Data Wrangling Lab Assignment 5

library(completejourney)

library(tidyverse)
library(lubridate)
library(ggtext)
library(dplyr)
library(ggtext)
library(ggplot2)
library(stringr)

campaign_tracs <- campaign_descriptions %>% 
  left_join(coupons) %>% 
  left_join(transactions)

typec<-campaign_tracs %>% 
  filter(transaction_timestamp >= "2017-03-13" & transaction_timestamp <= "2017-05-08") %>% 
  mutate(total_spend = sum(sales_value)) %>% 
  group_by(campaign_type)
#View(typec)

typeb<-campaign_tracs %>% 
  filter(transaction_timestamp >= "2017-03-03" & transaction_timestamp <= "2017-04-09") %>% 
  group_by(campaign_type)

typea<-campaign_tracs %>% 
  filter(transaction_timestamp >= "2017-08-08" & transaction_timestamp <= "2017-09-24") %>% 
  group_by(campaign_type)

ggplot() + 
  geom_line(data=typea, aes(x=transaction_timestamp, y=sales_value), color="#063970") + 
  geom_line(data=typeb, aes(x=transaction_timestamp, y=sales_value), color="#D16103") +
  geom_line(data=typec, aes(x=transaction_timestamp, y=sales_value), color='#7843a6')+
  theme(legend.text=element_text(size = 16))+
  theme(axis.title.y = element_text(size = 18))+
  theme(axis.title.x = element_text(size = 18))+
  theme(plot.title = element_text(size = 20))+
  labs(x = "Campaign months",
       y = "Total Sales Value",
       title = "Campaign Efffectiveness for Average Sales Won<br>in the Campaign Run Period")+ 
  theme(plot.title=element_text(hjust=0.5))+
  theme(plot.title.position = "plot",
        plot.title = element_markdown(),
        legend.position = "right")

library(ggplot2)
library(ggthemes)



# Aggregate redemption rates by week and campaign
aggregated_rates <- redemption_rates %>%
  group_by(campaign_id, week) %>%
  summarize(mean_redemption_rate = mean(redemption_rate))

`summarise()` has grouped output by 'campaign_id'. You can override using the `.groups` argument.

# Find the top 10 campaigns with the highest mean redemption rates
top_10_campaigns <- aggregated_rates %>%
  arrange(desc(mean_redemption_rate)) %>%
  head(10)


ggplot(top_10_campaigns, aes(x = week, y = mean_redemption_rate, color = campaign_id)) +
  geom_line(size = 1.5, aes(group = campaign_id)) +
  geom_point(size = 2, shape = 21, fill = "white", color = "black") +
  labs(
    x = "Week",
    y = "Mean Redemption Rate (%)",
    color = "Campaign"
  ) +
  theme_minimal() +
  theme(legend.position = "top") +
  theme_economist() +  
  scale_color_brewer(palette = "Set1") + 
  geom_text(
    aes(label = paste0(round(mean_redemption_rate, 2), "%")),
    hjust = -0.2, vjust = 0.5, size = 3, color = "black"
  ) +
  annotate(
    "text", x = max(top_10_campaigns$week), y = max(top_10_campaigns$mean_redemption_rate),
    label = "Top campaigns with highest redemption rates", hjust = 1.4, vjust = -0.3,
    size = 4, fontface = "bold", color = "black"
  ) +
  scale_x_continuous(breaks = seq(1, max(top_10_campaigns$week), by = 5))  

NA
NA

library(ggplot2)
library(ggthemes)

demo_transactions <- demographics %>%
  inner_join(transactions, by = "household_id") 

# scatter plot of household income vs. sales value 
ggplot(demo_transactions, aes(x = income, y = sales_value)) +
  geom_point(
    aes(color = quantity, size = quantity),
    alpha = 0.7,
    show.legend = TRUE
  ) +
  scale_color_gradient(low = "purple", high = "red") +
  scale_size_continuous(range = c(2, 7)) +
  labs(
    x = "Household Income",
    y = "Sales Value",
    title = "Sales based on household income & product quantity",
    size = "Quantity",
    color = "Quantity"
  ) +
  theme_economist() +  
  theme(
    legend.position = "bottom",
    text = element_text(size = 7)  
  ) +
  theme(plot.title = element_text(hjust = 0.5, size = 12)) 

NA
NA