Assignmnet 3b
Sharmin, Kylie, Gianna
2025-11-11
Load & Clean the Data:
library(tidyverse)## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.2
## ✔ ggplot2 4.0.0 ✔ tibble 3.3.0
## ✔ lubridate 1.9.4 ✔ tidyr 1.3.1
## ✔ purrr 1.1.0
## ── 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 errorscol_types_spec <- cols_only(
id = col_integer(),
voyage_id = col_integer(),
voyage_dates__imp_arrival_at_port_of_dis_sparsedate__year = col_double(),
voyage_slaves_numbers__imp_total_num_slaves_disembarked = col_double(),
voyage_slaves_numbers__imp_total_num_slaves_embarked = col_double(),
voyage_dates__length_middle_passage_days = col_double(),
voyage_dates__imp_length_home_to_disembark = col_double(),
voyage_crew__crew_first_landing = col_double(),
voyage_crew__crew_voyage_outset = col_double(),
voyage_ship__tonnage_mod = col_double(),
voyage_slaves_numbers__imp_jamaican_cash_price = col_double(),
voyage_slaves_numbers__imp_mortality_ratio = col_double(),
voyage_slaves_numbers__percentage_women_among_embarked_slaves = col_double(),
voyage_outcome__vessel_captured_outcome__name = col_character(),
voyage_ship__imputed_nationality__name = col_character(),
voyage_itinerary__imp_region_voyage_begin__name = col_character(),
voyage_ship__rig_of_vessel__name = col_character(),
voyage_itinerary__place_voyage_ended__name = col_character(),
# Force as character
voyage_dates__slave_purchase_began_sparsedate__month = col_double(),
voyage_slaves_numbers__percentage_men = col_double(),
voyage_dates__voyage_completed_sparsedate__month = col_double(),
voyage_itinerary__region_of_return__name = col_character(),
voyage_slaves_numbers__percentage_boy = col_double(),
voyage_itinerary__imp_principal_region_slave_dis__name = col_character(),
voyage_itinerary__imp_principal_region_of_slave_purchase__name = col_character(),
voyage_dates__date_departed_africa_sparsedate__month = col_double(),
voyage_dates__voyage_began_sparsedate__month = col_double(),
voyage_itinerary__imp_port_voyage_begin__name = col_character(),
voyage_dates__first_dis_of_slaves_sparsedate__month = col_double(),
voyage_itinerary__imp_broad_region_slave_dis__name = col_character(),
voyage_slaves_numbers__percentage_girl = col_double(),
voyage_outcome__particular_outcome__name = col_character(),
voyage_itinerary__imp_principal_port_slave_dis__name = col_character(),
voyage_slaves_numbers__percentage_child = col_double(),
voyage_slaves_numbers__percentage_women = col_double(),
voyage_dates__departure_last_place_of_landing_sparsedate__month = col_double(),
voyage_outcome__outcome_owner__name = col_character(),
voyage_outcome__outcome_slaves__name = col_character(),
voyage_itinerary__imp_principal_place_of_slave_purchase__name = col_character(),
voyage_outcome__resistance__name = col_character(),
voyage_slaves_numbers__percentage_male = col_double(),
voyage_slaves_numbers__percentage_female = col_double(),
voyage_itinerary__imp_broad_region_voyage_begin__name = col_character(),
voyage_itinerary__imp_broad_region_of_slave_purchase__name = col_character(),
voyage_sources = col_character(),
enslavers = col_character()
)
# Load the datasets
trans <- read_csv("https://raw.githubusercontent.com/imowerman-prog/data-3210/refs/heads/main/Data/trans-atlantic.csv",
col_types = col_types_spec)
intra <- read_csv("https://raw.githubusercontent.com/imowerman-prog/data-3210/refs/heads/main/Data/intra-american.csv",
col_types = col_types_spec)
# Define successful outcomes
successful_outcomes <- c(
"Sold slaves in Americas - subsequent fate unknown",
"Voyage completed as intended",
"Captured by pirates or privateers - after disembarkation",
"Condemned - Americas after disembarkation",
