Deliverable

Homework 1: ‘Esquisse’ for ggplot2

##Installing packages if needed
##install.packages("tidyverse")
##install.packages("ggplot2")
##install.packages("esquisse")
##install.packages("dplyr")
##install.packages("tidyr")
##install.packages("ggridges")
##install.packages("forcats")
##install.packages('gganimate')

##Importing required libraries and packages
library(tidyverse)

── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
✔ dplyr     1.1.4     ✔ 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(esquisse)
library(dplyr)

##Importing the Blackrock Data
library(tidyverse)
library(ggplot2)
library(esquisse)
library(dplyr)

github_url <- "https://raw.githubusercontent.com/t-emery/sais-susfin_data/main/datasets/etf_comparison-2022-10-03.csv"
blackrock_esg_vs_non_esg_etf <- github_url |> 
  read_csv() |>
  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.

##Using Esquisse
##esquisser(blackrock_esg_vs_non_esg_etf)

##Recreating the graph
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") +
  geom_abline()+ #add a 45degree line manually
  labs(
    x = "ESG ETF (ESGU)",
    y = "Standard ETF (IVV)",
    title = "We made this chart using Esquisse!",
    subtitle = "It's a great invention to learn about ggplot2,
    even with its limitations!",
    caption = "Yuhao Shen made this!"
  ) +
  theme_minimal() +
  theme(
    plot.title = element_text(size = 14L,
    face = "bold"),
    plot.caption = element_text(face = "bold.italic"),
    axis.title.y = element_text(face = "bold"),
    axis.title.x = element_text(face = "bold")
  ) +
  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()`).

##Recreating the graph (without any error codes)
ggplot(blackrock_esg_vs_non_esg_etf) +
  aes(x = log10(esg_etf + 1), y = log10(standard_etf + 1)) +
  geom_point(aes(colour = sector), shape = "circle", size = 1.5) +
  geom_smooth(method = 'lm') +
  scale_color_hue(direction = 1) +
  labs(
    x = "ESG ETF (ESGU)",
    y = "Stadard ETF (IVV)",
    title = "Recreating ESG vs non-ESG across sectors",
    subtitle = "Using esquisse",
    caption = "Made by Yuhao Shen"
  ) +
  theme_minimal() +
  theme(
    plot.title = element_text(size = 14L,
    face = "bold"),
    plot.caption = element_text(face = "bold.italic"),
    axis.title.y = element_text(face = "bold"),
    axis.title.x = element_text(face = "bold")
  ) +
  facet_wrap(vars(sector))

`geom_smooth()` using formula = 'y ~ x'

Homework 2: exploring the outliers

##Changing data from wide to long
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

##esquisser(blackrock_esg_vs_non_esg_etf_long)

##Reproducing Esquisse Graphs

library(dplyr)
library(ggplot2)

blackrock_esg_vs_non_esg_etf_long %>%
 filter(weight >= 1L & weight <= 7L) %>% #filter out datapoints that are above 1%
 ggplot() +
  aes(
    x = weight,
    y = company_name,
    colour = fund_type,
    size = weight
  ) +
  geom_point(shape = "circle") + #scatter plot
  scale_color_manual(
    values = c(`ESG ETF (ESGU)` = "#76F856",
    `Standard ETF (IVV)` = "#C9C9C9")
  ) + #changing the colors that represent different funds
  labs(
    x = "Weight (%)",
    y = "Company Names",
    title = "Portfolio Weight Distribution by Company in ESG vs. Standard ETFs",
    subtitle = "with companies over 1% weight",
    caption = "Yuhao Shen made this!",
    color = "Fund Type",
    size = "Weight (%)"
  ) + #labeling legends
  theme_minimal() +
  theme(
    plot.title = element_text(face = "bold"),
    plot.caption = element_text(face = "italic")
  ) #changing the fonts of the title and caption

Implication of the chart

This scatter plot is showing us the weight distribution of the companies in the ESG and non-ESG funds. The larger points suggest larger weights in the funds where the colors represent different types of funds. Noticeably, both funds seem to have adopted similar strategies selecting weights in these large cap companies.

