Bootcamp

library(esquisse)
library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.3     ✔ readr     2.1.4
✔ forcats   1.0.0     ✔ stringr   1.5.0
✔ ggplot2   3.4.4     ✔ tibble    3.2.1
✔ lubridate 1.9.3     ✔ tidyr     1.3.0
✔ purrr     1.0.2     
── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
✖ dplyr::filter() masks stats::filter()
✖ dplyr::lag()    masks stats::lag()
ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

library(ggplot2)

library(dplyr)
library(ggplot2)


# the URL of our data on GitHub
github_url <- "https://raw.githubusercontent.com/t-emery/sais-susfin_data/main/datasets/etf_comparison-2022-10-03.csv"


# read the data from GitHub
blackrock_esg_vs_non_esg_etf <- github_url |> 
  read_csv() |> 
  # select the four columns we will use in our anlaysis here
  select(company_name:standard_etf)

Rows: 537 Columns: 14
── Column specification ────────────────────────────────────────────────────────
Delimiter: ","
chr (4): ticker, company_name, sector, esg_uw_ow
dbl (7): esg_etf, standard_etf, esg_tilt, esg_tilt_z_score, esg_tilt_rank, e...
lgl (3): in_esg_only, in_standard_only, in_on_index_only

ℹ Use `spec()` to retrieve the full column specification for this data.
ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.

ggplot(`blackrock_esg_vs_non_esg_etf`) +
 aes(x = esg_etf, y = standard_etf, colour = sector) +
 geom_point(shape = "bullet", 
 size = 1.5) +
 geom_smooth(span = 0.54) +
 scale_color_manual(values = c(Communication = "#F8766D", 
`Consumer Discretionary` = "#DA8C15", `Consumer Staples` = "#ACA000", Energy = "#58B016", Financials = "#00BB4C", 
`Health Care` = "#00C19F", Industrials = "#00BAD5", `Information Technology` = "#3AA7F3", Materials = "#918BFD", 
`Real Estate` = "#E26EEF", Utilities = "#FF61C3")) +
 scale_x_continuous(trans = "log10") +
 scale_y_continuous(trans = "log10") +
 labs(title = "Shiyu Liao", subtitle = "Good！！！") +
 theme_classic() +
 theme(plot.title = element_text(size = 17L, 
 face = "bold", hjust = 0.5)) +
 facet_wrap(vars(sector))

Warning: Transformation introduced infinite values in continuous x-axis

Warning: Transformation introduced infinite values in continuous y-axis

Warning: Transformation introduced infinite values in continuous x-axis

Warning: Transformation introduced infinite values in continuous y-axis

`geom_smooth()` using method = 'loess' and formula = 'y ~ x'

Warning: Removed 261 rows containing non-finite values (`stat_smooth()`).

Warning in max(ids, na.rm = TRUE): no non-missing arguments to max; returning
-Inf

##1.5.1.3
blackrock_esg_vs_non_esg_etf_long <- blackrock_esg_vs_non_esg_etf |> 
  # we'll learn a lot more about long data & pivot_longer() in future weeks. 
  pivot_longer(cols = contains("etf"), names_to = "fund_type", values_to = "weight") |> 
  # case_when() is like an extended "if else"
  mutate(fund_type = case_when(fund_type == "esg_etf" ~ "ESG ETF (ESGU)",
                               fund_type == "standard_etf" ~ "Standard ETF (IVV)"))

blackrock_esg_vs_non_esg_etf_long

# A tibble: 1,074 × 4
   company_name                  sector                 fund_type         weight
   <chr>                         <chr>                  <chr>              <dbl>
 1 PRUDENTIAL FINANCIAL INC      Financials             ESG ETF (ESGU)    0.537 
 2 PRUDENTIAL FINANCIAL INC      Financials             Standard ETF (IV… 0.106 
 3 GENERAL MILLS INC             Consumer Staples       ESG ETF (ESGU)    0.552 
 4 GENERAL MILLS INC             Consumer Staples       Standard ETF (IV… 0.151 
 5 KELLOGG                       Consumer Staples       ESG ETF (ESGU)    0.453 
 6 KELLOGG                       Consumer Staples       Standard ETF (IV… 0.0592
 7 AUTOMATIC DATA PROCESSING INC Information Technology ESG ETF (ESGU)    0.649 
 8 AUTOMATIC DATA PROCESSING INC Information Technology Standard ETF (IV… 0.312 
 9 ECOLAB INC                    Materials              ESG ETF (ESGU)    0.441 
10 ECOLAB INC                    Materials              Standard ETF (IV… 0.118 
# ℹ 1,064 more rows

