library(tidyverse)
## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr 1.1.4 ✔ readr 2.1.5
## ✔ forcats 1.0.0 ✔ stringr 1.5.1
## ✔ ggplot2 3.5.1 ✔ tibble 3.2.1
## ✔ lubridate 1.9.3 ✔ tidyr 1.3.1
## ✔ 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
install.packages("pastecs")
## Installing package into 'C:/Users/Campo/AppData/Local/R/win-library/4.4'
## (as 'lib' is unspecified)
## package 'pastecs' successfully unpacked and MD5 sums checked
##
## The downloaded binary packages are in
## C:\Users\Campo\AppData\Local\Temp\RtmpAbdXxQ\downloaded_packages
library(pastecs)
##
## Attaching package: 'pastecs'
##
## The following objects are masked from 'package:dplyr':
##
## first, last
##
## The following object is masked from 'package:tidyr':
##
## extract
suicide_data <- read_csv("C:/Users/Campo/Downloads/Death_rates_for_suicide__by_sex__race__Hispanic_origin__and_age__United_States.csv")
## Rows: 6390 Columns: 13
## ── Column specification ────────────────────────────────────────────────────────
## Delimiter: ","
## chr (6): INDICATOR, UNIT, STUB_NAME, STUB_LABEL, AGE, FLAG
## dbl (7): UNIT_NUM, STUB_NAME_NUM, STUB_LABEL_NUM, YEAR, YEAR_NUM, AGE_NUM, E...
##
## 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.
print(head(suicide_data))
## # A tibble: 6 × 13
## INDICATOR UNIT UNIT_NUM STUB_NAME STUB_NAME_NUM STUB_LABEL STUB_LABEL_NUM
## <chr> <chr> <dbl> <chr> <dbl> <chr> <dbl>
## 1 Death rates … Deat… 1 Total 0 All perso… 0
## 2 Death rates … Deat… 1 Total 0 All perso… 0
## 3 Death rates … Deat… 1 Total 0 All perso… 0
## 4 Death rates … Deat… 1 Total 0 All perso… 0
## 5 Death rates … Deat… 1 Total 0 All perso… 0
## 6 Death rates … Deat… 1 Total 0 All perso… 0
## # ℹ 6 more variables: YEAR <dbl>, YEAR_NUM <dbl>, AGE <chr>, AGE_NUM <dbl>,
## # ESTIMATE <dbl>, FLAG <chr>
print(colnames(suicide_data))
## [1] "INDICATOR" "UNIT" "UNIT_NUM" "STUB_NAME"
## [5] "STUB_NAME_NUM" "STUB_LABEL" "STUB_LABEL_NUM" "YEAR"
## [9] "YEAR_NUM" "AGE" "AGE_NUM" "ESTIMATE"
## [13] "FLAG"
estimate_desc <- pastecs::stat.desc(suicide_data$ESTIMATE)
print(estimate_desc)
## nbr.val nbr.null nbr.na min max range
## 5.484000e+03 0.000000e+00 9.060000e+02 3.000000e-01 7.480000e+01 7.450000e+01
## sum median mean SE.mean CI.mean.0.95 var
## 7.518460e+04 1.050000e+01 1.370981e+01 1.557215e-01 3.052759e-01 1.329825e+02
## std.dev coef.var
## 1.153181e+01 8.411353e-01
suicide_data_clean <- suicide_data %>%
filter(!is.na(ESTIMATE))
install.packages("dplyr")
## Warning: package 'dplyr' is in use and will not be installed
library(dplyr)
suicide_data_clean <- suicide_data %>%
filter(!is.na(ESTIMATE))
install.packages("ggplot2")
## Warning: package 'ggplot2' is in use and will not be installed
library(ggplot2)
ggplot(suicide_data_clean, aes(x = ESTIMATE)) +
geom_histogram(binwidth = 1, fill = "blue", color = "black") +
labs(
title = "Histogram of Suicide Death Rates",
x = "Death Rate (Estimate)",
y = "Frequency"
) +
theme_minimal()
suicide_data_clean <- suicide_data_clean %>%
mutate(log_estimate = log(ESTIMATE + 1))
ggplot(suicide_data_clean, aes(x = log_estimate)) +
geom_histogram(binwidth = 0.1, fill = "green", color = "black") +
labs(
title = "Histogram of Log-Transformed Suicide Death Rates",
x = "Log(Death Rate (Estimate))",
y = "Frequency"
) +
theme_minimal()
