Lab11 Write-Up
EGOR CHERNIUK
Part 1
lab11_theme = theme_minimal(base_family = "Optima", base_size = 12)
data(temp_carbon)
temp_anomaly = temp_carbon %>%
select(Year = year, Global = temp_anomaly, Land = land_anomaly,
Ocean = ocean_anomaly) %>%
pivot_longer(Global:Ocean, names_to = "Region", values_to = "Anomaly") %>%
filter(!is.na(Anomaly))
anim_1 = temp_anomaly %>%
ggplot(aes(x = Year, y = Anomaly, col = Region)) +
geom_line(size = 1) +
geom_hline(aes(yintercept = 0), lty = 2) +
annotate("text", x = 2005, y = -.08,
label = "20th century mean", size = 3) +
scale_color_viridis_d(option = "C", end = .75) +
labs(
title = "Temperature anomaly relative to 20th century mean",
x = "Year",
y = "Temperature anomaly (degrees C)"
) +
lab11_theme +
transition_reveal(Year)
animate(anim_1, nframes = 15)
anim_2 = temp_anomaly %>%
ggplot(aes(x = Year, y = Anomaly, col = Region)) +
geom_line(size = 1) +
# a dotted line between the time series line and the label
# It gets the x and y aesthetic from ggplot2
geom_segment(aes(xend = 2030, yend = Anomaly), linetype = 2) +
# To label each line and keep the labels to the right side
# of the plot area, so x = 2030 to make sure the x position
# doesn't change. Lines are based on color, so label = Region.
geom_text(aes(x = 2030, label = Region), hjust = 0) +
geom_hline(aes(yintercept = 0), lty = 2) +
annotate("text", x = 2005, y = -.08,
label = "20th century mean", size = 3) +
scale_color_viridis_d(option = "C", end = .75) +
labs(
title = "Temperature anomaly relative to 20th century mean",
x = "Year",
y = "Temperature anomaly (degrees C)"
) +
xlim(1880, 2040) +
# To allow ggplot2 to draw anywhere on the plot (incl. on the margins)
coord_cartesian(clip = 'off') +
lab11_theme +
# Hide legend for color
guides(col = FALSE) +
transition_reveal(Year)
animate(anim_2, nframes = 15)
Part 2
covid_data = read_csv("covid_data.csv")##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## signal = col_character(),
## geo_value = col_character(),
## time_value = col_date(format = ""),
## value = col_double(),
## stderr = col_double(),
## sample_size = col_double()
## )covid_wide = covid_data %>%
pivot_wider(., id_cols = c(geo_value, time_value), names_from = signal,
values_from = value)
anim_3 = covid_wide %>%
ggplot(aes(x = smoothed_wearing_mask, y = smoothed_restaurant_1d, col = smoothed_cli, size = smoothed_cli)) +
geom_point(alpha = .5) +
scale_color_viridis_c(option = "C", end = .75) +
lab11_theme +
theme(legend.position = "bottom") +
transition_time(time_value)
animate(anim_3, nframes = 10)
anim_4 = covid_wide %>%
ggplot(aes(x = smoothed_wearing_mask, y = smoothed_restaurant_1d,
size = smoothed_cli, col = smoothed_cli)) +
geom_point(alpha = .5) +
scale_color_viridis_c(option = "C", end = .75, guide = "legend") +
lab11_theme +
theme(legend.position = "bottom") +
transition_time(time_value) +
shadow_mark(size = .1, alpha = .1) +
labs(
title = "Restaurant visits, mask-wearing, and COVID-like illness over time",
#add the date of each animation:
subtitle = "Date: {frame_time}",
x = "% Wearing Mask in Public",
y = "% Visited Restaurant",
col = "% with COVID-like Illness",
size = "% with COVID-like Illness",
caption = "Source: CMU Delphi Symptom Survey"
)
animate(anim_4, nframes = 10)
Part 3: Your turn!
(for more info, use ?anim_save)
