Problem

As students and travelers, we often struggle to find accurate information about living expenses in different parts of the world. This can lead to overspending or underestimating costs, causing financial strain and stress. We needed a solution that would provide us with reliable and up-to-date information on living expenses around the world.

The dataset being analyzed in this report was sourced from Kaggle.com (https://www.kaggle.com/datasets/mvieira101/global-cost-of-living), which was initially gathered by scraping Numbeo’s website (https://www.numbeo.com). Kaggle is a well-established platform that boasts a vast collection of high-quality and diverse datasets, which have been gathered and worked on by experts in various fields.

Working with uncleaned data is a common representation of real-world challenges in data science and machine learning, as data is rarely clean and ready to use in the real world. This presents an opportunity for data scientists to develop their skills in tackling real-world problems, making it an ideal platform for data analysis. The data in this dataset is updated until December 2022.

The purpose of selecting this dataset is to evaluate the ability to analyze the data and provide meaningful visualizations. The aim is to explore new libraries and functions in R programming, as well as to improve the skillset in data analysis. The context of this database is to gain valuable insights into the global cost of living and to identify any patterns or trends that may exist in the data.

I like to travel and I always work a lot to find the living expenses before planning a trip to the country. So personally these help me a lot to get an idea to find average living expenses in each place and try to find cheap ones. Also, I always get the query from students and professionals regarding studying abroad for their master’s degree. They are very curious about the living cost of the countries and they need to know whether they can manage it during their studies. So I decided to take this data and transform it into a meaningful form. The dataset is about the cost of living in almost 5000 cities across the world. The data were gathered by scraping Numbeo’s website (https://www.numbeo.com).

The dataset consists of 58 columns and initially contains 4956 rows. The columns “city” and “country” are character data types, representing the location of the data. A column “continent” has been added to the dataset, in order to provide a categorical variable for the corresponding “country” column.

The remaining columns in the dataset represent the expenses of various commodities, with the cost values being in US Dollars. However, these columns are not named in a descriptive manner and instead are labelled as “x1”, “x2”, “x3”, and so on. The delimiter used in the dataset is the comma (“,”).

DATA CLEANING METHODOLOGY

This is major part of project since we do not clean and format the data properly,it will affect our results and it give wrong judgments.

The methodology for the cleaning data is mentioned below:

First step is to import relevant libraries for cleaning the data
Data Cleaning and structuring
Removing outliers
Creating R shiny dashboard

Solution

I created R shiny dashboard https://rahuleldho.shinyapps.io/Rfirstassignment_Rahul_Bijoy/

Traveller Section:
- Present general information for travelers, outlining the benefits of using the dashboard for budget planning, destination selection, understanding local prices, and negotiation.
- Create tabs for expensive and cheap options, allowing users to filter by country and explore the top expensive and cheap cities and commodities.
Student Section:
- Highlight the relevance of the dataset for students planning to study abroad.
- Include tabs for expensive and cheap options, enabling students to explore the cost of living in specific countries and identify suitable destinations based on their budgets.
Data Exploration:
- Implement a tab for a data table, enabling users to explore the raw data.
- Provide a continent filter for users to narrow down their analysis.
Interactive Visualizations:
- Utilize plotly and other relevant libraries to create interactive bar charts displaying the most expensive and cheapest cities, commodities, and living expenses.
- Implement dynamic selection inputs for users to choose specific countries and visualize corresponding data.
Additional Features:
- Include a responsive dashboard layout with aesthetic design.
- Implement dropdowns, sliders, and other input elements for an interactive user experience.
- Ensure that the dashboard is hosted and accessible online, allowing users to explore the data remotely.

Evaluation Criteria:

Functionality: Ensure that the dashboard is interactive, allowing users to filter and explore data easily.
Visualization: Create visually appealing and informative charts to convey the cost of living information effectively.
User Experience: Design an intuitive and user-friendly interface with clear navigation.
Insights: Provide meaningful insights into the cost of living for both travelers and students.
Hosting: Host the dashboard online using platforms like shinyapps.io for accessibility.

"This dashboard creation helps me to learn R programming and understand the functions and libraries as a beginner"

Team

Team Member #1 - Data Analyst
- Gathered and analyzed data from multiple sources to ensure accuracy and reliability
- Created visualizations to make the data easily accessible and understandable for users
Team Member #2 - Web Developer
- Built the R Shiny dashboard from scratch, ensuring a user-friendly interface and seamless functionality
- Incorporated user-generated content to provide real-world insights into living expenses around the world

Creating R Shiny Dashboard for Global Living Expenses