Homework 3: Making Your Own Graphs

First Graph

##esquisser(blackrock_esg_vs_non_esg_etf_long)

##Reproducing Esquisse Graphs

library(dplyr)
library(ggplot2)

blackrock_esg_vs_non_esg_etf_long %>%
 filter(sector %in% c("Financials", "Utilities", "Real Estate")) %>%
 filter(weight >= 0.1 & weight <= 1) %>% #filter for selceted sectors and weights
 ggplot() +
  aes(
    x = weight,
    y = company_name,
    colour = fund_type, #color coding the ESG and Non-ESG funds
    size = weight #size of points shows graphically the size of weights
  ) +
  geom_point(shape = "circle") +  #scatter plot
  scale_color_hue(direction = 1) +
  labs(
    x = "Weight Distribution (%)",
    y = "Company Name",
    title = "Comparison of ESG Commitment Across Three Sectors",
    subtitle = "Looking at weights that are between 0 to 1% in the funds",
    caption = "Made by Yuhao Shen",
    color = "Fund Type",
    size = "Weight"
  ) +
  theme_minimal() +
  theme(
    plot.title = element_text(face = "bold"),
    plot.subtitle = element_text(face = "italic"),
    plot.caption = element_text(face = "bold.italic")
  ) +
  facet_wrap(vars(sector)) #facet by the different sectors

Implication of the chart

This scatter plot is showing us the weight distribution of the small percentage companies (0% to 1% weight) in the ESG and non-ESG funds. The larger points suggest larger weights in the funds where the colors represent different types of funds. Noticeably, we can see that the two funds seem to have a more different strategy investing in smaller percentage firms.

Second Graph

##esquisser(blackrock_esg_vs_non_esg_etf_long)

library(ggplot2)

ggplot(blackrock_esg_vs_non_esg_etf_long) +
  aes(x = weight, y = sector, colour = fund_type) +
  geom_boxplot(fill = "#112446") +
  scale_color_manual(
    values = c(`ESG ETF (ESGU)` = "#76F856",
    `Standard ETF (IVV)` = "#C9C9C9")
  ) +
  scale_x_continuous(trans = "log10") +
  labs(
    x = "Weight (log10)",
    y = "Sectors",
    title = "Box Plot Showing How Fund Strategies Differ",
    subtitle = "with log10 x(weight) scale ",
    caption = "Made by Yuhao Shen",
    color = "Fund Type"
  ) +
  theme_minimal() +
  theme(
    plot.title = element_text(face = "bold"),
    plot.subtitle = element_text(face = "italic"),
    plot.caption = element_text(face = "bold.italic")
  )

Warning: Transformation introduced infinite values in continuous x-axis

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

ggplot(blackrock_esg_vs_non_esg_etf_long) +
  aes(x = log10(weight + 1), y = sector) +  #fixing for values of log10(0)
  geom_point(aes(colour = fund_type))+
  geom_boxplot(fill = "#112446") +
  scale_color_manual(
    values = c(`ESG ETF (ESGU)` = "#76F856",
    `Standard ETF (IVV)` = "#C9C9C9")
  ) +
  labs(
    x = "Weight (log10)",
    y = "Sectors",
    title = "Box Plot Showing How Fund Strategies Differ",
    subtitle = "with log10 x(weight) scale ",
    caption = "Made by Yuhao Shen",
    color = "Fund Type"
  ) +
  theme_minimal() +
  theme(
    plot.title = element_text(face = "bold"),
    plot.subtitle = element_text(face = "italic"),
    plot.caption = element_text(face = "bold.italic")
  )

Implication of the chart

This box plot is showing us the distribution of the companies in the ESG and non-ESG funds. We can see that ESG in general has a similar interquartile range of distribution to that of a non-ESG funds, which leads us to think about how different are these two types of funds.

