library(esquisse)
library(readr)
library(dplyr)
Attaching package: 'dplyr'The following objects are masked from 'package:stats':
filter, lagThe following objects are masked from 'package:base':
intersect, setdiff, setequal, unionlibrary(ggplot2)
library(tidyr)
library(ggiraph)# 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.blackrock_esg_vs_non_esg_etf# A tibble: 537 × 4
company_name sector esg_etf standard_etf
<chr> <chr> <dbl> <dbl>
1 PRUDENTIAL FINANCIAL INC Financials 0.537 0.106
2 GENERAL MILLS INC Consumer Staples 0.552 0.151
3 KELLOGG Consumer Staples 0.453 0.0592
4 AUTOMATIC DATA PROCESSING INC Information Technolo… 0.649 0.312
5 ECOLAB INC Materials 0.441 0.118
6 JOHNSON CONTROLS INTERNATIONAL PLC Industrials 0.416 0.112
7 EVERSOURCE ENERGY Utilities 0.392 0.0896
8 PUBLIC SERVICE ENTERPRISE GROUP IN Utilities 0.376 0.0929
9 RAYTHEON TECHNOLOGIES CORP Industrials 0.677 0.401
10 CHENIERE ENERGY INC Energy 0.274 0
# ℹ 527 more rowsggplot(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_viridis_d(option = "plasma", direction = 1) +
scale_x_continuous(trans = "log10") +
scale_y_continuous(trans = "log10") +
labs(
x = " ESG ETF (ESGU)",
y = "Standard ETF(IVV)",
title = "ESG ETF vs. Standard ETF",
caption = "Sophia Wang"
) +
theme_minimal() +
facet_wrap(vars(sector))Warning: Transformation introduced infinite values in continuous x-axisWarning: Transformation introduced infinite values in continuous y-axisWarning: Transformation introduced infinite values in continuous x-axisWarning: 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()`).
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#import the dataset
blackrock_esg_vs_non_esg_etf_long %>%
#limit the weight variable to companies over a 1% weight
filter(weight >= 1 & weight <= 7) %>%
#set up the variables of the plot
ggplot() +
aes(
x = weight,
y = company_name,
colour = fund_type,
size = weight
) +
geom_point(shape = "circle") +
#set up the color for different groups
scale_color_manual(
values = c(`ESG ETF (ESGU)` = "#6DF874",
`Standard ETF (IVV)` = "#A19D9F")
) +
#set up the names of axis and the title of the graph
labs(
x = "weight",
y = "Company name",
title = "Weight of the Fund",
caption = "Sophia Wang"
) +
theme_minimal()
The graph is a bubble graph showing the weight of two different groups of funds: ESG ETF and Standard ETF, and the size of the bubble are corresponds to the weight of the company in the ETF. In the graph we can see that there are some larges outliers like Apple INC and Microsoft INC and there outliers indicate that these companies have a significant weight within ETF.
ggplot(blackrock_esg_vs_non_esg_etf_long) +
aes(x = fund_type, y = weight, colour = sector) +
geom_boxplot(fill = "#112446") +
scale_color_hue(direction = 1) +
labs(
x = "Weight",
y = "Fund Type",
title = "Distribution of Weights in ETF by Sector",
caption = "Sophia Wang"
) +
theme_minimal()
The purpose of this boxplot is to figure out of the weight distributed by fund type and sectors. The plot shows which sectors have a wider range of weights versus those that are more uniform. From the plot we can know that in most industries the weight of ESG ETF is higher than Standard ETF.
ggplot(blackrock_esg_vs_non_esg_etf) +
aes(x = esg_etf, y = standard_etf) +
geom_point(shape = "circle", size = 1.5, colour = "#112446") +
geom_smooth(span = 0.75) +
scale_x_continuous(trans = "log10") +
scale_y_continuous(trans = "log10") +
labs(
x = "ESG ETF",
y = "Standard ETF",
title = "ESG ETF vs. Standard ETF",
caption = "Sophia Wang"
) +
theme_minimal()Warning: Transformation introduced infinite values in continuous x-axisWarning: Transformation introduced infinite values in continuous y-axisWarning: Transformation introduced infinite values in continuous x-axisWarning: 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()`).