oakland_data <- read_csv("oakland_policing.csv")##
## ── Column specification ────────────────────────────────────────────────────────
## cols(
## .default = col_character(),
## date = col_date(format = ""),
## time = col_time(format = ""),
## lat = col_double(),
## lng = col_double(),
## beat = col_logical(),
## subject_age = col_logical(),
## officer_assignment = col_logical(),
## arrest_made = col_logical(),
## citation_issued = col_logical(),
## warning_issued = col_logical(),
## contraband_found = col_logical(),
## contraband_drugs = col_logical(),
## contraband_weapons = col_logical(),
## search_conducted = col_logical(),
## use_of_force_description = col_logical(),
## raw_subject_resultofsearch = col_logical()
## )
## ℹ Use `spec()` for the full column specifications.## Warning: 142089 parsing failures.
## row col expected actual file
## 72425 beat 1/0/T/F/TRUE/FALSE 14X 'oakland_policing.csv'
## 72425 raw_subject_resultofsearch 1/0/T/F/TRUE/FALSE None, 'oakland_policing.csv'
## 72426 beat 1/0/T/F/TRUE/FALSE 30X 'oakland_policing.csv'
## 72426 use_of_force_description 1/0/T/F/TRUE/FALSE handcuffed 'oakland_policing.csv'
## 72426 raw_subject_resultofsearch 1/0/T/F/TRUE/FALSE Other Weapons, 'oakland_policing.csv'
## ..... .......................... .................. .............. ......................
## See problems(...) for more details.oakland_data = oakland_data %>%
drop_na(date)
oakland_data = oakland_data %>%
group_by(date) %>%
mutate(black_daily = sum(subject_race == "black"),
white_daily = sum(subject_race == "white"),
hispanic_daily = sum(subject_race == "hispanic"),
asian_daily = sum(subject_race == "asian/pacific islander"),
other_daily = sum(subject_race == "other"),
unknown_daily = sum(subject_race == "unknown"),
daily_cases = black_daily + white_daily + hispanic_daily + asian_daily, other_daily, unknown_daily)
head(oakland_data)## # A tibble: 6 x 35
## # Groups: date [1]
## raw_row_number date time location lat lng beat subject_age
## <chr> <date> <tim> <chr> <dbl> <dbl> <lgl> <lgl>
## 1 1 2013-04-01 00:00 31st St… 37.8 -122. NA NA
## 2 2 2013-04-01 00:01 3000 Bl… 37.8 -122. NA NA
## 3 19 2013-04-01 10:41 12th St… 37.8 -122. NA NA
## 4 20 2013-04-01 14:18 2100 WE… 37.8 -122. NA NA
## 5 4 2013-04-01 00:15 2200 Bl… 37.8 -122. NA NA
## 6 21 2013-04-01 15:32 300 Blk… 37.7 -122. NA NA
## # … with 27 more variables: subject_race <chr>, subject_sex <chr>,
## # officer_assignment <lgl>, type <chr>, arrest_made <lgl>,
## # citation_issued <lgl>, warning_issued <lgl>, outcome <chr>,
## # contraband_found <lgl>, contraband_drugs <lgl>, contraband_weapons <lgl>,
## # search_conducted <lgl>, search_basis <chr>, reason_for_stop <chr>,
## # use_of_force_description <lgl>, raw_subject_sdrace <chr>,
## # raw_subject_resultofencounter <chr>, raw_subject_searchconducted <chr>,
## # raw_subject_typeofsearch <chr>, raw_subject_resultofsearch <lgl>,
## # black_daily <int>, white_daily <int>, hispanic_daily <int>,
## # asian_daily <int>, other_daily <int>, unknown_daily <int>,
## # daily_cases <int>head(temp_carbon)## year temp_anomaly land_anomaly ocean_anomaly carbon_emissions
## 1 1880 -0.11 -0.48 -0.01 236
## 2 1881 -0.08 -0.40 0.01 243
## 3 1882 -0.10 -0.48 0.00 256
## 4 1883 -0.18 -0.66 -0.04 272
## 5 1884 -0.26 -0.69 -0.14 275
## 6 1885 -0.25 -0.56 -0.17 277head(covid_data)## # A tibble: 6 x 6
## signal geo_value time_value value stderr sample_size
## <chr> <chr> <date> <dbl> <dbl> <dbl>
## 1 smoothed_cli ak 2020-10-01 1.59 0.429 760
## 2 smoothed_cli al 2020-10-01 0.983 0.141 3742.
## 3 smoothed_cli ar 2020-10-01 1.06 0.174 2587.
## 4 smoothed_cli az 2020-10-01 0.597 0.0905 5682.
## 5 smoothed_cli ca 2020-10-01 0.450 0.0399 21930.
## 6 smoothed_cli co 2020-10-01 0.561 0.0917 5137.anim_oakland = oakland_data %>%
ggplot(aes(x = date, fill = subject_race)) +
geom_area(stat = "bin", binwidth = 3) +
scale_color_viridis_d("Subject Race", end = .75, option = "C") +
scale_x_date(date_breaks = "3 months",
labels = date_format("%b-%Y"),
limits = as.Date(c('2016-04-01','2018-01-01'))) +
transition_reveal(date) +
labs(
title = "Police Stops by Race, Oakland, CA",
subtitle = "2016 - 2018",
x = "Date",
y = "Number of Cases",
fill = "Race",
caption = "Source: The Stanford Open Policing Project")
animate(anim_oakland, nframes = 90)## Warning: Removed 82711 rows containing non-finite values (stat_bin).