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   3.4.4     ✔ 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
library(dplyr)
cps <- read.csv("cpsa.csv") %>%
  select("year", "total.employed.labor.force", "total.unemployed.labor.force", "not.in.labor.force") %>%
  rename(total_employed_lf = total.employed.labor.force) %>%
  rename(total_unemployed_lf = total.unemployed.labor.force) %>%
  rename(non_lf = not.in.labor.force) %>%
  mutate(total_employed_lf = as.numeric(gsub(",", "", total_employed_lf)),
         total_unemployed_lf = as.numeric(gsub(",", "", total_unemployed_lf)),
         non_lf = as.numeric(gsub(",", "", non_lf)))

cpsa <- cps %>%
  filter(year >= 2017)

covid <- read.csv("WHO-COVID-19-global-data.csv") 

covid_use <- covid %>%
  filter(Country == "United States of America") %>%
  select("Date_reported", "Country_code", "New_cases", "New_deaths") %>%
  mutate(New_cases = ifelse(is.na(New_cases), 0, New_cases)) %>%
  mutate(New_deaths = ifelse(is.na(New_deaths), 0, New_deaths))

head(cpsa, 10)
##   year total_employed_lf total_unemployed_lf non_lf
## 1 2017            153337                6982  94759
## 2 2018            155761                6314  95716
## 3 2019            157538                6001  95636
## 4 2020            147795               12947  99587
## 5 2021            152581                8623 100241
## 6 2022            158291                5996  99686
## 7 2023            161037                6080  99826
head(covid_use, 10)
##    Date_reported Country_code New_cases New_deaths
## 1     2020-01-05           US         0          0
## 2     2020-01-12           US         0          0
## 3     2020-01-19           US         0          0
## 4     2020-01-26           US         7          0
## 5     2020-02-02           US         2          0
## 6     2020-02-09           US        11          0
## 7     2020-02-16           US         4          0
## 8     2020-02-23           US        16          0
## 9     2020-03-01           US        33          1
## 10    2020-03-08           US       391         18
library(dplyr)

## summarization data frame
## new categorical column
covid_case_average <- mean(covid$New_cases, na.rm = TRUE)
covid_death_average <- mean(covid$New_deaths, na.rm = TRUE)

covid_case_average
## [1] 21093.61
covid_death_average
## [1] 289.6709
covid_ave_df <- covid_use %>%
  summarize(
    date = Date_reported,
    cases = New_cases,
    ave_case_rate = ifelse(New_cases > covid_case_average, "above", "below"),
    deaths = New_deaths,
    ave_death_rate = ifelse(New_deaths > covid_death_average, "above", "below")
  )
## Warning: Returning more (or less) than 1 row per `summarise()` group was deprecated in
## dplyr 1.1.0.
## ℹ Please use `reframe()` instead.
## ℹ When switching from `summarise()` to `reframe()`, remember that `reframe()`
##   always returns an ungrouped data frame and adjust accordingly.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
head(covid_ave_df, 10)
##          date cases ave_case_rate deaths ave_death_rate
## 1  2020-01-05     0         below      0          below
## 2  2020-01-12     0         below      0          below
## 3  2020-01-19     0         below      0          below
## 4  2020-01-26     7         below      0          below
## 5  2020-02-02     2         below      0          below
## 6  2020-02-09    11         below      0          below
## 7  2020-02-16     4         below      0          below
## 8  2020-02-23    16         below      0          below
## 9  2020-03-01    33         below      1          below
## 10 2020-03-08   391         below     18          below
## new numerical column
cpsa <- cpsa %>%
  mutate(total_lf = total_employed_lf + total_unemployed_lf)
cpsa
##   year total_employed_lf total_unemployed_lf non_lf total_lf
## 1 2017            153337                6982  94759   160319
## 2 2018            155761                6314  95716   162075
## 3 2019            157538                6001  95636   163539
## 4 2020            147795               12947  99587   160742
## 5 2021            152581                8623 100241   161204
## 6 2022            158291                5996  99686   164287
## 7 2023            161037                6080  99826   167117
library(dplyr)

covid_use$Date_reported <- as.Date(covid_use$Date_reported)
covid_use$year <- format(covid_use$Date_reported, "%Y")

covid_merge <- covid_use %>%
  group_by(year) %>%
  summarise(
    total_case = sum(New_cases),
    total_deaths = sum(New_deaths)
  ) %>%
  filter(year != 2024) %>%
  mutate(year = as.numeric(year))

cpsa <- cpsa %>%
  mutate(year = as.numeric(year))

merge_df <- left_join(cpsa, covid_merge) %>%
  mutate(total_case = ifelse(is.na(total_case), 0, total_case)) %>%
  mutate(total_deaths = ifelse(is.na(total_deaths), 0, total_deaths))
## Joining with `by = join_by(year)`
merge_df
##   year total_employed_lf total_unemployed_lf non_lf total_lf total_case
## 1 2017            153337                6982  94759   160319          0
## 2 2018            155761                6314  95716   162075          0
## 3 2019            157538                6001  95636   163539          0
## 4 2020            147795               12947  99587   160742   18890446
## 5 2021            152581                8623 100241   161204   32988414
## 6 2022            158291                5996  99686   164287   47140633
## 7 2023            161037                6080  99826   167117    4417336
##   total_deaths
## 1            0
## 2            0
## 3            0
## 4       342920
## 5       469667
## 6       267389
## 7        83835
library(ggplot2)