"Detained and condemned in the United States after slaves disembarked",
"Condemned in the Americas by British after slaves disembarked",
"Captured by pirates - slaves sold in Americas from another ship",
"Shipwrecked or destroyed, after disembarkation",
"Privateer captured slaves at sea and delivered for sale in America",
"Prisoners of war stole slaves during escape and carried to port of sale",
"Captives seized from vessel by Spanish officials and sold",
"Captured by Dutch - after disembarkation",
"Shipwrecked, slaves salvaged",
"Captured by slaves, recaptured and landed slaves in the Americas"
)
# Process trans-atlantic data
trans <- trans %>%
rename(
year = voyage_dates__imp_arrival_at_port_of_dis_sparsedate__year,
slaves_embarked = voyage_slaves_numbers__imp_total_num_slaves_embarked,
slaves_disembarked = voyage_slaves_numbers__imp_total_num_slaves_disembarked,
particular_outcome = voyage_outcome__particular_outcome__name,
dis_broad = voyage_itinerary__imp_broad_region_slave_dis__name,
dis_port = voyage_itinerary__imp_principal_port_slave_dis__name,
embark_broad = voyage_itinerary__imp_broad_region_of_slave_purchase__name,
embark_port = voyage_itinerary__imp_principal_place_of_slave_purchase__name
) %>%
mutate(
year = as.integer(year),
slaves_embarked = as.numeric(slaves_embarked),
slaves_disembarked = as.numeric(slaves_disembarked)
) %>%
filter(
!is.na(slaves_disembarked),
slaves_disembarked > 0,
particular_outcome %in% successful_outcomes
) %>%
mutate(
decade = floor(year / 10) * 10,
estimated_deaths = slaves_embarked - slaves_disembarked,
is_us = dis_broad == "Mainland North America" |
grepl("New Orleans", dis_port, ignore.case = TRUE),
embark_is_us = embark_broad == "Mainland North America" |
grepl("New Orleans", embark_port, ignore.case = TRUE),
source_type = "Trans-Atlantic"
)
# Process intra-american data
intra <- intra %>%
rename(
year = voyage_dates__imp_arrival_at_port_of_dis_sparsedate__year,
slaves_embarked = voyage_slaves_numbers__imp_total_num_slaves_embarked,
slaves_disembarked = voyage_slaves_numbers__imp_total_num_slaves_disembarked,
particular_outcome = voyage_outcome__particular_outcome__name,
dis_broad = voyage_itinerary__imp_broad_region_slave_dis__name,
dis_port = voyage_itinerary__imp_principal_port_slave_dis__name,
embark_broad = voyage_itinerary__imp_broad_region_of_slave_purchase__name,
embark_port = voyage_itinerary__imp_principal_place_of_slave_purchase__name
) %>%
mutate(
year = as.integer(year),
slaves_embarked = as.numeric(slaves_embarked),
slaves_disembarked = as.numeric(slaves_disembarked)
) %>%
filter(
!is.na(slaves_disembarked),
slaves_disembarked > 0,
particular_outcome %in% successful_outcomes
) %>%
mutate(
decade = floor(year / 10) * 10,
estimated_deaths = slaves_embarked - slaves_disembarked,
is_us = dis_broad == "Mainland North America" |
grepl("New Orleans", dis_port, ignore.case = TRUE),
embark_is_us = embark_broad == "Mainland North America" |
grepl("New Orleans", embark_port, ignore.case = TRUE),
source_type = "Intra-American"
)
# Combine the datasets
combined <- bind_rows(trans, intra)Question 1:
gross_us <- combined %>%
filter(is_us == TRUE) %>%
summarise(gross_us = sum(slaves_disembarked, na.rm = TRUE)) %>%
pull(gross_us)
re_exports <- combined %>%
filter(source_type == "Intra-American", embark_is_us == TRUE, is_us == FALSE) %>%
summarise(re_exports = sum(slaves_embarked, na.rm = TRUE)) %>%
pull(re_exports)
net_us <- gross_us - re_exports
cat("Gross slaves imported to the US:", gross_us, "\n")## Gross slaves imported to the US: 395919cat("Slaves re-exported from the US:", re_exports, "\n")## Slaves re-exported from the US: 7652cat("Net slaves retained in the US:", net_us, "\n")## Net slaves retained in the US: 388267Question 2:
