[[j]] <- financials %>% filter(sector != "Telecommunication Services") %>% ggplot(aes(x=sector, y = cube_root(!!sym(i)))) + geom_boxplot(outlier.shape = NA) + geom_jitter(width=0.1, alpha=0.2, color = "#009966") + labs(x = "", y = paste(nums_original_names[j], "- Cube Root transformatted")) + theme_classic() + coord_flip() j = j+1 }
Price/Earnings
pt[[2]]
Dividend Yield
financials %>% filter(sector != "Telecommunication Services") %>% ggplot(aes(x=sector, y = dividend_yield)) + geom_boxplot(outlier.shape = NA) + geom_jitter(width=0.1, alpha=0.2, color = "#009966") + labs(x = "", y = "Dividend Yield") + theme_classic() + coord_flip()
Market Cap
pt[[7]]
EBITDA
pt[[8]]
Price/Sales
pt[[9]]
Price/Book
pt[[10]]
Sales
pt[[11]]
Net Profit
pt[[12]]
Relationship Financials {.tabset}
Similar to the graphs with sector, we will now for each relevant financial variable plot its relationship to the others. For all graphs in this section Cube root transformation is used. In general, we see a positiv relationship between the market cap, revenue (sales) and profit (EBITDA and net profit) variables, as expected.
Price/Earnings
indicator <- nums_names %in% selected_financials[selected_financials != "price_earnings"] selected_original_names <- nums_original_names[indicator] #loop through selected financial variable names without sales to plot each numeric variable cube root transformated with selected variable ps <- list() j = 1 for(i in c(selected_financials[selected_financials != "price_earnings"])){ ps[[j]] <- financials %>% ggplot(aes(x=price_earnings^(1/3), y = cube_root(!!sym(i)))) + geom_point(col = "black", alpha = 0.2) + geom_smooth(method='lm', formula= y~x, color = "#009966") + labs(x = "", y = "") + ggtitle(paste("Price/Earnings vs", selected_original_names[j])) + theme_classic() j = j+1 } do.call(grid.arrange,ps)
Market Cap
indicator <- nums_names %in% selected_financials[selected_financials != "market_cap"] selected_original_names <- nums_original_names[indicator] #loop through selected financial variable names without sales to plot each numeric variable cube root transformated with selected variable ps <- list() j = 1 for(i in c(selected_financials[selected_financials != "market_cap"])){ ps[[j]] <- financials %>% ggplot(aes(x=market_cap^(1/3), y = cube_root(!!sym(i)))) + geom_point(col = "black", alpha = 0.2) + geom_smooth(method='lm', formula= y~x, color = "#009966") + labs(x = "", y = "") + ggtitle(paste("Market Cap vs", selected_original_names[j])) + theme_classic() j = j+1 } do.call(grid.arrange,ps)
EBITDA
indicator <- nums_names %in% selected_financials[selected_financials != "ebitda"] selected_original_names <- nums_original_names[indicator] #loop through selected financial variable names without sales to plot each numeric variable cube root transformated with selected variable ps <- list() j = 1 for(i in c(selected_financials[selected_financials != "ebitda"])){ ps[[j]] <- financials %>% ggplot(aes(x=ebitda^(1/3), y = cube_root(!!sym(i)))) + geom_point(col = "black", alpha = 0.2) + geom_smooth(method='lm', formula= y~x, color = "#009966") + labs(x = "", y = "") + ggtitle(paste("EBITDA vs", selected_original_names[j])) + theme_classic() j = j+1 } do.call(grid.arrange,ps)
Price/Sales
indicator <- nums_names %in% selected_financials[selected_financials != "price_sales"] selected_original_names <- nums_original_names[indicator] #loop through selected financial variable names without sales to plot each numeric variable cube root transformated with selected variable ps <- list() j = 1 for(i in c(selected_financials[selected_financials != "price_sales"])){ ps[[j]] <- financials %>% ggplot(aes(x=price_sales^(1/3), y = cube_root(!!sym(i)))) + geom_point(col = "black", alpha = 0.2) + geom_smooth(method='lm', formula= y~x, color = "#009966") + labs(x = "", y = "") + ggtitle(paste("Price/Sales vs", selected_original_names[j])) + theme_classic() j = j+1 } do.call(grid.arrange,ps)
Price/Book
indicator <- nums_names %in% selected_financials[selected_financials != "price_book"] selected_original_names <- nums_original_names[indicator] #loop through selected financial variable names without sales to plot each numeric variable cube root transformated with selected variable ps <- list() j = 1 for(i in c(selected_financials[selected_financials != "price_book"])){ ps[[j]] <- financials %>% ggplot(aes(x=price_book^(1/3), y = cube_root(!!sym(i)))) + geom_point(col = "black", alpha = 0.2) + geom_smooth(method='lm', formula= y~x, color = "#009966") + labs(x = "", y = "") + ggtitle(paste("Price/Book vs", selected_original_names[j])) + theme_classic() j = j+1 } do.call(grid.arrange,ps)
Sales
indicator <- nums_names %in% selected_financials[selected_financials != "sales"] selected_original_names <- nums_original_names[indicator] #loop through selected financial variable names without sales to plot each numeric variable cube root transformated with selected variable ps <- list() j = 1 for(i in c(selected_financials[selected_financials != "sales"])){ ps[[j]] <- financials %>% ggplot(aes(x=sales^(1/3), y = cube_root(!!sym(i)))) + geom_point(col = "black", alpha = 0.2) + geom_smooth(method='lm', formula= y~x, color = "#009966") + labs(x = "", y = "") + ggtitle(paste("Sales vs", selected_original_names[j])) + theme_classic() j = j+1 } do.call(grid.arrange,ps)
Net Profit
indicator <- nums_names %in% selected_financials[selected_financials != "net_profit"] selected_original_names <- nums_original_names[indicator] #loop through selected financial variable names to plot each numeric variable cube root transformated with sector ps <- list() j = 1 for(i in c(selected_financials[selected_financials != "net_profit"])){ ps[[j]] <- financials %>% ggplot(aes(x=net_profit^(1/3), y = cube_root(!!sym(i)))) + geom_point(col = "black", alpha = 0.2) + geom_smooth(method='lm', formula= y~x, color = "#009966") + labs(x = "", y = "") + ggtitle(paste("Net Profit vs", selected_original_names[j])) + theme_classic() j = j+1 } do.call(grid.arrange,ps)
R Package Documentation
Browse R Packages
We want your feedback!
Note that we can't provide technical support on individual packages. You should contact the package authors for that.
Embedding an R snippet on your website
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.