---
title: "Hotel Booking Dashboard"
output: 
  flexdashboard::flex_dashboard:
    vertical_layout: fill
    orientation: rows
    social: menu
    source: embed
    html_document:
      df_print: paged
      pdf_document: default
---
```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)

library(flexdashboard)
library(readr)
library(ggplot2)
library(tidyverse)
library(lubridate)
library(knitr)
library(plotly)

# Load your dataset
dataset <- read_csv("../Data/hotel_revenue_cleaned.csv")

# Data Cleaning and Preprocessing
data <- dataset %>%
  dplyr::mutate(
    booking_date = as.Date(paste(arrival_date_year, arrival_date_month, arrival_date_day_of_month, sep = "-"), "%Y-%B-%d"),
    cancellation_rate = is_canceled / sum(is_canceled),
    adr_per_day = adr / (stays_in_week_nights + stays_in_weekend_nights)
  )
```

# Introduction

Row {data-height=10}
-----------------------------------------------------------------------
```{r echo = FALSE}
valueBox(value = "Lab1 - By Shweta Shankar Shete & Rohit Prasanna Chandramouli", icon = "fa-pencil")
```


Column {data-width=100}
-----------------------------------------------------------------------

### Total Bookings - 2020
```{r echo=FALSE}
total_bookings <- data %>% dplyr::filter(year == 2020) %>% nrow()
valueBox(value = total_bookings,icon = "fa-user-plus",caption = "Total Bookings - Current Year",color = "green")
```


### Total Cancellation - 2020
```{r echo=FALSE}
total_cancels <- data %>% dplyr::filter(year == 2020, is_canceled == 1) %>% nrow()
valueBox(value = total_cancels,icon = "fa-user-times",caption = "Total Cancellations - Current Year", color = "orange")
```

### Repeat Guests - Visits 2020
```{r echo=FALSE}
repeat_guests <- data %>% dplyr::filter(year == 2020, is_repeated_guest == 1) %>% nrow()
valueBox(value = repeat_guests,icon = "fa-arrow-up",caption = "Repeat Guest visits - Current Year", color = "coral")
```

Row {data-height=450}
-----------------------------------------------------------------------

### **Overview**

The hotel booking dataset is a comprehensive collection of booking information for two types of hotels: a city hotel and a resort hotel. This dataset provides detailed information on various aspects of hotel bookings, including the booking time, length of stay, number of adults, children, and babies, as well as the number of available parking spaces and the booking's source. The dataset spans a significant period, capturing a wide range of booking behaviors and patterns, making it a valuable resource for analysis and decision-making.

### **Objective**

This analysis aims to design an information dashboard using the hotel booking dataset to support quantitative decision-making. The dashboard will offer insights into booking trends, cancellation rates, and customer demographics, aiding hotel management in optimizing operations and maximizing revenue. Through visualizations and key insights, the dashboard will present business information clearly, enhancing strategic planning and operational efficiency.

**Key features of the dataset include:**

**Booking Details**: Information on the type of hotel, booking lead time, and the dates of arrival and departure.</br>
**Guest Demographics**: Number of adults, children, and babies included in each booking.</br>
**Booking Modifications**: Data on changes to bookings, such as cancellations and rebookings.</br>
**Market Segmentation**: Insights into the market segment and distribution channels through which bookings were made.</br>
**Financial Metrics**: Metrics such as the average daily rate (ADR) and total revenue generated from bookings.</br>
**Customer Preferences**: Information on the type of meal booked, special requests, and room preferences.</br>
**Operational Metrics**: Details on the number of stays in weekend nights versus week nights, and any waiting list entries.</br>

Row {data-height=500}
-----------------------------------------------------------------------
### **Dataset**

```{r echo = FALSE}
knitr::kable(top_n(data, n = 100))
```


# Booking Trends

## Column {data-height=900 .tabset .tabset-fade}

### **ADR Overtime** {data-width=900}
```{r echo=FALSE, warning=FALSE, message=FALSE}
# Time Series Plot for ADR Over Time
adr_time_series <- ggplot(data, aes(x = booking_date, y = adr)) +
  geom_line(color = "blue") +
  labs(title = "ADR Over Time", x = "Date", y = "Average Daily Rate (ADR)") +
  theme_minimal()

ggplotly(adr_time_series)
```