trans_total_embarked <- trans %>%
summarise(total_embarked = sum(slaves_embarked, na.rm = TRUE)) %>%
pull(total_embarked)
proportion <- net_us / trans_total_embarked
cat("Proportion of all slaves taken from Africa (net US):", proportion, "\n")## Proportion of all slaves taken from Africa (net US): 0.05107614Question 3:
library(ggplot2)
us_by_decade <- combined %>%
filter(is_us == TRUE) %>%
group_by(decade) %>%
summarise(total_disembarked = sum(slaves_disembarked, na.rm = TRUE)) %>%
arrange(decade)
# Plot
ggplot(us_by_decade, aes(x = factor(decade), y = total_disembarked)) +
geom_col(fill = "#4682B4") +
labs(
title = "Slaves Disembarked in US by Decade",
x = "Decade",
y = "Number of Slaves Disembarked"
) +
scale_y_continuous(labels = scales::comma)
Question 4:
us_ports_state <- combined %>%
filter(is_us == TRUE) %>%
mutate(state = case_when(
grepl("New Orleans", dis_port, ignore.case = TRUE) ~ "Louisiana",
grepl("Charleston", dis_port, ignore.case = TRUE) ~ "South Carolina",
grepl("Savannah", dis_port, ignore.case = TRUE) ~ "Georgia",
grepl("Baltimore", dis_port, ignore.case = TRUE) ~ "Maryland",
grepl("Philadelphia", dis_port, ignore.case = TRUE) ~ "Pennsylvania",
grepl("New York", dis_port, ignore.case = TRUE) ~ "New York",
grepl("Boston", dis_port, ignore.case = TRUE) ~ "Massachusetts",
grepl("Norfolk", dis_port, ignore.case = TRUE) ~ "Virginia",
TRUE ~ "Other/Unknown"
))
# Table: total by decade and state
us_state_table <- us_ports_state %>%
group_by(decade, state) %>%
summarise(total_disembarked = sum(slaves_disembarked, na.rm = TRUE), .groups = "drop")
print(us_state_table)## # A tibble: 85 × 3
## decade state total_disembarked
## <dbl> <chr> <dbl>
## 1 1610 Other/Unknown 29
## 2 1620 Other/Unknown 3
## 3 1630 Massachusetts 7
## 4 1630 New York 53
## 5 1630 Other/Unknown 13
## 6 1640 New York 69
## 7 1640 Other/Unknown 12
## 8 1650 New York 477
## 9 1650 Other/Unknown 130
## 10 1660 New York 436
## # ℹ 75 more rows# Faceted plot
ggplot(us_state_table, aes(x = factor(decade), y = total_disembarked, fill = state)) +
geom_col(show.legend = FALSE) +
facet_wrap(~ state, scales = "free_y") +
labs(
title = "US Slave Imports by Decade and State (Approx.)",
x = "Decade",
y = "Slaves Disembarked"
) +
scale_y_continuous(labels = scales::comma) +
theme(axis.text.x = element_text(angle = 45, hjust = 1))
Optional:
top_countries <- combined %>%
group_by(voyage_ship__imputed_nationality__name) %>%
summarise(total_disembarked = sum(slaves_disembarked, na.rm = TRUE)) %>%
arrange(desc(total_disembarked)) %>%
slice_head(n = 10)
print(top_countries)## # A tibble: 10 × 2
## voyage_ship__imputed_nationality__name total_disembarked
## <chr> <dbl>
## 1 Great Britain 2414960
## 2 Portugal / Brazil 2154060
## 3 France 890381
## 4 Spain / Uruguay 480527
## 5 Netherlands 471709
## 6 0 401948
## 7 U.S.A. 289462
## 8 Denmark / Baltic 83221
## 9 Austria 2098
## 10 Other 1962# OPTIONAL: Visualization
library(ggplot2)
ggplot(top_countries, aes(x = reorder(voyage_ship__imputed_nationality__name, total_disembarked),
y = total_disembarked)) +
geom_col(fill = "steelblue") +
coord_flip() +
labs(
title = "Top 10 Nationalities by Total Slaves Disembarked",
x = "Ship Nationality",
y = "Total Slaves Disembarked"
) +
theme_minimal()
Summary:
This project showed that only a small share of enslaved Africans were brought to the U.S., while most were taken to the Caribbean and South America. Some enslaved people were re-exported from the U.S. to other regions. Countries like Britain, Portugal, and Spain were major players in the slave trade. Overall, the U.S. was part of a much larger and tragic system.