blackrock_esg_vs_non_esg_etf_long %>%
  ##filter is the tool to change the weight,
  filter(weight >= 1L & weight <= 7L) %>%
  ggplot() +
  ##for aes we basically set up all the variable that we need.
  aes(
    x = weight,
    y = company_name,
    colour = fund_type,
    size = weight
  ) +
  ##here we go a point chart with shape of each point 'circle'
  geom_point(shape = "circle") +
  ##set up the point color for different variables
  scale_color_manual(
    values = c(`ESG ETF (ESGU)` = "#15C179",
               `Standard ETF (IVV)` = "#A6A59F")
  ) +
  ##we add title here
  labs(title = "Shiyu Liao", subtitle = "developing ESG") +
  theme_bw() +
  ##theme for my title
  theme(
    plot.title = element_text(size = 19L,
                              face = "bold",
                              hjust = 0.5),
    plot.subtitle = element_text(hjust = 0.5)
  )

##This chart tells us how many ETFs of these major companies are based on ESG
##and how many are not based on ESG. Several technology companies are very large 
##in this picture. This is a big problem because these technology companies have
##a great impact on ESG, which greatly aggravates the risk of developing ESG. 
##And because the point is too large, I can’t see Apple’s weight clearly.

##1.5.1.4
blackrock_esg_vs_non_esg_etf %>%
  filter(esg_etf >= 0.9 & esg_etf <= 7) %>%
  ##it's a filter to filt in the esg etf above and bwloe 0.9,7.
  ggplot() +
  aes(x = company_name, y = esg_etf, fill = sector) +
  ##we basically build a col chart
  geom_col() +
  scale_fill_hue(direction = 1) +
  ##label part, I set up the title and the author's name
  labs(
    title = "Company above 1 weight in esg market",
    subtitle = "by Jack"
  ) +
  ##size, face of the title
  theme_minimal() +
 theme(
    plot.title = element_text(size = 20L, face = "bold", hjust = 0.5),
    axis.text.x = element_text(angle = 45, vjust = 1, hjust=1, size = 10)
  )

##Second one
blackrock_esg_vs_non_esg_etf_long %>%
  filter(weight >= 0.9 & weight <= 7) %>%
  ggplot() +
  aes(x = company_name, fill = fund_type, weight = weight) +
  geom_bar() +
  scale_fill_hue(direction = 1) +
  labs(
    title = "Compare the weight of each type of fund",
    subtitle = "by jack"
  ) +
  theme_minimal() +
  theme(
    plot.title = element_text(size = 20L, face = "bold", hjust = 0.5),
    axis.text.x = element_text(angle = 45, vjust = 1, hjust=1, size = 10) 
  )

##1.5.2.1

library(ggplot2)
ggplot(blackrock_esg_vs_non_esg_etf) +
  aes(x = esg_etf, y = standard_etf, colour = sector, group = 1) +##set up the x, y, color
  geom_point(shape = "circle", size = 1.5) +
  geom_smooth(method = "lm", formula = y ~ poly(x, 3, raw = TRUE)) + ##here we set up a line, in order to make it curve, we do poly.
  scale_color_hue(direction = 1) +
  scale_x_continuous(trans = "log10") +##basic log
  scale_y_continuous(trans = "log10") +
  theme_minimal()## theme of our title

Warning: Transformation introduced infinite values in continuous x-axis

Warning: Transformation introduced infinite values in continuous y-axis

Warning: Transformation introduced infinite values in continuous x-axis

Warning: Transformation introduced infinite values in continuous y-axis

Warning: Removed 261 rows containing non-finite values (`stat_smooth()`).

Warning: The following aesthetics were dropped during statistical transformation: colour
ℹ This can happen when ggplot fails to infer the correct grouping structure in
  the data.
ℹ Did you forget to specify a `group` aesthetic or to convert a numerical
  variable into a factor?