### **Average Daily Rate (ADR) by Month** {data-width=900}

```{r echo=FALSE, warning=FALSE, message=FALSE}
# Calculate the average ADR by month
adr_by_month <- data %>%
  group_by(arrival_date_month) %>%
  summarize(avg_adr = mean(adr, na.rm = TRUE))

# Create an interactive bar chart
bar_chart <- ggplot(adr_by_month, aes(x = factor(arrival_date_month, levels = month.name), y = avg_adr, fill = factor(arrival_date_month))) +
  geom_bar(stat = "identity") +
  labs(title = "Average Daily Rate (ADR) by Month",
       x = "Month",
       y = "Average Daily Rate (ADR)") +
  theme_minimal() +
  theme(legend.position = "none")# +
  #scale_fill_manual(values = rainbow(n = 12))  # Use rainbow colors

# Convert to Plotly for interactivity
bar_chart_interactive <- ggplotly(bar_chart)

# Print the interactive chart
bar_chart_interactive

```

### **Market Segment Distribution** {data-width=900}

```{r echo=FALSE, warning=FALSE, message=FALSE}

# Prepare data: count reservations by market segment
market_segment_dist <- data %>%
  group_by(market_segment) %>%
  summarize(count = n())

# Create a pie chart
pie_chart <- ggplot(market_segment_dist, aes(x = "", y = count, fill = market_segment)) +
  geom_bar(stat = "identity", width = 1) +
  coord_polar("y", start = 0) +
  labs(title = "Market Segment Distribution",
       x = "",
       y = "") +
  theme_minimal() +
  theme(axis.line = element_blank(),
        axis.text = element_blank(),
        axis.ticks = element_blank())

# Print the chart
print(pie_chart)

```

### **Revenue Breakdown by Customer Type** {data-width=900}
```{r echo=FALSE, warning=FALSE, message=FALSE}
revenue_by_customer_type <- data %>%
  group_by(customer_type) %>%
  summarise(total_revenue = sum(adr, na.rm = TRUE))

ggplot(revenue_by_customer_type, aes(x = customer_type, y = total_revenue, fill = customer_type)) +
  geom_bar(stat = "identity") +
  theme_minimal() +
  labs(title = "Revenue Breakdown by Customer Type", x = "Customer Type", y = "Total Revenue")
```

### **Reservations per month (by year)** {data-width=1400}
```{r echo=FALSE, warning=FALSE, message=FALSE, fig.width=16}
staypermonth <- data %>% 
                dplyr::filter(is_canceled == 0, country != "NULL") %>%
                dplyr::select(year, hotel, arrival_date_month, country)

staypermonth_agg <- staypermonth %>% group_by(year, hotel, arrival_date_month) %>% summarise(count = n())


ggplot(data = staypermonth_agg, aes(x = arrival_date_month, y = count, fill = as.factor(year))) +
  geom_bar(position="dodge", stat="identity") +
  facet_wrap(.~hotel) +
  xlab("Months") + 
  ylab("Number of Stays") +
  theme_minimal() +
  theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
  guides(fill=guide_legend(title="Year"))
```


# Conclusion

### **Conclusion**

The analysis of the hotel booking dataset provides valuable insights into various aspects of hotel operations and customer behavior. Key findings from the visualizations and data analysis include:

**ADR Trends**: The Average Daily Rate (ADR) shows significant seasonal variation, with distinct peaks and troughs throughout the year. This information can help hotel management optimize pricing strategies during high and low demand periods to maximize revenue.

**Market Segment Distribution**: The pie chart on market segment distribution highlights the diverse sources of hotel bookings. This insight helps in tailoring marketing efforts and partnership strategies to target the most profitable segments effectively.

**Revenue Breakdown by Customer Type**: The visualization shows how much revenue each customer type contributes. It helps identify the most profitable customer segments. If transient customers generate the most revenue, it suggests focusing marketing efforts on attracting more of these customers. Conversely, if corporate or group customers bring in significant revenue, offering more tailored packages to these segments might be beneficial.

**Reservations per month (by year)**: Analyzing reservations per month by each year provides valuable insights into seasonal booking patterns, trends over time, and the impact of events or seasons on demand. This analysis helps hotels make informed decisions regarding pricing, staffing, and marketing to effectively manage their operations and meet the needs of their guests.