This plot is a scatter plot comparing companies’ weights in an ESG ETF versus a Standard ETF. From this plot, we can infer a positive relationship between the weights in the ESG ETF and the Standard ETF. As the weight in one ETF increases, the weight in the other tends to increase.
aes()# Specifying the dataset and aesthetic mappings
ggplot(blackrock_esg_vs_non_esg_etf) +
# Set up x-axis and y-axis for the plot
aes(x = esg_etf, y = standard_etf) +
# Add points to the plot
geom_point(aes(colour = sector), shape = "circle", size = 1.5) +
# Add a smooth line to show the trend
geom_smooth(span = 0.75) +
scale_color_hue(direction = 1) +
# Transform the scales of the x and y axes to logarithmic
scale_x_continuous(trans = "log10") +
scale_y_continuous(trans = "log10") +
# Apply a minimalistic theme for a clean and simple plot appearance.
theme_minimal() Warning: Transformation introduced infinite values in continuous x-axisWarning: Transformation introduced infinite values in continuous y-axisWarning: Transformation introduced infinite values in continuous x-axisWarning: 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()`).
In the plot we add the aes(colour=sector) in geom_point when add points to just color the point so that we can get only one smooth line in the plot.
# Specifying the dataset and aesthetic mappings
ggplot(blackrock_esg_vs_non_esg_etf) +
# Set up x-axis and y-axis for the plot
aes(x = esg_etf, y = standard_etf, colour = sector) +
# Add points to the plot
geom_point(shape = "circle", size = 1.5) +
# Add a smooth line to show the trend
geom_smooth(span = 0.75) +
scale_color_hue(direction = 1) +
# Transform the scales of the x and y axes to logarithmic
scale_x_continuous(trans = "log10") +
scale_y_continuous(trans = "log10") +
# Apply a minimalistic theme for a clean and simple plot appearance
theme_minimal()Warning: Transformation introduced infinite values in continuous x-axisWarning: Transformation introduced infinite values in continuous y-axisWarning: Transformation introduced infinite values in continuous x-axisWarning: 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()`).
In this plot we put “colour=sector” when setting up the x and y axis so we got smooth lines for different sectors of data
# Specifying the dataset and aesthetic mappings
ggplot(blackrock_esg_vs_non_esg_etf) +
# Set up x-axis and y-axis for the plot
aes(x = esg_etf, y = standard_etf) +
# Add points to the plot and choose the color of points
geom_point(shape = "circle", size = 1.5, colour = "purple") +
# Add a smooth line to show the trend
geom_smooth(span = 0.75, colour = "yellow") +
# Transform the scales of the x and y axes to logarithmic
scale_x_continuous(trans = "log10") +
scale_y_continuous(trans = "log10") +
# Apply a minimalistic theme for a clean and simple plot appearance
theme_minimal()Warning: Transformation introduced infinite values in continuous x-axisWarning: Transformation introduced infinite values in continuous y-axisWarning: Transformation introduced infinite values in continuous x-axisWarning: 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()`).
in this plot we use color to set up the color for both points and smooth line.
ggplot(blackrock_esg_vs_non_esg_etf_long, aes(fill=sector, y=weight, x=fund_type)) +
geom_bar(position="dodge", stat="identity") +
labs(title = "Weight of ETF investment by Sector")
The graph is showing the perfermance of different industries on ETF investment.
ggplot2 Extensions Gallerygg_point=ggplot(data = blackrock_esg_vs_non_esg_etf_long) +
geom_point_interactive(aes(x=company_name, y=weight, color=sector,
tooltip = fund_type, data_id = fund_type)) +
theme_minimal()+
labs(
title = "Distribution of Company Weights in ESG vs. Non-ESG ETFs",
x = "Company Name",
y = "Weight in ETF",
color = "Sector"
)
girafe(ggobj = gg_point)The graph allows to visually assess the composition of ESG versus non-ESG ETFs in terms of companies included, their sectoral distribution, and their relative weights within the funds.