##simple one we just basically set up the smooth and log
ggplot(blackrock_esg_vs_non_esg_etf) +
 aes(x = esg_etf, y = standard_etf, colour = sector) +
 geom_point(shape = "circle", 
 size = 1.5) +
 geom_smooth(span = 0.75) +
 scale_color_hue(direction = 1) +
 scale_x_continuous(trans = "log10") +
 scale_y_continuous(trans = "log10") +
 theme_minimal()

Warning: Transformation introduced infinite values in continuous x-axis

Warning: Transformation introduced infinite values in continuous y-axis

Warning: Transformation introduced infinite values in continuous x-axis

Warning: Transformation introduced infinite values in continuous y-axis

`geom_smooth()` using method = 'loess' and formula = 'y ~ x'

Warning: Removed 261 rows containing non-finite values (`stat_smooth()`).

ggplot(blackrock_esg_vs_non_esg_etf) +
  aes(x = esg_etf, y = standard_etf, colour = sector, group = 1) +
  geom_point(shape = "circle", size = 1.5, colour = "purple") + ##basically we only need purple 
  geom_smooth(method = "lm", formula = y ~ poly(x, 3, raw = TRUE), colour = "yellow") +##set the color for smooth line
  scale_color_manual(values = "purple") + 
  scale_x_continuous(trans = "log10") +
  scale_y_continuous(trans = "log10") +
  theme_minimal()

Warning: Transformation introduced infinite values in continuous x-axis

Warning: Transformation introduced infinite values in continuous y-axis

Warning: Transformation introduced infinite values in continuous x-axis

Warning: Transformation introduced infinite values in continuous y-axis

Warning: Removed 261 rows containing non-finite values (`stat_smooth()`).

##1.5.3

library(ggplot2)
ggplot(blackrock_esg_vs_non_esg_etf) +
  aes(x = esg_etf, y = standard_etf, group = 1) +
  geom_point(shape = 21, size = 2, colour = "black", fill = "white") +
  geom_smooth(method = "lm", formula = y ~ x, colour = "blue", se = FALSE) +
  scale_x_continuous(trans = "log10") +  
  scale_y_continuous(trans = "log10") +  
  labs(title = "Relationship between ESG and Standard ETFs", x = "ESG ETF", y = "Standard ETF") +
  theme_minimal() +
  theme(plot.title = element_text(face = "italic", size = 18, hjust = 0.5),
        axis.title = element_text(face = "bold", size = 12),
        axis.text = element_text(size = 10),
        legend.position = "bottom")

Warning: Transformation introduced infinite values in continuous x-axis

Warning: Transformation introduced infinite values in continuous y-axis

Warning: Transformation introduced infinite values in continuous x-axis

Warning: Transformation introduced infinite values in continuous y-axis

Warning: Removed 261 rows containing non-finite values (`stat_smooth()`).

##The key change made was applying a logarithmic transformation to both the 
##x-axis and y-axis of the plot. This transformation helps to better visualize 
##the data when it is highly concentrated in a small range of values, 
##effectively spreading out the data points and allowing for clearer interpretation of trends and relationships.

Last question

install.packages(“ggthemes”)library(ggthemes)ggplot(blackrock_esg_vs_non_esg_etf) + aes(x = esg_etf, y = standard_etf, colour = sector, group = 1) + geom_point(shape = 21, size = 2, fill = “white”) + geom_smooth(method = “lm”, formula = y ~ poly(x, 3, raw = TRUE), colour = “blue”) + scale_color_hue(direction = 1) + scale_x_continuous(trans = “log10”) + scale_y_continuous(trans = “log10”) + theme_excel() + labs(title = “Relationship between ESG and Standard ETFs”, x = “ESG ETF”, y = “Standard ETF”)

##The theme function in ggplot2 allows you to personalize the visual aspects of your plot, such as background, axis ticks, and legend placement. With various themes, you can adjust the plot’s style to your liking or to fit specific design needs. In this example, the theme_excel() function from the ggthemes package is utilized to give the plot a resemblance to Microsoft Excel’s appearance.