Churn Rate Exploration

churn_exploration.R

library(data.table)
library(dplyr)
library(tidyr)
library(ggplot2)


## Read CSV from Looker
churn <- read.table("~/Downloads/trailing_churn.csv",sep=",",header=T)
names(churn) <- c("date","awesome","business","overall")


## Format Data to correct types
churn$date <- as.Date(churn$date,format="%Y-%m-%d")
churn$overall <- as.numeric(sub("%", "", churn$overall))
churn$awesome <- as.numeric(sub("%", "", churn$awesome))
churn$business <- as.numeric(sub("%", "", churn$business))


## Tidy data for analysis
churn_rates <- churn %>%
  gather(type,count,-date) %>%
  rename(churn_rate = count)


## Plot churn rates over time
churn_plot <-ggplot(churn_rates, aes(x=date, y=churn_rate, color=type)) +
            geom_line(stat="identity",size=1) + geom_smooth(size=1) + fte_theme() +
            labs(y="Churn Rate",x="Date",title="Churn Rates by Date") +
            scale_y_continuous(breaks = round(seq(min(churn_rates$churn_rate), max(churn_rates$churn_rate), by = 0.25),1))



## Plot churn rate distributions
churn_density <- ggplot(churn_rates, aes(x=churn_rate, fill=type)) + geom_density(alpha=0.5) + 
            labs(x="Churn Rate",title="Churn Density by Plan Type") + fte_theme() +
            scale_x_continuous(breaks = round(seq(min(churn_rates$churn_rate), 
            max(churn_rates$churn_rate), by = 0.25),1))


## Plot box plots of churn rates
churn_boxplots <- ggplot(churn_rates, aes(x=type, y=churn_rate)) + geom_boxplot(width=0.5) + 
            labs(x="Type",y="Churn Rate", title="Churn Rates by Plan Type") + fte_theme() +
            scale_y_continuous(breaks = round(seq(min(churn_rates$churn_rate), max(churn_rates$churn_rate), by = 0.25),1))



###########################################################
## Churn by Month Paying
###########################################################


## Import and Tidy Data
churn_by_paying <- read.table("~/Downloads/churn_by_months_paying.csv",sep=",",header=T)
names(churn_by_paying) <- c("date","0","1","2","3","4","5","6","7","8",
                            "9","10","11","12", "13","14","15")

churn_by_paying <- churn_by_paying[,c(1:17)]


## Gather Churn Rates
churn_by_month_paying <- churn_by_paying %>%
  gather(month_paying,count,-date) %>%
  rename(churn_rate=count) %>%
  mutate(churn_rate = as.numeric(sub("%", "", churn_rate)), date=as.Date(date,"%Y-%m-%d"))


## Average Churn Rate by Month Paying
average_churn_by_paying <- churn_by_month_paying %>%
  select(-date)
  group_by(month_paying) %>%
  summarise(avg_churn=mean(churn_rate),med_churn=median(churn_rate))


## Plot Average Churn Rate by Month Paying
average_churn_plot <- ggplot(average_churn_by_paying, aes(x=month_paying, y=avg_churn)) +
  geom_bar(stat="identity") + geom_text(aes(label=round(avg_churn,2)), vjust=-0.2) + fte_theme() + ylim(0,80) +
  scale_x_discrete(breaks=c("0","1","2","3","4","5","6","7","8","9","10","11","12", "13","14","15")) +
  labs(x="Months Paying", y="Average Churn Rate",title="Average Churn Rate by Months Paying") 


## Plot Median Churn Rate by Month Paying
median_churn_plot <- ggplot(average_churn_by_paying, aes(x=month_paying, y=med_churn)) +
  geom_bar(stat="identity") + geom_text(aes(label=round(med_churn,2)), vjust=-0.2) + fte_theme() + ylim(0,80) +
  scale_x_discrete(breaks=c("0","1","2","3","4","5","6","7","8","9","10","11","12", "13","14","15")) +
  labs(x="Months Paying", y="Median Churn Rate",title="Median Churn Rate by Months Paying")


###########################################################
## ggplot Theme
###########################################################

## ggplot Theme
fte_theme <- function() {
  
  # Generate the colors for the chart procedurally with RColorBrewer
  palette <- brewer.pal("Greys", n=9)
  color.background = palette[2]
  color.grid.major = palette[3]
  color.axis.text = palette[6]
  color.axis.title = palette[7]
  color.title = palette[9]
  
  # Begin construction of chart
  theme_bw(base_size=9) +
    
    # Set the entire chart region to a light gray color
    theme(panel.background=element_rect(fill=color.background, color=color.background)) +
    theme(plot.background=element_rect(fill=color.background, color=color.background)) +
    theme(panel.border=element_rect(color=color.background)) +
    
    # Format the grid
    theme(panel.grid.major=element_line(color=color.grid.major,size=.25)) +
    theme(panel.grid.minor=element_blank()) +
    theme(axis.ticks=element_blank()) +
    theme(panel.grid.major.x = element_blank(),panel.grid.minor.x = element_blank()) +
    
    # Format the legend, but hide by default
    theme(legend.background = element_rect(fill=color.background)) +
    theme(legend.text = element_text(size=15,color=color.axis.title)) +
    
    # Set title and axis labels, and format these and tick marks
    theme(plot.title=element_text(color=color.title, size=20, vjust=1.25)) +
    theme(axis.text.x=element_text(size=10,color=color.axis.text)) +
    theme(axis.text.y=element_text(size=10,color=color.axis.text)) +
    theme(axis.title.x=element_text(size=15,color=color.axis.title, vjust=0)) +
    theme(axis.title.y=element_text(size=15,color=color.axis.title, vjust=1.25)) +
    
    # Plot margins
    theme(plot.margin = unit(c(0.35, 0.2, 0.3, 0.35), "cm"))
}