Homework 4

Reproduction of ‘elegantaly’ fixed graph 1

#?geom_smooth
ggplot(blackrock_esg_vs_non_esg_etf) + 
  aes(x = log10(esg_etf + 1), y = log10(standard_etf + 1)) +
  geom_point(shape = 'circle', size = 1.5, aes(colour = sector)) + 
  #Since we want points to be colored based on species but don’t want the lines 
  #to be separated out for them, we should specify color = species for geom_point() only.
  geom_smooth(method = "lm", formula = y ~ poly(x, 3), se = TRUE) +
  labs(
    x = "ESG ETF (ESGU)",
    y = "Stadard ETF (IVV)",
  ) 

Reproduction of non-fixed graph 2

ggplot(blackrock_esg_vs_non_esg_etf) + 
  aes(x = esg_etf, y = standard_etf, color = sector) + 
  #having the color here means we're passing down the different labels to geom_points
  geom_point(shape = 'circle', size = 1.5) + 
  geom_smooth(method = "lm", formula = y ~ poly(x, 3), se = TRUE) +
  labs(
    x = "ESG ETF (ESGU)",
    y = "Standard ETF (IVV)",
  ) +
  scale_x_log10()+
  scale_y_log10()

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()`).

Reproduction of ‘elegantly’ fixed graph 3

ggplot(blackrock_esg_vs_non_esg_etf) + 
  aes(x = esg_etf, y = standard_etf) +
  #NO color coding means that are points are treated as one
  geom_point(shape = 'circle', size = 1.5, color = "purple") + 
  geom_smooth(method = "lm", formula = y ~ poly(x, 3), se = TRUE, color = "yellow") +
  labs(
    x = "ESG ETF (ESGU)",
    y = "Standard ETF (IVV)",
  ) +
  scale_x_log10()+
  scale_y_log10()

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()`).

Some fancy and fun stuff

Ridgeline Plot

library(ggridges)
library(ggplot2)
library(dplyr)
library(tidyr)
library(forcats)
#?scale_fill_viridis_b

ggplot(blackrock_esg_vs_non_esg_etf_long, aes(x = weight, y = sector, fill = ..x..)) +
  geom_density_ridges_gradient(scale = 3, rel_min_height = 0.01) +
  scale_fill_viridis_b(name = "Weight, %", option = "B") +
  labs(title = 'Ridgeline plot showing frequency of investment in each sectors')

Warning: The dot-dot notation (`..x..`) was deprecated in ggplot2 3.4.0.
ℹ Please use `after_stat(x)` instead.

Picking joint bandwidth of 0.0435

Animated :( Tried and failed

library(gganimate)

No renderer backend detected. gganimate will default to writing frames to separate files
Consider installing:
- the `gifski` package for gif output
- the `av` package for video output
and restarting the R session

##github_url <- "https://raw.githubusercontent.com/t-emery/sais-susfin_data/main/datasets/etf_comparison-2022-10-03.csv"
##blackrock_esg_vs_non_esg_etf_standard <- github_url |> 
  ##read_csv() |>
  #select(company_name:standard_etf)

#ggplot(blackrock_esg_vs_non_esg_etf_long, aes(weight, company_name , colour = fund_type)) +
#  geom_point(alpha = 0.7, show.legend = FALSE) +
#  scale_size(range = c(2, 12)) +
#  scale_x_log10() +
#  facet_wrap(~sector) +
#  # Here comes the gganimate specific bits
#  transition_state(
#  weight,
#    transition_length = 2,
#    state_length = 1
#  ) +
#  enter_fade() + 
#  exit_shrink() +
#  ease_aes('sine-in-out')

#ggplot(blackrock_esg_vs_non_esg_etf_long, aes(factor(weight), fund_type)) + 
#  geom_boxplot() + 
#  # Here comes the gganimate code
#  transition_states(
#    gear,
#    transition_length = 2,
#    state_length = 1
#  ) +
#  enter_fade() + 
#  exit_shrink() +
#  ease_aes('sine-in-out')

Thank you so much for sticking around!