TidyTuesday

Data from #tidytuesday week of 2019-07-30 (source) Load R packages library(tidyverse) library(RColorBrewer) library(scales) Download data steam_raw <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-07-30/video_games.csv") Parse data steam_games <- steam_raw %>% # VARIABLE FOR AGE OF GAME mutate(release_year = substring(release_date, 8, 12), # EXTRACT YEAR release_year = as.numeric(str_trim(release_year)), release_year = case_when(release_year == 5 ~ 2015, # INCORRECT DATA POINT TRUE ~ release_year), age = 2019 - release_year) %>% # VARIABLE FOR MIN/MAX NUMBER OF OWNERS mutate(max_owners = str_trim(word(owners, 2, sep = "\\....

Data from #tidytuesday week of 2019-06-04 (source) Load R packages library(tidyverse) library(plotly) Download and parse data frame ramen_raw <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-06-04/ramen_ratings.csv") ramen <- ramen_raw %>% group_by(brand, country) %>% summarize(avg_rating = round(mean(stars),2), total_reviews = n()) Build plotly chart plot_ly(data = ramen, x = ~total_reviews, y = ~avg_rating, size = 15, color = ~country, colors = 'Paired', text = ~paste("Brand: ", brand, "<br>Average Rating: ", avg_rating), showlegend = FALSE) %>% layout(xaxis = list(title = "Total Reviews"), yaxis = list(title = "Average Ratings")) {"...

Analyzing data for #tidytuesday week of 3/05/2019 (source) Load libraries library(tidyverse) library(scales) library(lubridate) jobs_gender <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-03-05/jobs_gender.csv") Clean & plot data jobs_gender %>% filter(year == '2016') %>% mutate(male_diff = ((((total_earnings_male/total_earnings)-1)*workers_male)/total_workers), female_diff = (((total_earnings_female/total_earnings)-1)*workers_female)/total_workers) %>% ggplot() + geom_jitter(aes(total_earnings, female_diff), color = 'salmon', alpha = 0.5, size = 2.5) + geom_jitter(aes(total_earnings, male_diff), color = 'steelblue', alpha = 0.5, size = 2.5) + geom_hline(yintercept = 0, color = 'grey54', lty = 'dashed') + facet_wrap(~major_category) + scale_x_continuous(labels = dollar_format(), limits = c(0,200000)) + scale_y_continuous(labels = percent_format(round(1)), limits = c(-0....

Instead of a static visualization I decided to build a barebones Shiny app this week. The purpose is to improve the interactivity of the final output - one of my 2019 goals to level up advanced R knowledge. You can find the full code here. Analyzing data for #tidytuesday week of 2/5/2019 (source) # LOAD PACKAGES library(tidyverse) library(scales) library(shiny) state_hpi_raw <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-02-05/state_hpi.csv") Process the raw data state_hpi <- state_hpi_raw %>% group_by(state, year) %>% summarize(us_avg = mean(us_avg), price_index = mean(price_index)) %>% mutate(pct_diff = (price_index / us_avg) - 1, segment = ifelse(pct_diff > 0, 'above', 'below'), segment = str_to_title(segment)) Build the UI level Include a drop down menu to select output data by state abbreviation ui <- fluidPage( "Housing Price Index: US Average vs State", selectInput(inputId = "select_state", label = "Choose a state", c(state....

Analyzing data for #tidytuesday week of 1/29/2019 (source) # LOAD PACKAGES library(tidyverse) library(scales) library(lubridate) library(ggmap) library(gganimate) library(ggthemes) library(transformr) library(gifski) library(mapproj) milk_raw <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-01-29/state_milk_production.csv") milk <- milk_raw Extract geospatial data and parse data usa <- as_tibble(map_data("state")) usa$region <- str_to_title(usa$region) usa <- usa %>% rename(state = region) milk_parsed <- milk %>% select(-region) %>% mutate(milk_10billion = milk_produced / 10000000000, year = as.integer(year)) %>% full_join(usa) %>% filter(!is.na(year), !is.na(long), !is.na(lat)) Build animation milk_animation <- milk_parsed %>% ggplot(aes(long, lat, group = group, fill = milk_10billion)) + geom_polygon(color = 'black') + scale_fill_gradient2(low = "gray97", mid = "steelblue", high = "midnightblue", midpoint = 2....

Analyzing data for #tidytuesday week of 1/22/2019 (source) # LOAD PACKAGES AND PARSE DATA library(tidyverse) library(scales) library(lubridate) library(RColorBrewer) prison_raw <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-01-22/prison_population.csv") prison <- prison_raw Process the raw data total <- prison %>% filter(pop_category != 'Total' & pop_category != 'Male' & pop_category != 'Female') %>% select(county_name, urbanicity, pop_category, population, prison_population) %>% na.omit() %>% group_by(county_name, urbanicity, pop_category) %>% summarize(population = sum(population), prison_population = sum(prison_population)) %>% ungroup() %>% group_by(county_name, urbanicity) %>% mutate(pct_population = population / sum(population), pct_prisoner = prison_population / sum(prison_population)) What is the proportion of population:prisoners per demographic group ?...

Analyzing data for #tidytuesday week of 1/15/2019 (source) # LOAD PACKAGES AND PARSE DATA library(tidyverse) library(RColorBrewer) library(forcats) library(scales) library(ebbr) launches_raw <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-01-15/launches.csv") launches <- launches_raw %>% filter(launch_year >= '1960') Distribution of the most space launches over time? countries <- launches %>% count(state_code, sort = TRUE) %>% filter(n >= 100) launches %>% inner_join(countries) %>% # INCOMING NASTY IFELSE CODE (NEED TO REFACTOR) mutate(state_code = ifelse(state_code == 'RU', 'Russia / Soviet Union', ifelse(state_code == 'SU', 'Russia / Soviet Union', ifelse(state_code == 'US', 'United States', ifelse(state_code == 'CN', 'China', ifelse(state_code == 'IN', 'India', ifelse(state_code == 'F', 'France', ifelse(state_code == 'J', 'Japan', state_code)))))))) %>% ggplot() + geom_density(aes(launch_year, fill = state_code, color = state_code), alpha = 0....

Analyzing data for #tidytuesday week of 01/08/2019 (source) # LOAD PACKAGES AND PARSE DATA library(knitr) library(tidyverse) library(RColorBrewer) library(forcats) library(lubridate) library(broom) tv_data_raw <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-01-08/IMDb_Economist_tv_ratings.csv") tv_data <- tv_data_raw Prepare the data for k-means clustering tv_data_summarized <- tv_data %>% group_by(title, genres, date) %>% summarize(min_rating = min(av_rating), avg_rating = mean(av_rating), max_rating = max(av_rating), min_share = min(share), avg_share = mean(share), max_share = max(share)) %>% ungroup() kclust_data <- tv_data_summarized %>% select(-title, -genres, -date) kclust_results <- kmeans(kclust_data, center = 9) Check output data (boxplot) # CHECK OUTPUT DATA tv_data_summarized %>% left_join(augment(kclust_results, kclust_data)) %>% mutate(title = factor(title)) %>% group_by(....