## line plot for unemployment vs. covid cases
ggplot(merge_df, aes(x = total_case, y = total_unemployed_lf, color = year)) +
  geom_line() +
  geom_point(value = year) +
  scale_color_gradient(low = "darkblue", high = "red") +
  scale_x_continuous(labels = scales::comma) +
  labs(
    title = "Relationship Between COVID 19 Cases and Unemployement",
    x = "Total COVID 19 Cases",
    y = "Total Unemployement (in thousand)",
    color = "Year"
  )
## Warning in geom_point(value = year): Ignoring unknown parameters: `value`

## line plot for employment vs. covid cases
ggplot(merge_df, aes(x = total_case, y = total_employed_lf, color = year)) +
  geom_line() +
  geom_point(value = year) +
  scale_color_gradient(low = "red", high = "blue") +
  scale_x_continuous(labels = scales::comma) +
  labs(
    title = "Relationship Between COVID 19 Cases and Employement",
    x = "Total COVID 19 Cases",
    y = "Total Employement (in thousand)",
    color = "Year"
  )
## Warning in geom_point(value = year): Ignoring unknown parameters: `value`

## unemployement vs. employment
ggplot(cps, aes(x = total_employed_lf, y = total_unemployed_lf)) +
  geom_point(size = 1, color = "red") +
  geom_smooth(method = "lm", se = FALSE, size = 0.5, color = "black") +
  labs(
    title = "Relationship between Employment and Unemployment Over Time in America",
    x = "Total Employment (in thousand)",
    y = "Total Unemployement (in thousand)"
  )
## Warning: Using `size` aesthetic for lines was deprecated in ggplot2 3.4.0.
## ℹ Please use `linewidth` instead.
## This warning is displayed once every 8 hours.
## Call `lifecycle::last_lifecycle_warnings()` to see where this warning was
## generated.
## `geom_smooth()` using formula = 'y ~ x'

## barplot for confirmed cases
ggplot(covid_use, aes(x = Date_reported, y = New_cases)) +
  geom_bar(stat = "identity", fill = "orange") +
  scale_y_continuous(labels = scales::comma) +
  labs(
    title = "Confirmed COVID 19 Cases Over Time in America",
    x = "Date",
    y = "Confirmend Cases"
  )

## barplot for death cases
ggplot(covid_use, aes(x = Date_reported, y = New_deaths)) +
  geom_bar(stat = "identity", fill = "red") +
  scale_y_continuous(labels = scales::comma) +
  labs(
    title = "COVID 19 Death Cases Over Time in America",
    x = "Date",
    y = "Death Cases"
  )

## employed and unemployed status overtime
ggplot(merge_df, aes(x = year)) +
  geom_line(aes(y = total_employed_lf, color = "Employed")) +
  geom_point(aes(y = total_employed_lf, color = "Employed"), size = 2) +
  geom_line(aes(y = total_unemployed_lf, color = "Unemployed")) +
  geom_point(aes(y = total_unemployed_lf, color = "Unemployed"), size = 2) +
  labs(
    title = "Working Status in America 3 Years Before and After COVID 19",
    x = "Year",
    y = "Population (in thousand)",
    color = "Status"
  )

## cases status flow overtime
ggplot(covid_ave_df, aes(x = date, y = cases, color = ave_case_rate)) +
  geom_point(size = 1) +
  scale_y_continuous(labels = scales::comma) +
  scale_color_manual(values = c("above" = "purple", "below" = "pink")) +
  labs(title = "COVID 19 Confirmed Cases Status Over Time",
       x = "Date",
       y = "Cases",
       color = "Cases Status") 

## deaths status flow overtime
ggplot(covid_ave_df, aes(x = date, y = deaths, color = ave_death_rate)) +
  geom_point(size = 1) +
  scale_y_continuous(labels = scales::comma) +
  scale_color_manual(values = c("above" = "blue", "below" = "lightgreen")) +
  labs(title = "COVID 19 Confirmed Cases Status Over Time",
       x = "Year",
       y = "Deaths",
       color = "Death Rate")